diff options
Diffstat (limited to 'thirdparty/icu4c/common/unicode')
99 files changed, 57429 insertions, 0 deletions
diff --git a/thirdparty/icu4c/common/unicode/appendable.h b/thirdparty/icu4c/common/unicode/appendable.h new file mode 100644 index 0000000000..fc99254de1 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/appendable.h @@ -0,0 +1,239 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2011-2012, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: appendable.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2010dec07 +* created by: Markus W. Scherer +*/ + +#ifndef __APPENDABLE_H__ +#define __APPENDABLE_H__ + +/** + * \file + * \brief C++ API: Appendable class: Sink for Unicode code points and 16-bit code units (char16_ts). + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + +U_NAMESPACE_BEGIN + +class UnicodeString; + +/** + * Base class for objects to which Unicode characters and strings can be appended. + * Combines elements of Java Appendable and ICU4C ByteSink. + * + * This class can be used in APIs where it does not matter whether the actual destination is + * a UnicodeString, a char16_t[] array, a UnicodeSet, or any other object + * that receives and processes characters and/or strings. + * + * Implementation classes must implement at least appendCodeUnit(char16_t). + * The base class provides default implementations for the other methods. + * + * The methods do not take UErrorCode parameters. + * If an error occurs (e.g., out-of-memory), + * in addition to returning false from failing operations, + * the implementation must prevent unexpected behavior (e.g., crashes) + * from further calls and should make the error condition available separately + * (e.g., store a UErrorCode, make/keep a UnicodeString bogus). + * @stable ICU 4.8 + */ +class U_COMMON_API Appendable : public UObject { +public: + /** + * Destructor. + * @stable ICU 4.8 + */ + ~Appendable(); + + /** + * Appends a 16-bit code unit. + * @param c code unit + * @return true if the operation succeeded + * @stable ICU 4.8 + */ + virtual UBool appendCodeUnit(char16_t c) = 0; + + /** + * Appends a code point. + * The default implementation calls appendCodeUnit(char16_t) once or twice. + * @param c code point 0..0x10ffff + * @return true if the operation succeeded + * @stable ICU 4.8 + */ + virtual UBool appendCodePoint(UChar32 c); + + /** + * Appends a string. + * The default implementation calls appendCodeUnit(char16_t) for each code unit. + * @param s string, must not be NULL if length!=0 + * @param length string length, or -1 if NUL-terminated + * @return true if the operation succeeded + * @stable ICU 4.8 + */ + virtual UBool appendString(const char16_t *s, int32_t length); + + /** + * Tells the object that the caller is going to append roughly + * appendCapacity char16_ts. A subclass might use this to pre-allocate + * a larger buffer if necessary. + * The default implementation does nothing. (It always returns true.) + * @param appendCapacity estimated number of char16_ts that will be appended + * @return true if the operation succeeded + * @stable ICU 4.8 + */ + virtual UBool reserveAppendCapacity(int32_t appendCapacity); + + /** + * Returns a writable buffer for appending and writes the buffer's capacity to + * *resultCapacity. Guarantees *resultCapacity>=minCapacity. + * May return a pointer to the caller-owned scratch buffer which must have + * scratchCapacity>=minCapacity. + * The returned buffer is only valid until the next operation + * on this Appendable. + * + * After writing at most *resultCapacity char16_ts, call appendString() with the + * pointer returned from this function and the number of char16_ts written. + * Many appendString() implementations will avoid copying char16_ts if this function + * returned an internal buffer. + * + * Partial usage example: + * \code + * int32_t capacity; + * char16_t* buffer = app.getAppendBuffer(..., &capacity); + * ... Write n char16_ts into buffer, with n <= capacity. + * app.appendString(buffer, n); + * \endcode + * In many implementations, that call to append will avoid copying char16_ts. + * + * If the Appendable allocates or reallocates an internal buffer, it should use + * the desiredCapacityHint if appropriate. + * If a caller cannot provide a reasonable guess at the desired capacity, + * it should pass desiredCapacityHint=0. + * + * If a non-scratch buffer is returned, the caller may only pass + * a prefix to it to appendString(). + * That is, it is not correct to pass an interior pointer to appendString(). + * + * The default implementation always returns the scratch buffer. + * + * @param minCapacity required minimum capacity of the returned buffer; + * must be non-negative + * @param desiredCapacityHint desired capacity of the returned buffer; + * must be non-negative + * @param scratch default caller-owned buffer + * @param scratchCapacity capacity of the scratch buffer + * @param resultCapacity pointer to an integer which will be set to the + * capacity of the returned buffer + * @return a buffer with *resultCapacity>=minCapacity + * @stable ICU 4.8 + */ + virtual char16_t *getAppendBuffer(int32_t minCapacity, + int32_t desiredCapacityHint, + char16_t *scratch, int32_t scratchCapacity, + int32_t *resultCapacity); +}; + +/** + * An Appendable implementation which writes to a UnicodeString. + * + * This class is not intended for public subclassing. + * @stable ICU 4.8 + */ +class U_COMMON_API UnicodeStringAppendable : public Appendable { +public: + /** + * Aliases the UnicodeString (keeps its reference) for writing. + * @param s The UnicodeString to which this Appendable will write. + * @stable ICU 4.8 + */ + explicit UnicodeStringAppendable(UnicodeString &s) : str(s) {} + + /** + * Destructor. + * @stable ICU 4.8 + */ + ~UnicodeStringAppendable(); + + /** + * Appends a 16-bit code unit to the string. + * @param c code unit + * @return true if the operation succeeded + * @stable ICU 4.8 + */ + virtual UBool appendCodeUnit(char16_t c); + + /** + * Appends a code point to the string. + * @param c code point 0..0x10ffff + * @return true if the operation succeeded + * @stable ICU 4.8 + */ + virtual UBool appendCodePoint(UChar32 c); + + /** + * Appends a string to the UnicodeString. + * @param s string, must not be NULL if length!=0 + * @param length string length, or -1 if NUL-terminated + * @return true if the operation succeeded + * @stable ICU 4.8 + */ + virtual UBool appendString(const char16_t *s, int32_t length); + + /** + * Tells the UnicodeString that the caller is going to append roughly + * appendCapacity char16_ts. + * @param appendCapacity estimated number of char16_ts that will be appended + * @return true if the operation succeeded + * @stable ICU 4.8 + */ + virtual UBool reserveAppendCapacity(int32_t appendCapacity); + + /** + * Returns a writable buffer for appending and writes the buffer's capacity to + * *resultCapacity. Guarantees *resultCapacity>=minCapacity. + * May return a pointer to the caller-owned scratch buffer which must have + * scratchCapacity>=minCapacity. + * The returned buffer is only valid until the next write operation + * on the UnicodeString. + * + * For details see Appendable::getAppendBuffer(). + * + * @param minCapacity required minimum capacity of the returned buffer; + * must be non-negative + * @param desiredCapacityHint desired capacity of the returned buffer; + * must be non-negative + * @param scratch default caller-owned buffer + * @param scratchCapacity capacity of the scratch buffer + * @param resultCapacity pointer to an integer which will be set to the + * capacity of the returned buffer + * @return a buffer with *resultCapacity>=minCapacity + * @stable ICU 4.8 + */ + virtual char16_t *getAppendBuffer(int32_t minCapacity, + int32_t desiredCapacityHint, + char16_t *scratch, int32_t scratchCapacity, + int32_t *resultCapacity); + +private: + UnicodeString &str; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __APPENDABLE_H__ diff --git a/thirdparty/icu4c/common/unicode/brkiter.h b/thirdparty/icu4c/common/unicode/brkiter.h new file mode 100644 index 0000000000..9bba5fcccc --- /dev/null +++ b/thirdparty/icu4c/common/unicode/brkiter.h @@ -0,0 +1,670 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************** +* Copyright (C) 1997-2016, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************** +* +* File brkiter.h +* +* Modification History: +* +* Date Name Description +* 02/18/97 aliu Added typedef for TextCount. Made DONE const. +* 05/07/97 aliu Fixed DLL declaration. +* 07/09/97 jfitz Renamed BreakIterator and interface synced with JDK +* 08/11/98 helena Sync-up JDK1.2. +* 01/13/2000 helena Added UErrorCode parameter to createXXXInstance methods. +******************************************************************************** +*/ + +#ifndef BRKITER_H +#define BRKITER_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Break Iterator. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#if UCONFIG_NO_BREAK_ITERATION + +U_NAMESPACE_BEGIN + +/* + * Allow the declaration of APIs with pointers to BreakIterator + * even when break iteration is removed from the build. + */ +class BreakIterator; + +U_NAMESPACE_END + +#else + +#include "unicode/uobject.h" +#include "unicode/unistr.h" +#include "unicode/chariter.h" +#include "unicode/locid.h" +#include "unicode/ubrk.h" +#include "unicode/strenum.h" +#include "unicode/utext.h" +#include "unicode/umisc.h" + +U_NAMESPACE_BEGIN + +/** + * The BreakIterator class implements methods for finding the location + * of boundaries in text. BreakIterator is an abstract base class. + * Instances of BreakIterator maintain a current position and scan over + * text returning the index of characters where boundaries occur. + * <p> + * Line boundary analysis determines where a text string can be broken + * when line-wrapping. The mechanism correctly handles punctuation and + * hyphenated words. + * <p> + * Sentence boundary analysis allows selection with correct + * interpretation of periods within numbers and abbreviations, and + * trailing punctuation marks such as quotation marks and parentheses. + * <p> + * Word boundary analysis is used by search and replace functions, as + * well as within text editing applications that allow the user to + * select words with a double click. Word selection provides correct + * interpretation of punctuation marks within and following + * words. Characters that are not part of a word, such as symbols or + * punctuation marks, have word-breaks on both sides. + * <p> + * Character boundary analysis allows users to interact with + * characters as they expect to, for example, when moving the cursor + * through a text string. Character boundary analysis provides correct + * navigation of through character strings, regardless of how the + * character is stored. For example, an accented character might be + * stored as a base character and a diacritical mark. What users + * consider to be a character can differ between languages. + * <p> + * The text boundary positions are found according to the rules + * described in Unicode Standard Annex #29, Text Boundaries, and + * Unicode Standard Annex #14, Line Breaking Properties. These + * are available at http://www.unicode.org/reports/tr14/ and + * http://www.unicode.org/reports/tr29/. + * <p> + * In addition to the C++ API defined in this header file, a + * plain C API with equivalent functionality is defined in the + * file ubrk.h + * <p> + * Code snippets illustrating the use of the Break Iterator APIs + * are available in the ICU User Guide, + * http://icu-project.org/userguide/boundaryAnalysis.html + * and in the sample program icu/source/samples/break/break.cpp + * + */ +class U_COMMON_API BreakIterator : public UObject { +public: + /** + * destructor + * @stable ICU 2.0 + */ + virtual ~BreakIterator(); + + /** + * Return true if another object is semantically equal to this + * one. The other object should be an instance of the same subclass of + * BreakIterator. Objects of different subclasses are considered + * unequal. + * <P> + * Return true if this BreakIterator is at the same position in the + * same text, and is the same class and type (word, line, etc.) of + * BreakIterator, as the argument. Text is considered the same if + * it contains the same characters, it need not be the same + * object, and styles are not considered. + * @stable ICU 2.0 + */ + virtual UBool operator==(const BreakIterator&) const = 0; + + /** + * Returns the complement of the result of operator== + * @param rhs The BreakIterator to be compared for inequality + * @return the complement of the result of operator== + * @stable ICU 2.0 + */ + UBool operator!=(const BreakIterator& rhs) const { return !operator==(rhs); } + + /** + * Return a polymorphic copy of this object. This is an abstract + * method which subclasses implement. + * @stable ICU 2.0 + */ + virtual BreakIterator* clone() const = 0; + + /** + * Return a polymorphic class ID for this object. Different subclasses + * will return distinct unequal values. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const = 0; + + /** + * Return a CharacterIterator over the text being analyzed. + * @stable ICU 2.0 + */ + virtual CharacterIterator& getText(void) const = 0; + + + /** + * Get a UText for the text being analyzed. + * The returned UText is a shallow clone of the UText used internally + * by the break iterator implementation. It can safely be used to + * access the text without impacting any break iterator operations, + * but the underlying text itself must not be altered. + * + * @param fillIn A UText to be filled in. If NULL, a new UText will be + * allocated to hold the result. + * @param status receives any error codes. + * @return The current UText for this break iterator. If an input + * UText was provided, it will always be returned. + * @stable ICU 3.4 + */ + virtual UText *getUText(UText *fillIn, UErrorCode &status) const = 0; + + /** + * Change the text over which this operates. The text boundary is + * reset to the start. + * + * The BreakIterator will retain a reference to the supplied string. + * The caller must not modify or delete the text while the BreakIterator + * retains the reference. + * + * @param text The UnicodeString used to change the text. + * @stable ICU 2.0 + */ + virtual void setText(const UnicodeString &text) = 0; + + /** + * Reset the break iterator to operate over the text represented by + * the UText. The iterator position is reset to the start. + * + * This function makes a shallow clone of the supplied UText. This means + * that the caller is free to immediately close or otherwise reuse the + * Utext that was passed as a parameter, but that the underlying text itself + * must not be altered while being referenced by the break iterator. + * + * All index positions returned by break iterator functions are + * native indices from the UText. For example, when breaking UTF-8 + * encoded text, the break positions returned by next(), previous(), etc. + * will be UTF-8 string indices, not UTF-16 positions. + * + * @param text The UText used to change the text. + * @param status receives any error codes. + * @stable ICU 3.4 + */ + virtual void setText(UText *text, UErrorCode &status) = 0; + + /** + * Change the text over which this operates. The text boundary is + * reset to the start. + * Note that setText(UText *) provides similar functionality to this function, + * and is more efficient. + * @param it The CharacterIterator used to change the text. + * @stable ICU 2.0 + */ + virtual void adoptText(CharacterIterator* it) = 0; + + enum { + /** + * DONE is returned by previous() and next() after all valid + * boundaries have been returned. + * @stable ICU 2.0 + */ + DONE = (int32_t)-1 + }; + + /** + * Sets the current iteration position to the beginning of the text, position zero. + * @return The offset of the beginning of the text, zero. + * @stable ICU 2.0 + */ + virtual int32_t first(void) = 0; + + /** + * Set the iterator position to the index immediately BEYOND the last character in the text being scanned. + * @return The index immediately BEYOND the last character in the text being scanned. + * @stable ICU 2.0 + */ + virtual int32_t last(void) = 0; + + /** + * Set the iterator position to the boundary preceding the current boundary. + * @return The character index of the previous text boundary or DONE if all + * boundaries have been returned. + * @stable ICU 2.0 + */ + virtual int32_t previous(void) = 0; + + /** + * Advance the iterator to the boundary following the current boundary. + * @return The character index of the next text boundary or DONE if all + * boundaries have been returned. + * @stable ICU 2.0 + */ + virtual int32_t next(void) = 0; + + /** + * Return character index of the current iterator position within the text. + * @return The boundary most recently returned. + * @stable ICU 2.0 + */ + virtual int32_t current(void) const = 0; + + /** + * Advance the iterator to the first boundary following the specified offset. + * The value returned is always greater than the offset or + * the value BreakIterator.DONE + * @param offset the offset to begin scanning. + * @return The first boundary after the specified offset. + * @stable ICU 2.0 + */ + virtual int32_t following(int32_t offset) = 0; + + /** + * Set the iterator position to the first boundary preceding the specified offset. + * The value returned is always smaller than the offset or + * the value BreakIterator.DONE + * @param offset the offset to begin scanning. + * @return The first boundary before the specified offset. + * @stable ICU 2.0 + */ + virtual int32_t preceding(int32_t offset) = 0; + + /** + * Return true if the specified position is a boundary position. + * As a side effect, the current position of the iterator is set + * to the first boundary position at or following the specified offset. + * @param offset the offset to check. + * @return True if "offset" is a boundary position. + * @stable ICU 2.0 + */ + virtual UBool isBoundary(int32_t offset) = 0; + + /** + * Set the iterator position to the nth boundary from the current boundary + * @param n the number of boundaries to move by. A value of 0 + * does nothing. Negative values move to previous boundaries + * and positive values move to later boundaries. + * @return The new iterator position, or + * DONE if there are fewer than |n| boundaries in the specified direction. + * @stable ICU 2.0 + */ + virtual int32_t next(int32_t n) = 0; + + /** + * For RuleBasedBreakIterators, return the status tag from the break rule + * that determined the boundary at the current iteration position. + * <p> + * For break iterator types that do not support a rule status, + * a default value of 0 is returned. + * <p> + * @return the status from the break rule that determined the boundary at + * the current iteration position. + * @see RuleBaseBreakIterator::getRuleStatus() + * @see UWordBreak + * @stable ICU 52 + */ + virtual int32_t getRuleStatus() const; + + /** + * For RuleBasedBreakIterators, get the status (tag) values from the break rule(s) + * that determined the boundary at the current iteration position. + * <p> + * For break iterator types that do not support rule status, + * no values are returned. + * <p> + * The returned status value(s) are stored into an array provided by the caller. + * The values are stored in sorted (ascending) order. + * If the capacity of the output array is insufficient to hold the data, + * the output will be truncated to the available length, and a + * U_BUFFER_OVERFLOW_ERROR will be signaled. + * <p> + * @see RuleBaseBreakIterator::getRuleStatusVec + * + * @param fillInVec an array to be filled in with the status values. + * @param capacity the length of the supplied vector. A length of zero causes + * the function to return the number of status values, in the + * normal way, without attempting to store any values. + * @param status receives error codes. + * @return The number of rule status values from rules that determined + * the boundary at the current iteration position. + * In the event of a U_BUFFER_OVERFLOW_ERROR, the return value + * is the total number of status values that were available, + * not the reduced number that were actually returned. + * @see getRuleStatus + * @stable ICU 52 + */ + virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status); + + /** + * Create BreakIterator for word-breaks using the given locale. + * Returns an instance of a BreakIterator implementing word breaks. + * WordBreak is useful for word selection (ex. double click) + * @param where the locale. + * @param status the error code + * @return A BreakIterator for word-breaks. The UErrorCode& status + * parameter is used to return status information to the user. + * To check whether the construction succeeded or not, you should check + * the value of U_SUCCESS(err). If you wish more detailed information, you + * can check for informational error results which still indicate success. + * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For + * example, 'de_CH' was requested, but nothing was found there, so 'de' was + * used. U_USING_DEFAULT_WARNING indicates that the default locale data was + * used; neither the requested locale nor any of its fall back locales + * could be found. + * The caller owns the returned object and is responsible for deleting it. + * @stable ICU 2.0 + */ + static BreakIterator* U_EXPORT2 + createWordInstance(const Locale& where, UErrorCode& status); + + /** + * Create BreakIterator for line-breaks using specified locale. + * Returns an instance of a BreakIterator implementing line breaks. Line + * breaks are logically possible line breaks, actual line breaks are + * usually determined based on display width. + * LineBreak is useful for word wrapping text. + * @param where the locale. + * @param status The error code. + * @return A BreakIterator for line-breaks. The UErrorCode& status + * parameter is used to return status information to the user. + * To check whether the construction succeeded or not, you should check + * the value of U_SUCCESS(err). If you wish more detailed information, you + * can check for informational error results which still indicate success. + * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For + * example, 'de_CH' was requested, but nothing was found there, so 'de' was + * used. U_USING_DEFAULT_WARNING indicates that the default locale data was + * used; neither the requested locale nor any of its fall back locales + * could be found. + * The caller owns the returned object and is responsible for deleting it. + * @stable ICU 2.0 + */ + static BreakIterator* U_EXPORT2 + createLineInstance(const Locale& where, UErrorCode& status); + + /** + * Create BreakIterator for character-breaks using specified locale + * Returns an instance of a BreakIterator implementing character breaks. + * Character breaks are boundaries of combining character sequences. + * @param where the locale. + * @param status The error code. + * @return A BreakIterator for character-breaks. The UErrorCode& status + * parameter is used to return status information to the user. + * To check whether the construction succeeded or not, you should check + * the value of U_SUCCESS(err). If you wish more detailed information, you + * can check for informational error results which still indicate success. + * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For + * example, 'de_CH' was requested, but nothing was found there, so 'de' was + * used. U_USING_DEFAULT_WARNING indicates that the default locale data was + * used; neither the requested locale nor any of its fall back locales + * could be found. + * The caller owns the returned object and is responsible for deleting it. + * @stable ICU 2.0 + */ + static BreakIterator* U_EXPORT2 + createCharacterInstance(const Locale& where, UErrorCode& status); + + /** + * Create BreakIterator for sentence-breaks using specified locale + * Returns an instance of a BreakIterator implementing sentence breaks. + * @param where the locale. + * @param status The error code. + * @return A BreakIterator for sentence-breaks. The UErrorCode& status + * parameter is used to return status information to the user. + * To check whether the construction succeeded or not, you should check + * the value of U_SUCCESS(err). If you wish more detailed information, you + * can check for informational error results which still indicate success. + * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For + * example, 'de_CH' was requested, but nothing was found there, so 'de' was + * used. U_USING_DEFAULT_WARNING indicates that the default locale data was + * used; neither the requested locale nor any of its fall back locales + * could be found. + * The caller owns the returned object and is responsible for deleting it. + * @stable ICU 2.0 + */ + static BreakIterator* U_EXPORT2 + createSentenceInstance(const Locale& where, UErrorCode& status); + +#ifndef U_HIDE_DEPRECATED_API + /** + * Create BreakIterator for title-casing breaks using the specified locale + * Returns an instance of a BreakIterator implementing title breaks. + * The iterator returned locates title boundaries as described for + * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration, + * please use a word boundary iterator. See {@link #createWordInstance }. + * + * @param where the locale. + * @param status The error code. + * @return A BreakIterator for title-breaks. The UErrorCode& status + * parameter is used to return status information to the user. + * To check whether the construction succeeded or not, you should check + * the value of U_SUCCESS(err). If you wish more detailed information, you + * can check for informational error results which still indicate success. + * U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For + * example, 'de_CH' was requested, but nothing was found there, so 'de' was + * used. U_USING_DEFAULT_WARNING indicates that the default locale data was + * used; neither the requested locale nor any of its fall back locales + * could be found. + * The caller owns the returned object and is responsible for deleting it. + * @deprecated ICU 64 Use createWordInstance instead. + */ + static BreakIterator* U_EXPORT2 + createTitleInstance(const Locale& where, UErrorCode& status); +#endif /* U_HIDE_DEPRECATED_API */ + + /** + * Get the set of Locales for which TextBoundaries are installed. + * <p><b>Note:</b> this will not return locales added through the register + * call. To see the registered locales too, use the getAvailableLocales + * function that returns a StringEnumeration object </p> + * @param count the output parameter of number of elements in the locale list + * @return available locales + * @stable ICU 2.0 + */ + static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count); + + /** + * Get name of the object for the desired Locale, in the desired language. + * @param objectLocale must be from getAvailableLocales. + * @param displayLocale specifies the desired locale for output. + * @param name the fill-in parameter of the return value + * Uses best match. + * @return user-displayable name + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale, + const Locale& displayLocale, + UnicodeString& name); + + /** + * Get name of the object for the desired Locale, in the language of the + * default locale. + * @param objectLocale must be from getMatchingLocales + * @param name the fill-in parameter of the return value + * @return user-displayable name + * @stable ICU 2.0 + */ + static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale, + UnicodeString& name); + +#ifndef U_FORCE_HIDE_DEPRECATED_API + /** + * Deprecated functionality. Use clone() instead. + * + * Thread safe client-buffer-based cloning operation + * Do NOT call delete on a safeclone, since 'new' is not used to create it. + * @param stackBuffer user allocated space for the new clone. If NULL new memory will be allocated. + * If buffer is not large enough, new memory will be allocated. + * @param BufferSize reference to size of allocated space. + * If BufferSize == 0, a sufficient size for use in cloning will + * be returned ('pre-flighting') + * If BufferSize is not enough for a stack-based safe clone, + * new memory will be allocated. + * @param status to indicate whether the operation went on smoothly or there were errors + * An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were + * necessary. + * @return pointer to the new clone + * + * @deprecated ICU 52. Use clone() instead. + */ + virtual BreakIterator * createBufferClone(void *stackBuffer, + int32_t &BufferSize, + UErrorCode &status) = 0; +#endif // U_FORCE_HIDE_DEPRECATED_API + +#ifndef U_HIDE_DEPRECATED_API + + /** + * Determine whether the BreakIterator was created in user memory by + * createBufferClone(), and thus should not be deleted. Such objects + * must be closed by an explicit call to the destructor (not delete). + * @deprecated ICU 52. Always delete the BreakIterator. + */ + inline UBool isBufferClone(void); + +#endif /* U_HIDE_DEPRECATED_API */ + +#if !UCONFIG_NO_SERVICE + /** + * Register a new break iterator of the indicated kind, to use in the given locale. + * The break iterator will be adopted. Clones of the iterator will be returned + * if a request for a break iterator of the given kind matches or falls back to + * this locale. + * Because ICU may choose to cache BreakIterators internally, this must + * be called at application startup, prior to any calls to + * BreakIterator::createXXXInstance to avoid undefined behavior. + * @param toAdopt the BreakIterator instance to be adopted + * @param locale the Locale for which this instance is to be registered + * @param kind the type of iterator for which this instance is to be registered + * @param status the in/out status code, no special meanings are assigned + * @return a registry key that can be used to unregister this instance + * @stable ICU 2.4 + */ + static URegistryKey U_EXPORT2 registerInstance(BreakIterator* toAdopt, + const Locale& locale, + UBreakIteratorType kind, + UErrorCode& status); + + /** + * Unregister a previously-registered BreakIterator using the key returned from the + * register call. Key becomes invalid after a successful call and should not be used again. + * The BreakIterator corresponding to the key will be deleted. + * Because ICU may choose to cache BreakIterators internally, this should + * be called during application shutdown, after all calls to + * BreakIterator::createXXXInstance to avoid undefined behavior. + * @param key the registry key returned by a previous call to registerInstance + * @param status the in/out status code, no special meanings are assigned + * @return true if the iterator for the key was successfully unregistered + * @stable ICU 2.4 + */ + static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status); + + /** + * Return a StringEnumeration over the locales available at the time of the call, + * including registered locales. + * @return a StringEnumeration over the locales available at the time of the call + * @stable ICU 2.4 + */ + static StringEnumeration* U_EXPORT2 getAvailableLocales(void); +#endif + + /** + * Returns the locale for this break iterator. Two flavors are available: valid and + * actual locale. + * @stable ICU 2.8 + */ + Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const; + +#ifndef U_HIDE_INTERNAL_API + /** Get the locale for this break iterator object. You can choose between valid and actual locale. + * @param type type of the locale we're looking for (valid or actual) + * @param status error code for the operation + * @return the locale + * @internal + */ + const char *getLocaleID(ULocDataLocaleType type, UErrorCode& status) const; +#endif /* U_HIDE_INTERNAL_API */ + + /** + * Set the subject text string upon which the break iterator is operating + * without changing any other aspect of the matching state. + * The new and previous text strings must have the same content. + * + * This function is intended for use in environments where ICU is operating on + * strings that may move around in memory. It provides a mechanism for notifying + * ICU that the string has been relocated, and providing a new UText to access the + * string in its new position. + * + * Note that the break iterator implementation never copies the underlying text + * of a string being processed, but always operates directly on the original text + * provided by the user. Refreshing simply drops the references to the old text + * and replaces them with references to the new. + * + * Caution: this function is normally used only by very specialized, + * system-level code. One example use case is with garbage collection that moves + * the text in memory. + * + * @param input The new (moved) text string. + * @param status Receives errors detected by this function. + * @return *this + * + * @stable ICU 49 + */ + virtual BreakIterator &refreshInputText(UText *input, UErrorCode &status) = 0; + + private: + static BreakIterator* buildInstance(const Locale& loc, const char *type, UErrorCode& status); + static BreakIterator* createInstance(const Locale& loc, int32_t kind, UErrorCode& status); + static BreakIterator* makeInstance(const Locale& loc, int32_t kind, UErrorCode& status); + + friend class ICUBreakIteratorFactory; + friend class ICUBreakIteratorService; + +protected: + // Do not enclose protected default/copy constructors with #ifndef U_HIDE_INTERNAL_API + // or else the compiler will create a public ones. + /** @internal */ + BreakIterator(); + /** @internal */ + BreakIterator (const BreakIterator &other); +#ifndef U_HIDE_INTERNAL_API + /** @internal */ + BreakIterator (const Locale& valid, const Locale &actual); + /** @internal. Assignment Operator, used by RuleBasedBreakIterator. */ + BreakIterator &operator = (const BreakIterator &other); +#endif /* U_HIDE_INTERNAL_API */ + +private: + + /** @internal (private) */ + char actualLocale[ULOC_FULLNAME_CAPACITY]; + char validLocale[ULOC_FULLNAME_CAPACITY]; +}; + +#ifndef U_HIDE_DEPRECATED_API + +inline UBool BreakIterator::isBufferClone() +{ + return false; +} + +#endif /* U_HIDE_DEPRECATED_API */ + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_BREAK_ITERATION */ + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // BRKITER_H +//eof diff --git a/thirdparty/icu4c/common/unicode/bytestream.h b/thirdparty/icu4c/common/unicode/bytestream.h new file mode 100644 index 0000000000..044f7a77e7 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/bytestream.h @@ -0,0 +1,309 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +// Copyright (C) 2009-2012, International Business Machines +// Corporation and others. All Rights Reserved. +// +// Copyright 2007 Google Inc. All Rights Reserved. +// Author: sanjay@google.com (Sanjay Ghemawat) +// +// Abstract interface that consumes a sequence of bytes (ByteSink). +// +// Used so that we can write a single piece of code that can operate +// on a variety of output string types. +// +// Various implementations of this interface are provided: +// ByteSink: +// CheckedArrayByteSink Write to a flat array, with bounds checking +// StringByteSink Write to an STL string + +// This code is a contribution of Google code, and the style used here is +// a compromise between the original Google code and the ICU coding guidelines. +// For example, data types are ICU-ified (size_t,int->int32_t), +// and API comments doxygen-ified, but function names and behavior are +// as in the original, if possible. +// Assertion-style error handling, not available in ICU, was changed to +// parameter "pinning" similar to UnicodeString. +// +// In addition, this is only a partial port of the original Google code, +// limited to what was needed so far. The (nearly) complete original code +// is in the ICU svn repository at icuhtml/trunk/design/strings/contrib +// (see ICU ticket 6765, r25517). + +#ifndef __BYTESTREAM_H__ +#define __BYTESTREAM_H__ + +/** + * \file + * \brief C++ API: Interface for writing bytes, and implementation classes. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" +#include "unicode/std_string.h" + +U_NAMESPACE_BEGIN + +/** + * A ByteSink can be filled with bytes. + * @stable ICU 4.2 + */ +class U_COMMON_API ByteSink : public UMemory { +public: + /** + * Default constructor. + * @stable ICU 4.2 + */ + ByteSink() { } + /** + * Virtual destructor. + * @stable ICU 4.2 + */ + virtual ~ByteSink(); + + /** + * Append "bytes[0,n-1]" to this. + * @param bytes the pointer to the bytes + * @param n the number of bytes; must be non-negative + * @stable ICU 4.2 + */ + virtual void Append(const char* bytes, int32_t n) = 0; + +#ifndef U_HIDE_DRAFT_API + /** + * Appends n bytes to this. Same as Append(). + * Call AppendU8() with u8"string literals" which are const char * in C++11 + * but const char8_t * in C++20. + * If the compiler does support char8_t as a distinct type, + * then an AppendU8() overload for that is defined and will be chosen. + * + * @param bytes the pointer to the bytes + * @param n the number of bytes; must be non-negative + * @draft ICU 67 + */ + inline void AppendU8(const char* bytes, int32_t n) { + Append(bytes, n); + } + +#if defined(__cpp_char8_t) || defined(U_IN_DOXYGEN) + /** + * Appends n bytes to this. Same as Append() but for a const char8_t * pointer. + * Call AppendU8() with u8"string literals" which are const char * in C++11 + * but const char8_t * in C++20. + * If the compiler does support char8_t as a distinct type, + * then this AppendU8() overload for that is defined and will be chosen. + * + * @param bytes the pointer to the bytes + * @param n the number of bytes; must be non-negative + * @draft ICU 67 + */ + inline void AppendU8(const char8_t* bytes, int32_t n) { + Append(reinterpret_cast<const char*>(bytes), n); + } +#endif +#endif // U_HIDE_DRAFT_API + + /** + * Returns a writable buffer for appending and writes the buffer's capacity to + * *result_capacity. Guarantees *result_capacity>=min_capacity. + * May return a pointer to the caller-owned scratch buffer which must have + * scratch_capacity>=min_capacity. + * The returned buffer is only valid until the next operation + * on this ByteSink. + * + * After writing at most *result_capacity bytes, call Append() with the + * pointer returned from this function and the number of bytes written. + * Many Append() implementations will avoid copying bytes if this function + * returned an internal buffer. + * + * Partial usage example: + * int32_t capacity; + * char* buffer = sink->GetAppendBuffer(..., &capacity); + * ... Write n bytes into buffer, with n <= capacity. + * sink->Append(buffer, n); + * In many implementations, that call to Append will avoid copying bytes. + * + * If the ByteSink allocates or reallocates an internal buffer, it should use + * the desired_capacity_hint if appropriate. + * If a caller cannot provide a reasonable guess at the desired capacity, + * it should pass desired_capacity_hint=0. + * + * If a non-scratch buffer is returned, the caller may only pass + * a prefix to it to Append(). + * That is, it is not correct to pass an interior pointer to Append(). + * + * The default implementation always returns the scratch buffer. + * + * @param min_capacity required minimum capacity of the returned buffer; + * must be non-negative + * @param desired_capacity_hint desired capacity of the returned buffer; + * must be non-negative + * @param scratch default caller-owned buffer + * @param scratch_capacity capacity of the scratch buffer + * @param result_capacity pointer to an integer which will be set to the + * capacity of the returned buffer + * @return a buffer with *result_capacity>=min_capacity + * @stable ICU 4.2 + */ + virtual char* GetAppendBuffer(int32_t min_capacity, + int32_t desired_capacity_hint, + char* scratch, int32_t scratch_capacity, + int32_t* result_capacity); + + /** + * Flush internal buffers. + * Some byte sinks use internal buffers or provide buffering + * and require calling Flush() at the end of the stream. + * The ByteSink should be ready for further Append() calls after Flush(). + * The default implementation of Flush() does nothing. + * @stable ICU 4.2 + */ + virtual void Flush(); + +private: + ByteSink(const ByteSink &) = delete; + ByteSink &operator=(const ByteSink &) = delete; +}; + +// ------------------------------------------------------------- +// Some standard implementations + +/** + * Implementation of ByteSink that writes to a flat byte array, + * with bounds-checking: + * This sink will not write more than capacity bytes to outbuf. + * If more than capacity bytes are Append()ed, then excess bytes are ignored, + * and Overflowed() will return true. + * Overflow does not cause a runtime error. + * @stable ICU 4.2 + */ +class U_COMMON_API CheckedArrayByteSink : public ByteSink { +public: + /** + * Constructs a ByteSink that will write to outbuf[0..capacity-1]. + * @param outbuf buffer to write to + * @param capacity size of the buffer + * @stable ICU 4.2 + */ + CheckedArrayByteSink(char* outbuf, int32_t capacity); + /** + * Destructor. + * @stable ICU 4.2 + */ + virtual ~CheckedArrayByteSink(); + /** + * Returns the sink to its original state, without modifying the buffer. + * Useful for reusing both the buffer and the sink for multiple streams. + * Resets the state to NumberOfBytesWritten()=NumberOfBytesAppended()=0 + * and Overflowed()=false. + * @return *this + * @stable ICU 4.6 + */ + virtual CheckedArrayByteSink& Reset(); + /** + * Append "bytes[0,n-1]" to this. + * @param bytes the pointer to the bytes + * @param n the number of bytes; must be non-negative + * @stable ICU 4.2 + */ + virtual void Append(const char* bytes, int32_t n); + /** + * Returns a writable buffer for appending and writes the buffer's capacity to + * *result_capacity. For details see the base class documentation. + * @param min_capacity required minimum capacity of the returned buffer; + * must be non-negative + * @param desired_capacity_hint desired capacity of the returned buffer; + * must be non-negative + * @param scratch default caller-owned buffer + * @param scratch_capacity capacity of the scratch buffer + * @param result_capacity pointer to an integer which will be set to the + * capacity of the returned buffer + * @return a buffer with *result_capacity>=min_capacity + * @stable ICU 4.2 + */ + virtual char* GetAppendBuffer(int32_t min_capacity, + int32_t desired_capacity_hint, + char* scratch, int32_t scratch_capacity, + int32_t* result_capacity); + /** + * Returns the number of bytes actually written to the sink. + * @return number of bytes written to the buffer + * @stable ICU 4.2 + */ + int32_t NumberOfBytesWritten() const { return size_; } + /** + * Returns true if any bytes were discarded, i.e., if there was an + * attempt to write more than 'capacity' bytes. + * @return true if more than 'capacity' bytes were Append()ed + * @stable ICU 4.2 + */ + UBool Overflowed() const { return overflowed_; } + /** + * Returns the number of bytes appended to the sink. + * If Overflowed() then NumberOfBytesAppended()>NumberOfBytesWritten() + * else they return the same number. + * @return number of bytes written to the buffer + * @stable ICU 4.6 + */ + int32_t NumberOfBytesAppended() const { return appended_; } +private: + char* outbuf_; + const int32_t capacity_; + int32_t size_; + int32_t appended_; + UBool overflowed_; + + CheckedArrayByteSink() = delete; + CheckedArrayByteSink(const CheckedArrayByteSink &) = delete; + CheckedArrayByteSink &operator=(const CheckedArrayByteSink &) = delete; +}; + +/** + * Implementation of ByteSink that writes to a "string". + * The StringClass is usually instantiated with a std::string. + * @stable ICU 4.2 + */ +template<typename StringClass> +class StringByteSink : public ByteSink { + public: + /** + * Constructs a ByteSink that will append bytes to the dest string. + * @param dest pointer to string object to append to + * @stable ICU 4.2 + */ + StringByteSink(StringClass* dest) : dest_(dest) { } + /** + * Constructs a ByteSink that reserves append capacity and will append bytes to the dest string. + * + * @param dest pointer to string object to append to + * @param initialAppendCapacity capacity beyond dest->length() to be reserve()d + * @stable ICU 60 + */ + StringByteSink(StringClass* dest, int32_t initialAppendCapacity) : dest_(dest) { + if (initialAppendCapacity > 0 && + (uint32_t)initialAppendCapacity > (dest->capacity() - dest->length())) { + dest->reserve(dest->length() + initialAppendCapacity); + } + } + /** + * Append "bytes[0,n-1]" to this. + * @param data the pointer to the bytes + * @param n the number of bytes; must be non-negative + * @stable ICU 4.2 + */ + virtual void Append(const char* data, int32_t n) { dest_->append(data, n); } + private: + StringClass* dest_; + + StringByteSink() = delete; + StringByteSink(const StringByteSink &) = delete; + StringByteSink &operator=(const StringByteSink &) = delete; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __BYTESTREAM_H__ diff --git a/thirdparty/icu4c/common/unicode/bytestrie.h b/thirdparty/icu4c/common/unicode/bytestrie.h new file mode 100644 index 0000000000..85f802df42 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/bytestrie.h @@ -0,0 +1,565 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2010-2012, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: bytestrie.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2010sep25 +* created by: Markus W. Scherer +*/ + +#ifndef __BYTESTRIE_H__ +#define __BYTESTRIE_H__ + +/** + * \file + * \brief C++ API: Trie for mapping byte sequences to integer values. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/stringpiece.h" +#include "unicode/uobject.h" +#include "unicode/ustringtrie.h" + +U_NAMESPACE_BEGIN + +class ByteSink; +class BytesTrieBuilder; +class CharString; +class UVector32; + +/** + * Light-weight, non-const reader class for a BytesTrie. + * Traverses a byte-serialized data structure with minimal state, + * for mapping byte sequences to non-negative integer values. + * + * This class owns the serialized trie data only if it was constructed by + * the builder's build() method. + * The public constructor and the copy constructor only alias the data (only copy the pointer). + * There is no assignment operator. + * + * This class is not intended for public subclassing. + * @stable ICU 4.8 + */ +class U_COMMON_API BytesTrie : public UMemory { +public: + /** + * Constructs a BytesTrie reader instance. + * + * The trieBytes must contain a copy of a byte sequence from the BytesTrieBuilder, + * starting with the first byte of that sequence. + * The BytesTrie object will not read more bytes than + * the BytesTrieBuilder generated in the corresponding build() call. + * + * The array is not copied/cloned and must not be modified while + * the BytesTrie object is in use. + * + * @param trieBytes The byte array that contains the serialized trie. + * @stable ICU 4.8 + */ + BytesTrie(const void *trieBytes) + : ownedArray_(NULL), bytes_(static_cast<const uint8_t *>(trieBytes)), + pos_(bytes_), remainingMatchLength_(-1) {} + + /** + * Destructor. + * @stable ICU 4.8 + */ + ~BytesTrie(); + + /** + * Copy constructor, copies the other trie reader object and its state, + * but not the byte array which will be shared. (Shallow copy.) + * @param other Another BytesTrie object. + * @stable ICU 4.8 + */ + BytesTrie(const BytesTrie &other) + : ownedArray_(NULL), bytes_(other.bytes_), + pos_(other.pos_), remainingMatchLength_(other.remainingMatchLength_) {} + + /** + * Resets this trie to its initial state. + * @return *this + * @stable ICU 4.8 + */ + BytesTrie &reset() { + pos_=bytes_; + remainingMatchLength_=-1; + return *this; + } + + /** + * Returns the state of this trie as a 64-bit integer. + * The state value is never 0. + * + * @return opaque state value + * @see resetToState64 + * @stable ICU 65 + */ + uint64_t getState64() const { + return (static_cast<uint64_t>(remainingMatchLength_ + 2) << kState64RemainingShift) | + (uint64_t)(pos_ - bytes_); + } + + /** + * Resets this trie to the saved state. + * Unlike resetToState(State), the 64-bit state value + * must be from getState64() from the same trie object or + * from one initialized the exact same way. + * Because of no validation, this method is faster. + * + * @param state The opaque trie state value from getState64(). + * @return *this + * @see getState64 + * @see resetToState + * @see reset + * @stable ICU 65 + */ + BytesTrie &resetToState64(uint64_t state) { + remainingMatchLength_ = static_cast<int32_t>(state >> kState64RemainingShift) - 2; + pos_ = bytes_ + (state & kState64PosMask); + return *this; + } + + /** + * BytesTrie state object, for saving a trie's current state + * and resetting the trie back to this state later. + * @stable ICU 4.8 + */ + class State : public UMemory { + public: + /** + * Constructs an empty State. + * @stable ICU 4.8 + */ + State() { bytes=NULL; } + private: + friend class BytesTrie; + + const uint8_t *bytes; + const uint8_t *pos; + int32_t remainingMatchLength; + }; + + /** + * Saves the state of this trie. + * @param state The State object to hold the trie's state. + * @return *this + * @see resetToState + * @stable ICU 4.8 + */ + const BytesTrie &saveState(State &state) const { + state.bytes=bytes_; + state.pos=pos_; + state.remainingMatchLength=remainingMatchLength_; + return *this; + } + + /** + * Resets this trie to the saved state. + * If the state object contains no state, or the state of a different trie, + * then this trie remains unchanged. + * @param state The State object which holds a saved trie state. + * @return *this + * @see saveState + * @see reset + * @stable ICU 4.8 + */ + BytesTrie &resetToState(const State &state) { + if(bytes_==state.bytes && bytes_!=NULL) { + pos_=state.pos; + remainingMatchLength_=state.remainingMatchLength; + } + return *this; + } + + /** + * Determines whether the byte sequence so far matches, whether it has a value, + * and whether another input byte can continue a matching byte sequence. + * @return The match/value Result. + * @stable ICU 4.8 + */ + UStringTrieResult current() const; + + /** + * Traverses the trie from the initial state for this input byte. + * Equivalent to reset().next(inByte). + * @param inByte Input byte value. Values -0x100..-1 are treated like 0..0xff. + * Values below -0x100 and above 0xff will never match. + * @return The match/value Result. + * @stable ICU 4.8 + */ + inline UStringTrieResult first(int32_t inByte) { + remainingMatchLength_=-1; + if(inByte<0) { + inByte+=0x100; + } + return nextImpl(bytes_, inByte); + } + + /** + * Traverses the trie from the current state for this input byte. + * @param inByte Input byte value. Values -0x100..-1 are treated like 0..0xff. + * Values below -0x100 and above 0xff will never match. + * @return The match/value Result. + * @stable ICU 4.8 + */ + UStringTrieResult next(int32_t inByte); + + /** + * Traverses the trie from the current state for this byte sequence. + * Equivalent to + * \code + * Result result=current(); + * for(each c in s) + * if(!USTRINGTRIE_HAS_NEXT(result)) return USTRINGTRIE_NO_MATCH; + * result=next(c); + * return result; + * \endcode + * @param s A string or byte sequence. Can be NULL if length is 0. + * @param length The length of the byte sequence. Can be -1 if NUL-terminated. + * @return The match/value Result. + * @stable ICU 4.8 + */ + UStringTrieResult next(const char *s, int32_t length); + + /** + * Returns a matching byte sequence's value if called immediately after + * current()/first()/next() returned USTRINGTRIE_INTERMEDIATE_VALUE or USTRINGTRIE_FINAL_VALUE. + * getValue() can be called multiple times. + * + * Do not call getValue() after USTRINGTRIE_NO_MATCH or USTRINGTRIE_NO_VALUE! + * @return The value for the byte sequence so far. + * @stable ICU 4.8 + */ + inline int32_t getValue() const { + const uint8_t *pos=pos_; + int32_t leadByte=*pos++; + // U_ASSERT(leadByte>=kMinValueLead); + return readValue(pos, leadByte>>1); + } + + /** + * Determines whether all byte sequences reachable from the current state + * map to the same value. + * @param uniqueValue Receives the unique value, if this function returns true. + * (output-only) + * @return true if all byte sequences reachable from the current state + * map to the same value. + * @stable ICU 4.8 + */ + inline UBool hasUniqueValue(int32_t &uniqueValue) const { + const uint8_t *pos=pos_; + // Skip the rest of a pending linear-match node. + return pos!=NULL && findUniqueValue(pos+remainingMatchLength_+1, false, uniqueValue); + } + + /** + * Finds each byte which continues the byte sequence from the current state. + * That is, each byte b for which it would be next(b)!=USTRINGTRIE_NO_MATCH now. + * @param out Each next byte is appended to this object. + * (Only uses the out.Append(s, length) method.) + * @return the number of bytes which continue the byte sequence from here + * @stable ICU 4.8 + */ + int32_t getNextBytes(ByteSink &out) const; + + /** + * Iterator for all of the (byte sequence, value) pairs in a BytesTrie. + * @stable ICU 4.8 + */ + class U_COMMON_API Iterator : public UMemory { + public: + /** + * Iterates from the root of a byte-serialized BytesTrie. + * @param trieBytes The trie bytes. + * @param maxStringLength If 0, the iterator returns full strings/byte sequences. + * Otherwise, the iterator returns strings with this maximum length. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @stable ICU 4.8 + */ + Iterator(const void *trieBytes, int32_t maxStringLength, UErrorCode &errorCode); + + /** + * Iterates from the current state of the specified BytesTrie. + * @param trie The trie whose state will be copied for iteration. + * @param maxStringLength If 0, the iterator returns full strings/byte sequences. + * Otherwise, the iterator returns strings with this maximum length. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @stable ICU 4.8 + */ + Iterator(const BytesTrie &trie, int32_t maxStringLength, UErrorCode &errorCode); + + /** + * Destructor. + * @stable ICU 4.8 + */ + ~Iterator(); + + /** + * Resets this iterator to its initial state. + * @return *this + * @stable ICU 4.8 + */ + Iterator &reset(); + + /** + * @return true if there are more elements. + * @stable ICU 4.8 + */ + UBool hasNext() const; + + /** + * Finds the next (byte sequence, value) pair if there is one. + * + * If the byte sequence is truncated to the maximum length and does not + * have a real value, then the value is set to -1. + * In this case, this "not a real value" is indistinguishable from + * a real value of -1. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return true if there is another element. + * @stable ICU 4.8 + */ + UBool next(UErrorCode &errorCode); + + /** + * @return The NUL-terminated byte sequence for the last successful next(). + * @stable ICU 4.8 + */ + StringPiece getString() const; + /** + * @return The value for the last successful next(). + * @stable ICU 4.8 + */ + int32_t getValue() const { return value_; } + + private: + UBool truncateAndStop(); + + const uint8_t *branchNext(const uint8_t *pos, int32_t length, UErrorCode &errorCode); + + const uint8_t *bytes_; + const uint8_t *pos_; + const uint8_t *initialPos_; + int32_t remainingMatchLength_; + int32_t initialRemainingMatchLength_; + + CharString *str_; + int32_t maxLength_; + int32_t value_; + + // The stack stores pairs of integers for backtracking to another + // outbound edge of a branch node. + // The first integer is an offset from bytes_. + // The second integer has the str_->length() from before the node in bits 15..0, + // and the remaining branch length in bits 24..16. (Bits 31..25 are unused.) + // (We could store the remaining branch length minus 1 in bits 23..16 and not use bits 31..24, + // but the code looks more confusing that way.) + UVector32 *stack_; + }; + +private: + friend class BytesTrieBuilder; + + /** + * Constructs a BytesTrie reader instance. + * Unlike the public constructor which just aliases an array, + * this constructor adopts the builder's array. + * This constructor is only called by the builder. + */ + BytesTrie(void *adoptBytes, const void *trieBytes) + : ownedArray_(static_cast<uint8_t *>(adoptBytes)), + bytes_(static_cast<const uint8_t *>(trieBytes)), + pos_(bytes_), remainingMatchLength_(-1) {} + + // No assignment operator. + BytesTrie &operator=(const BytesTrie &other); + + inline void stop() { + pos_=NULL; + } + + // Reads a compact 32-bit integer. + // pos is already after the leadByte, and the lead byte is already shifted right by 1. + static int32_t readValue(const uint8_t *pos, int32_t leadByte); + static inline const uint8_t *skipValue(const uint8_t *pos, int32_t leadByte) { + // U_ASSERT(leadByte>=kMinValueLead); + if(leadByte>=(kMinTwoByteValueLead<<1)) { + if(leadByte<(kMinThreeByteValueLead<<1)) { + ++pos; + } else if(leadByte<(kFourByteValueLead<<1)) { + pos+=2; + } else { + pos+=3+((leadByte>>1)&1); + } + } + return pos; + } + static inline const uint8_t *skipValue(const uint8_t *pos) { + int32_t leadByte=*pos++; + return skipValue(pos, leadByte); + } + + // Reads a jump delta and jumps. + static const uint8_t *jumpByDelta(const uint8_t *pos); + + static inline const uint8_t *skipDelta(const uint8_t *pos) { + int32_t delta=*pos++; + if(delta>=kMinTwoByteDeltaLead) { + if(delta<kMinThreeByteDeltaLead) { + ++pos; + } else if(delta<kFourByteDeltaLead) { + pos+=2; + } else { + pos+=3+(delta&1); + } + } + return pos; + } + + static inline UStringTrieResult valueResult(int32_t node) { + return (UStringTrieResult)(USTRINGTRIE_INTERMEDIATE_VALUE-(node&kValueIsFinal)); + } + + // Handles a branch node for both next(byte) and next(string). + UStringTrieResult branchNext(const uint8_t *pos, int32_t length, int32_t inByte); + + // Requires remainingLength_<0. + UStringTrieResult nextImpl(const uint8_t *pos, int32_t inByte); + + // Helper functions for hasUniqueValue(). + // Recursively finds a unique value (or whether there is not a unique one) + // from a branch. + static const uint8_t *findUniqueValueFromBranch(const uint8_t *pos, int32_t length, + UBool haveUniqueValue, int32_t &uniqueValue); + // Recursively finds a unique value (or whether there is not a unique one) + // starting from a position on a node lead byte. + static UBool findUniqueValue(const uint8_t *pos, UBool haveUniqueValue, int32_t &uniqueValue); + + // Helper functions for getNextBytes(). + // getNextBytes() when pos is on a branch node. + static void getNextBranchBytes(const uint8_t *pos, int32_t length, ByteSink &out); + static void append(ByteSink &out, int c); + + // BytesTrie data structure + // + // The trie consists of a series of byte-serialized nodes for incremental + // string/byte sequence matching. The root node is at the beginning of the trie data. + // + // Types of nodes are distinguished by their node lead byte ranges. + // After each node, except a final-value node, another node follows to + // encode match values or continue matching further bytes. + // + // Node types: + // - Value node: Stores a 32-bit integer in a compact, variable-length format. + // The value is for the string/byte sequence so far. + // One node bit indicates whether the value is final or whether + // matching continues with the next node. + // - Linear-match node: Matches a number of bytes. + // - Branch node: Branches to other nodes according to the current input byte. + // The node byte is the length of the branch (number of bytes to select from) + // minus 1. It is followed by a sub-node: + // - If the length is at most kMaxBranchLinearSubNodeLength, then + // there are length-1 (key, value) pairs and then one more comparison byte. + // If one of the key bytes matches, then the value is either a final value for + // the string/byte sequence so far, or a "jump" delta to the next node. + // If the last byte matches, then matching continues with the next node. + // (Values have the same encoding as value nodes.) + // - If the length is greater than kMaxBranchLinearSubNodeLength, then + // there is one byte and one "jump" delta. + // If the input byte is less than the sub-node byte, then "jump" by delta to + // the next sub-node which will have a length of length/2. + // (The delta has its own compact encoding.) + // Otherwise, skip the "jump" delta to the next sub-node + // which will have a length of length-length/2. + + // Node lead byte values. + + // 00..0f: Branch node. If node!=0 then the length is node+1, otherwise + // the length is one more than the next byte. + + // For a branch sub-node with at most this many entries, we drop down + // to a linear search. + static const int32_t kMaxBranchLinearSubNodeLength=5; + + // 10..1f: Linear-match node, match 1..16 bytes and continue reading the next node. + static const int32_t kMinLinearMatch=0x10; + static const int32_t kMaxLinearMatchLength=0x10; + + // 20..ff: Variable-length value node. + // If odd, the value is final. (Otherwise, intermediate value or jump delta.) + // Then shift-right by 1 bit. + // The remaining lead byte value indicates the number of following bytes (0..4) + // and contains the value's top bits. + static const int32_t kMinValueLead=kMinLinearMatch+kMaxLinearMatchLength; // 0x20 + // It is a final value if bit 0 is set. + static const int32_t kValueIsFinal=1; + + // Compact value: After testing bit 0, shift right by 1 and then use the following thresholds. + static const int32_t kMinOneByteValueLead=kMinValueLead/2; // 0x10 + static const int32_t kMaxOneByteValue=0x40; // At least 6 bits in the first byte. + + static const int32_t kMinTwoByteValueLead=kMinOneByteValueLead+kMaxOneByteValue+1; // 0x51 + static const int32_t kMaxTwoByteValue=0x1aff; + + static const int32_t kMinThreeByteValueLead=kMinTwoByteValueLead+(kMaxTwoByteValue>>8)+1; // 0x6c + static const int32_t kFourByteValueLead=0x7e; + + // A little more than Unicode code points. (0x11ffff) + static const int32_t kMaxThreeByteValue=((kFourByteValueLead-kMinThreeByteValueLead)<<16)-1; + + static const int32_t kFiveByteValueLead=0x7f; + + // Compact delta integers. + static const int32_t kMaxOneByteDelta=0xbf; + static const int32_t kMinTwoByteDeltaLead=kMaxOneByteDelta+1; // 0xc0 + static const int32_t kMinThreeByteDeltaLead=0xf0; + static const int32_t kFourByteDeltaLead=0xfe; + static const int32_t kFiveByteDeltaLead=0xff; + + static const int32_t kMaxTwoByteDelta=((kMinThreeByteDeltaLead-kMinTwoByteDeltaLead)<<8)-1; // 0x2fff + static const int32_t kMaxThreeByteDelta=((kFourByteDeltaLead-kMinThreeByteDeltaLead)<<16)-1; // 0xdffff + + // For getState64(): + // The remainingMatchLength_ is -1..14=(kMaxLinearMatchLength=0x10)-2 + // so we need at least 5 bits for that. + // We add 2 to store it as a positive value 1..16=kMaxLinearMatchLength. + static constexpr int32_t kState64RemainingShift = 59; + static constexpr uint64_t kState64PosMask = (UINT64_C(1) << kState64RemainingShift) - 1; + + uint8_t *ownedArray_; + + // Fixed value referencing the BytesTrie bytes. + const uint8_t *bytes_; + + // Iterator variables. + + // Pointer to next trie byte to read. NULL if no more matches. + const uint8_t *pos_; + // Remaining length of a linear-match node, minus 1. Negative if not in such a node. + int32_t remainingMatchLength_; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __BYTESTRIE_H__ diff --git a/thirdparty/icu4c/common/unicode/bytestriebuilder.h b/thirdparty/icu4c/common/unicode/bytestriebuilder.h new file mode 100644 index 0000000000..cae16e48b4 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/bytestriebuilder.h @@ -0,0 +1,188 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2010-2016, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: bytestriebuilder.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2010sep25 +* created by: Markus W. Scherer +*/ + +/** + * \file + * \brief C++ API: Builder for icu::BytesTrie + */ + +#ifndef __BYTESTRIEBUILDER_H__ +#define __BYTESTRIEBUILDER_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/bytestrie.h" +#include "unicode/stringpiece.h" +#include "unicode/stringtriebuilder.h" + +U_NAMESPACE_BEGIN + +class BytesTrieElement; +class CharString; +/** + * Builder class for BytesTrie. + * + * This class is not intended for public subclassing. + * @stable ICU 4.8 + */ +class U_COMMON_API BytesTrieBuilder : public StringTrieBuilder { +public: + /** + * Constructs an empty builder. + * @param errorCode Standard ICU error code. + * @stable ICU 4.8 + */ + BytesTrieBuilder(UErrorCode &errorCode); + + /** + * Destructor. + * @stable ICU 4.8 + */ + virtual ~BytesTrieBuilder(); + + /** + * Adds a (byte sequence, value) pair. + * The byte sequence must be unique. + * The bytes will be copied; the builder does not keep + * a reference to the input StringPiece or its data(). + * @param s The input byte sequence. + * @param value The value associated with this byte sequence. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return *this + * @stable ICU 4.8 + */ + BytesTrieBuilder &add(StringPiece s, int32_t value, UErrorCode &errorCode); + + /** + * Builds a BytesTrie for the add()ed data. + * Once built, no further data can be add()ed until clear() is called. + * + * A BytesTrie cannot be empty. At least one (byte sequence, value) pair + * must have been add()ed. + * + * This method passes ownership of the builder's internal result array to the new trie object. + * Another call to any build() variant will re-serialize the trie. + * After clear() has been called, a new array will be used as well. + * @param buildOption Build option, see UStringTrieBuildOption. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return A new BytesTrie for the add()ed data. + * @stable ICU 4.8 + */ + BytesTrie *build(UStringTrieBuildOption buildOption, UErrorCode &errorCode); + + /** + * Builds a BytesTrie for the add()ed data and byte-serializes it. + * Once built, no further data can be add()ed until clear() is called. + * + * A BytesTrie cannot be empty. At least one (byte sequence, value) pair + * must have been add()ed. + * + * Multiple calls to buildStringPiece() return StringPieces referring to the + * builder's same byte array, without rebuilding. + * If buildStringPiece() is called after build(), the trie will be + * re-serialized into a new array (because build() passes on ownership). + * If build() is called after buildStringPiece(), the trie object returned + * by build() will become the owner of the underlying string for the + * previously returned StringPiece. + * After clear() has been called, a new array will be used as well. + * @param buildOption Build option, see UStringTrieBuildOption. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return A StringPiece which refers to the byte-serialized BytesTrie for the add()ed data. + * @stable ICU 4.8 + */ + StringPiece buildStringPiece(UStringTrieBuildOption buildOption, UErrorCode &errorCode); + + /** + * Removes all (byte sequence, value) pairs. + * New data can then be add()ed and a new trie can be built. + * @return *this + * @stable ICU 4.8 + */ + BytesTrieBuilder &clear(); + +private: + BytesTrieBuilder(const BytesTrieBuilder &other); // no copy constructor + BytesTrieBuilder &operator=(const BytesTrieBuilder &other); // no assignment operator + + void buildBytes(UStringTrieBuildOption buildOption, UErrorCode &errorCode); + + virtual int32_t getElementStringLength(int32_t i) const; + virtual char16_t getElementUnit(int32_t i, int32_t byteIndex) const; + virtual int32_t getElementValue(int32_t i) const; + + virtual int32_t getLimitOfLinearMatch(int32_t first, int32_t last, int32_t byteIndex) const; + + virtual int32_t countElementUnits(int32_t start, int32_t limit, int32_t byteIndex) const; + virtual int32_t skipElementsBySomeUnits(int32_t i, int32_t byteIndex, int32_t count) const; + virtual int32_t indexOfElementWithNextUnit(int32_t i, int32_t byteIndex, char16_t byte) const; + + virtual UBool matchNodesCanHaveValues() const { return false; } + + virtual int32_t getMaxBranchLinearSubNodeLength() const { return BytesTrie::kMaxBranchLinearSubNodeLength; } + virtual int32_t getMinLinearMatch() const { return BytesTrie::kMinLinearMatch; } + virtual int32_t getMaxLinearMatchLength() const { return BytesTrie::kMaxLinearMatchLength; } + + /** + * @internal (private) + */ + class BTLinearMatchNode : public LinearMatchNode { + public: + BTLinearMatchNode(const char *units, int32_t len, Node *nextNode); + virtual UBool operator==(const Node &other) const; + virtual void write(StringTrieBuilder &builder); + private: + const char *s; + }; + + virtual Node *createLinearMatchNode(int32_t i, int32_t byteIndex, int32_t length, + Node *nextNode) const; + + UBool ensureCapacity(int32_t length); + virtual int32_t write(int32_t byte); + int32_t write(const char *b, int32_t length); + virtual int32_t writeElementUnits(int32_t i, int32_t byteIndex, int32_t length); + virtual int32_t writeValueAndFinal(int32_t i, UBool isFinal); + virtual int32_t writeValueAndType(UBool hasValue, int32_t value, int32_t node); + virtual int32_t writeDeltaTo(int32_t jumpTarget); + + CharString *strings; // Pointer not object so we need not #include internal charstr.h. + BytesTrieElement *elements; + int32_t elementsCapacity; + int32_t elementsLength; + + // Byte serialization of the trie. + // Grows from the back: bytesLength measures from the end of the buffer! + char *bytes; + int32_t bytesCapacity; + int32_t bytesLength; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __BYTESTRIEBUILDER_H__ diff --git a/thirdparty/icu4c/common/unicode/caniter.h b/thirdparty/icu4c/common/unicode/caniter.h new file mode 100644 index 0000000000..4ed2b74b10 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/caniter.h @@ -0,0 +1,214 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* + ******************************************************************************* + * Copyright (C) 1996-2014, International Business Machines Corporation and + * others. All Rights Reserved. + ******************************************************************************* + */ + +#ifndef CANITER_H +#define CANITER_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#if !UCONFIG_NO_NORMALIZATION + +#include "unicode/uobject.h" +#include "unicode/unistr.h" + +/** + * \file + * \brief C++ API: Canonical Iterator + */ + +/** Should permutation skip characters with combining class zero + * Should be either true or false. This is a compile time option + * @stable ICU 2.4 + */ +#ifndef CANITER_SKIP_ZEROES +#define CANITER_SKIP_ZEROES true +#endif + +U_NAMESPACE_BEGIN + +class Hashtable; +class Normalizer2; +class Normalizer2Impl; + +/** + * This class allows one to iterate through all the strings that are canonically equivalent to a given + * string. For example, here are some sample results: +Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} +1: \\u0041\\u030A\\u0064\\u0307\\u0327 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} +2: \\u0041\\u030A\\u0064\\u0327\\u0307 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} +3: \\u0041\\u030A\\u1E0B\\u0327 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} +4: \\u0041\\u030A\\u1E11\\u0307 + = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} +5: \\u00C5\\u0064\\u0307\\u0327 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} +6: \\u00C5\\u0064\\u0327\\u0307 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} +7: \\u00C5\\u1E0B\\u0327 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} +8: \\u00C5\\u1E11\\u0307 + = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} +9: \\u212B\\u0064\\u0307\\u0327 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} +10: \\u212B\\u0064\\u0327\\u0307 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} +11: \\u212B\\u1E0B\\u0327 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} +12: \\u212B\\u1E11\\u0307 + = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} + *<br>Note: the code is intended for use with small strings, and is not suitable for larger ones, + * since it has not been optimized for that situation. + * Note, CanonicalIterator is not intended to be subclassed. + * @author M. Davis + * @author C++ port by V. Weinstein + * @stable ICU 2.4 + */ +class U_COMMON_API CanonicalIterator U_FINAL : public UObject { +public: + /** + * Construct a CanonicalIterator object + * @param source string to get results for + * @param status Fill-in parameter which receives the status of this operation. + * @stable ICU 2.4 + */ + CanonicalIterator(const UnicodeString &source, UErrorCode &status); + + /** Destructor + * Cleans pieces + * @stable ICU 2.4 + */ + virtual ~CanonicalIterator(); + + /** + * Gets the NFD form of the current source we are iterating over. + * @return gets the source: NOTE: it is the NFD form of source + * @stable ICU 2.4 + */ + UnicodeString getSource(); + + /** + * Resets the iterator so that one can start again from the beginning. + * @stable ICU 2.4 + */ + void reset(); + + /** + * Get the next canonically equivalent string. + * <br><b>Warning: The strings are not guaranteed to be in any particular order.</b> + * @return the next string that is canonically equivalent. A bogus string is returned when + * the iteration is done. + * @stable ICU 2.4 + */ + UnicodeString next(); + + /** + * Set a new source for this iterator. Allows object reuse. + * @param newSource the source string to iterate against. This allows the same iterator to be used + * while changing the source string, saving object creation. + * @param status Fill-in parameter which receives the status of this operation. + * @stable ICU 2.4 + */ + void setSource(const UnicodeString &newSource, UErrorCode &status); + +#ifndef U_HIDE_INTERNAL_API + /** + * Dumb recursive implementation of permutation. + * TODO: optimize + * @param source the string to find permutations for + * @param skipZeros determine if skip zeros + * @param result the results in a set. + * @param status Fill-in parameter which receives the status of this operation. + * @internal + */ + static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status); +#endif /* U_HIDE_INTERNAL_API */ + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + +private: + // ===================== PRIVATES ============================== + // private default constructor + CanonicalIterator(); + + + /** + * Copy constructor. Private for now. + * @internal (private) + */ + CanonicalIterator(const CanonicalIterator& other); + + /** + * Assignment operator. Private for now. + * @internal (private) + */ + CanonicalIterator& operator=(const CanonicalIterator& other); + + // fields + UnicodeString source; + UBool done; + + // 2 dimensional array holds the pieces of the string with + // their different canonically equivalent representations + UnicodeString **pieces; + int32_t pieces_length; + int32_t *pieces_lengths; + + // current is used in iterating to combine pieces + int32_t *current; + int32_t current_length; + + // transient fields + UnicodeString buffer; + + const Normalizer2 &nfd; + const Normalizer2Impl &nfcImpl; + + // we have a segment, in NFD. Find all the strings that are canonically equivalent to it. + UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment) + + //Set getEquivalents2(String segment); + Hashtable *getEquivalents2(Hashtable *fillinResult, const char16_t *segment, int32_t segLen, UErrorCode &status); + //Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status); + + /** + * See if the decomposition of cp2 is at segment starting at segmentPos + * (with canonical rearrangment!) + * If so, take the remainder, and return the equivalents + */ + //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer); + Hashtable *extract(Hashtable *fillinResult, UChar32 comp, const char16_t *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status); + //Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status); + + void cleanPieces(); + +}; + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_NORMALIZATION */ + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/casemap.h b/thirdparty/icu4c/common/unicode/casemap.h new file mode 100644 index 0000000000..53af84fa74 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/casemap.h @@ -0,0 +1,497 @@ +// © 2017 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// casemap.h +// created: 2017jan12 Markus W. Scherer + +#ifndef __CASEMAP_H__ +#define __CASEMAP_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/stringpiece.h" +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: Low-level C++ case mapping functions. + */ + +U_NAMESPACE_BEGIN + +class BreakIterator; +class ByteSink; +class Edits; + +/** + * Low-level C++ case mapping functions. + * + * @stable ICU 59 + */ +class U_COMMON_API CaseMap U_FINAL : public UMemory { +public: + /** + * Lowercases a UTF-16 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of char16_ts). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful. + * When the result would be longer than destCapacity, + * the full length is returned and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see u_strToLower + * @stable ICU 59 + */ + static int32_t toLower( + const char *locale, uint32_t options, + const char16_t *src, int32_t srcLength, + char16_t *dest, int32_t destCapacity, Edits *edits, + UErrorCode &errorCode); + + /** + * Uppercases a UTF-16 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of char16_ts). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful. + * When the result would be longer than destCapacity, + * the full length is returned and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see u_strToUpper + * @stable ICU 59 + */ + static int32_t toUpper( + const char *locale, uint32_t options, + const char16_t *src, int32_t srcLength, + char16_t *dest, int32_t destCapacity, Edits *edits, + UErrorCode &errorCode); + +#if !UCONFIG_NO_BREAK_ITERATION + + /** + * Titlecases a UTF-16 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. (This can be modified with options bits.) + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT, U_EDITS_NO_RESET, + * U_TITLECASE_NO_LOWERCASE, + * U_TITLECASE_NO_BREAK_ADJUSTMENT, U_TITLECASE_ADJUST_TO_CASED, + * U_TITLECASE_WHOLE_STRING, U_TITLECASE_SENTENCES. + * @param iter A break iterator to find the first characters of words that are to be titlecased. + * It is set to the source string (setText()) + * and used one or more times for iteration (first() and next()). + * If NULL, then a word break iterator for the locale is used + * (or something equivalent). + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of char16_ts). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful. + * When the result would be longer than destCapacity, + * the full length is returned and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see u_strToTitle + * @see ucasemap_toTitle + * @stable ICU 59 + */ + static int32_t toTitle( + const char *locale, uint32_t options, BreakIterator *iter, + const char16_t *src, int32_t srcLength, + char16_t *dest, int32_t destCapacity, Edits *edits, + UErrorCode &errorCode); + +#endif // UCONFIG_NO_BREAK_ITERATION + + /** + * Case-folds a UTF-16 string and optionally records edits. + * + * Case folding is locale-independent and not context-sensitive, + * but there is an option for whether to include or exclude mappings for dotted I + * and dotless i that are marked with 'T' in CaseFolding.txt. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT, U_EDITS_NO_RESET, + * U_FOLD_CASE_DEFAULT, U_FOLD_CASE_EXCLUDE_SPECIAL_I. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of char16_ts). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful. + * When the result would be longer than destCapacity, + * the full length is returned and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see u_strFoldCase + * @stable ICU 59 + */ + static int32_t fold( + uint32_t options, + const char16_t *src, int32_t srcLength, + char16_t *dest, int32_t destCapacity, Edits *edits, + UErrorCode &errorCode); + + /** + * Lowercases a UTF-8 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src The original string. + * @param sink A ByteSink to which the result string is written. + * sink.Flush() is called at the end. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * + * @see ucasemap_utf8ToLower + * @stable ICU 60 + */ + static void utf8ToLower( + const char *locale, uint32_t options, + StringPiece src, ByteSink &sink, Edits *edits, + UErrorCode &errorCode); + + /** + * Uppercases a UTF-8 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src The original string. + * @param sink A ByteSink to which the result string is written. + * sink.Flush() is called at the end. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * + * @see ucasemap_utf8ToUpper + * @stable ICU 60 + */ + static void utf8ToUpper( + const char *locale, uint32_t options, + StringPiece src, ByteSink &sink, Edits *edits, + UErrorCode &errorCode); + +#if !UCONFIG_NO_BREAK_ITERATION + + /** + * Titlecases a UTF-8 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. (This can be modified with options bits.) + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT, U_EDITS_NO_RESET, + * U_TITLECASE_NO_LOWERCASE, + * U_TITLECASE_NO_BREAK_ADJUSTMENT, U_TITLECASE_ADJUST_TO_CASED, + * U_TITLECASE_WHOLE_STRING, U_TITLECASE_SENTENCES. + * @param iter A break iterator to find the first characters of words that are to be titlecased. + * It is set to the source string (setUText()) + * and used one or more times for iteration (first() and next()). + * If NULL, then a word break iterator for the locale is used + * (or something equivalent). + * @param src The original string. + * @param sink A ByteSink to which the result string is written. + * sink.Flush() is called at the end. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * + * @see ucasemap_utf8ToTitle + * @stable ICU 60 + */ + static void utf8ToTitle( + const char *locale, uint32_t options, BreakIterator *iter, + StringPiece src, ByteSink &sink, Edits *edits, + UErrorCode &errorCode); + +#endif // UCONFIG_NO_BREAK_ITERATION + + /** + * Case-folds a UTF-8 string and optionally records edits. + * + * Case folding is locale-independent and not context-sensitive, + * but there is an option for whether to include or exclude mappings for dotted I + * and dotless i that are marked with 'T' in CaseFolding.txt. + * + * The result may be longer or shorter than the original. + * + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src The original string. + * @param sink A ByteSink to which the result string is written. + * sink.Flush() is called at the end. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * + * @see ucasemap_utf8FoldCase + * @stable ICU 60 + */ + static void utf8Fold( + uint32_t options, + StringPiece src, ByteSink &sink, Edits *edits, + UErrorCode &errorCode); + + /** + * Lowercases a UTF-8 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of bytes). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful. + * When the result would be longer than destCapacity, + * the full length is returned and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see ucasemap_utf8ToLower + * @stable ICU 59 + */ + static int32_t utf8ToLower( + const char *locale, uint32_t options, + const char *src, int32_t srcLength, + char *dest, int32_t destCapacity, Edits *edits, + UErrorCode &errorCode); + + /** + * Uppercases a UTF-8 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of bytes). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful. + * When the result would be longer than destCapacity, + * the full length is returned and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see ucasemap_utf8ToUpper + * @stable ICU 59 + */ + static int32_t utf8ToUpper( + const char *locale, uint32_t options, + const char *src, int32_t srcLength, + char *dest, int32_t destCapacity, Edits *edits, + UErrorCode &errorCode); + +#if !UCONFIG_NO_BREAK_ITERATION + + /** + * Titlecases a UTF-8 string and optionally records edits. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. (This can be modified with options bits.) + * + * @param locale The locale ID. ("" = root locale, NULL = default locale.) + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT, U_EDITS_NO_RESET, + * U_TITLECASE_NO_LOWERCASE, + * U_TITLECASE_NO_BREAK_ADJUSTMENT, U_TITLECASE_ADJUST_TO_CASED, + * U_TITLECASE_WHOLE_STRING, U_TITLECASE_SENTENCES. + * @param iter A break iterator to find the first characters of words that are to be titlecased. + * It is set to the source string (setUText()) + * and used one or more times for iteration (first() and next()). + * If NULL, then a word break iterator for the locale is used + * (or something equivalent). + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of bytes). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful. + * When the result would be longer than destCapacity, + * the full length is returned and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see ucasemap_utf8ToTitle + * @stable ICU 59 + */ + static int32_t utf8ToTitle( + const char *locale, uint32_t options, BreakIterator *iter, + const char *src, int32_t srcLength, + char *dest, int32_t destCapacity, Edits *edits, + UErrorCode &errorCode); + +#endif // UCONFIG_NO_BREAK_ITERATION + + /** + * Case-folds a UTF-8 string and optionally records edits. + * + * Case folding is locale-independent and not context-sensitive, + * but there is an option for whether to include or exclude mappings for dotted I + * and dotless i that are marked with 'T' in CaseFolding.txt. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT, U_EDITS_NO_RESET, + * U_FOLD_CASE_DEFAULT, U_FOLD_CASE_EXCLUDE_SPECIAL_I. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of bytes). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be NULL. + * @param errorCode Reference to an in/out error code value + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful. + * When the result would be longer than destCapacity, + * the full length is returned and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see ucasemap_utf8FoldCase + * @stable ICU 59 + */ + static int32_t utf8Fold( + uint32_t options, + const char *src, int32_t srcLength, + char *dest, int32_t destCapacity, Edits *edits, + UErrorCode &errorCode); + +private: + CaseMap() = delete; + CaseMap(const CaseMap &other) = delete; + CaseMap &operator=(const CaseMap &other) = delete; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __CASEMAP_H__ diff --git a/thirdparty/icu4c/common/unicode/char16ptr.h b/thirdparty/icu4c/common/unicode/char16ptr.h new file mode 100644 index 0000000000..c8a9ae6c35 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/char16ptr.h @@ -0,0 +1,313 @@ +// © 2017 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// char16ptr.h +// created: 2017feb28 Markus W. Scherer + +#ifndef __CHAR16PTR_H__ +#define __CHAR16PTR_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include <cstddef> + +/** + * \file + * \brief C++ API: char16_t pointer wrappers with + * implicit conversion from bit-compatible raw pointer types. + * Also conversion functions from char16_t * to UChar * and OldUChar *. + */ + +U_NAMESPACE_BEGIN + +/** + * \def U_ALIASING_BARRIER + * Barrier for pointer anti-aliasing optimizations even across function boundaries. + * @internal + */ +#ifdef U_ALIASING_BARRIER + // Use the predefined value. +#elif (defined(__clang__) || defined(__GNUC__)) && U_PLATFORM != U_PF_BROWSER_NATIVE_CLIENT +# define U_ALIASING_BARRIER(ptr) asm volatile("" : : "rm"(ptr) : "memory") +#elif defined(U_IN_DOXYGEN) +# define U_ALIASING_BARRIER(ptr) +#endif + +/** + * char16_t * wrapper with implicit conversion from distinct but bit-compatible pointer types. + * @stable ICU 59 + */ +class U_COMMON_API Char16Ptr U_FINAL { +public: + /** + * Copies the pointer. + * @param p pointer + * @stable ICU 59 + */ + inline Char16Ptr(char16_t *p); +#if !U_CHAR16_IS_TYPEDEF + /** + * Converts the pointer to char16_t *. + * @param p pointer to be converted + * @stable ICU 59 + */ + inline Char16Ptr(uint16_t *p); +#endif +#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN) + /** + * Converts the pointer to char16_t *. + * (Only defined if U_SIZEOF_WCHAR_T==2.) + * @param p pointer to be converted + * @stable ICU 59 + */ + inline Char16Ptr(wchar_t *p); +#endif + /** + * nullptr constructor. + * @param p nullptr + * @stable ICU 59 + */ + inline Char16Ptr(std::nullptr_t p); + /** + * Destructor. + * @stable ICU 59 + */ + inline ~Char16Ptr(); + + /** + * Pointer access. + * @return the wrapped pointer + * @stable ICU 59 + */ + inline char16_t *get() const; + /** + * char16_t pointer access via type conversion (e.g., static_cast). + * @return the wrapped pointer + * @stable ICU 59 + */ + inline operator char16_t *() const { return get(); } + +private: + Char16Ptr() = delete; + +#ifdef U_ALIASING_BARRIER + template<typename T> static char16_t *cast(T *t) { + U_ALIASING_BARRIER(t); + return reinterpret_cast<char16_t *>(t); + } + + char16_t *p_; +#else + union { + char16_t *cp; + uint16_t *up; + wchar_t *wp; + } u_; +#endif +}; + +/// \cond +#ifdef U_ALIASING_BARRIER + +Char16Ptr::Char16Ptr(char16_t *p) : p_(p) {} +#if !U_CHAR16_IS_TYPEDEF +Char16Ptr::Char16Ptr(uint16_t *p) : p_(cast(p)) {} +#endif +#if U_SIZEOF_WCHAR_T==2 +Char16Ptr::Char16Ptr(wchar_t *p) : p_(cast(p)) {} +#endif +Char16Ptr::Char16Ptr(std::nullptr_t p) : p_(p) {} +Char16Ptr::~Char16Ptr() { + U_ALIASING_BARRIER(p_); +} + +char16_t *Char16Ptr::get() const { return p_; } + +#else + +Char16Ptr::Char16Ptr(char16_t *p) { u_.cp = p; } +#if !U_CHAR16_IS_TYPEDEF +Char16Ptr::Char16Ptr(uint16_t *p) { u_.up = p; } +#endif +#if U_SIZEOF_WCHAR_T==2 +Char16Ptr::Char16Ptr(wchar_t *p) { u_.wp = p; } +#endif +Char16Ptr::Char16Ptr(std::nullptr_t p) { u_.cp = p; } +Char16Ptr::~Char16Ptr() {} + +char16_t *Char16Ptr::get() const { return u_.cp; } + +#endif +/// \endcond + +/** + * const char16_t * wrapper with implicit conversion from distinct but bit-compatible pointer types. + * @stable ICU 59 + */ +class U_COMMON_API ConstChar16Ptr U_FINAL { +public: + /** + * Copies the pointer. + * @param p pointer + * @stable ICU 59 + */ + inline ConstChar16Ptr(const char16_t *p); +#if !U_CHAR16_IS_TYPEDEF + /** + * Converts the pointer to char16_t *. + * @param p pointer to be converted + * @stable ICU 59 + */ + inline ConstChar16Ptr(const uint16_t *p); +#endif +#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN) + /** + * Converts the pointer to char16_t *. + * (Only defined if U_SIZEOF_WCHAR_T==2.) + * @param p pointer to be converted + * @stable ICU 59 + */ + inline ConstChar16Ptr(const wchar_t *p); +#endif + /** + * nullptr constructor. + * @param p nullptr + * @stable ICU 59 + */ + inline ConstChar16Ptr(const std::nullptr_t p); + + /** + * Destructor. + * @stable ICU 59 + */ + inline ~ConstChar16Ptr(); + + /** + * Pointer access. + * @return the wrapped pointer + * @stable ICU 59 + */ + inline const char16_t *get() const; + /** + * char16_t pointer access via type conversion (e.g., static_cast). + * @return the wrapped pointer + * @stable ICU 59 + */ + inline operator const char16_t *() const { return get(); } + +private: + ConstChar16Ptr() = delete; + +#ifdef U_ALIASING_BARRIER + template<typename T> static const char16_t *cast(const T *t) { + U_ALIASING_BARRIER(t); + return reinterpret_cast<const char16_t *>(t); + } + + const char16_t *p_; +#else + union { + const char16_t *cp; + const uint16_t *up; + const wchar_t *wp; + } u_; +#endif +}; + +/// \cond +#ifdef U_ALIASING_BARRIER + +ConstChar16Ptr::ConstChar16Ptr(const char16_t *p) : p_(p) {} +#if !U_CHAR16_IS_TYPEDEF +ConstChar16Ptr::ConstChar16Ptr(const uint16_t *p) : p_(cast(p)) {} +#endif +#if U_SIZEOF_WCHAR_T==2 +ConstChar16Ptr::ConstChar16Ptr(const wchar_t *p) : p_(cast(p)) {} +#endif +ConstChar16Ptr::ConstChar16Ptr(const std::nullptr_t p) : p_(p) {} +ConstChar16Ptr::~ConstChar16Ptr() { + U_ALIASING_BARRIER(p_); +} + +const char16_t *ConstChar16Ptr::get() const { return p_; } + +#else + +ConstChar16Ptr::ConstChar16Ptr(const char16_t *p) { u_.cp = p; } +#if !U_CHAR16_IS_TYPEDEF +ConstChar16Ptr::ConstChar16Ptr(const uint16_t *p) { u_.up = p; } +#endif +#if U_SIZEOF_WCHAR_T==2 +ConstChar16Ptr::ConstChar16Ptr(const wchar_t *p) { u_.wp = p; } +#endif +ConstChar16Ptr::ConstChar16Ptr(const std::nullptr_t p) { u_.cp = p; } +ConstChar16Ptr::~ConstChar16Ptr() {} + +const char16_t *ConstChar16Ptr::get() const { return u_.cp; } + +#endif +/// \endcond + +/** + * Converts from const char16_t * to const UChar *. + * Includes an aliasing barrier if available. + * @param p pointer + * @return p as const UChar * + * @stable ICU 59 + */ +inline const UChar *toUCharPtr(const char16_t *p) { +#ifdef U_ALIASING_BARRIER + U_ALIASING_BARRIER(p); +#endif + return reinterpret_cast<const UChar *>(p); +} + +/** + * Converts from char16_t * to UChar *. + * Includes an aliasing barrier if available. + * @param p pointer + * @return p as UChar * + * @stable ICU 59 + */ +inline UChar *toUCharPtr(char16_t *p) { +#ifdef U_ALIASING_BARRIER + U_ALIASING_BARRIER(p); +#endif + return reinterpret_cast<UChar *>(p); +} + +/** + * Converts from const char16_t * to const OldUChar *. + * Includes an aliasing barrier if available. + * @param p pointer + * @return p as const OldUChar * + * @stable ICU 59 + */ +inline const OldUChar *toOldUCharPtr(const char16_t *p) { +#ifdef U_ALIASING_BARRIER + U_ALIASING_BARRIER(p); +#endif + return reinterpret_cast<const OldUChar *>(p); +} + +/** + * Converts from char16_t * to OldUChar *. + * Includes an aliasing barrier if available. + * @param p pointer + * @return p as OldUChar * + * @stable ICU 59 + */ +inline OldUChar *toOldUCharPtr(char16_t *p) { +#ifdef U_ALIASING_BARRIER + U_ALIASING_BARRIER(p); +#endif + return reinterpret_cast<OldUChar *>(p); +} + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __CHAR16PTR_H__ diff --git a/thirdparty/icu4c/common/unicode/chariter.h b/thirdparty/icu4c/common/unicode/chariter.h new file mode 100644 index 0000000000..96dc5db7c9 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/chariter.h @@ -0,0 +1,734 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************** +* +* Copyright (C) 1997-2011, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************** +*/ + +#ifndef CHARITER_H +#define CHARITER_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" +#include "unicode/unistr.h" +/** + * \file + * \brief C++ API: Character Iterator + */ + +U_NAMESPACE_BEGIN +/** + * Abstract class that defines an API for forward-only iteration + * on text objects. + * This is a minimal interface for iteration without random access + * or backwards iteration. It is especially useful for wrapping + * streams with converters into an object for collation or + * normalization. + * + * <p>Characters can be accessed in two ways: as code units or as + * code points. + * Unicode code points are 21-bit integers and are the scalar values + * of Unicode characters. ICU uses the type UChar32 for them. + * Unicode code units are the storage units of a given + * Unicode/UCS Transformation Format (a character encoding scheme). + * With UTF-16, all code points can be represented with either one + * or two code units ("surrogates"). + * String storage is typically based on code units, while properties + * of characters are typically determined using code point values. + * Some processes may be designed to work with sequences of code units, + * or it may be known that all characters that are important to an + * algorithm can be represented with single code units. + * Other processes will need to use the code point access functions.</p> + * + * <p>ForwardCharacterIterator provides nextPostInc() to access + * a code unit and advance an internal position into the text object, + * similar to a <code>return text[position++]</code>.<br> + * It provides next32PostInc() to access a code point and advance an internal + * position.</p> + * + * <p>next32PostInc() assumes that the current position is that of + * the beginning of a code point, i.e., of its first code unit. + * After next32PostInc(), this will be true again. + * In general, access to code units and code points in the same + * iteration loop should not be mixed. In UTF-16, if the current position + * is on a second code unit (Low Surrogate), then only that code unit + * is returned even by next32PostInc().</p> + * + * <p>For iteration with either function, there are two ways to + * check for the end of the iteration. When there are no more + * characters in the text object: + * <ul> + * <li>The hasNext() function returns false.</li> + * <li>nextPostInc() and next32PostInc() return DONE + * when one attempts to read beyond the end of the text object.</li> + * </ul> + * + * Example: + * \code + * void function1(ForwardCharacterIterator &it) { + * UChar32 c; + * while(it.hasNext()) { + * c=it.next32PostInc(); + * // use c + * } + * } + * + * void function1(ForwardCharacterIterator &it) { + * char16_t c; + * while((c=it.nextPostInc())!=ForwardCharacterIterator::DONE) { + * // use c + * } + * } + * \endcode + * </p> + * + * @stable ICU 2.0 + */ +class U_COMMON_API ForwardCharacterIterator : public UObject { +public: + /** + * Value returned by most of ForwardCharacterIterator's functions + * when the iterator has reached the limits of its iteration. + * @stable ICU 2.0 + */ + enum { DONE = 0xffff }; + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~ForwardCharacterIterator(); + + /** + * Returns true when both iterators refer to the same + * character in the same character-storage object. + * @param that The ForwardCharacterIterator to be compared for equality + * @return true when both iterators refer to the same + * character in the same character-storage object + * @stable ICU 2.0 + */ + virtual UBool operator==(const ForwardCharacterIterator& that) const = 0; + + /** + * Returns true when the iterators refer to different + * text-storage objects, or to different characters in the + * same text-storage object. + * @param that The ForwardCharacterIterator to be compared for inequality + * @return true when the iterators refer to different + * text-storage objects, or to different characters in the + * same text-storage object + * @stable ICU 2.0 + */ + inline UBool operator!=(const ForwardCharacterIterator& that) const; + + /** + * Generates a hash code for this iterator. + * @return the hash code. + * @stable ICU 2.0 + */ + virtual int32_t hashCode(void) const = 0; + + /** + * Returns a UClassID for this ForwardCharacterIterator ("poor man's + * RTTI").<P> Despite the fact that this function is public, + * DO NOT CONSIDER IT PART OF CHARACTERITERATOR'S API! + * @return a UClassID for this ForwardCharacterIterator + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const = 0; + + /** + * Gets the current code unit for returning and advances to the next code unit + * in the iteration range + * (toward endIndex()). If there are + * no more code units to return, returns DONE. + * @return the current code unit. + * @stable ICU 2.0 + */ + virtual char16_t nextPostInc(void) = 0; + + /** + * Gets the current code point for returning and advances to the next code point + * in the iteration range + * (toward endIndex()). If there are + * no more code points to return, returns DONE. + * @return the current code point. + * @stable ICU 2.0 + */ + virtual UChar32 next32PostInc(void) = 0; + + /** + * Returns false if there are no more code units or code points + * at or after the current position in the iteration range. + * This is used with nextPostInc() or next32PostInc() in forward + * iteration. + * @returns false if there are no more code units or code points + * at or after the current position in the iteration range. + * @stable ICU 2.0 + */ + virtual UBool hasNext() = 0; + +protected: + /** Default constructor to be overridden in the implementing class. @stable ICU 2.0*/ + ForwardCharacterIterator(); + + /** Copy constructor to be overridden in the implementing class. @stable ICU 2.0*/ + ForwardCharacterIterator(const ForwardCharacterIterator &other); + + /** + * Assignment operator to be overridden in the implementing class. + * @stable ICU 2.0 + */ + ForwardCharacterIterator &operator=(const ForwardCharacterIterator&) { return *this; } +}; + +/** + * Abstract class that defines an API for iteration + * on text objects. + * This is an interface for forward and backward iteration + * and random access into a text object. + * + * <p>The API provides backward compatibility to the Java and older ICU + * CharacterIterator classes but extends them significantly: + * <ol> + * <li>CharacterIterator is now a subclass of ForwardCharacterIterator.</li> + * <li>While the old API functions provided forward iteration with + * "pre-increment" semantics, the new one also provides functions + * with "post-increment" semantics. They are more efficient and should + * be the preferred iterator functions for new implementations. + * The backward iteration always had "pre-decrement" semantics, which + * are efficient.</li> + * <li>Just like ForwardCharacterIterator, it provides access to + * both code units and code points. Code point access versions are available + * for the old and the new iteration semantics.</li> + * <li>There are new functions for setting and moving the current position + * without returning a character, for efficiency.</li> + * </ol> + * + * See ForwardCharacterIterator for examples for using the new forward iteration + * functions. For backward iteration, there is also a hasPrevious() function + * that can be used analogously to hasNext(). + * The old functions work as before and are shown below.</p> + * + * <p>Examples for some of the new functions:</p> + * + * Forward iteration with hasNext(): + * \code + * void forward1(CharacterIterator &it) { + * UChar32 c; + * for(it.setToStart(); it.hasNext();) { + * c=it.next32PostInc(); + * // use c + * } + * } + * \endcode + * Forward iteration more similar to loops with the old forward iteration, + * showing a way to convert simple for() loops: + * \code + * void forward2(CharacterIterator &it) { + * char16_t c; + * for(c=it.firstPostInc(); c!=CharacterIterator::DONE; c=it.nextPostInc()) { + * // use c + * } + * } + * \endcode + * Backward iteration with setToEnd() and hasPrevious(): + * \code + * void backward1(CharacterIterator &it) { + * UChar32 c; + * for(it.setToEnd(); it.hasPrevious();) { + * c=it.previous32(); + * // use c + * } + * } + * \endcode + * Backward iteration with a more traditional for() loop: + * \code + * void backward2(CharacterIterator &it) { + * char16_t c; + * for(c=it.last(); c!=CharacterIterator::DONE; c=it.previous()) { + * // use c + * } + * } + * \endcode + * + * Example for random access: + * \code + * void random(CharacterIterator &it) { + * // set to the third code point from the beginning + * it.move32(3, CharacterIterator::kStart); + * // get a code point from here without moving the position + * UChar32 c=it.current32(); + * // get the position + * int32_t pos=it.getIndex(); + * // get the previous code unit + * char16_t u=it.previous(); + * // move back one more code unit + * it.move(-1, CharacterIterator::kCurrent); + * // set the position back to where it was + * // and read the same code point c and move beyond it + * it.setIndex(pos); + * if(c!=it.next32PostInc()) { + * exit(1); // CharacterIterator inconsistent + * } + * } + * \endcode + * + * <p>Examples, especially for the old API:</p> + * + * Function processing characters, in this example simple output + * <pre> + * \code + * void processChar( char16_t c ) + * { + * cout << " " << c; + * } + * \endcode + * </pre> + * Traverse the text from start to finish + * <pre> + * \code + * void traverseForward(CharacterIterator& iter) + * { + * for(char16_t c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) { + * processChar(c); + * } + * } + * \endcode + * </pre> + * Traverse the text backwards, from end to start + * <pre> + * \code + * void traverseBackward(CharacterIterator& iter) + * { + * for(char16_t c = iter.last(); c != CharacterIterator.DONE; c = iter.previous()) { + * processChar(c); + * } + * } + * \endcode + * </pre> + * Traverse both forward and backward from a given position in the text. + * Calls to notBoundary() in this example represents some additional stopping criteria. + * <pre> + * \code + * void traverseOut(CharacterIterator& iter, int32_t pos) + * { + * char16_t c; + * for (c = iter.setIndex(pos); + * c != CharacterIterator.DONE && (Unicode::isLetter(c) || Unicode::isDigit(c)); + * c = iter.next()) {} + * int32_t end = iter.getIndex(); + * for (c = iter.setIndex(pos); + * c != CharacterIterator.DONE && (Unicode::isLetter(c) || Unicode::isDigit(c)); + * c = iter.previous()) {} + * int32_t start = iter.getIndex() + 1; + * + * cout << "start: " << start << " end: " << end << endl; + * for (c = iter.setIndex(start); iter.getIndex() < end; c = iter.next() ) { + * processChar(c); + * } + * } + * \endcode + * </pre> + * Creating a StringCharacterIterator and calling the test functions + * <pre> + * \code + * void CharacterIterator_Example( void ) + * { + * cout << endl << "===== CharacterIterator_Example: =====" << endl; + * UnicodeString text("Ein kleiner Satz."); + * StringCharacterIterator iterator(text); + * cout << "----- traverseForward: -----------" << endl; + * traverseForward( iterator ); + * cout << endl << endl << "----- traverseBackward: ----------" << endl; + * traverseBackward( iterator ); + * cout << endl << endl << "----- traverseOut: ---------------" << endl; + * traverseOut( iterator, 7 ); + * cout << endl << endl << "-----" << endl; + * } + * \endcode + * </pre> + * + * @stable ICU 2.0 + */ +class U_COMMON_API CharacterIterator : public ForwardCharacterIterator { +public: + /** + * Origin enumeration for the move() and move32() functions. + * @stable ICU 2.0 + */ + enum EOrigin { kStart, kCurrent, kEnd }; + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~CharacterIterator(); + + /** + * Returns a pointer to a new CharacterIterator of the same + * concrete class as this one, and referring to the same + * character in the same text-storage object as this one. The + * caller is responsible for deleting the new clone. + * @return a pointer to a new CharacterIterator + * @stable ICU 2.0 + */ + virtual CharacterIterator* clone() const = 0; + + /** + * Sets the iterator to refer to the first code unit in its + * iteration range, and returns that code unit. + * This can be used to begin an iteration with next(). + * @return the first code unit in its iteration range. + * @stable ICU 2.0 + */ + virtual char16_t first(void) = 0; + + /** + * Sets the iterator to refer to the first code unit in its + * iteration range, returns that code unit, and moves the position + * to the second code unit. This is an alternative to setToStart() + * for forward iteration with nextPostInc(). + * @return the first code unit in its iteration range. + * @stable ICU 2.0 + */ + virtual char16_t firstPostInc(void); + + /** + * Sets the iterator to refer to the first code point in its + * iteration range, and returns that code unit, + * This can be used to begin an iteration with next32(). + * Note that an iteration with next32PostInc(), beginning with, + * e.g., setToStart() or firstPostInc(), is more efficient. + * @return the first code point in its iteration range. + * @stable ICU 2.0 + */ + virtual UChar32 first32(void) = 0; + + /** + * Sets the iterator to refer to the first code point in its + * iteration range, returns that code point, and moves the position + * to the second code point. This is an alternative to setToStart() + * for forward iteration with next32PostInc(). + * @return the first code point in its iteration range. + * @stable ICU 2.0 + */ + virtual UChar32 first32PostInc(void); + + /** + * Sets the iterator to refer to the first code unit or code point in its + * iteration range. This can be used to begin a forward + * iteration with nextPostInc() or next32PostInc(). + * @return the start position of the iteration range + * @stable ICU 2.0 + */ + inline int32_t setToStart(); + + /** + * Sets the iterator to refer to the last code unit in its + * iteration range, and returns that code unit. + * This can be used to begin an iteration with previous(). + * @return the last code unit. + * @stable ICU 2.0 + */ + virtual char16_t last(void) = 0; + + /** + * Sets the iterator to refer to the last code point in its + * iteration range, and returns that code unit. + * This can be used to begin an iteration with previous32(). + * @return the last code point. + * @stable ICU 2.0 + */ + virtual UChar32 last32(void) = 0; + + /** + * Sets the iterator to the end of its iteration range, just behind + * the last code unit or code point. This can be used to begin a backward + * iteration with previous() or previous32(). + * @return the end position of the iteration range + * @stable ICU 2.0 + */ + inline int32_t setToEnd(); + + /** + * Sets the iterator to refer to the "position"-th code unit + * in the text-storage object the iterator refers to, and + * returns that code unit. + * @param position the "position"-th code unit in the text-storage object + * @return the "position"-th code unit. + * @stable ICU 2.0 + */ + virtual char16_t setIndex(int32_t position) = 0; + + /** + * Sets the iterator to refer to the beginning of the code point + * that contains the "position"-th code unit + * in the text-storage object the iterator refers to, and + * returns that code point. + * The current position is adjusted to the beginning of the code point + * (its first code unit). + * @param position the "position"-th code unit in the text-storage object + * @return the "position"-th code point. + * @stable ICU 2.0 + */ + virtual UChar32 setIndex32(int32_t position) = 0; + + /** + * Returns the code unit the iterator currently refers to. + * @return the current code unit. + * @stable ICU 2.0 + */ + virtual char16_t current(void) const = 0; + + /** + * Returns the code point the iterator currently refers to. + * @return the current code point. + * @stable ICU 2.0 + */ + virtual UChar32 current32(void) const = 0; + + /** + * Advances to the next code unit in the iteration range + * (toward endIndex()), and returns that code unit. If there are + * no more code units to return, returns DONE. + * @return the next code unit. + * @stable ICU 2.0 + */ + virtual char16_t next(void) = 0; + + /** + * Advances to the next code point in the iteration range + * (toward endIndex()), and returns that code point. If there are + * no more code points to return, returns DONE. + * Note that iteration with "pre-increment" semantics is less + * efficient than iteration with "post-increment" semantics + * that is provided by next32PostInc(). + * @return the next code point. + * @stable ICU 2.0 + */ + virtual UChar32 next32(void) = 0; + + /** + * Advances to the previous code unit in the iteration range + * (toward startIndex()), and returns that code unit. If there are + * no more code units to return, returns DONE. + * @return the previous code unit. + * @stable ICU 2.0 + */ + virtual char16_t previous(void) = 0; + + /** + * Advances to the previous code point in the iteration range + * (toward startIndex()), and returns that code point. If there are + * no more code points to return, returns DONE. + * @return the previous code point. + * @stable ICU 2.0 + */ + virtual UChar32 previous32(void) = 0; + + /** + * Returns false if there are no more code units or code points + * before the current position in the iteration range. + * This is used with previous() or previous32() in backward + * iteration. + * @return false if there are no more code units or code points + * before the current position in the iteration range, return true otherwise. + * @stable ICU 2.0 + */ + virtual UBool hasPrevious() = 0; + + /** + * Returns the numeric index in the underlying text-storage + * object of the character returned by first(). Since it's + * possible to create an iterator that iterates across only + * part of a text-storage object, this number isn't + * necessarily 0. + * @returns the numeric index in the underlying text-storage + * object of the character returned by first(). + * @stable ICU 2.0 + */ + inline int32_t startIndex(void) const; + + /** + * Returns the numeric index in the underlying text-storage + * object of the position immediately BEYOND the character + * returned by last(). + * @return the numeric index in the underlying text-storage + * object of the position immediately BEYOND the character + * returned by last(). + * @stable ICU 2.0 + */ + inline int32_t endIndex(void) const; + + /** + * Returns the numeric index in the underlying text-storage + * object of the character the iterator currently refers to + * (i.e., the character returned by current()). + * @return the numeric index in the text-storage object of + * the character the iterator currently refers to + * @stable ICU 2.0 + */ + inline int32_t getIndex(void) const; + + /** + * Returns the length of the entire text in the underlying + * text-storage object. + * @return the length of the entire text in the text-storage object + * @stable ICU 2.0 + */ + inline int32_t getLength() const; + + /** + * Moves the current position relative to the start or end of the + * iteration range, or relative to the current position itself. + * The movement is expressed in numbers of code units forward + * or backward by specifying a positive or negative delta. + * @param delta the position relative to origin. A positive delta means forward; + * a negative delta means backward. + * @param origin Origin enumeration {kStart, kCurrent, kEnd} + * @return the new position + * @stable ICU 2.0 + */ + virtual int32_t move(int32_t delta, EOrigin origin) = 0; + + /** + * Moves the current position relative to the start or end of the + * iteration range, or relative to the current position itself. + * The movement is expressed in numbers of code points forward + * or backward by specifying a positive or negative delta. + * @param delta the position relative to origin. A positive delta means forward; + * a negative delta means backward. + * @param origin Origin enumeration {kStart, kCurrent, kEnd} + * @return the new position + * @stable ICU 2.0 + */ +#ifdef move32 + // One of the system headers right now is sometimes defining a conflicting macro we don't use +#undef move32 +#endif + virtual int32_t move32(int32_t delta, EOrigin origin) = 0; + + /** + * Copies the text under iteration into the UnicodeString + * referred to by "result". + * @param result Receives a copy of the text under iteration. + * @stable ICU 2.0 + */ + virtual void getText(UnicodeString& result) = 0; + +protected: + /** + * Empty constructor. + * @stable ICU 2.0 + */ + CharacterIterator(); + + /** + * Constructor, just setting the length field in this base class. + * @stable ICU 2.0 + */ + CharacterIterator(int32_t length); + + /** + * Constructor, just setting the length and position fields in this base class. + * @stable ICU 2.0 + */ + CharacterIterator(int32_t length, int32_t position); + + /** + * Constructor, just setting the length, start, end, and position fields in this base class. + * @stable ICU 2.0 + */ + CharacterIterator(int32_t length, int32_t textBegin, int32_t textEnd, int32_t position); + + /** + * Copy constructor. + * + * @param that The CharacterIterator to be copied + * @stable ICU 2.0 + */ + CharacterIterator(const CharacterIterator &that); + + /** + * Assignment operator. Sets this CharacterIterator to have the same behavior, + * as the one passed in. + * @param that The CharacterIterator passed in. + * @return the newly set CharacterIterator. + * @stable ICU 2.0 + */ + CharacterIterator &operator=(const CharacterIterator &that); + + /** + * Base class text length field. + * Necessary this for correct getText() and hashCode(). + * @stable ICU 2.0 + */ + int32_t textLength; + + /** + * Base class field for the current position. + * @stable ICU 2.0 + */ + int32_t pos; + + /** + * Base class field for the start of the iteration range. + * @stable ICU 2.0 + */ + int32_t begin; + + /** + * Base class field for the end of the iteration range. + * @stable ICU 2.0 + */ + int32_t end; +}; + +inline UBool +ForwardCharacterIterator::operator!=(const ForwardCharacterIterator& that) const { + return !operator==(that); +} + +inline int32_t +CharacterIterator::setToStart() { + return move(0, kStart); +} + +inline int32_t +CharacterIterator::setToEnd() { + return move(0, kEnd); +} + +inline int32_t +CharacterIterator::startIndex(void) const { + return begin; +} + +inline int32_t +CharacterIterator::endIndex(void) const { + return end; +} + +inline int32_t +CharacterIterator::getIndex(void) const { + return pos; +} + +inline int32_t +CharacterIterator::getLength(void) const { + return textLength; +} + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/dbbi.h b/thirdparty/icu4c/common/unicode/dbbi.h new file mode 100644 index 0000000000..3de9cc3814 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/dbbi.h @@ -0,0 +1,48 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1999-2006,2013 IBM Corp. All rights reserved. +********************************************************************** +* Date Name Description +* 12/1/99 rgillam Complete port from Java. +* 01/13/2000 helena Added UErrorCode to ctors. +********************************************************************** +*/ + +#ifndef DBBI_H +#define DBBI_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/rbbi.h" + +#if !UCONFIG_NO_BREAK_ITERATION + +/** + * \file + * \brief C++ API: Dictionary Based Break Iterator + */ + +U_NAMESPACE_BEGIN + +#ifndef U_HIDE_DEPRECATED_API +/** + * An obsolete subclass of RuleBasedBreakIterator. Handling of dictionary- + * based break iteration has been folded into the base class. This class + * is deprecated as of ICU 3.6. + * @deprecated ICU 3.6 + */ +typedef RuleBasedBreakIterator DictionaryBasedBreakIterator; + +#endif /* U_HIDE_DEPRECATED_API */ + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_BREAK_ITERATION */ + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/docmain.h b/thirdparty/icu4c/common/unicode/docmain.h new file mode 100644 index 0000000000..b7984ada03 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/docmain.h @@ -0,0 +1,232 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/******************************************************************** + * COPYRIGHT: + * Copyright (c) 1997-2012, International Business Machines Corporation and + * others. All Rights Reserved. + * + * FILE NAME: DOCMAIN.h + * + * Date Name Description + * 12/11/2000 Ram Creation. + */ + +/** + * \file + * \brief (Non API- contains Doxygen definitions) + * + * This file contains documentation for Doxygen and doesnot have + * any significance with respect to C or C++ API + */ + +/*! \mainpage + * + * \section API API Reference Usage + * + * <h3>C++ Programmers:</h3> + * <p>Use <a href="hierarchy.html">Class Hierarchy</a> or <a href="classes.html"> Alphabetical List </a> + * or <a href="annotated.html"> Compound List</a> + * to find the class you are interested in. For example, to find BreakIterator, + * you can go to the <a href="classes.html"> Alphabetical List</a>, then click on + * "BreakIterator". Once you are at the class, you will find an inheritance + * chart, a list of the public members, a detailed description of the class, + * then detailed member descriptions.</p> + * + * <h3>C Programmers:</h3> + * <p>Use <a href="#Module">Module List</a> or <a href="globals_u.html">File Members</a> + * to find a list of all the functions and constants. + * For example, to find BreakIterator functions you would click on + * <a href="files.html"> File List</a>, + * then find "ubrk.h" and click on it. You will find descriptions of Defines, + * Typedefs, Enumerations, and Functions, with detailed descriptions below. + * If you want to find a specific function, such as ubrk_next(), then click + * first on <a href="globals.html"> File Members</a>, then use your browser + * Find dialog to search for "ubrk_next()".</p> + * + * + * <h3>API References for Previous Releases</h3> + * <p>The API References for each release of ICU are also available as + * a zip file from the ICU + * <a href="http://site.icu-project.org/download">download page</a>.</p> + * + * <hr> + * + * <h2>Architecture (User's Guide)</h2> + * <ul> + * <li><a href="https://unicode-org.github.io/icu/userguide/">Introduction</a></li> + * <li><a href="https://unicode-org.github.io/icu/userguide/i18n">Internationalization</a></li> + * <li><a href="https://unicode-org.github.io/icu/userguide/design">Locale Model, Multithreading, Error Handling, etc.</a></li> + * <li><a href="https://unicode-org.github.io/icu/userguide/conversion">Conversion</a></li> + * </ul> + * + * <hr> + *\htmlonly <h2><a NAME="Module">Module List</a></h2> \endhtmlonly + * <table border="1" cols="3" align="center"> + * <tr> + * <td><strong>Module Name</strong></td> + * <td><strong>C</strong></td> + * <td><strong>C++</strong></td> + * </tr> + * <tr> + * <td>Basic Types and Constants</td> + * <td>utypes.h</td> + * <td>utypes.h</td> + * </tr> + * <tr> + * <td>Strings and Character Iteration</td> + * <td>ustring.h, utf8.h, utf16.h, UText, UCharIterator</td> + * <td>icu::UnicodeString, icu::CharacterIterator, icu::Appendable, icu::StringPiece,icu::ByteSink</td> + * </tr> + * <tr> + * <td>Unicode Character<br/>Properties and Names</td> + * <td>uchar.h, uscript.h</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>Sets of Unicode Code Points and Strings</td> + * <td>uset.h</td> + * <td>icu::UnicodeSet</td> + * </tr> + * <tr> + * <td>Maps from Unicode Code Points to Integer Values</td> + * <td>ucptrie.h, umutablecptrie.h</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>Maps from Strings to Integer Values</td> + * <td>(no C API)</td> + * <td>icu::BytesTrie, icu::UCharsTrie</td> + * </tr> + * <tr> + * <td>Codepage Conversion</td> + * <td>ucnv.h, ucnvsel.h</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>Codepage Detection</td> + * <td>ucsdet.h</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>Unicode Text Compression</td> + * <td>ucnv.h<br/>(encoding name "SCSU" or "BOCU-1")</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>Locales </td> + * <td>uloc.h</a></td> + * <td>icu::Locale, icu::LocaleBuilder, icu::LocaleMatcher</td> + * </tr> + * <tr> + * <td>Resource Bundles</td> + * <td>ures.h</td> + * <td>icu::ResourceBundle</td> + * </tr> + * <tr> + * <td>Normalization</td> + * <td>unorm2.h</td> + * <td>icu::Normalizer2</td> + * </tr> + * <tr> + * <td>Calendars</td> + * <td>ucal.h</td> + * <td>icu::Calendar</td> + * </tr> + * <tr> + * <td>Date and Time Formatting</td> + * <td>udat.h</td> + * <td>icu::DateFormat</td> + * </tr> + * <tr> + * <td>Message Formatting</td> + * <td>umsg.h</td> + * <td>icu::MessageFormat</td> + * </tr> + * <tr> + * <td>Number Formatting<br/>(includes currency and unit formatting)</td> + * <td>unumberformatter.h, unum.h</td> + * <td>icu::number::NumberFormatter (ICU 60+) or icu::NumberFormat (older versions)</td> + * </tr> + * <tr> + * <td>Number Range Formatting<br />(includes currency and unit ranges)</td> + * <td>unumberrangeformatter.h</td> + * <td>icu::number::NumberRangeFormatter</td> + * </tr> + * <tr> + * <td>Number Spellout<br/>(Rule Based Number Formatting)</td> + * <td>unum.h<br/>(use UNUM_SPELLOUT)</td> + * <td>icu::RuleBasedNumberFormat</td> + * </tr> + * <tr> + * <td>Text Transformation<br/>(Transliteration)</td> + * <td>utrans.h</td> + * <td>icu::Transliterator</td> + * </tr> + * <tr> + * <td>Bidirectional Algorithm</td> + * <td>ubidi.h, ubiditransform.h</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>Arabic Shaping</td> + * <td>ushape.h</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>Collation</td> + * <td>ucol.h</td> + * <td>icu::Collator</td> + * </tr> + * <tr> + * <td>String Searching</td> + * <td>usearch.h</td> + * <td>icu::StringSearch</td> + * </tr> + * <tr> + * <td>Index Characters/<br/>Bucketing for Sorted Lists</td> + * <td>(no C API)</td> + * <td>icu::AlphabeticIndex</td> + * </tr> + * <tr> + * <td>Text Boundary Analysis<br/>(Break Iteration)</td> + * <td>ubrk.h</td> + * <td>icu::BreakIterator</td> + * </tr> + * <tr> + * <td>Regular Expressions</td> + * <td>uregex.h</td> + * <td>icu::RegexPattern, icu::RegexMatcher</td> + * </tr> + * <tr> + * <td>StringPrep</td> + * <td>usprep.h</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>International Domain Names in Applications:<br/> + * UTS #46 in C/C++, IDNA2003 only via C API</td> + * <td>uidna.h</td> + * <td>idna.h</td> + * </tr> + * <tr> + * <td>Identifier Spoofing & Confusability</td> + * <td>uspoof.h</td> + * <td>C API</td> + * <tr> + * <td>Universal Time Scale</td> + * <td>utmscale.h</td> + * <td>C API</td> + * </tr> + * <tr> + * <td>Paragraph Layout / Complex Text Layout</td> + * <td>playout.h</td> + * <td>icu::ParagraphLayout</td> + * </tr> + * <tr> + * <td>ICU I/O</td> + * <td>ustdio.h</td> + * <td>ustream.h</td> + * </tr> + * </table> + * <i>This main page is generated from docmain.h</i> + */ diff --git a/thirdparty/icu4c/common/unicode/dtintrv.h b/thirdparty/icu4c/common/unicode/dtintrv.h new file mode 100644 index 0000000000..4f4b6bf7f4 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/dtintrv.h @@ -0,0 +1,164 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2008-2009, International Business Machines Corporation and +* others. All Rights Reserved. +******************************************************************************* +* +* File DTINTRV.H +* +******************************************************************************* +*/ + +#ifndef __DTINTRV_H__ +#define __DTINTRV_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: Date Interval data type + */ + +U_NAMESPACE_BEGIN + + +/** + * This class represents a date interval. + * It is a pair of UDate representing from UDate 1 to UDate 2. + * @stable ICU 4.0 +**/ +class U_COMMON_API DateInterval : public UObject { +public: + + /** + * Construct a DateInterval given a from date and a to date. + * @param fromDate The from date in date interval. + * @param toDate The to date in date interval. + * @stable ICU 4.0 + */ + DateInterval(UDate fromDate, UDate toDate); + + /** + * destructor + * @stable ICU 4.0 + */ + virtual ~DateInterval(); + + /** + * Get the from date. + * @return the from date in dateInterval. + * @stable ICU 4.0 + */ + inline UDate getFromDate() const; + + /** + * Get the to date. + * @return the to date in dateInterval. + * @stable ICU 4.0 + */ + inline UDate getToDate() const; + + + /** + * Return the class ID for this class. This is useful only for comparing to + * a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . derived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @stable ICU 4.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This + * method is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and clone() + * methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @stable ICU 4.0 + */ + virtual UClassID getDynamicClassID(void) const; + + + /** + * Copy constructor. + * @stable ICU 4.0 + */ + DateInterval(const DateInterval& other); + + /** + * Default assignment operator + * @stable ICU 4.0 + */ + DateInterval& operator=(const DateInterval&); + + /** + * Equality operator. + * @return true if the two DateIntervals are the same + * @stable ICU 4.0 + */ + virtual UBool operator==(const DateInterval& other) const; + + /** + * Non-equality operator + * @return true if the two DateIntervals are not the same + * @stable ICU 4.0 + */ + inline UBool operator!=(const DateInterval& other) const; + + + /** + * clone this object. + * The caller owns the result and should delete it when done. + * @return a cloned DateInterval + * @stable ICU 4.0 + */ + virtual DateInterval* clone() const; + +private: + /** + * Default constructor, not implemented. + */ + DateInterval(); + + UDate fromDate; + UDate toDate; + +} ;// end class DateInterval + + +inline UDate +DateInterval::getFromDate() const { + return fromDate; +} + + +inline UDate +DateInterval::getToDate() const { + return toDate; +} + + +inline UBool +DateInterval::operator!=(const DateInterval& other) const { + return ( !operator==(other) ); +} + + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/edits.h b/thirdparty/icu4c/common/unicode/edits.h new file mode 100644 index 0000000000..bfa07fa676 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/edits.h @@ -0,0 +1,531 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// edits.h +// created: 2016dec30 Markus W. Scherer + +#ifndef __EDITS_H__ +#define __EDITS_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: C++ class Edits for low-level string transformations on styled text. + */ + +U_NAMESPACE_BEGIN + +class UnicodeString; + +/** + * Records lengths of string edits but not replacement text. Supports replacements, insertions, deletions + * in linear progression. Does not support moving/reordering of text. + * + * There are two types of edits: <em>change edits</em> and <em>no-change edits</em>. Add edits to + * instances of this class using {@link #addReplace(int32_t, int32_t)} (for change edits) and + * {@link #addUnchanged(int32_t)} (for no-change edits). Change edits are retained with full granularity, + * whereas adjacent no-change edits are always merged together. In no-change edits, there is a one-to-one + * mapping between code points in the source and destination strings. + * + * After all edits have been added, instances of this class should be considered immutable, and an + * {@link Edits::Iterator} can be used for queries. + * + * There are four flavors of Edits::Iterator: + * + * <ul> + * <li>{@link #getFineIterator()} retains full granularity of change edits. + * <li>{@link #getFineChangesIterator()} retains full granularity of change edits, and when calling + * next() on the iterator, skips over no-change edits (unchanged regions). + * <li>{@link #getCoarseIterator()} treats adjacent change edits as a single edit. (Adjacent no-change + * edits are automatically merged during the construction phase.) + * <li>{@link #getCoarseChangesIterator()} treats adjacent change edits as a single edit, and when + * calling next() on the iterator, skips over no-change edits (unchanged regions). + * </ul> + * + * For example, consider the string "abcßDeF", which case-folds to "abcssdef". This string has the + * following fine edits: + * <ul> + * <li>abc ⇨ abc (no-change) + * <li>ß ⇨ ss (change) + * <li>D ⇨ d (change) + * <li>e ⇨ e (no-change) + * <li>F ⇨ f (change) + * </ul> + * and the following coarse edits (note how adjacent change edits get merged together): + * <ul> + * <li>abc ⇨ abc (no-change) + * <li>ßD ⇨ ssd (change) + * <li>e ⇨ e (no-change) + * <li>F ⇨ f (change) + * </ul> + * + * The "fine changes" and "coarse changes" iterators will step through only the change edits when their + * `Edits::Iterator::next()` methods are called. They are identical to the non-change iterators when + * their `Edits::Iterator::findSourceIndex()` or `Edits::Iterator::findDestinationIndex()` + * methods are used to walk through the string. + * + * For examples of how to use this class, see the test `TestCaseMapEditsIteratorDocs` in + * UCharacterCaseTest.java. + * + * An Edits object tracks a separate UErrorCode, but ICU string transformation functions + * (e.g., case mapping functions) merge any such errors into their API's UErrorCode. + * + * @stable ICU 59 + */ +class U_COMMON_API Edits U_FINAL : public UMemory { +public: + /** + * Constructs an empty object. + * @stable ICU 59 + */ + Edits() : + array(stackArray), capacity(STACK_CAPACITY), length(0), delta(0), numChanges(0), + errorCode_(U_ZERO_ERROR) {} + /** + * Copy constructor. + * @param other source edits + * @stable ICU 60 + */ + Edits(const Edits &other) : + array(stackArray), capacity(STACK_CAPACITY), length(other.length), + delta(other.delta), numChanges(other.numChanges), + errorCode_(other.errorCode_) { + copyArray(other); + } + /** + * Move constructor, might leave src empty. + * This object will have the same contents that the source object had. + * @param src source edits + * @stable ICU 60 + */ + Edits(Edits &&src) U_NOEXCEPT : + array(stackArray), capacity(STACK_CAPACITY), length(src.length), + delta(src.delta), numChanges(src.numChanges), + errorCode_(src.errorCode_) { + moveArray(src); + } + + /** + * Destructor. + * @stable ICU 59 + */ + ~Edits(); + + /** + * Assignment operator. + * @param other source edits + * @return *this + * @stable ICU 60 + */ + Edits &operator=(const Edits &other); + + /** + * Move assignment operator, might leave src empty. + * This object will have the same contents that the source object had. + * The behavior is undefined if *this and src are the same object. + * @param src source edits + * @return *this + * @stable ICU 60 + */ + Edits &operator=(Edits &&src) U_NOEXCEPT; + + /** + * Resets the data but may not release memory. + * @stable ICU 59 + */ + void reset() U_NOEXCEPT; + + /** + * Adds a no-change edit: a record for an unchanged segment of text. + * Normally called from inside ICU string transformation functions, not user code. + * @stable ICU 59 + */ + void addUnchanged(int32_t unchangedLength); + /** + * Adds a change edit: a record for a text replacement/insertion/deletion. + * Normally called from inside ICU string transformation functions, not user code. + * @stable ICU 59 + */ + void addReplace(int32_t oldLength, int32_t newLength); + /** + * Sets the UErrorCode if an error occurred while recording edits. + * Preserves older error codes in the outErrorCode. + * Normally called from inside ICU string transformation functions, not user code. + * @param outErrorCode Set to an error code if it does not contain one already + * and an error occurred while recording edits. + * Otherwise unchanged. + * @return true if U_FAILURE(outErrorCode) + * @stable ICU 59 + */ + UBool copyErrorTo(UErrorCode &outErrorCode) const; + + /** + * How much longer is the new text compared with the old text? + * @return new length minus old length + * @stable ICU 59 + */ + int32_t lengthDelta() const { return delta; } + /** + * @return true if there are any change edits + * @stable ICU 59 + */ + UBool hasChanges() const { return numChanges != 0; } + + /** + * @return the number of change edits + * @stable ICU 60 + */ + int32_t numberOfChanges() const { return numChanges; } + + /** + * Access to the list of edits. + * + * At any moment in time, an instance of this class points to a single edit: a "window" into a span + * of the source string and the corresponding span of the destination string. The source string span + * starts at {@link #sourceIndex()} and runs for {@link #oldLength()} chars; the destination string + * span starts at {@link #destinationIndex()} and runs for {@link #newLength()} chars. + * + * The iterator can be moved between edits using the `next()`, `findSourceIndex(int32_t, UErrorCode &)`, + * and `findDestinationIndex(int32_t, UErrorCode &)` methods. + * Calling any of these methods mutates the iterator to make it point to the corresponding edit. + * + * For more information, see the documentation for {@link Edits}. + * + * @see getCoarseIterator + * @see getFineIterator + * @stable ICU 59 + */ + struct U_COMMON_API Iterator U_FINAL : public UMemory { + /** + * Default constructor, empty iterator. + * @stable ICU 60 + */ + Iterator() : + array(nullptr), index(0), length(0), + remaining(0), onlyChanges_(false), coarse(false), + dir(0), changed(false), oldLength_(0), newLength_(0), + srcIndex(0), replIndex(0), destIndex(0) {} + /** + * Copy constructor. + * @stable ICU 59 + */ + Iterator(const Iterator &other) = default; + /** + * Assignment operator. + * @stable ICU 59 + */ + Iterator &operator=(const Iterator &other) = default; + + /** + * Advances the iterator to the next edit. + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return true if there is another edit + * @stable ICU 59 + */ + UBool next(UErrorCode &errorCode) { return next(onlyChanges_, errorCode); } + + /** + * Moves the iterator to the edit that contains the source index. + * The source index may be found in a no-change edit + * even if normal iteration would skip no-change edits. + * Normal iteration can continue from a found edit. + * + * The iterator state before this search logically does not matter. + * (It may affect the performance of the search.) + * + * The iterator state after this search is undefined + * if the source index is out of bounds for the source string. + * + * @param i source index + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return true if the edit for the source index was found + * @stable ICU 59 + */ + UBool findSourceIndex(int32_t i, UErrorCode &errorCode) { + return findIndex(i, true, errorCode) == 0; + } + + /** + * Moves the iterator to the edit that contains the destination index. + * The destination index may be found in a no-change edit + * even if normal iteration would skip no-change edits. + * Normal iteration can continue from a found edit. + * + * The iterator state before this search logically does not matter. + * (It may affect the performance of the search.) + * + * The iterator state after this search is undefined + * if the source index is out of bounds for the source string. + * + * @param i destination index + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return true if the edit for the destination index was found + * @stable ICU 60 + */ + UBool findDestinationIndex(int32_t i, UErrorCode &errorCode) { + return findIndex(i, false, errorCode) == 0; + } + + /** + * Computes the destination index corresponding to the given source index. + * If the source index is inside a change edit (not at its start), + * then the destination index at the end of that edit is returned, + * since there is no information about index mapping inside a change edit. + * + * (This means that indexes to the start and middle of an edit, + * for example around a grapheme cluster, are mapped to indexes + * encompassing the entire edit. + * The alternative, mapping an interior index to the start, + * would map such an interval to an empty one.) + * + * This operation will usually but not always modify this object. + * The iterator state after this search is undefined. + * + * @param i source index + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return destination index; undefined if i is not 0..string length + * @stable ICU 60 + */ + int32_t destinationIndexFromSourceIndex(int32_t i, UErrorCode &errorCode); + + /** + * Computes the source index corresponding to the given destination index. + * If the destination index is inside a change edit (not at its start), + * then the source index at the end of that edit is returned, + * since there is no information about index mapping inside a change edit. + * + * (This means that indexes to the start and middle of an edit, + * for example around a grapheme cluster, are mapped to indexes + * encompassing the entire edit. + * The alternative, mapping an interior index to the start, + * would map such an interval to an empty one.) + * + * This operation will usually but not always modify this object. + * The iterator state after this search is undefined. + * + * @param i destination index + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return source index; undefined if i is not 0..string length + * @stable ICU 60 + */ + int32_t sourceIndexFromDestinationIndex(int32_t i, UErrorCode &errorCode); + + /** + * Returns whether the edit currently represented by the iterator is a change edit. + * + * @return true if this edit replaces oldLength() units with newLength() different ones. + * false if oldLength units remain unchanged. + * @stable ICU 59 + */ + UBool hasChange() const { return changed; } + + /** + * The length of the current span in the source string, which starts at {@link #sourceIndex}. + * + * @return the number of units in the original string which are replaced or remain unchanged. + * @stable ICU 59 + */ + int32_t oldLength() const { return oldLength_; } + + /** + * The length of the current span in the destination string, which starts at + * {@link #destinationIndex}, or in the replacement string, which starts at + * {@link #replacementIndex}. + * + * @return the number of units in the modified string, if hasChange() is true. + * Same as oldLength if hasChange() is false. + * @stable ICU 59 + */ + int32_t newLength() const { return newLength_; } + + /** + * The start index of the current span in the source string; the span has length + * {@link #oldLength}. + * + * @return the current index into the source string + * @stable ICU 59 + */ + int32_t sourceIndex() const { return srcIndex; } + + /** + * The start index of the current span in the replacement string; the span has length + * {@link #newLength}. Well-defined only if the current edit is a change edit. + * + * The *replacement string* is the concatenation of all substrings of the destination + * string corresponding to change edits. + * + * This method is intended to be used together with operations that write only replacement + * characters (e.g. operations specifying the \ref U_OMIT_UNCHANGED_TEXT option). + * The source string can then be modified in-place. + * + * @return the current index into the replacement-characters-only string, + * not counting unchanged spans + * @stable ICU 59 + */ + int32_t replacementIndex() const { + // TODO: Throw an exception if we aren't in a change edit? + return replIndex; + } + + /** + * The start index of the current span in the destination string; the span has length + * {@link #newLength}. + * + * @return the current index into the full destination string + * @stable ICU 59 + */ + int32_t destinationIndex() const { return destIndex; } + +#ifndef U_HIDE_INTERNAL_API + /** + * A string representation of the current edit represented by the iterator for debugging. You + * should not depend on the contents of the return string. + * @internal + */ + UnicodeString& toString(UnicodeString& appendTo) const; +#endif // U_HIDE_INTERNAL_API + + private: + friend class Edits; + + Iterator(const uint16_t *a, int32_t len, UBool oc, UBool crs); + + int32_t readLength(int32_t head); + void updateNextIndexes(); + void updatePreviousIndexes(); + UBool noNext(); + UBool next(UBool onlyChanges, UErrorCode &errorCode); + UBool previous(UErrorCode &errorCode); + /** @return -1: error or i<0; 0: found; 1: i>=string length */ + int32_t findIndex(int32_t i, UBool findSource, UErrorCode &errorCode); + + const uint16_t *array; + int32_t index, length; + // 0 if we are not within compressed equal-length changes. + // Otherwise the number of remaining changes, including the current one. + int32_t remaining; + UBool onlyChanges_, coarse; + + int8_t dir; // iteration direction: back(<0), initial(0), forward(>0) + UBool changed; + int32_t oldLength_, newLength_; + int32_t srcIndex, replIndex, destIndex; + }; + + /** + * Returns an Iterator for coarse-grained change edits + * (adjacent change edits are treated as one). + * Can be used to perform simple string updates. + * Skips no-change edits. + * @return an Iterator that merges adjacent changes. + * @stable ICU 59 + */ + Iterator getCoarseChangesIterator() const { + return Iterator(array, length, true, true); + } + + /** + * Returns an Iterator for coarse-grained change and no-change edits + * (adjacent change edits are treated as one). + * Can be used to perform simple string updates. + * Adjacent change edits are treated as one edit. + * @return an Iterator that merges adjacent changes. + * @stable ICU 59 + */ + Iterator getCoarseIterator() const { + return Iterator(array, length, false, true); + } + + /** + * Returns an Iterator for fine-grained change edits + * (full granularity of change edits is retained). + * Can be used for modifying styled text. + * Skips no-change edits. + * @return an Iterator that separates adjacent changes. + * @stable ICU 59 + */ + Iterator getFineChangesIterator() const { + return Iterator(array, length, true, false); + } + + /** + * Returns an Iterator for fine-grained change and no-change edits + * (full granularity of change edits is retained). + * Can be used for modifying styled text. + * @return an Iterator that separates adjacent changes. + * @stable ICU 59 + */ + Iterator getFineIterator() const { + return Iterator(array, length, false, false); + } + + /** + * Merges the two input Edits and appends the result to this object. + * + * Consider two string transformations (for example, normalization and case mapping) + * where each records Edits in addition to writing an output string.<br> + * Edits ab reflect how substrings of input string a + * map to substrings of intermediate string b.<br> + * Edits bc reflect how substrings of intermediate string b + * map to substrings of output string c.<br> + * This function merges ab and bc such that the additional edits + * recorded in this object reflect how substrings of input string a + * map to substrings of output string c. + * + * If unrelated Edits are passed in where the output string of the first + * has a different length than the input string of the second, + * then a U_ILLEGAL_ARGUMENT_ERROR is reported. + * + * @param ab reflects how substrings of input string a + * map to substrings of intermediate string b. + * @param bc reflects how substrings of intermediate string b + * map to substrings of output string c. + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return *this, with the merged edits appended + * @stable ICU 60 + */ + Edits &mergeAndAppend(const Edits &ab, const Edits &bc, UErrorCode &errorCode); + +private: + void releaseArray() U_NOEXCEPT; + Edits ©Array(const Edits &other); + Edits &moveArray(Edits &src) U_NOEXCEPT; + + void setLastUnit(int32_t last) { array[length - 1] = (uint16_t)last; } + int32_t lastUnit() const { return length > 0 ? array[length - 1] : 0xffff; } + + void append(int32_t r); + UBool growArray(); + + static const int32_t STACK_CAPACITY = 100; + uint16_t *array; + int32_t capacity; + int32_t length; + int32_t delta; + int32_t numChanges; + UErrorCode errorCode_; + uint16_t stackArray[STACK_CAPACITY]; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __EDITS_H__ diff --git a/thirdparty/icu4c/common/unicode/enumset.h b/thirdparty/icu4c/common/unicode/enumset.h new file mode 100644 index 0000000000..bde8c455c0 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/enumset.h @@ -0,0 +1,69 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 2012,2014 International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +*/ + +/** + * \file + * \brief C++: internal template EnumSet<> + */ + +#ifndef ENUMSET_H +#define ENUMSET_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/* Can't use #ifndef U_HIDE_INTERNAL_API for the entire EnumSet class, needed in .h file declarations */ +/** + * enum bitset for boolean fields. Similar to Java EnumSet<>. + * Needs to range check. Used for private instance variables. + * @internal + * \cond + */ +template<typename T, uint32_t minValue, uint32_t limitValue> +class EnumSet { +public: + inline EnumSet() : fBools(0) {} + inline EnumSet(const EnumSet<T,minValue,limitValue>& other) : fBools(other.fBools) {} + inline ~EnumSet() {} +#ifndef U_HIDE_INTERNAL_API + inline void clear() { fBools=0; } + inline void add(T toAdd) { set(toAdd, 1); } + inline void remove(T toRemove) { set(toRemove, 0); } + inline int32_t contains(T toCheck) const { return get(toCheck); } + inline void set(T toSet, int32_t v) { fBools=(fBools&(~flag(toSet)))|(v?(flag(toSet)):0); } + inline int32_t get(T toCheck) const { return (fBools & flag(toCheck))?1:0; } + inline UBool isValidEnum(T toCheck) const { return (toCheck>=minValue&&toCheck<limitValue); } + inline UBool isValidValue(int32_t v) const { return (v==0||v==1); } + inline const EnumSet<T,minValue,limitValue>& operator=(const EnumSet<T,minValue,limitValue>& other) { + fBools = other.fBools; + return *this; + } + + inline uint32_t getAll() const { + return fBools; + } +#endif /* U_HIDE_INTERNAL_API */ + +private: + inline uint32_t flag(T toCheck) const { return (1<<(toCheck-minValue)); } +private: + uint32_t fBools; +}; + +/** \endcond */ + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ +#endif /* ENUMSET_H */ diff --git a/thirdparty/icu4c/common/unicode/errorcode.h b/thirdparty/icu4c/common/unicode/errorcode.h new file mode 100644 index 0000000000..fe7b518323 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/errorcode.h @@ -0,0 +1,144 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2009-2011, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: errorcode.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2009mar10 +* created by: Markus W. Scherer +*/ + +#ifndef __ERRORCODE_H__ +#define __ERRORCODE_H__ + +/** + * \file + * \brief C++ API: ErrorCode class intended to make it easier to use + * ICU C and C++ APIs from C++ user code. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + +U_NAMESPACE_BEGIN + +/** + * Wrapper class for UErrorCode, with conversion operators for direct use + * in ICU C and C++ APIs. + * Intended to be used as a base class, where a subclass overrides + * the handleFailure() function so that it throws an exception, + * does an assert(), logs an error, etc. + * This is not an abstract base class. This class can be used and instantiated + * by itself, although it will be more useful when subclassed. + * + * Features: + * - The constructor initializes the internal UErrorCode to U_ZERO_ERROR, + * removing one common source of errors. + * - Same use in C APIs taking a UErrorCode * (pointer) + * and C++ taking UErrorCode & (reference) via conversion operators. + * - Possible automatic checking for success when it goes out of scope. + * + * Note: For automatic checking for success in the destructor, a subclass + * must implement such logic in its own destructor because the base class + * destructor cannot call a subclass function (like handleFailure()). + * The ErrorCode base class destructor does nothing. + * + * Note also: While it is possible for a destructor to throw an exception, + * it is generally unsafe to do so. This means that in a subclass the destructor + * and the handleFailure() function may need to take different actions. + * + * Sample code: + * \code + * class IcuErrorCode: public icu::ErrorCode { + * public: + * virtual ~IcuErrorCode() { // should be defined in .cpp as "key function" + * // Safe because our handleFailure() does not throw exceptions. + * if(isFailure()) { handleFailure(); } + * } + * protected: + * virtual void handleFailure() const { + * log_failure(u_errorName(errorCode)); + * exit(errorCode); + * } + * }; + * IcuErrorCode error_code; + * UConverter *cnv = ucnv_open("Shift-JIS", error_code); + * length = ucnv_fromUChars(dest, capacity, src, length, error_code); + * ucnv_close(cnv); + * // IcuErrorCode destructor checks for success. + * \endcode + * + * @stable ICU 4.2 + */ +class U_COMMON_API ErrorCode: public UMemory { +public: + /** + * Default constructor. Initializes its UErrorCode to U_ZERO_ERROR. + * @stable ICU 4.2 + */ + ErrorCode() : errorCode(U_ZERO_ERROR) {} + /** Destructor, does nothing. See class documentation for details. @stable ICU 4.2 */ + virtual ~ErrorCode(); + /** Conversion operator, returns a reference. @stable ICU 4.2 */ + operator UErrorCode & () { return errorCode; } + /** Conversion operator, returns a pointer. @stable ICU 4.2 */ + operator UErrorCode * () { return &errorCode; } + /** Tests for U_SUCCESS(). @stable ICU 4.2 */ + UBool isSuccess() const { return U_SUCCESS(errorCode); } + /** Tests for U_FAILURE(). @stable ICU 4.2 */ + UBool isFailure() const { return U_FAILURE(errorCode); } + /** Returns the UErrorCode value. @stable ICU 4.2 */ + UErrorCode get() const { return errorCode; } + /** Sets the UErrorCode value. @stable ICU 4.2 */ + void set(UErrorCode value) { errorCode=value; } + /** Returns the UErrorCode value and resets it to U_ZERO_ERROR. @stable ICU 4.2 */ + UErrorCode reset(); + /** + * Asserts isSuccess(). + * In other words, this method checks for a failure code, + * and the base class handles it like this: + * \code + * if(isFailure()) { handleFailure(); } + * \endcode + * @stable ICU 4.4 + */ + void assertSuccess() const; + /** + * Return a string for the UErrorCode value. + * The string will be the same as the name of the error code constant + * in the UErrorCode enum. + * @stable ICU 4.4 + */ + const char* errorName() const; + +protected: + /** + * Internal UErrorCode, accessible to subclasses. + * @stable ICU 4.2 + */ + UErrorCode errorCode; + /** + * Called by assertSuccess() if isFailure() is true. + * A subclass should override this function to deal with a failure code: + * Throw an exception, log an error, terminate the program, or similar. + * @stable ICU 4.2 + */ + virtual void handleFailure() const {} +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __ERRORCODE_H__ diff --git a/thirdparty/icu4c/common/unicode/filteredbrk.h b/thirdparty/icu4c/common/unicode/filteredbrk.h new file mode 100644 index 0000000000..8b07e39ae1 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/filteredbrk.h @@ -0,0 +1,152 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************** +* Copyright (C) 1997-2015, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************** +*/ + +#ifndef FILTEREDBRK_H +#define FILTEREDBRK_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/brkiter.h" + +#if !UCONFIG_NO_BREAK_ITERATION && !UCONFIG_NO_FILTERED_BREAK_ITERATION + +U_NAMESPACE_BEGIN + +/** + * \file + * \brief C++ API: FilteredBreakIteratorBuilder + */ + +/** + * The BreakIteratorFilter is used to modify the behavior of a BreakIterator + * by constructing a new BreakIterator which suppresses certain segment boundaries. + * See http://www.unicode.org/reports/tr35/tr35-general.html#Segmentation_Exceptions . + * For example, a typical English Sentence Break Iterator would break on the space + * in the string "Mr. Smith" (resulting in two segments), + * but with "Mr." as an exception, a filtered break iterator + * would consider the string "Mr. Smith" to be a single segment. + * + * @stable ICU 56 + */ +class U_COMMON_API FilteredBreakIteratorBuilder : public UObject { + public: + /** + * destructor. + * @stable ICU 56 + */ + virtual ~FilteredBreakIteratorBuilder(); + + /** + * Construct a FilteredBreakIteratorBuilder based on rules in a locale. + * The rules are taken from CLDR exception data for the locale, + * see http://www.unicode.org/reports/tr35/tr35-general.html#Segmentation_Exceptions + * This is the equivalent of calling createInstance(UErrorCode&) + * and then repeatedly calling addNoBreakAfter(...) with the contents + * of the CLDR exception data. + * @param where the locale. + * @param status The error code. + * @return the new builder + * @stable ICU 56 + */ + static FilteredBreakIteratorBuilder *createInstance(const Locale& where, UErrorCode& status); + +#ifndef U_HIDE_DEPRECATED_API + /** + * This function has been deprecated in favor of createEmptyInstance, which has + * identical behavior. + * @param status The error code. + * @return the new builder + * @deprecated ICU 60 use createEmptyInstance instead + * @see createEmptyInstance() + */ + static FilteredBreakIteratorBuilder *createInstance(UErrorCode &status); +#endif /* U_HIDE_DEPRECATED_API */ + + /** + * Construct an empty FilteredBreakIteratorBuilder. + * In this state, it will not suppress any segment boundaries. + * @param status The error code. + * @return the new builder + * @stable ICU 60 + */ + static FilteredBreakIteratorBuilder *createEmptyInstance(UErrorCode &status); + + /** + * Suppress a certain string from being the end of a segment. + * For example, suppressing "Mr.", then segments ending in "Mr." will not be returned + * by the iterator. + * @param string the string to suppress, such as "Mr." + * @param status error code + * @return returns true if the string was not present and now added, + * false if the call was a no-op because the string was already being suppressed. + * @stable ICU 56 + */ + virtual UBool suppressBreakAfter(const UnicodeString& string, UErrorCode& status) = 0; + + /** + * Stop suppressing a certain string from being the end of the segment. + * This function does not create any new segment boundaries, but only serves to un-do + * the effect of earlier calls to suppressBreakAfter, or to un-do the effect of + * locale data which may be suppressing certain strings. + * @param string the exception to remove + * @param status error code + * @return returns true if the string was present and now removed, + * false if the call was a no-op because the string was not being suppressed. + * @stable ICU 56 + */ + virtual UBool unsuppressBreakAfter(const UnicodeString& string, UErrorCode& status) = 0; + +#ifndef U_FORCE_HIDE_DEPRECATED_API + /** + * This function has been deprecated in favor of wrapIteratorWithFilter() + * The behavior is identical. + * @param adoptBreakIterator the break iterator to adopt + * @param status error code + * @return the new BreakIterator, owned by the caller. + * @deprecated ICU 60 use wrapIteratorWithFilter() instead + * @see wrapBreakIteratorWithFilter() + */ + virtual BreakIterator *build(BreakIterator* adoptBreakIterator, UErrorCode& status) = 0; +#endif // U_FORCE_HIDE_DEPRECATED_API + + /** + * Wrap (adopt) an existing break iterator in a new filtered instance. + * The resulting BreakIterator is owned by the caller. + * The BreakIteratorFilter may be destroyed before the BreakIterator is destroyed. + * Note that the adoptBreakIterator is adopted by the new BreakIterator + * and should no longer be used by the caller. + * The FilteredBreakIteratorBuilder may be reused. + * This function is an alias for build() + * @param adoptBreakIterator the break iterator to adopt + * @param status error code + * @return the new BreakIterator, owned by the caller. + * @stable ICU 60 + */ + inline BreakIterator *wrapIteratorWithFilter(BreakIterator* adoptBreakIterator, UErrorCode& status) { + return build(adoptBreakIterator, status); + } + + protected: + /** + * For subclass use + * @stable ICU 56 + */ + FilteredBreakIteratorBuilder(); +}; + + +U_NAMESPACE_END + +#endif // #if !UCONFIG_NO_BREAK_ITERATION && !UCONFIG_NO_FILTERED_BREAK_ITERATION + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // #ifndef FILTEREDBRK_H diff --git a/thirdparty/icu4c/common/unicode/icudataver.h b/thirdparty/icu4c/common/unicode/icudataver.h new file mode 100644 index 0000000000..f218ed8ebc --- /dev/null +++ b/thirdparty/icu4c/common/unicode/icudataver.h @@ -0,0 +1,43 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 2009-2013, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +*/ + + +/** + * \file + * \brief C API: access to ICU Data Version number + */ + +#ifndef __ICU_DATA_VER_H__ +#define __ICU_DATA_VER_H__ + +#include "unicode/utypes.h" + +/** + * @stable ICU 49 + */ +#define U_ICU_VERSION_BUNDLE "icuver" + +/** + * @stable ICU 49 + */ +#define U_ICU_DATA_KEY "DataVersion" + +/** + * Retrieves the data version from icuver and stores it in dataVersionFillin. + * + * @param dataVersionFillin icuver data version information to be filled in if not-null + * @param status stores the error code from the calls to resource bundle + * + * @stable ICU 49 + */ +U_CAPI void U_EXPORT2 u_getDataVersion(UVersionInfo dataVersionFillin, UErrorCode *status); + +#endif diff --git a/thirdparty/icu4c/common/unicode/icuplug.h b/thirdparty/icu4c/common/unicode/icuplug.h new file mode 100644 index 0000000000..52f810da57 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/icuplug.h @@ -0,0 +1,388 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 2009-2015, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* +* FILE NAME : icuplug.h +* +* Date Name Description +* 10/29/2009 sl New. +****************************************************************************** +*/ + +/** + * \file + * \brief C API: ICU Plugin API + * + * <h2>C API: ICU Plugin API</h2> + * + * <p>C API allowing run-time loadable modules that extend or modify ICU functionality.</p> + * + * <h3>Loading and Configuration</h3> + * + * <p>At ICU startup time, the environment variable "ICU_PLUGINS" will be + * queried for a directory name. If it is not set, the preprocessor symbol + * "DEFAULT_ICU_PLUGINS" will be checked for a default value.</p> + * + * <p>Within the above-named directory, the file "icuplugins##.txt" will be + * opened, if present, where ## is the major+minor number of the currently + * running ICU (such as, 44 for ICU 4.4, thus icuplugins44.txt)</p> + * + * <p>The configuration file has this format:</p> + * + * <ul> + * <li>Hash (#) begins a comment line</li> + * + * <li>Non-comment lines have two or three components: + * LIBRARYNAME ENTRYPOINT [ CONFIGURATION .. ]</li> + * + * <li>Tabs or spaces separate the three items.</li> + * + * <li>LIBRARYNAME is the name of a shared library, either a short name if + * it is on the loader path, or a full pathname.</li> + * + * <li>ENTRYPOINT is the short (undecorated) symbol name of the plugin's + * entrypoint, as above.</li> + * + * <li>CONFIGURATION is the entire rest of the line . It's passed as-is to + * the plugin.</li> + * </ul> + * + * <p>An example configuration file is, in its entirety:</p> + * + * \code + * # this is icuplugins44.txt + * testplug.dll myPlugin hello=world + * \endcode + * <p>Plugins are categorized as "high" or "low" level. Low level are those + * which must be run BEFORE high level plugins, and before any operations + * which cause ICU to be 'initialized'. If a plugin is low level but + * causes ICU to allocate memory or become initialized, that plugin is said + * to cause a 'level change'. </p> + * + * <p>At load time, ICU first queries all plugins to determine their level, + * then loads all 'low' plugins first, and then loads all 'high' plugins. + * Plugins are otherwise loaded in the order listed in the configuration file.</p> + * + * <h3>Implementing a Plugin</h3> + * \code + * U_CAPI UPlugTokenReturn U_EXPORT2 + * myPlugin (UPlugData *plug, UPlugReason reason, UErrorCode *status) { + * if(reason==UPLUG_REASON_QUERY) { + * uplug_setPlugName(plug, "Simple Plugin"); + * uplug_setPlugLevel(plug, UPLUG_LEVEL_HIGH); + * } else if(reason==UPLUG_REASON_LOAD) { + * ... Set up some ICU things here.... + * } else if(reason==UPLUG_REASON_UNLOAD) { + * ... unload, clean up ... + * } + * return UPLUG_TOKEN; + * } + * \endcode + * + * <p>The UPlugData* is an opaque pointer to the plugin-specific data, and is + * used in all other API calls.</p> + * + * <p>The API contract is:</p> + * <ol><li>The plugin MUST always return UPLUG_TOKEN as a return value- to + * indicate that it is a valid plugin.</li> + * + * <li>When the 'reason' parameter is set to UPLUG_REASON_QUERY, the + * plugin MUST call uplug_setPlugLevel() to indicate whether it is a high + * level or low level plugin.</li> + * + * <li>When the 'reason' parameter is UPLUG_REASON_QUERY, the plugin + * SHOULD call uplug_setPlugName to indicate a human readable plugin name.</li></ol> + * + * + * \internal ICU 4.4 Technology Preview + */ + + +#ifndef ICUPLUG_H +#define ICUPLUG_H + +#include "unicode/utypes.h" + + +#if UCONFIG_ENABLE_PLUGINS || defined(U_IN_DOXYGEN) + + + +/* === Basic types === */ + +#ifndef U_HIDE_INTERNAL_API +/** + * @{ + * Opaque structure passed to/from a plugin. + * use the APIs to access it. + * @internal ICU 4.4 Technology Preview + */ + +struct UPlugData; +typedef struct UPlugData UPlugData; + +/** @} */ + +/** + * Random Token to identify a valid ICU plugin. Plugins must return this + * from the entrypoint. + * @internal ICU 4.4 Technology Preview + */ +#define UPLUG_TOKEN 0x54762486 + +/** + * Max width of names, symbols, and configuration strings + * @internal ICU 4.4 Technology Preview + */ +#define UPLUG_NAME_MAX 100 + + +/** + * Return value from a plugin entrypoint. + * Must always be set to UPLUG_TOKEN + * @see UPLUG_TOKEN + * @internal ICU 4.4 Technology Preview + */ +typedef uint32_t UPlugTokenReturn; + +/** + * Reason code for the entrypoint's call + * @internal ICU 4.4 Technology Preview + */ +typedef enum { + UPLUG_REASON_QUERY = 0, /**< The plugin is being queried for info. **/ + UPLUG_REASON_LOAD = 1, /**< The plugin is being loaded. **/ + UPLUG_REASON_UNLOAD = 2, /**< The plugin is being unloaded. **/ + /** + * Number of known reasons. + * @internal The numeric value may change over time, see ICU ticket #12420. + */ + UPLUG_REASON_COUNT +} UPlugReason; + + +/** + * Level of plugin loading + * INITIAL: UNKNOWN + * QUERY: INVALID -> { LOW | HIGH } + * ERR -> INVALID + * @internal ICU 4.4 Technology Preview + */ +typedef enum { + UPLUG_LEVEL_INVALID = 0, /**< The plugin is invalid, hasn't called uplug_setLevel, or can't load. **/ + UPLUG_LEVEL_UNKNOWN = 1, /**< The plugin is waiting to be installed. **/ + UPLUG_LEVEL_LOW = 2, /**< The plugin must be called before u_init completes **/ + UPLUG_LEVEL_HIGH = 3, /**< The plugin can run at any time. **/ + /** + * Number of known levels. + * @internal The numeric value may change over time, see ICU ticket #12420. + */ + UPLUG_LEVEL_COUNT +} UPlugLevel; + +/** + * Entrypoint for an ICU plugin. + * @param plug the UPlugData handle. + * @param status the plugin's extended status code. + * @return A valid plugin must return UPLUG_TOKEN + * @internal ICU 4.4 Technology Preview + */ +typedef UPlugTokenReturn (U_EXPORT2 UPlugEntrypoint) ( + UPlugData *plug, + UPlugReason reason, + UErrorCode *status); + +/* === Needed for Implementing === */ + +/** + * Request that this plugin not be unloaded at cleanup time. + * This is appropriate for plugins which cannot be cleaned up. + * @see u_cleanup() + * @param plug plugin + * @param dontUnload set true if this plugin can't be unloaded + * @internal ICU 4.4 Technology Preview + */ +U_CAPI void U_EXPORT2 +uplug_setPlugNoUnload(UPlugData *plug, UBool dontUnload); + +/** + * Set the level of this plugin. + * @param plug plugin data handle + * @param level the level of this plugin + * @internal ICU 4.4 Technology Preview + */ +U_CAPI void U_EXPORT2 +uplug_setPlugLevel(UPlugData *plug, UPlugLevel level); + +/** + * Get the level of this plugin. + * @param plug plugin data handle + * @return the level of this plugin + * @internal ICU 4.4 Technology Preview + */ +U_CAPI UPlugLevel U_EXPORT2 +uplug_getPlugLevel(UPlugData *plug); + +/** + * Get the lowest level of plug which can currently load. + * For example, if UPLUG_LEVEL_LOW is returned, then low level plugins may load + * if UPLUG_LEVEL_HIGH is returned, then only high level plugins may load. + * @return the lowest level of plug which can currently load + * @internal ICU 4.4 Technology Preview + */ +U_CAPI UPlugLevel U_EXPORT2 +uplug_getCurrentLevel(void); + + +/** + * Get plug load status + * @return The error code of this plugin's load attempt. + * @internal ICU 4.4 Technology Preview + */ +U_CAPI UErrorCode U_EXPORT2 +uplug_getPlugLoadStatus(UPlugData *plug); + +/** + * Set the human-readable name of this plugin. + * @param plug plugin data handle + * @param name the name of this plugin. The first UPLUG_NAME_MAX characters willi be copied into a new buffer. + * @internal ICU 4.4 Technology Preview + */ +U_CAPI void U_EXPORT2 +uplug_setPlugName(UPlugData *plug, const char *name); + +/** + * Get the human-readable name of this plugin. + * @param plug plugin data handle + * @return the name of this plugin + * @internal ICU 4.4 Technology Preview + */ +U_CAPI const char * U_EXPORT2 +uplug_getPlugName(UPlugData *plug); + +/** + * Return the symbol name for this plugin, if known. + * @param plug plugin data handle + * @return the symbol name, or NULL + * @internal ICU 4.4 Technology Preview + */ +U_CAPI const char * U_EXPORT2 +uplug_getSymbolName(UPlugData *plug); + +/** + * Return the library name for this plugin, if known. + * @param plug plugin data handle + * @param status error code + * @return the library name, or NULL + * @internal ICU 4.4 Technology Preview + */ +U_CAPI const char * U_EXPORT2 +uplug_getLibraryName(UPlugData *plug, UErrorCode *status); + +/** + * Return the library used for this plugin, if known. + * Plugins could use this to load data out of their + * @param plug plugin data handle + * @return the library, or NULL + * @internal ICU 4.4 Technology Preview + */ +U_CAPI void * U_EXPORT2 +uplug_getLibrary(UPlugData *plug); + +/** + * Return the plugin-specific context data. + * @param plug plugin data handle + * @return the context, or NULL if not set + * @internal ICU 4.4 Technology Preview + */ +U_CAPI void * U_EXPORT2 +uplug_getContext(UPlugData *plug); + +/** + * Set the plugin-specific context data. + * @param plug plugin data handle + * @param context new context to set + * @internal ICU 4.4 Technology Preview + */ +U_CAPI void U_EXPORT2 +uplug_setContext(UPlugData *plug, void *context); + + +/** + * Get the configuration string, if available. + * The string is in the platform default codepage. + * @param plug plugin data handle + * @return configuration string, or else null. + * @internal ICU 4.4 Technology Preview + */ +U_CAPI const char * U_EXPORT2 +uplug_getConfiguration(UPlugData *plug); + +/** + * Return all currently installed plugins, from newest to oldest + * Usage Example: + * \code + * UPlugData *plug = NULL; + * while(plug=uplug_nextPlug(plug)) { + * ... do something with 'plug' ... + * } + * \endcode + * Not thread safe- do not call while plugs are added or removed. + * @param prior pass in 'NULL' to get the first (most recent) plug, + * otherwise pass the value returned on a prior call to uplug_nextPlug + * @return the next oldest plugin, or NULL if no more. + * @internal ICU 4.4 Technology Preview + */ +U_CAPI UPlugData* U_EXPORT2 +uplug_nextPlug(UPlugData *prior); + +/** + * Inject a plugin as if it were loaded from a library. + * This is useful for testing plugins. + * Note that it will have a 'NULL' library pointer associated + * with it, and therefore no llibrary will be closed at cleanup time. + * Low level plugins may not be able to load, as ordering can't be enforced. + * @param entrypoint entrypoint to install + * @param config user specified configuration string, if available, or NULL. + * @param status error result + * @return the new UPlugData associated with this plugin, or NULL if error. + * @internal ICU 4.4 Technology Preview + */ +U_CAPI UPlugData* U_EXPORT2 +uplug_loadPlugFromEntrypoint(UPlugEntrypoint *entrypoint, const char *config, UErrorCode *status); + + +/** + * Inject a plugin from a library, as if the information came from a config file. + * Low level plugins may not be able to load, and ordering can't be enforced. + * @param libName DLL name to load + * @param sym symbol of plugin (UPlugEntrypoint function) + * @param config configuration string, or NULL + * @param status error result + * @return the new UPlugData associated with this plugin, or NULL if error. + * @internal ICU 4.4 Technology Preview + */ +U_CAPI UPlugData* U_EXPORT2 +uplug_loadPlugFromLibrary(const char *libName, const char *sym, const char *config, UErrorCode *status); + +/** + * Remove a plugin. + * Will request the plugin to be unloaded, and close the library if needed + * @param plug plugin handle to close + * @param status error result + * @internal ICU 4.4 Technology Preview + */ +U_CAPI void U_EXPORT2 +uplug_removePlug(UPlugData *plug, UErrorCode *status); +#endif /* U_HIDE_INTERNAL_API */ + +#endif /* UCONFIG_ENABLE_PLUGINS */ + +#endif /* _ICUPLUG */ + diff --git a/thirdparty/icu4c/common/unicode/idna.h b/thirdparty/icu4c/common/unicode/idna.h new file mode 100644 index 0000000000..1305dc6048 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/idna.h @@ -0,0 +1,330 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2010-2012, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: idna.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2010mar05 +* created by: Markus W. Scherer +*/ + +#ifndef __IDNA_H__ +#define __IDNA_H__ + +/** + * \file + * \brief C++ API: Internationalizing Domain Names in Applications (IDNA) + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#if !UCONFIG_NO_IDNA + +#include "unicode/bytestream.h" +#include "unicode/stringpiece.h" +#include "unicode/uidna.h" +#include "unicode/unistr.h" + +U_NAMESPACE_BEGIN + +class IDNAInfo; + +/** + * Abstract base class for IDNA processing. + * See http://www.unicode.org/reports/tr46/ + * and http://www.ietf.org/rfc/rfc3490.txt + * + * The IDNA class is not intended for public subclassing. + * + * This C++ API currently only implements UTS #46. + * The uidna.h C API implements both UTS #46 (functions using UIDNA service object) + * and IDNA2003 (functions that do not use a service object). + * @stable ICU 4.6 + */ +class U_COMMON_API IDNA : public UObject { +public: + /** + * Destructor. + * @stable ICU 4.6 + */ + ~IDNA(); + + /** + * Returns an IDNA instance which implements UTS #46. + * Returns an unmodifiable instance, owned by the caller. + * Cache it for multiple operations, and delete it when done. + * The instance is thread-safe, that is, it can be used concurrently. + * + * UTS #46 defines Unicode IDNA Compatibility Processing, + * updated to the latest version of Unicode and compatible with both + * IDNA2003 and IDNA2008. + * + * The worker functions use transitional processing, including deviation mappings, + * unless UIDNA_NONTRANSITIONAL_TO_ASCII or UIDNA_NONTRANSITIONAL_TO_UNICODE + * is used in which case the deviation characters are passed through without change. + * + * Disallowed characters are mapped to U+FFFD. + * + * For available options see the uidna.h header. + * Operations with the UTS #46 instance do not support the + * UIDNA_ALLOW_UNASSIGNED option. + * + * By default, the UTS #46 implementation allows all ASCII characters (as valid or mapped). + * When the UIDNA_USE_STD3_RULES option is used, ASCII characters other than + * letters, digits, hyphen (LDH) and dot/full stop are disallowed and mapped to U+FFFD. + * + * @param options Bit set to modify the processing and error checking. + * See option bit set values in uidna.h. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the UTS #46 IDNA instance, if successful + * @stable ICU 4.6 + */ + static IDNA * + createUTS46Instance(uint32_t options, UErrorCode &errorCode); + + /** + * Converts a single domain name label into its ASCII form for DNS lookup. + * If any processing step fails, then info.hasErrors() will be true and + * the result might not be an ASCII string. + * The label might be modified according to the types of errors. + * Labels with severe errors will be left in (or turned into) their Unicode form. + * + * The UErrorCode indicates an error only in exceptional cases, + * such as a U_MEMORY_ALLOCATION_ERROR. + * + * @param label Input domain name label + * @param dest Destination string object + * @param info Output container of IDNA processing details. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.6 + */ + virtual UnicodeString & + labelToASCII(const UnicodeString &label, UnicodeString &dest, + IDNAInfo &info, UErrorCode &errorCode) const = 0; + + /** + * Converts a single domain name label into its Unicode form for human-readable display. + * If any processing step fails, then info.hasErrors() will be true. + * The label might be modified according to the types of errors. + * + * The UErrorCode indicates an error only in exceptional cases, + * such as a U_MEMORY_ALLOCATION_ERROR. + * + * @param label Input domain name label + * @param dest Destination string object + * @param info Output container of IDNA processing details. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.6 + */ + virtual UnicodeString & + labelToUnicode(const UnicodeString &label, UnicodeString &dest, + IDNAInfo &info, UErrorCode &errorCode) const = 0; + + /** + * Converts a whole domain name into its ASCII form for DNS lookup. + * If any processing step fails, then info.hasErrors() will be true and + * the result might not be an ASCII string. + * The domain name might be modified according to the types of errors. + * Labels with severe errors will be left in (or turned into) their Unicode form. + * + * The UErrorCode indicates an error only in exceptional cases, + * such as a U_MEMORY_ALLOCATION_ERROR. + * + * @param name Input domain name + * @param dest Destination string object + * @param info Output container of IDNA processing details. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.6 + */ + virtual UnicodeString & + nameToASCII(const UnicodeString &name, UnicodeString &dest, + IDNAInfo &info, UErrorCode &errorCode) const = 0; + + /** + * Converts a whole domain name into its Unicode form for human-readable display. + * If any processing step fails, then info.hasErrors() will be true. + * The domain name might be modified according to the types of errors. + * + * The UErrorCode indicates an error only in exceptional cases, + * such as a U_MEMORY_ALLOCATION_ERROR. + * + * @param name Input domain name + * @param dest Destination string object + * @param info Output container of IDNA processing details. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.6 + */ + virtual UnicodeString & + nameToUnicode(const UnicodeString &name, UnicodeString &dest, + IDNAInfo &info, UErrorCode &errorCode) const = 0; + + // UTF-8 versions of the processing methods ---------------------------- *** + + /** + * Converts a single domain name label into its ASCII form for DNS lookup. + * UTF-8 version of labelToASCII(), same behavior. + * + * @param label Input domain name label + * @param dest Destination byte sink; Flush()ed if successful + * @param info Output container of IDNA processing details. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.6 + */ + virtual void + labelToASCII_UTF8(StringPiece label, ByteSink &dest, + IDNAInfo &info, UErrorCode &errorCode) const; + + /** + * Converts a single domain name label into its Unicode form for human-readable display. + * UTF-8 version of labelToUnicode(), same behavior. + * + * @param label Input domain name label + * @param dest Destination byte sink; Flush()ed if successful + * @param info Output container of IDNA processing details. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.6 + */ + virtual void + labelToUnicodeUTF8(StringPiece label, ByteSink &dest, + IDNAInfo &info, UErrorCode &errorCode) const; + + /** + * Converts a whole domain name into its ASCII form for DNS lookup. + * UTF-8 version of nameToASCII(), same behavior. + * + * @param name Input domain name + * @param dest Destination byte sink; Flush()ed if successful + * @param info Output container of IDNA processing details. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.6 + */ + virtual void + nameToASCII_UTF8(StringPiece name, ByteSink &dest, + IDNAInfo &info, UErrorCode &errorCode) const; + + /** + * Converts a whole domain name into its Unicode form for human-readable display. + * UTF-8 version of nameToUnicode(), same behavior. + * + * @param name Input domain name + * @param dest Destination byte sink; Flush()ed if successful + * @param info Output container of IDNA processing details. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.6 + */ + virtual void + nameToUnicodeUTF8(StringPiece name, ByteSink &dest, + IDNAInfo &info, UErrorCode &errorCode) const; +}; + +class UTS46; + +/** + * Output container for IDNA processing errors. + * The IDNAInfo class is not suitable for subclassing. + * @stable ICU 4.6 + */ +class U_COMMON_API IDNAInfo : public UMemory { +public: + /** + * Constructor for stack allocation. + * @stable ICU 4.6 + */ + IDNAInfo() : errors(0), labelErrors(0), isTransDiff(false), isBiDi(false), isOkBiDi(true) {} + /** + * Were there IDNA processing errors? + * @return true if there were processing errors + * @stable ICU 4.6 + */ + UBool hasErrors() const { return errors!=0; } + /** + * Returns a bit set indicating IDNA processing errors. + * See UIDNA_ERROR_... constants in uidna.h. + * @return bit set of processing errors + * @stable ICU 4.6 + */ + uint32_t getErrors() const { return errors; } + /** + * Returns true if transitional and nontransitional processing produce different results. + * This is the case when the input label or domain name contains + * one or more deviation characters outside a Punycode label (see UTS #46). + * <ul> + * <li>With nontransitional processing, such characters are + * copied to the destination string. + * <li>With transitional processing, such characters are + * mapped (sharp s/sigma) or removed (joiner/nonjoiner). + * </ul> + * @return true if transitional and nontransitional processing produce different results + * @stable ICU 4.6 + */ + UBool isTransitionalDifferent() const { return isTransDiff; } + +private: + friend class UTS46; + + IDNAInfo(const IDNAInfo &other); // no copying + IDNAInfo &operator=(const IDNAInfo &other); // no copying + + void reset() { + errors=labelErrors=0; + isTransDiff=false; + isBiDi=false; + isOkBiDi=true; + } + + uint32_t errors, labelErrors; + UBool isTransDiff; + UBool isBiDi; + UBool isOkBiDi; +}; + +U_NAMESPACE_END + +#endif // UCONFIG_NO_IDNA + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __IDNA_H__ diff --git a/thirdparty/icu4c/common/unicode/localebuilder.h b/thirdparty/icu4c/common/unicode/localebuilder.h new file mode 100644 index 0000000000..27a894de10 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/localebuilder.h @@ -0,0 +1,311 @@ +// © 2018 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +#ifndef __LOCALEBUILDER_H__ +#define __LOCALEBUILDER_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/locid.h" +#include "unicode/localematcher.h" +#include "unicode/stringpiece.h" +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: Builder API for Locale + */ + +U_NAMESPACE_BEGIN +class CharString; + +/** + * <code>LocaleBuilder</code> is used to build instances of <code>Locale</code> + * from values configured by the setters. Unlike the <code>Locale</code> + * constructors, the <code>LocaleBuilder</code> checks if a value configured by a + * setter satisfies the syntax requirements defined by the <code>Locale</code> + * class. A <code>Locale</code> object created by a <code>LocaleBuilder</code> is + * well-formed and can be transformed to a well-formed IETF BCP 47 language tag + * without losing information. + * + * <p>The following example shows how to create a <code>Locale</code> object + * with the <code>LocaleBuilder</code>. + * <blockquote> + * <pre> + * UErrorCode status = U_ZERO_ERROR; + * Locale aLocale = LocaleBuilder() + * .setLanguage("sr") + * .setScript("Latn") + * .setRegion("RS") + * .build(status); + * if (U_SUCCESS(status)) { + * // ... + * } + * </pre> + * </blockquote> + * + * <p>LocaleBuilders can be reused; <code>clear()</code> resets all + * fields to their default values. + * + * <p>LocaleBuilder tracks errors in an internal UErrorCode. For all setters, + * except setLanguageTag and setLocale, LocaleBuilder will return immediately + * if the internal UErrorCode is in error state. + * To reset internal state and error code, call clear method. + * The setLanguageTag and setLocale method will first clear the internal + * UErrorCode, then track the error of the validation of the input parameter + * into the internal UErrorCode. + * + * @stable ICU 64 + */ +class U_COMMON_API LocaleBuilder : public UObject { +public: + /** + * Constructs an empty LocaleBuilder. The default value of all + * fields, extensions, and private use information is the + * empty string. + * + * @stable ICU 64 + */ + LocaleBuilder(); + + /** + * Destructor + * @stable ICU 64 + */ + virtual ~LocaleBuilder(); + + /** + * Resets the <code>LocaleBuilder</code> to match the provided + * <code>locale</code>. Existing state is discarded. + * + * <p>All fields of the locale must be well-formed. + * <p>This method clears the internal UErrorCode. + * + * @param locale the locale + * @return This builder. + * + * @stable ICU 64 + */ + LocaleBuilder& setLocale(const Locale& locale); + + /** + * Resets the LocaleBuilder to match the provided + * [Unicode Locale Identifier](http://www.unicode.org/reports/tr35/tr35.html#unicode_locale_id) . + * Discards the existing state. + * The empty string causes the builder to be reset, like {@link #clear}. + * Legacy language tags (marked as “Type: grandfathered” in BCP 47) + * are converted to their canonical form before being processed. + * Otherwise, the <code>language tag</code> must be well-formed, + * or else the build() method will later report an U_ILLEGAL_ARGUMENT_ERROR. + * + * <p>This method clears the internal UErrorCode. + * + * @param tag the language tag, defined as + * [unicode_locale_id](http://www.unicode.org/reports/tr35/tr35.html#unicode_locale_id). + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& setLanguageTag(StringPiece tag); + + /** + * Sets the language. If <code>language</code> is the empty string, the + * language in this <code>LocaleBuilder</code> is removed. Otherwise, the + * <code>language</code> must be well-formed, or else the build() method will + * later report an U_ILLEGAL_ARGUMENT_ERROR. + * + * <p>The syntax of language value is defined as + * [unicode_language_subtag](http://www.unicode.org/reports/tr35/tr35.html#unicode_language_subtag). + * + * @param language the language + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& setLanguage(StringPiece language); + + /** + * Sets the script. If <code>script</code> is the empty string, the script in + * this <code>LocaleBuilder</code> is removed. + * Otherwise, the <code>script</code> must be well-formed, or else the build() + * method will later report an U_ILLEGAL_ARGUMENT_ERROR. + * + * <p>The script value is a four-letter script code as + * [unicode_script_subtag](http://www.unicode.org/reports/tr35/tr35.html#unicode_script_subtag) + * defined by ISO 15924 + * + * @param script the script + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& setScript(StringPiece script); + + /** + * Sets the region. If region is the empty string, the region in this + * <code>LocaleBuilder</code> is removed. Otherwise, the <code>region</code> + * must be well-formed, or else the build() method will later report an + * U_ILLEGAL_ARGUMENT_ERROR. + * + * <p>The region value is defined by + * [unicode_region_subtag](http://www.unicode.org/reports/tr35/tr35.html#unicode_region_subtag) + * as a two-letter ISO 3166 code or a three-digit UN M.49 area code. + * + * <p>The region value in the <code>Locale</code> created by the + * <code>LocaleBuilder</code> is always normalized to upper case. + * + * @param region the region + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& setRegion(StringPiece region); + + /** + * Sets the variant. If variant is the empty string, the variant in this + * <code>LocaleBuilder</code> is removed. Otherwise, the <code>variant</code> + * must be well-formed, or else the build() method will later report an + * U_ILLEGAL_ARGUMENT_ERROR. + * + * <p><b>Note:</b> This method checks if <code>variant</code> + * satisfies the + * [unicode_variant_subtag](http://www.unicode.org/reports/tr35/tr35.html#unicode_variant_subtag) + * syntax requirements, and normalizes the value to lowercase letters. However, + * the <code>Locale</code> class does not impose any syntactic + * restriction on variant. To set an ill-formed variant, use a Locale constructor. + * If there are multiple unicode_variant_subtag, the caller must concatenate + * them with '-' as separator (ex: "foobar-fibar"). + * + * @param variant the variant + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& setVariant(StringPiece variant); + + /** + * Sets the extension for the given key. If the value is the empty string, + * the extension is removed. Otherwise, the <code>key</code> and + * <code>value</code> must be well-formed, or else the build() method will + * later report an U_ILLEGAL_ARGUMENT_ERROR. + * + * <p><b>Note:</b> The key ('u') is used for the Unicode locale extension. + * Setting a value for this key replaces any existing Unicode locale key/type + * pairs with those defined in the extension. + * + * <p><b>Note:</b> The key ('x') is used for the private use code. To be + * well-formed, the value for this key needs only to have subtags of one to + * eight alphanumeric characters, not two to eight as in the general case. + * + * @param key the extension key + * @param value the extension value + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& setExtension(char key, StringPiece value); + + /** + * Sets the Unicode locale keyword type for the given key. If the type + * StringPiece is constructed with a nullptr, the keyword is removed. + * If the type is the empty string, the keyword is set without type subtags. + * Otherwise, the key and type must be well-formed, or else the build() + * method will later report an U_ILLEGAL_ARGUMENT_ERROR. + * + * <p>Keys and types are converted to lower case. + * + * <p><b>Note</b>:Setting the 'u' extension via {@link #setExtension} + * replaces all Unicode locale keywords with those defined in the + * extension. + * + * @param key the Unicode locale key + * @param type the Unicode locale type + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& setUnicodeLocaleKeyword( + StringPiece key, StringPiece type); + + /** + * Adds a unicode locale attribute, if not already present, otherwise + * has no effect. The attribute must not be empty string and must be + * well-formed or U_ILLEGAL_ARGUMENT_ERROR will be set to status + * during the build() call. + * + * @param attribute the attribute + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& addUnicodeLocaleAttribute(StringPiece attribute); + + /** + * Removes a unicode locale attribute, if present, otherwise has no + * effect. The attribute must not be empty string and must be well-formed + * or U_ILLEGAL_ARGUMENT_ERROR will be set to status during the build() call. + * + * <p>Attribute comparison for removal is case-insensitive. + * + * @param attribute the attribute + * @return This builder. + * @stable ICU 64 + */ + LocaleBuilder& removeUnicodeLocaleAttribute(StringPiece attribute); + + /** + * Resets the builder to its initial, empty state. + * <p>This method clears the internal UErrorCode. + * + * @return this builder + * @stable ICU 64 + */ + LocaleBuilder& clear(); + + /** + * Resets the extensions to their initial, empty state. + * Language, script, region and variant are unchanged. + * + * @return this builder + * @stable ICU 64 + */ + LocaleBuilder& clearExtensions(); + + /** + * Returns an instance of <code>Locale</code> created from the fields set + * on this builder. + * If any set methods or during the build() call require memory allocation + * but fail U_MEMORY_ALLOCATION_ERROR will be set to status. + * If any of the fields set by the setters are not well-formed, the status + * will be set to U_ILLEGAL_ARGUMENT_ERROR. The state of the builder will + * not change after the build() call and the caller is free to keep using + * the same builder to build more locales. + * + * @return a new Locale + * @stable ICU 64 + */ + Locale build(UErrorCode& status); + + /** + * Sets the UErrorCode if an error occurred while recording sets. + * Preserves older error codes in the outErrorCode. + * @param outErrorCode Set to an error code that occurred while setting subtags. + * Unchanged if there is no such error or if outErrorCode + * already contained an error. + * @return true if U_FAILURE(outErrorCode) + * @stable ICU 65 + */ + UBool copyErrorTo(UErrorCode &outErrorCode) const; + +private: + friend class LocaleMatcher::Result; + + void copyExtensionsFrom(const Locale& src, UErrorCode& errorCode); + + UErrorCode status_; + char language_[9]; + char script_[5]; + char region_[4]; + CharString *variant_; // Pointer not object so we need not #include internal charstr.h. + icu::Locale *extensions_; // Pointer not object. Storage for all other fields. + +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __LOCALEBUILDER_H__ diff --git a/thirdparty/icu4c/common/unicode/localematcher.h b/thirdparty/icu4c/common/unicode/localematcher.h new file mode 100644 index 0000000000..63a68b0b7f --- /dev/null +++ b/thirdparty/icu4c/common/unicode/localematcher.h @@ -0,0 +1,720 @@ +// © 2019 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// localematcher.h +// created: 2019may08 Markus W. Scherer + +#ifndef __LOCALEMATCHER_H__ +#define __LOCALEMATCHER_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/locid.h" +#include "unicode/stringpiece.h" +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: Locale matcher: User's desired locales vs. application's supported locales. + */ + +/** + * Builder option for whether the language subtag or the script subtag is most important. + * + * @see LocaleMatcher::Builder#setFavorSubtag(ULocMatchFavorSubtag) + * @stable ICU 65 + */ +enum ULocMatchFavorSubtag { + /** + * Language differences are most important, then script differences, then region differences. + * (This is the default behavior.) + * + * @stable ICU 65 + */ + ULOCMATCH_FAVOR_LANGUAGE, + /** + * Makes script differences matter relatively more than language differences. + * + * @stable ICU 65 + */ + ULOCMATCH_FAVOR_SCRIPT +}; +#ifndef U_IN_DOXYGEN +typedef enum ULocMatchFavorSubtag ULocMatchFavorSubtag; +#endif + +/** + * Builder option for whether all desired locales are treated equally or + * earlier ones are preferred. + * + * @see LocaleMatcher::Builder#setDemotionPerDesiredLocale(ULocMatchDemotion) + * @stable ICU 65 + */ +enum ULocMatchDemotion { + /** + * All desired locales are treated equally. + * + * @stable ICU 65 + */ + ULOCMATCH_DEMOTION_NONE, + /** + * Earlier desired locales are preferred. + * + * <p>From each desired locale to the next, + * the distance to any supported locale is increased by an additional amount + * which is at least as large as most region mismatches. + * A later desired locale has to have a better match with some supported locale + * due to more than merely having the same region subtag. + * + * <p>For example: <code>Supported={en, sv} desired=[en-GB, sv]</code> + * yields <code>Result(en-GB, en)</code> because + * with the demotion of sv its perfect match is no better than + * the region distance between the earlier desired locale en-GB and en=en-US. + * + * <p>Notes: + * <ul> + * <li>In some cases, language and/or script differences can be as small as + * the typical region difference. (Example: sr-Latn vs. sr-Cyrl) + * <li>It is possible for certain region differences to be larger than usual, + * and larger than the demotion. + * (As of CLDR 35 there is no such case, but + * this is possible in future versions of the data.) + * </ul> + * + * @stable ICU 65 + */ + ULOCMATCH_DEMOTION_REGION +}; +#ifndef U_IN_DOXYGEN +typedef enum ULocMatchDemotion ULocMatchDemotion; +#endif + +#ifndef U_FORCE_HIDE_DRAFT_API + +/** + * Builder option for whether to include or ignore one-way (fallback) match data. + * The LocaleMatcher uses CLDR languageMatch data which includes fallback (oneway=true) entries. + * Sometimes it is desirable to ignore those. + * + * <p>For example, consider a web application with the UI in a given language, + * with a link to another, related web app. + * The link should include the UI language, and the target server may also use + * the client’s Accept-Language header data. + * The target server has its own list of supported languages. + * One may want to favor UI language consistency, that is, + * if there is a decent match for the original UI language, we want to use it, + * but not if it is merely a fallback. + * + * @see LocaleMatcher::Builder#setDirection(ULocMatchDirection) + * @draft ICU 67 + */ +enum ULocMatchDirection { + /** + * Locale matching includes one-way matches such as Breton→French. (default) + * + * @draft ICU 67 + */ + ULOCMATCH_DIRECTION_WITH_ONE_WAY, + /** + * Locale matching limited to two-way matches including e.g. Danish↔Norwegian + * but ignoring one-way matches. + * + * @draft ICU 67 + */ + ULOCMATCH_DIRECTION_ONLY_TWO_WAY +}; +#ifndef U_IN_DOXYGEN +typedef enum ULocMatchDirection ULocMatchDirection; +#endif + +#endif // U_FORCE_HIDE_DRAFT_API + +struct UHashtable; + +U_NAMESPACE_BEGIN + +struct LSR; + +class LocaleDistance; +class LocaleLsrIterator; +class UVector; +class XLikelySubtags; + +/** + * Immutable class that picks the best match between a user's desired locales and + * an application's supported locales. + * Movable but not copyable. + * + * <p>Example: + * <pre> + * UErrorCode errorCode = U_ZERO_ERROR; + * LocaleMatcher matcher = LocaleMatcher::Builder().setSupportedLocales("fr, en-GB, en").build(errorCode); + * Locale *bestSupported = matcher.getBestLocale(Locale.US, errorCode); // "en" + * </pre> + * + * <p>A matcher takes into account when languages are close to one another, + * such as Danish and Norwegian, + * and when regional variants are close, like en-GB and en-AU as opposed to en-US. + * + * <p>If there are multiple supported locales with the same (language, script, region) + * likely subtags, then the current implementation returns the first of those locales. + * It ignores variant subtags (except for pseudolocale variants) and extensions. + * This may change in future versions. + * + * <p>For example, the current implementation does not distinguish between + * de, de-DE, de-Latn, de-1901, de-u-co-phonebk. + * + * <p>If you prefer one equivalent locale over another, then provide only the preferred one, + * or place it earlier in the list of supported locales. + * + * <p>Otherwise, the order of supported locales may have no effect on the best-match results. + * The current implementation compares each desired locale with supported locales + * in the following order: + * 1. Default locale, if supported; + * 2. CLDR "paradigm locales" like en-GB and es-419; + * 3. other supported locales. + * This may change in future versions. + * + * <p>Often a product will just need one matcher instance, built with the languages + * that it supports. However, it may want multiple instances with different + * default languages based on additional information, such as the domain. + * + * <p>This class is not intended for public subclassing. + * + * @stable ICU 65 + */ +class U_COMMON_API LocaleMatcher : public UMemory { +public: + /** + * Data for the best-matching pair of a desired and a supported locale. + * Movable but not copyable. + * + * @stable ICU 65 + */ + class U_COMMON_API Result : public UMemory { + public: + /** + * Move constructor; might modify the source. + * This object will have the same contents that the source object had. + * + * @param src Result to move contents from. + * @stable ICU 65 + */ + Result(Result &&src) U_NOEXCEPT; + + /** + * Destructor. + * + * @stable ICU 65 + */ + ~Result(); + + /** + * Move assignment; might modify the source. + * This object will have the same contents that the source object had. + * + * @param src Result to move contents from. + * @stable ICU 65 + */ + Result &operator=(Result &&src) U_NOEXCEPT; + + /** + * Returns the best-matching desired locale. + * nullptr if the list of desired locales is empty or if none matched well enough. + * + * @return the best-matching desired locale, or nullptr. + * @stable ICU 65 + */ + inline const Locale *getDesiredLocale() const { return desiredLocale; } + + /** + * Returns the best-matching supported locale. + * If none matched well enough, this is the default locale. + * The default locale is nullptr if Builder::setNoDefaultLocale() was called, + * or if the list of supported locales is empty and no explicit default locale is set. + * + * @return the best-matching supported locale, or nullptr. + * @stable ICU 65 + */ + inline const Locale *getSupportedLocale() const { return supportedLocale; } + + /** + * Returns the index of the best-matching desired locale in the input Iterable order. + * -1 if the list of desired locales is empty or if none matched well enough. + * + * @return the index of the best-matching desired locale, or -1. + * @stable ICU 65 + */ + inline int32_t getDesiredIndex() const { return desiredIndex; } + + /** + * Returns the index of the best-matching supported locale in the + * constructor’s or builder’s input order (“set” Collection plus “added” locales). + * If the matcher was built from a locale list string, then the iteration order is that + * of a LocalePriorityList built from the same string. + * -1 if the list of supported locales is empty or if none matched well enough. + * + * @return the index of the best-matching supported locale, or -1. + * @stable ICU 65 + */ + inline int32_t getSupportedIndex() const { return supportedIndex; } + + /** + * Takes the best-matching supported locale and adds relevant fields of the + * best-matching desired locale, such as the -t- and -u- extensions. + * May replace some fields of the supported locale. + * The result is the locale that should be used for date and number formatting, collation, etc. + * Returns the root locale if getSupportedLocale() returns nullptr. + * + * <p>Example: desired=ar-SA-u-nu-latn, supported=ar-EG, resolved locale=ar-SA-u-nu-latn + * + * @return a locale combining the best-matching desired and supported locales. + * @stable ICU 65 + */ + Locale makeResolvedLocale(UErrorCode &errorCode) const; + + private: + Result(const Locale *desired, const Locale *supported, + int32_t desIndex, int32_t suppIndex, UBool owned) : + desiredLocale(desired), supportedLocale(supported), + desiredIndex(desIndex), supportedIndex(suppIndex), + desiredIsOwned(owned) {} + + Result(const Result &other) = delete; + Result &operator=(const Result &other) = delete; + + const Locale *desiredLocale; + const Locale *supportedLocale; + int32_t desiredIndex; + int32_t supportedIndex; + UBool desiredIsOwned; + + friend class LocaleMatcher; + }; + + /** + * LocaleMatcher builder. + * Movable but not copyable. + * + * @stable ICU 65 + */ + class U_COMMON_API Builder : public UMemory { + public: + /** + * Constructs a builder used in chaining parameters for building a LocaleMatcher. + * + * @return a new Builder object + * @stable ICU 65 + */ + Builder() {} + + /** + * Move constructor; might modify the source. + * This builder will have the same contents that the source builder had. + * + * @param src Builder to move contents from. + * @stable ICU 65 + */ + Builder(Builder &&src) U_NOEXCEPT; + + /** + * Destructor. + * + * @stable ICU 65 + */ + ~Builder(); + + /** + * Move assignment; might modify the source. + * This builder will have the same contents that the source builder had. + * + * @param src Builder to move contents from. + * @stable ICU 65 + */ + Builder &operator=(Builder &&src) U_NOEXCEPT; + + /** + * Parses an Accept-Language string + * (<a href="https://tools.ietf.org/html/rfc2616#section-14.4">RFC 2616 Section 14.4</a>), + * such as "af, en, fr;q=0.9", and sets the supported locales accordingly. + * Allows whitespace in more places but does not allow "*". + * Clears any previously set/added supported locales first. + * + * @param locales the Accept-Language string of locales to set + * @return this Builder object + * @stable ICU 65 + */ + Builder &setSupportedLocalesFromListString(StringPiece locales); + + /** + * Copies the supported locales, preserving iteration order. + * Clears any previously set/added supported locales first. + * Duplicates are allowed, and are not removed. + * + * @param locales the list of locale + * @return this Builder object + * @stable ICU 65 + */ + Builder &setSupportedLocales(Locale::Iterator &locales); + + /** + * Copies the supported locales from the begin/end range, preserving iteration order. + * Clears any previously set/added supported locales first. + * Duplicates are allowed, and are not removed. + * + * Each of the iterator parameter values must be an + * input iterator whose value is convertible to const Locale &. + * + * @param begin Start of range. + * @param end Exclusive end of range. + * @return this Builder object + * @stable ICU 65 + */ + template<typename Iter> + Builder &setSupportedLocales(Iter begin, Iter end) { + if (U_FAILURE(errorCode_)) { return *this; } + clearSupportedLocales(); + while (begin != end) { + addSupportedLocale(*begin++); + } + return *this; + } + + /** + * Copies the supported locales from the begin/end range, preserving iteration order. + * Calls the converter to convert each *begin to a Locale or const Locale &. + * Clears any previously set/added supported locales first. + * Duplicates are allowed, and are not removed. + * + * Each of the iterator parameter values must be an + * input iterator whose value is convertible to const Locale &. + * + * @param begin Start of range. + * @param end Exclusive end of range. + * @param converter Converter from *begin to const Locale & or compatible. + * @return this Builder object + * @stable ICU 65 + */ + template<typename Iter, typename Conv> + Builder &setSupportedLocalesViaConverter(Iter begin, Iter end, Conv converter) { + if (U_FAILURE(errorCode_)) { return *this; } + clearSupportedLocales(); + while (begin != end) { + addSupportedLocale(converter(*begin++)); + } + return *this; + } + + /** + * Adds another supported locale. + * Duplicates are allowed, and are not removed. + * + * @param locale another locale + * @return this Builder object + * @stable ICU 65 + */ + Builder &addSupportedLocale(const Locale &locale); + +#ifndef U_HIDE_DRAFT_API + /** + * Sets no default locale. + * There will be no explicit or implicit default locale. + * If there is no good match, then the matcher will return nullptr for the + * best supported locale. + * + * @draft ICU 68 + */ + Builder &setNoDefaultLocale(); +#endif // U_HIDE_DRAFT_API + + /** + * Sets the default locale; if nullptr, or if it is not set explicitly, + * then the first supported locale is used as the default locale. + * There is no default locale at all (nullptr will be returned instead) + * if setNoDefaultLocale() is called. + * + * @param defaultLocale the default locale (will be copied) + * @return this Builder object + * @stable ICU 65 + */ + Builder &setDefaultLocale(const Locale *defaultLocale); + + /** + * If ULOCMATCH_FAVOR_SCRIPT, then the language differences are smaller than script + * differences. + * This is used in situations (such as maps) where + * it is better to fall back to the same script than a similar language. + * + * @param subtag the subtag to favor + * @return this Builder object + * @stable ICU 65 + */ + Builder &setFavorSubtag(ULocMatchFavorSubtag subtag); + + /** + * Option for whether all desired locales are treated equally or + * earlier ones are preferred (this is the default). + * + * @param demotion the demotion per desired locale to set. + * @return this Builder object + * @stable ICU 65 + */ + Builder &setDemotionPerDesiredLocale(ULocMatchDemotion demotion); + +#ifndef U_HIDE_DRAFT_API + /** + * Option for whether to include or ignore one-way (fallback) match data. + * By default, they are included. + * + * @param direction the match direction to set. + * @return this Builder object + * @draft ICU 67 + */ + Builder &setDirection(ULocMatchDirection direction) { + if (U_SUCCESS(errorCode_)) { + direction_ = direction; + } + return *this; + } +#endif // U_HIDE_DRAFT_API + +#ifndef U_HIDE_DRAFT_API + /** + * Sets the maximum distance for an acceptable match. + * The matcher will return a match for a pair of locales only if + * they match at least as well as the pair given here. + * + * For example, setMaxDistance(en-US, en-GB) limits matches to ones where the + * (desired, support) locales have a distance no greater than a region subtag difference. + * This is much stricter than the CLDR default. + * + * The details of locale matching are subject to changes in + * CLDR data and in the algorithm. + * Specifying a maximum distance in relative terms via a sample pair of locales + * insulates from changes that affect all distance metrics similarly, + * but some changes will necessarily affect relative distances between + * different pairs of locales. + * + * @param desired the desired locale for distance comparison. + * @param supported the supported locale for distance comparison. + * @return this Builder object + * @draft ICU 68 + */ + Builder &setMaxDistance(const Locale &desired, const Locale &supported); +#endif // U_HIDE_DRAFT_API + + /** + * Sets the UErrorCode if an error occurred while setting parameters. + * Preserves older error codes in the outErrorCode. + * + * @param outErrorCode Set to an error code if it does not contain one already + * and an error occurred while setting parameters. + * Otherwise unchanged. + * @return true if U_FAILURE(outErrorCode) + * @stable ICU 65 + */ + UBool copyErrorTo(UErrorCode &outErrorCode) const; + + /** + * Builds and returns a new locale matcher. + * This builder can continue to be used. + * + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return LocaleMatcher + * @stable ICU 65 + */ + LocaleMatcher build(UErrorCode &errorCode) const; + + private: + friend class LocaleMatcher; + + Builder(const Builder &other) = delete; + Builder &operator=(const Builder &other) = delete; + + void clearSupportedLocales(); + bool ensureSupportedLocaleVector(); + + UErrorCode errorCode_ = U_ZERO_ERROR; + UVector *supportedLocales_ = nullptr; + int32_t thresholdDistance_ = -1; + ULocMatchDemotion demotion_ = ULOCMATCH_DEMOTION_REGION; + Locale *defaultLocale_ = nullptr; + bool withDefault_ = true; + ULocMatchFavorSubtag favor_ = ULOCMATCH_FAVOR_LANGUAGE; + ULocMatchDirection direction_ = ULOCMATCH_DIRECTION_WITH_ONE_WAY; + Locale *maxDistanceDesired_ = nullptr; + Locale *maxDistanceSupported_ = nullptr; + }; + + // FYI No public LocaleMatcher constructors in C++; use the Builder. + + /** + * Move copy constructor; might modify the source. + * This matcher will have the same settings that the source matcher had. + * @param src source matcher + * @stable ICU 65 + */ + LocaleMatcher(LocaleMatcher &&src) U_NOEXCEPT; + + /** + * Destructor. + * @stable ICU 65 + */ + ~LocaleMatcher(); + + /** + * Move assignment operator; might modify the source. + * This matcher will have the same settings that the source matcher had. + * The behavior is undefined if *this and src are the same object. + * @param src source matcher + * @return *this + * @stable ICU 65 + */ + LocaleMatcher &operator=(LocaleMatcher &&src) U_NOEXCEPT; + + /** + * Returns the supported locale which best matches the desired locale. + * + * @param desiredLocale Typically a user's language. + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return the best-matching supported locale. + * @stable ICU 65 + */ + const Locale *getBestMatch(const Locale &desiredLocale, UErrorCode &errorCode) const; + + /** + * Returns the supported locale which best matches one of the desired locales. + * + * @param desiredLocales Typically a user's languages, in order of preference (descending). + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return the best-matching supported locale. + * @stable ICU 65 + */ + const Locale *getBestMatch(Locale::Iterator &desiredLocales, UErrorCode &errorCode) const; + + /** + * Parses an Accept-Language string + * (<a href="https://tools.ietf.org/html/rfc2616#section-14.4">RFC 2616 Section 14.4</a>), + * such as "af, en, fr;q=0.9", + * and returns the supported locale which best matches one of the desired locales. + * Allows whitespace in more places but does not allow "*". + * + * @param desiredLocaleList Typically a user's languages, as an Accept-Language string. + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return the best-matching supported locale. + * @stable ICU 65 + */ + const Locale *getBestMatchForListString(StringPiece desiredLocaleList, UErrorCode &errorCode) const; + + /** + * Returns the best match between the desired locale and the supported locales. + * If the result's desired locale is not nullptr, then it is the address of the input locale. + * It has not been cloned. + * + * @param desiredLocale Typically a user's language. + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return the best-matching pair of the desired and a supported locale. + * @stable ICU 65 + */ + Result getBestMatchResult(const Locale &desiredLocale, UErrorCode &errorCode) const; + + /** + * Returns the best match between the desired and supported locales. + * If the result's desired locale is not nullptr, then it is a clone of + * the best-matching desired locale. The Result object owns the clone. + * + * @param desiredLocales Typically a user's languages, in order of preference (descending). + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return the best-matching pair of a desired and a supported locale. + * @stable ICU 65 + */ + Result getBestMatchResult(Locale::Iterator &desiredLocales, UErrorCode &errorCode) const; + +#ifndef U_HIDE_DRAFT_API + /** + * Returns true if the pair of locales matches acceptably. + * This is influenced by Builder options such as setDirection(), setFavorSubtag(), + * and setMaxDistance(). + * + * @param desired The desired locale. + * @param supported The supported locale. + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return true if the pair of locales matches acceptably. + * @draft ICU 68 + */ + UBool isMatch(const Locale &desired, const Locale &supported, UErrorCode &errorCode) const; +#endif // U_HIDE_DRAFT_API + +#ifndef U_HIDE_INTERNAL_API + /** + * Returns a fraction between 0 and 1, where 1 means that the languages are a + * perfect match, and 0 means that they are completely different. + * + * <p>This is mostly an implementation detail, and the precise values may change over time. + * The implementation may use either the maximized forms or the others ones, or both. + * The implementation may or may not rely on the forms to be consistent with each other. + * + * <p>Callers should construct and use a matcher rather than match pairs of locales directly. + * + * @param desired Desired locale. + * @param supported Supported locale. + * @param errorCode ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return value between 0 and 1, inclusive. + * @internal (has a known user) + */ + double internalMatch(const Locale &desired, const Locale &supported, UErrorCode &errorCode) const; +#endif // U_HIDE_INTERNAL_API + +private: + LocaleMatcher(const Builder &builder, UErrorCode &errorCode); + LocaleMatcher(const LocaleMatcher &other) = delete; + LocaleMatcher &operator=(const LocaleMatcher &other) = delete; + + int32_t putIfAbsent(const LSR &lsr, int32_t i, int32_t suppLength, UErrorCode &errorCode); + + int32_t getBestSuppIndex(LSR desiredLSR, LocaleLsrIterator *remainingIter, UErrorCode &errorCode) const; + + const XLikelySubtags &likelySubtags; + const LocaleDistance &localeDistance; + int32_t thresholdDistance; + int32_t demotionPerDesiredLocale; + ULocMatchFavorSubtag favorSubtag; + ULocMatchDirection direction; + + // These are in input order. + const Locale ** supportedLocales; + LSR *lsrs; + int32_t supportedLocalesLength; + // These are in preference order: 1. Default locale 2. paradigm locales 3. others. + UHashtable *supportedLsrToIndex; // Map<LSR, Integer> stores index+1 because 0 is "not found" + // Array versions of the supportedLsrToIndex keys and values. + // The distance lookup loops over the supportedLSRs and returns the index of the best match. + const LSR **supportedLSRs; + int32_t *supportedIndexes; + int32_t supportedLSRsLength; + Locale *ownedDefaultLocale; + const Locale *defaultLocale; +}; + +U_NAMESPACE_END + +#endif // U_SHOW_CPLUSPLUS_API +#endif // __LOCALEMATCHER_H__ diff --git a/thirdparty/icu4c/common/unicode/localpointer.h b/thirdparty/icu4c/common/unicode/localpointer.h new file mode 100644 index 0000000000..2a65f2d382 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/localpointer.h @@ -0,0 +1,595 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2009-2016, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: localpointer.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2009nov13 +* created by: Markus W. Scherer +*/ + +#ifndef __LOCALPOINTER_H__ +#define __LOCALPOINTER_H__ + +/** + * \file + * \brief C++ API: "Smart pointers" for use with and in ICU4C C++ code. + * + * These classes are inspired by + * - std::auto_ptr + * - boost::scoped_ptr & boost::scoped_array + * - Taligent Safe Pointers (TOnlyPointerTo) + * + * but none of those provide for all of the goals for ICU smart pointers: + * - Smart pointer owns the object and releases it when it goes out of scope. + * - No transfer of ownership via copy/assignment to reduce misuse. Simpler & more robust. + * - ICU-compatible: No exceptions. + * - Need to be able to orphan/release the pointer and its ownership. + * - Need variants for normal C++ object pointers, C++ arrays, and ICU C service objects. + * + * For details see http://site.icu-project.org/design/cpp/scoped_ptr + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include <memory> + +U_NAMESPACE_BEGIN + +/** + * "Smart pointer" base class; do not use directly: use LocalPointer etc. + * + * Base class for smart pointer classes that do not throw exceptions. + * + * Do not use this base class directly, since it does not delete its pointer. + * A subclass must implement methods that delete the pointer: + * Destructor and adoptInstead(). + * + * There is no operator T *() provided because the programmer must decide + * whether to use getAlias() (without transfer of ownership) or orphan() + * (with transfer of ownership and NULLing of the pointer). + * + * @see LocalPointer + * @see LocalArray + * @see U_DEFINE_LOCAL_OPEN_POINTER + * @stable ICU 4.4 + */ +template<typename T> +class LocalPointerBase { +public: + // No heap allocation. Use only on the stack. + static void* U_EXPORT2 operator new(size_t) = delete; + static void* U_EXPORT2 operator new[](size_t) = delete; +#if U_HAVE_PLACEMENT_NEW + static void* U_EXPORT2 operator new(size_t, void*) = delete; +#endif + + /** + * Constructor takes ownership. + * @param p simple pointer to an object that is adopted + * @stable ICU 4.4 + */ + explicit LocalPointerBase(T *p=NULL) : ptr(p) {} + /** + * Destructor deletes the object it owns. + * Subclass must override: Base class does nothing. + * @stable ICU 4.4 + */ + ~LocalPointerBase() { /* delete ptr; */ } + /** + * NULL check. + * @return true if ==NULL + * @stable ICU 4.4 + */ + UBool isNull() const { return ptr==NULL; } + /** + * NULL check. + * @return true if !=NULL + * @stable ICU 4.4 + */ + UBool isValid() const { return ptr!=NULL; } + /** + * Comparison with a simple pointer, so that existing code + * with ==NULL need not be changed. + * @param other simple pointer for comparison + * @return true if this pointer value equals other + * @stable ICU 4.4 + */ + bool operator==(const T *other) const { return ptr==other; } + /** + * Comparison with a simple pointer, so that existing code + * with !=NULL need not be changed. + * @param other simple pointer for comparison + * @return true if this pointer value differs from other + * @stable ICU 4.4 + */ + bool operator!=(const T *other) const { return ptr!=other; } + /** + * Access without ownership change. + * @return the pointer value + * @stable ICU 4.4 + */ + T *getAlias() const { return ptr; } + /** + * Access without ownership change. + * @return the pointer value as a reference + * @stable ICU 4.4 + */ + T &operator*() const { return *ptr; } + /** + * Access without ownership change. + * @return the pointer value + * @stable ICU 4.4 + */ + T *operator->() const { return ptr; } + /** + * Gives up ownership; the internal pointer becomes NULL. + * @return the pointer value; + * caller becomes responsible for deleting the object + * @stable ICU 4.4 + */ + T *orphan() { + T *p=ptr; + ptr=NULL; + return p; + } + /** + * Deletes the object it owns, + * and adopts (takes ownership of) the one passed in. + * Subclass must override: Base class does not delete the object. + * @param p simple pointer to an object that is adopted + * @stable ICU 4.4 + */ + void adoptInstead(T *p) { + // delete ptr; + ptr=p; + } +protected: + /** + * Actual pointer. + * @internal + */ + T *ptr; +private: + // No comparison operators with other LocalPointerBases. + bool operator==(const LocalPointerBase<T> &other); + bool operator!=(const LocalPointerBase<T> &other); + // No ownership sharing: No copy constructor, no assignment operator. + LocalPointerBase(const LocalPointerBase<T> &other); + void operator=(const LocalPointerBase<T> &other); +}; + +/** + * "Smart pointer" class, deletes objects via the standard C++ delete operator. + * For most methods see the LocalPointerBase base class. + * + * Usage example: + * \code + * LocalPointer<UnicodeString> s(new UnicodeString((UChar32)0x50005)); + * int32_t length=s->length(); // 2 + * char16_t lead=s->charAt(0); // 0xd900 + * if(some condition) { return; } // no need to explicitly delete the pointer + * s.adoptInstead(new UnicodeString((char16_t)0xfffc)); + * length=s->length(); // 1 + * // no need to explicitly delete the pointer + * \endcode + * + * @see LocalPointerBase + * @stable ICU 4.4 + */ +template<typename T> +class LocalPointer : public LocalPointerBase<T> { +public: + using LocalPointerBase<T>::operator*; + using LocalPointerBase<T>::operator->; + /** + * Constructor takes ownership. + * @param p simple pointer to an object that is adopted + * @stable ICU 4.4 + */ + explicit LocalPointer(T *p=NULL) : LocalPointerBase<T>(p) {} + /** + * Constructor takes ownership and reports an error if NULL. + * + * This constructor is intended to be used with other-class constructors + * that may report a failure UErrorCode, + * so that callers need to check only for U_FAILURE(errorCode) + * and not also separately for isNull(). + * + * @param p simple pointer to an object that is adopted + * @param errorCode in/out UErrorCode, set to U_MEMORY_ALLOCATION_ERROR + * if p==NULL and no other failure code had been set + * @stable ICU 55 + */ + LocalPointer(T *p, UErrorCode &errorCode) : LocalPointerBase<T>(p) { + if(p==NULL && U_SUCCESS(errorCode)) { + errorCode=U_MEMORY_ALLOCATION_ERROR; + } + } + /** + * Move constructor, leaves src with isNull(). + * @param src source smart pointer + * @stable ICU 56 + */ + LocalPointer(LocalPointer<T> &&src) U_NOEXCEPT : LocalPointerBase<T>(src.ptr) { + src.ptr=NULL; + } + + /** + * Constructs a LocalPointer from a C++11 std::unique_ptr. + * The LocalPointer steals the object owned by the std::unique_ptr. + * + * This constructor works via move semantics. If your std::unique_ptr is + * in a local variable, you must use std::move. + * + * @param p The std::unique_ptr from which the pointer will be stolen. + * @stable ICU 64 + */ + explicit LocalPointer(std::unique_ptr<T> &&p) + : LocalPointerBase<T>(p.release()) {} + + /** + * Destructor deletes the object it owns. + * @stable ICU 4.4 + */ + ~LocalPointer() { + delete LocalPointerBase<T>::ptr; + } + /** + * Move assignment operator, leaves src with isNull(). + * The behavior is undefined if *this and src are the same object. + * @param src source smart pointer + * @return *this + * @stable ICU 56 + */ + LocalPointer<T> &operator=(LocalPointer<T> &&src) U_NOEXCEPT { + delete LocalPointerBase<T>::ptr; + LocalPointerBase<T>::ptr=src.ptr; + src.ptr=NULL; + return *this; + } + + /** + * Move-assign from an std::unique_ptr to this LocalPointer. + * Steals the pointer from the std::unique_ptr. + * + * @param p The std::unique_ptr from which the pointer will be stolen. + * @return *this + * @stable ICU 64 + */ + LocalPointer<T> &operator=(std::unique_ptr<T> &&p) U_NOEXCEPT { + adoptInstead(p.release()); + return *this; + } + + /** + * Swap pointers. + * @param other other smart pointer + * @stable ICU 56 + */ + void swap(LocalPointer<T> &other) U_NOEXCEPT { + T *temp=LocalPointerBase<T>::ptr; + LocalPointerBase<T>::ptr=other.ptr; + other.ptr=temp; + } + /** + * Non-member LocalPointer swap function. + * @param p1 will get p2's pointer + * @param p2 will get p1's pointer + * @stable ICU 56 + */ + friend inline void swap(LocalPointer<T> &p1, LocalPointer<T> &p2) U_NOEXCEPT { + p1.swap(p2); + } + /** + * Deletes the object it owns, + * and adopts (takes ownership of) the one passed in. + * @param p simple pointer to an object that is adopted + * @stable ICU 4.4 + */ + void adoptInstead(T *p) { + delete LocalPointerBase<T>::ptr; + LocalPointerBase<T>::ptr=p; + } + /** + * Deletes the object it owns, + * and adopts (takes ownership of) the one passed in. + * + * If U_FAILURE(errorCode), then the current object is retained and the new one deleted. + * + * If U_SUCCESS(errorCode) but the input pointer is NULL, + * then U_MEMORY_ALLOCATION_ERROR is set, + * the current object is deleted, and NULL is set. + * + * @param p simple pointer to an object that is adopted + * @param errorCode in/out UErrorCode, set to U_MEMORY_ALLOCATION_ERROR + * if p==NULL and no other failure code had been set + * @stable ICU 55 + */ + void adoptInsteadAndCheckErrorCode(T *p, UErrorCode &errorCode) { + if(U_SUCCESS(errorCode)) { + delete LocalPointerBase<T>::ptr; + LocalPointerBase<T>::ptr=p; + if(p==NULL) { + errorCode=U_MEMORY_ALLOCATION_ERROR; + } + } else { + delete p; + } + } + + /** + * Conversion operator to a C++11 std::unique_ptr. + * Disowns the object and gives it to the returned std::unique_ptr. + * + * This operator works via move semantics. If your LocalPointer is + * in a local variable, you must use std::move. + * + * @return An std::unique_ptr owning the pointer previously owned by this + * icu::LocalPointer. + * @stable ICU 64 + */ + operator std::unique_ptr<T> () && { + return std::unique_ptr<T>(LocalPointerBase<T>::orphan()); + } +}; + +/** + * "Smart pointer" class, deletes objects via the C++ array delete[] operator. + * For most methods see the LocalPointerBase base class. + * Adds operator[] for array item access. + * + * Usage example: + * \code + * LocalArray<UnicodeString> a(new UnicodeString[2]); + * a[0].append((char16_t)0x61); + * if(some condition) { return; } // no need to explicitly delete the array + * a.adoptInstead(new UnicodeString[4]); + * a[3].append((char16_t)0x62).append((char16_t)0x63).reverse(); + * // no need to explicitly delete the array + * \endcode + * + * @see LocalPointerBase + * @stable ICU 4.4 + */ +template<typename T> +class LocalArray : public LocalPointerBase<T> { +public: + using LocalPointerBase<T>::operator*; + using LocalPointerBase<T>::operator->; + /** + * Constructor takes ownership. + * @param p simple pointer to an array of T objects that is adopted + * @stable ICU 4.4 + */ + explicit LocalArray(T *p=NULL) : LocalPointerBase<T>(p) {} + /** + * Constructor takes ownership and reports an error if NULL. + * + * This constructor is intended to be used with other-class constructors + * that may report a failure UErrorCode, + * so that callers need to check only for U_FAILURE(errorCode) + * and not also separately for isNull(). + * + * @param p simple pointer to an array of T objects that is adopted + * @param errorCode in/out UErrorCode, set to U_MEMORY_ALLOCATION_ERROR + * if p==NULL and no other failure code had been set + * @stable ICU 56 + */ + LocalArray(T *p, UErrorCode &errorCode) : LocalPointerBase<T>(p) { + if(p==NULL && U_SUCCESS(errorCode)) { + errorCode=U_MEMORY_ALLOCATION_ERROR; + } + } + /** + * Move constructor, leaves src with isNull(). + * @param src source smart pointer + * @stable ICU 56 + */ + LocalArray(LocalArray<T> &&src) U_NOEXCEPT : LocalPointerBase<T>(src.ptr) { + src.ptr=NULL; + } + + /** + * Constructs a LocalArray from a C++11 std::unique_ptr of an array type. + * The LocalPointer steals the array owned by the std::unique_ptr. + * + * This constructor works via move semantics. If your std::unique_ptr is + * in a local variable, you must use std::move. + * + * @param p The std::unique_ptr from which the array will be stolen. + * @stable ICU 64 + */ + explicit LocalArray(std::unique_ptr<T[]> &&p) + : LocalPointerBase<T>(p.release()) {} + + /** + * Destructor deletes the array it owns. + * @stable ICU 4.4 + */ + ~LocalArray() { + delete[] LocalPointerBase<T>::ptr; + } + /** + * Move assignment operator, leaves src with isNull(). + * The behavior is undefined if *this and src are the same object. + * @param src source smart pointer + * @return *this + * @stable ICU 56 + */ + LocalArray<T> &operator=(LocalArray<T> &&src) U_NOEXCEPT { + delete[] LocalPointerBase<T>::ptr; + LocalPointerBase<T>::ptr=src.ptr; + src.ptr=NULL; + return *this; + } + + /** + * Move-assign from an std::unique_ptr to this LocalPointer. + * Steals the array from the std::unique_ptr. + * + * @param p The std::unique_ptr from which the array will be stolen. + * @return *this + * @stable ICU 64 + */ + LocalArray<T> &operator=(std::unique_ptr<T[]> &&p) U_NOEXCEPT { + adoptInstead(p.release()); + return *this; + } + + /** + * Swap pointers. + * @param other other smart pointer + * @stable ICU 56 + */ + void swap(LocalArray<T> &other) U_NOEXCEPT { + T *temp=LocalPointerBase<T>::ptr; + LocalPointerBase<T>::ptr=other.ptr; + other.ptr=temp; + } + /** + * Non-member LocalArray swap function. + * @param p1 will get p2's pointer + * @param p2 will get p1's pointer + * @stable ICU 56 + */ + friend inline void swap(LocalArray<T> &p1, LocalArray<T> &p2) U_NOEXCEPT { + p1.swap(p2); + } + /** + * Deletes the array it owns, + * and adopts (takes ownership of) the one passed in. + * @param p simple pointer to an array of T objects that is adopted + * @stable ICU 4.4 + */ + void adoptInstead(T *p) { + delete[] LocalPointerBase<T>::ptr; + LocalPointerBase<T>::ptr=p; + } + /** + * Deletes the array it owns, + * and adopts (takes ownership of) the one passed in. + * + * If U_FAILURE(errorCode), then the current array is retained and the new one deleted. + * + * If U_SUCCESS(errorCode) but the input pointer is NULL, + * then U_MEMORY_ALLOCATION_ERROR is set, + * the current array is deleted, and NULL is set. + * + * @param p simple pointer to an array of T objects that is adopted + * @param errorCode in/out UErrorCode, set to U_MEMORY_ALLOCATION_ERROR + * if p==NULL and no other failure code had been set + * @stable ICU 56 + */ + void adoptInsteadAndCheckErrorCode(T *p, UErrorCode &errorCode) { + if(U_SUCCESS(errorCode)) { + delete[] LocalPointerBase<T>::ptr; + LocalPointerBase<T>::ptr=p; + if(p==NULL) { + errorCode=U_MEMORY_ALLOCATION_ERROR; + } + } else { + delete[] p; + } + } + /** + * Array item access (writable). + * No index bounds check. + * @param i array index + * @return reference to the array item + * @stable ICU 4.4 + */ + T &operator[](ptrdiff_t i) const { return LocalPointerBase<T>::ptr[i]; } + + /** + * Conversion operator to a C++11 std::unique_ptr. + * Disowns the object and gives it to the returned std::unique_ptr. + * + * This operator works via move semantics. If your LocalPointer is + * in a local variable, you must use std::move. + * + * @return An std::unique_ptr owning the pointer previously owned by this + * icu::LocalPointer. + * @stable ICU 64 + */ + operator std::unique_ptr<T[]> () && { + return std::unique_ptr<T[]>(LocalPointerBase<T>::orphan()); + } +}; + +/** + * \def U_DEFINE_LOCAL_OPEN_POINTER + * "Smart pointer" definition macro, deletes objects via the closeFunction. + * Defines a subclass of LocalPointerBase which works just + * like LocalPointer<Type> except that this subclass will use the closeFunction + * rather than the C++ delete operator. + * + * Usage example: + * \code + * LocalUCaseMapPointer csm(ucasemap_open(localeID, options, &errorCode)); + * utf8OutLength=ucasemap_utf8ToLower(csm.getAlias(), + * utf8Out, (int32_t)sizeof(utf8Out), + * utf8In, utf8InLength, &errorCode); + * if(U_FAILURE(errorCode)) { return; } // no need to explicitly delete the UCaseMap + * \endcode + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +#define U_DEFINE_LOCAL_OPEN_POINTER(LocalPointerClassName, Type, closeFunction) \ + class LocalPointerClassName : public LocalPointerBase<Type> { \ + public: \ + using LocalPointerBase<Type>::operator*; \ + using LocalPointerBase<Type>::operator->; \ + explicit LocalPointerClassName(Type *p=NULL) : LocalPointerBase<Type>(p) {} \ + LocalPointerClassName(LocalPointerClassName &&src) U_NOEXCEPT \ + : LocalPointerBase<Type>(src.ptr) { \ + src.ptr=NULL; \ + } \ + /* TODO: Be agnostic of the deleter function signature from the user-provided std::unique_ptr? */ \ + explicit LocalPointerClassName(std::unique_ptr<Type, decltype(&closeFunction)> &&p) \ + : LocalPointerBase<Type>(p.release()) {} \ + ~LocalPointerClassName() { if (ptr != NULL) { closeFunction(ptr); } } \ + LocalPointerClassName &operator=(LocalPointerClassName &&src) U_NOEXCEPT { \ + if (ptr != NULL) { closeFunction(ptr); } \ + LocalPointerBase<Type>::ptr=src.ptr; \ + src.ptr=NULL; \ + return *this; \ + } \ + /* TODO: Be agnostic of the deleter function signature from the user-provided std::unique_ptr? */ \ + LocalPointerClassName &operator=(std::unique_ptr<Type, decltype(&closeFunction)> &&p) { \ + adoptInstead(p.release()); \ + return *this; \ + } \ + void swap(LocalPointerClassName &other) U_NOEXCEPT { \ + Type *temp=LocalPointerBase<Type>::ptr; \ + LocalPointerBase<Type>::ptr=other.ptr; \ + other.ptr=temp; \ + } \ + friend inline void swap(LocalPointerClassName &p1, LocalPointerClassName &p2) U_NOEXCEPT { \ + p1.swap(p2); \ + } \ + void adoptInstead(Type *p) { \ + if (ptr != NULL) { closeFunction(ptr); } \ + ptr=p; \ + } \ + operator std::unique_ptr<Type, decltype(&closeFunction)> () && { \ + return std::unique_ptr<Type, decltype(&closeFunction)>(LocalPointerBase<Type>::orphan(), closeFunction); \ + } \ + } + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ +#endif /* __LOCALPOINTER_H__ */ diff --git a/thirdparty/icu4c/common/unicode/locdspnm.h b/thirdparty/icu4c/common/unicode/locdspnm.h new file mode 100644 index 0000000000..4f06f85704 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/locdspnm.h @@ -0,0 +1,211 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* Copyright (C) 2010-2016, International Business Machines Corporation and +* others. All Rights Reserved. +****************************************************************************** +*/ + +#ifndef LOCDSPNM_H +#define LOCDSPNM_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +/** + * \file + * \brief C++ API: Provides display names of Locale and its components. + */ + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/locid.h" +#include "unicode/strenum.h" +#include "unicode/uscript.h" +#include "unicode/uldnames.h" +#include "unicode/udisplaycontext.h" + +U_NAMESPACE_BEGIN + +/** + * Returns display names of Locales and components of Locales. For + * more information on language, script, region, variant, key, and + * values, see Locale. + * @stable ICU 4.4 + */ +class U_COMMON_API LocaleDisplayNames : public UObject { +public: + /** + * Destructor. + * @stable ICU 4.4 + */ + virtual ~LocaleDisplayNames(); + + /** + * Convenience overload of + * {@link #createInstance(const Locale& locale, UDialectHandling dialectHandling)} + * that specifies STANDARD dialect handling. + * @param locale the display locale + * @return a LocaleDisplayNames instance + * @stable ICU 4.4 + */ + inline static LocaleDisplayNames* U_EXPORT2 createInstance(const Locale& locale); + + /** + * Returns an instance of LocaleDisplayNames that returns names + * formatted for the provided locale, using the provided + * dialectHandling. + * + * @param locale the display locale + * @param dialectHandling how to select names for locales + * @return a LocaleDisplayNames instance + * @stable ICU 4.4 + */ + static LocaleDisplayNames* U_EXPORT2 createInstance(const Locale& locale, + UDialectHandling dialectHandling); + + /** + * Returns an instance of LocaleDisplayNames that returns names formatted + * for the provided locale, using the provided UDisplayContext settings. + * + * @param locale the display locale + * @param contexts List of one or more context settings (e.g. for dialect + * handling, capitalization, etc. + * @param length Number of items in the contexts list + * @return a LocaleDisplayNames instance + * @stable ICU 51 + */ + static LocaleDisplayNames* U_EXPORT2 createInstance(const Locale& locale, + UDisplayContext *contexts, int32_t length); + + // getters for state + /** + * Returns the locale used to determine the display names. This is + * not necessarily the same locale passed to {@link #createInstance}. + * @return the display locale + * @stable ICU 4.4 + */ + virtual const Locale& getLocale() const = 0; + + /** + * Returns the dialect handling used in the display names. + * @return the dialect handling enum + * @stable ICU 4.4 + */ + virtual UDialectHandling getDialectHandling() const = 0; + + /** + * Returns the UDisplayContext value for the specified UDisplayContextType. + * @param type the UDisplayContextType whose value to return + * @return the UDisplayContext for the specified type. + * @stable ICU 51 + */ + virtual UDisplayContext getContext(UDisplayContextType type) const = 0; + + // names for entire locales + /** + * Returns the display name of the provided locale. + * @param locale the locale whose display name to return + * @param result receives the locale's display name + * @return the display name of the provided locale + * @stable ICU 4.4 + */ + virtual UnicodeString& localeDisplayName(const Locale& locale, + UnicodeString& result) const = 0; + + /** + * Returns the display name of the provided locale id. + * @param localeId the id of the locale whose display name to return + * @param result receives the locale's display name + * @return the display name of the provided locale + * @stable ICU 4.4 + */ + virtual UnicodeString& localeDisplayName(const char* localeId, + UnicodeString& result) const = 0; + + // names for components of a locale id + /** + * Returns the display name of the provided language code. + * @param lang the language code + * @param result receives the language code's display name + * @return the display name of the provided language code + * @stable ICU 4.4 + */ + virtual UnicodeString& languageDisplayName(const char* lang, + UnicodeString& result) const = 0; + + /** + * Returns the display name of the provided script code. + * @param script the script code + * @param result receives the script code's display name + * @return the display name of the provided script code + * @stable ICU 4.4 + */ + virtual UnicodeString& scriptDisplayName(const char* script, + UnicodeString& result) const = 0; + + /** + * Returns the display name of the provided script code. + * @param scriptCode the script code number + * @param result receives the script code's display name + * @return the display name of the provided script code + * @stable ICU 4.4 + */ + virtual UnicodeString& scriptDisplayName(UScriptCode scriptCode, + UnicodeString& result) const = 0; + + /** + * Returns the display name of the provided region code. + * @param region the region code + * @param result receives the region code's display name + * @return the display name of the provided region code + * @stable ICU 4.4 + */ + virtual UnicodeString& regionDisplayName(const char* region, + UnicodeString& result) const = 0; + + /** + * Returns the display name of the provided variant. + * @param variant the variant string + * @param result receives the variant's display name + * @return the display name of the provided variant + * @stable ICU 4.4 + */ + virtual UnicodeString& variantDisplayName(const char* variant, + UnicodeString& result) const = 0; + + /** + * Returns the display name of the provided locale key. + * @param key the locale key name + * @param result receives the locale key's display name + * @return the display name of the provided locale key + * @stable ICU 4.4 + */ + virtual UnicodeString& keyDisplayName(const char* key, + UnicodeString& result) const = 0; + + /** + * Returns the display name of the provided value (used with the provided key). + * @param key the locale key name + * @param value the locale key's value + * @param result receives the value's display name + * @return the display name of the provided value + * @stable ICU 4.4 + */ + virtual UnicodeString& keyValueDisplayName(const char* key, const char* value, + UnicodeString& result) const = 0; +}; + +inline LocaleDisplayNames* LocaleDisplayNames::createInstance(const Locale& locale) { + return LocaleDisplayNames::createInstance(locale, ULDN_STANDARD_NAMES); +} + +U_NAMESPACE_END + +#endif + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/locid.h b/thirdparty/icu4c/common/unicode/locid.h new file mode 100644 index 0000000000..ba858d702a --- /dev/null +++ b/thirdparty/icu4c/common/unicode/locid.h @@ -0,0 +1,1274 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1996-2015, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* +* File locid.h +* +* Created by: Helena Shih +* +* Modification History: +* +* Date Name Description +* 02/11/97 aliu Changed gLocPath to fgLocPath and added methods to +* get and set it. +* 04/02/97 aliu Made operator!= inline; fixed return value of getName(). +* 04/15/97 aliu Cleanup for AIX/Win32. +* 04/24/97 aliu Numerous changes per code review. +* 08/18/98 stephen Added tokenizeString(),changed getDisplayName() +* 09/08/98 stephen Moved definition of kEmptyString for Mac Port +* 11/09/99 weiv Added const char * getName() const; +* 04/12/00 srl removing unicodestring api's and cached hash code +* 08/10/01 grhoten Change the static Locales to accessor functions +****************************************************************************** +*/ + +#ifndef LOCID_H +#define LOCID_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/bytestream.h" +#include "unicode/localpointer.h" +#include "unicode/strenum.h" +#include "unicode/stringpiece.h" +#include "unicode/uobject.h" +#include "unicode/putil.h" +#include "unicode/uloc.h" + +/** + * \file + * \brief C++ API: Locale ID object. + */ + +U_NAMESPACE_BEGIN + +// Forward Declarations +void U_CALLCONV locale_available_init(); /**< @internal */ + +class StringEnumeration; +class UnicodeString; + +/** + * A <code>Locale</code> object represents a specific geographical, political, + * or cultural region. An operation that requires a <code>Locale</code> to perform + * its task is called <em>locale-sensitive</em> and uses the <code>Locale</code> + * to tailor information for the user. For example, displaying a number + * is a locale-sensitive operation--the number should be formatted + * according to the customs/conventions of the user's native country, + * region, or culture. + * + * The Locale class is not suitable for subclassing. + * + * <P> + * You can create a <code>Locale</code> object using the constructor in + * this class: + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * Locale( const char* language, + * const char* country, + * const char* variant); + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * The first argument to the constructors is a valid <STRONG>ISO + * Language Code.</STRONG> These codes are the lower-case two-letter + * codes as defined by ISO-639. + * You can find a full list of these codes at: + * <BR><a href ="http://www.loc.gov/standards/iso639-2/"> + * http://www.loc.gov/standards/iso639-2/</a> + * + * <P> + * The second argument to the constructors is a valid <STRONG>ISO Country + * Code.</STRONG> These codes are the upper-case two-letter codes + * as defined by ISO-3166. + * You can find a full list of these codes at a number of sites, such as: + * <BR><a href="http://www.iso.org/iso/en/prods-services/iso3166ma/index.html"> + * http://www.iso.org/iso/en/prods-services/iso3166ma/index.html</a> + * + * <P> + * The third constructor requires a third argument--the <STRONG>Variant.</STRONG> + * The Variant codes are vendor and browser-specific. + * For example, use REVISED for a language's revised script orthography, and POSIX for POSIX. + * Where there are two variants, separate them with an underscore, and + * put the most important one first. For + * example, a Traditional Spanish collation might be referenced, with + * "ES", "ES", "Traditional_POSIX". + * + * <P> + * Because a <code>Locale</code> object is just an identifier for a region, + * no validity check is performed when you construct a <code>Locale</code>. + * If you want to see whether particular resources are available for the + * <code>Locale</code> you construct, you must query those resources. For + * example, ask the <code>NumberFormat</code> for the locales it supports + * using its <code>getAvailableLocales</code> method. + * <BR><STRONG>Note:</STRONG> When you ask for a resource for a particular + * locale, you get back the best available match, not necessarily + * precisely what you asked for. For more information, look at + * <code>ResourceBundle</code>. + * + * <P> + * The <code>Locale</code> class provides a number of convenient constants + * that you can use to create <code>Locale</code> objects for commonly used + * locales. For example, the following refers to a <code>Locale</code> object + * for the United States: + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * Locale::getUS() + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * <P> + * Once you've created a <code>Locale</code> you can query it for information about + * itself. Use <code>getCountry</code> to get the ISO Country Code and + * <code>getLanguage</code> to get the ISO Language Code. You can + * use <code>getDisplayCountry</code> to get the + * name of the country suitable for displaying to the user. Similarly, + * you can use <code>getDisplayLanguage</code> to get the name of + * the language suitable for displaying to the user. Interestingly, + * the <code>getDisplayXXX</code> methods are themselves locale-sensitive + * and have two versions: one that uses the default locale and one + * that takes a locale as an argument and displays the name or country in + * a language appropriate to that locale. + * + * <P> + * ICU provides a number of classes that perform locale-sensitive + * operations. For example, the <code>NumberFormat</code> class formats + * numbers, currency, or percentages in a locale-sensitive manner. Classes + * such as <code>NumberFormat</code> have a number of convenience methods + * for creating a default object of that type. For example, the + * <code>NumberFormat</code> class provides these three convenience methods + * for creating a default <code>NumberFormat</code> object: + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * UErrorCode success = U_ZERO_ERROR; + * Locale myLocale; + * NumberFormat *nf; + * + * nf = NumberFormat::createInstance( success ); delete nf; + * nf = NumberFormat::createCurrencyInstance( success ); delete nf; + * nf = NumberFormat::createPercentInstance( success ); delete nf; + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * Each of these methods has two variants; one with an explicit locale + * and one without; the latter using the default locale. + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * nf = NumberFormat::createInstance( myLocale, success ); delete nf; + * nf = NumberFormat::createCurrencyInstance( myLocale, success ); delete nf; + * nf = NumberFormat::createPercentInstance( myLocale, success ); delete nf; + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * A <code>Locale</code> is the mechanism for identifying the kind of object + * (<code>NumberFormat</code>) that you would like to get. The locale is + * <STRONG>just</STRONG> a mechanism for identifying objects, + * <STRONG>not</STRONG> a container for the objects themselves. + * + * <P> + * Each class that performs locale-sensitive operations allows you + * to get all the available objects of that type. You can sift + * through these objects by language, country, or variant, + * and use the display names to present a menu to the user. + * For example, you can create a menu of all the collation objects + * suitable for a given language. Such classes implement these + * three class methods: + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * static Locale* getAvailableLocales(int32_t& numLocales) + * static UnicodeString& getDisplayName(const Locale& objectLocale, + * const Locale& displayLocale, + * UnicodeString& displayName) + * static UnicodeString& getDisplayName(const Locale& objectLocale, + * UnicodeString& displayName) + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * @stable ICU 2.0 + * @see ResourceBundle + */ +class U_COMMON_API Locale : public UObject { +public: + /** Useful constant for the Root locale. @stable ICU 4.4 */ + static const Locale &U_EXPORT2 getRoot(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getEnglish(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getFrench(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getGerman(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getItalian(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getJapanese(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getKorean(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getChinese(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getSimplifiedChinese(void); + /** Useful constant for this language. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getTraditionalChinese(void); + + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getFrance(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getGermany(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getItaly(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getJapan(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getKorea(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getChina(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getPRC(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getTaiwan(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getUK(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getUS(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getCanada(void); + /** Useful constant for this country/region. @stable ICU 2.0 */ + static const Locale &U_EXPORT2 getCanadaFrench(void); + + + /** + * Construct a default locale object, a Locale for the default locale ID. + * + * @see getDefault + * @see uloc_getDefault + * @stable ICU 2.0 + */ + Locale(); + + /** + * Construct a locale from language, country, variant. + * If an error occurs, then the constructed object will be "bogus" + * (isBogus() will return true). + * + * @param language Lowercase two-letter or three-letter ISO-639 code. + * This parameter can instead be an ICU style C locale (e.g. "en_US"), + * but the other parameters must not be used. + * This parameter can be NULL; if so, + * the locale is initialized to match the current default locale. + * (This is the same as using the default constructor.) + * Please note: The Java Locale class does NOT accept the form + * 'new Locale("en_US")' but only 'new Locale("en","US")' + * + * @param country Uppercase two-letter ISO-3166 code. (optional) + * @param variant Uppercase vendor and browser specific code. See class + * description. (optional) + * @param keywordsAndValues A string consisting of keyword/values pairs, such as + * "collation=phonebook;currency=euro" + * + * @see getDefault + * @see uloc_getDefault + * @stable ICU 2.0 + */ + Locale( const char * language, + const char * country = 0, + const char * variant = 0, + const char * keywordsAndValues = 0); + + /** + * Initializes a Locale object from another Locale object. + * + * @param other The Locale object being copied in. + * @stable ICU 2.0 + */ + Locale(const Locale& other); + + /** + * Move constructor; might leave source in bogus state. + * This locale will have the same contents that the source locale had. + * + * @param other The Locale object being moved in. + * @stable ICU 63 + */ + Locale(Locale&& other) U_NOEXCEPT; + + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~Locale() ; + + /** + * Replaces the entire contents of *this with the specified value. + * + * @param other The Locale object being copied in. + * @return *this + * @stable ICU 2.0 + */ + Locale& operator=(const Locale& other); + + /** + * Move assignment operator; might leave source in bogus state. + * This locale will have the same contents that the source locale had. + * The behavior is undefined if *this and the source are the same object. + * + * @param other The Locale object being moved in. + * @return *this + * @stable ICU 63 + */ + Locale& operator=(Locale&& other) U_NOEXCEPT; + + /** + * Checks if two locale keys are the same. + * + * @param other The locale key object to be compared with this. + * @return True if the two locale keys are the same, false otherwise. + * @stable ICU 2.0 + */ + UBool operator==(const Locale& other) const; + + /** + * Checks if two locale keys are not the same. + * + * @param other The locale key object to be compared with this. + * @return True if the two locale keys are not the same, false + * otherwise. + * @stable ICU 2.0 + */ + inline UBool operator!=(const Locale& other) const; + + /** + * Clone this object. + * Clones can be used concurrently in multiple threads. + * If an error occurs, then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see getDynamicClassID + * @stable ICU 2.8 + */ + Locale *clone() const; + +#ifndef U_HIDE_SYSTEM_API + /** + * Common methods of getting the current default Locale. Used for the + * presentation: menus, dialogs, etc. Generally set once when your applet or + * application is initialized, then never reset. (If you do reset the + * default locale, you probably want to reload your GUI, so that the change + * is reflected in your interface.) + * + * More advanced programs will allow users to use different locales for + * different fields, e.g. in a spreadsheet. + * + * Note that the initial setting will match the host system. + * @return a reference to the Locale object for the default locale ID + * @system + * @stable ICU 2.0 + */ + static const Locale& U_EXPORT2 getDefault(void); + + /** + * Sets the default. Normally set once at the beginning of a process, + * then never reset. + * setDefault() only changes ICU's default locale ID, <strong>not</strong> + * the default locale ID of the runtime environment. + * + * @param newLocale Locale to set to. If NULL, set to the value obtained + * from the runtime environment. + * @param success The error code. + * @system + * @stable ICU 2.0 + */ + static void U_EXPORT2 setDefault(const Locale& newLocale, + UErrorCode& success); +#endif /* U_HIDE_SYSTEM_API */ + + /** + * Returns a Locale for the specified BCP47 language tag string. + * If the specified language tag contains any ill-formed subtags, + * the first such subtag and all following subtags are ignored. + * <p> + * This implements the 'Language-Tag' production of BCP 47, and so + * supports legacy language tags (marked as “Type: grandfathered” in BCP 47) + * (regular and irregular) as well as private use language tags. + * + * Private use tags are represented as 'x-whatever', + * and legacy tags are converted to their canonical replacements where they exist. + * + * Note that a few legacy tags have no modern replacement; + * these will be converted using the fallback described in + * the first paragraph, so some information might be lost. + * + * @param tag the input BCP47 language tag. + * @param status error information if creating the Locale failed. + * @return the Locale for the specified BCP47 language tag. + * @stable ICU 63 + */ + static Locale U_EXPORT2 forLanguageTag(StringPiece tag, UErrorCode& status); + + /** + * Returns a well-formed language tag for this Locale. + * <p> + * <b>Note</b>: Any locale fields which do not satisfy the BCP47 syntax + * requirement will be silently omitted from the result. + * + * If this function fails, partial output may have been written to the sink. + * + * @param sink the output sink receiving the BCP47 language + * tag for this Locale. + * @param status error information if creating the language tag failed. + * @stable ICU 63 + */ + void toLanguageTag(ByteSink& sink, UErrorCode& status) const; + + /** + * Returns a well-formed language tag for this Locale. + * <p> + * <b>Note</b>: Any locale fields which do not satisfy the BCP47 syntax + * requirement will be silently omitted from the result. + * + * @param status error information if creating the language tag failed. + * @return the BCP47 language tag for this Locale. + * @stable ICU 63 + */ + template<typename StringClass> + inline StringClass toLanguageTag(UErrorCode& status) const; + + /** + * Creates a locale which has had minimal canonicalization + * as per uloc_getName(). + * @param name The name to create from. If name is null, + * the default Locale is used. + * @return new locale object + * @stable ICU 2.0 + * @see uloc_getName + */ + static Locale U_EXPORT2 createFromName(const char *name); + + /** + * Creates a locale from the given string after canonicalizing + * the string according to CLDR by calling uloc_canonicalize(). + * @param name the locale ID to create from. Must not be NULL. + * @return a new locale object corresponding to the given name + * @stable ICU 3.0 + * @see uloc_canonicalize + */ + static Locale U_EXPORT2 createCanonical(const char* name); + + /** + * Returns the locale's ISO-639 language code. + * @return An alias to the code + * @stable ICU 2.0 + */ + inline const char * getLanguage( ) const; + + /** + * Returns the locale's ISO-15924 abbreviation script code. + * @return An alias to the code + * @see uscript_getShortName + * @see uscript_getCode + * @stable ICU 2.8 + */ + inline const char * getScript( ) const; + + /** + * Returns the locale's ISO-3166 country code. + * @return An alias to the code + * @stable ICU 2.0 + */ + inline const char * getCountry( ) const; + + /** + * Returns the locale's variant code. + * @return An alias to the code + * @stable ICU 2.0 + */ + inline const char * getVariant( ) const; + + /** + * Returns the programmatic name of the entire locale, with the language, + * country and variant separated by underbars. If a field is missing, up + * to two leading underbars will occur. Example: "en", "de_DE", "en_US_WIN", + * "de__POSIX", "fr__MAC", "__MAC", "_MT", "_FR_EURO" + * @return A pointer to "name". + * @stable ICU 2.0 + */ + inline const char * getName() const; + + /** + * Returns the programmatic name of the entire locale as getName() would return, + * but without keywords. + * @return A pointer to "name". + * @see getName + * @stable ICU 2.8 + */ + const char * getBaseName() const; + + /** + * Add the likely subtags for this Locale, per the algorithm described + * in the following CLDR technical report: + * + * http://www.unicode.org/reports/tr35/#Likely_Subtags + * + * If this Locale is already in the maximal form, or not valid, or there is + * no data available for maximization, the Locale will be unchanged. + * + * For example, "und-Zzzz" cannot be maximized, since there is no + * reasonable maximization. + * + * Examples: + * + * "en" maximizes to "en_Latn_US" + * + * "de" maximizes to "de_Latn_US" + * + * "sr" maximizes to "sr_Cyrl_RS" + * + * "sh" maximizes to "sr_Latn_RS" (Note this will not reverse.) + * + * "zh_Hani" maximizes to "zh_Hans_CN" (Note this will not reverse.) + * + * @param status error information if maximizing this Locale failed. + * If this Locale is not well-formed, the error code is + * U_ILLEGAL_ARGUMENT_ERROR. + * @stable ICU 63 + */ + void addLikelySubtags(UErrorCode& status); + + /** + * Minimize the subtags for this Locale, per the algorithm described + * in the following CLDR technical report: + * + * http://www.unicode.org/reports/tr35/#Likely_Subtags + * + * If this Locale is already in the minimal form, or not valid, or there is + * no data available for minimization, the Locale will be unchanged. + * + * Since the minimization algorithm relies on proper maximization, see the + * comments for addLikelySubtags for reasons why there might not be any + * data. + * + * Examples: + * + * "en_Latn_US" minimizes to "en" + * + * "de_Latn_US" minimizes to "de" + * + * "sr_Cyrl_RS" minimizes to "sr" + * + * "zh_Hant_TW" minimizes to "zh_TW" (The region is preferred to the + * script, and minimizing to "zh" would imply "zh_Hans_CN".) + * + * @param status error information if maximizing this Locale failed. + * If this Locale is not well-formed, the error code is + * U_ILLEGAL_ARGUMENT_ERROR. + * @stable ICU 63 + */ + void minimizeSubtags(UErrorCode& status); + +#ifndef U_HIDE_DRAFT_API + /** + * Canonicalize the locale ID of this object according to CLDR. + * @param status the status code + * @draft ICU 67 + * @see createCanonical + */ + void canonicalize(UErrorCode& status); +#endif // U_HIDE_DRAFT_API + + /** + * Gets the list of keywords for the specified locale. + * + * @param status the status code + * @return pointer to StringEnumeration class, or NULL if there are no keywords. + * Client must dispose of it by calling delete. + * @see getKeywords + * @stable ICU 2.8 + */ + StringEnumeration * createKeywords(UErrorCode &status) const; + + /** + * Gets the list of Unicode keywords for the specified locale. + * + * @param status the status code + * @return pointer to StringEnumeration class, or NULL if there are no keywords. + * Client must dispose of it by calling delete. + * @see getUnicodeKeywords + * @stable ICU 63 + */ + StringEnumeration * createUnicodeKeywords(UErrorCode &status) const; + + /** + * Gets the set of keywords for this Locale. + * + * A wrapper to call createKeywords() and write the resulting + * keywords as standard strings (or compatible objects) into any kind of + * container that can be written to by an STL style output iterator. + * + * @param iterator an STL style output iterator to write the keywords to. + * @param status error information if creating set of keywords failed. + * @stable ICU 63 + */ + template<typename StringClass, typename OutputIterator> + inline void getKeywords(OutputIterator iterator, UErrorCode& status) const; + + /** + * Gets the set of Unicode keywords for this Locale. + * + * A wrapper to call createUnicodeKeywords() and write the resulting + * keywords as standard strings (or compatible objects) into any kind of + * container that can be written to by an STL style output iterator. + * + * @param iterator an STL style output iterator to write the keywords to. + * @param status error information if creating set of keywords failed. + * @stable ICU 63 + */ + template<typename StringClass, typename OutputIterator> + inline void getUnicodeKeywords(OutputIterator iterator, UErrorCode& status) const; + + /** + * Gets the value for a keyword. + * + * This uses legacy keyword=value pairs, like "collation=phonebook". + * + * ICU4C doesn't do automatic conversion between legacy and Unicode + * keywords and values in getters and setters (as opposed to ICU4J). + * + * @param keywordName name of the keyword for which we want the value. Case insensitive. + * @param buffer The buffer to receive the keyword value. + * @param bufferCapacity The capacity of receiving buffer + * @param status Returns any error information while performing this operation. + * @return the length of the keyword value + * + * @stable ICU 2.8 + */ + int32_t getKeywordValue(const char* keywordName, char *buffer, int32_t bufferCapacity, UErrorCode &status) const; + + /** + * Gets the value for a keyword. + * + * This uses legacy keyword=value pairs, like "collation=phonebook". + * + * ICU4C doesn't do automatic conversion between legacy and Unicode + * keywords and values in getters and setters (as opposed to ICU4J). + * + * @param keywordName name of the keyword for which we want the value. + * @param sink the sink to receive the keyword value. + * @param status error information if getting the value failed. + * @stable ICU 63 + */ + void getKeywordValue(StringPiece keywordName, ByteSink& sink, UErrorCode& status) const; + + /** + * Gets the value for a keyword. + * + * This uses legacy keyword=value pairs, like "collation=phonebook". + * + * ICU4C doesn't do automatic conversion between legacy and Unicode + * keywords and values in getters and setters (as opposed to ICU4J). + * + * @param keywordName name of the keyword for which we want the value. + * @param status error information if getting the value failed. + * @return the keyword value. + * @stable ICU 63 + */ + template<typename StringClass> + inline StringClass getKeywordValue(StringPiece keywordName, UErrorCode& status) const; + + /** + * Gets the Unicode value for a Unicode keyword. + * + * This uses Unicode key-value pairs, like "co-phonebk". + * + * ICU4C doesn't do automatic conversion between legacy and Unicode + * keywords and values in getters and setters (as opposed to ICU4J). + * + * @param keywordName name of the keyword for which we want the value. + * @param sink the sink to receive the keyword value. + * @param status error information if getting the value failed. + * @stable ICU 63 + */ + void getUnicodeKeywordValue(StringPiece keywordName, ByteSink& sink, UErrorCode& status) const; + + /** + * Gets the Unicode value for a Unicode keyword. + * + * This uses Unicode key-value pairs, like "co-phonebk". + * + * ICU4C doesn't do automatic conversion between legacy and Unicode + * keywords and values in getters and setters (as opposed to ICU4J). + * + * @param keywordName name of the keyword for which we want the value. + * @param status error information if getting the value failed. + * @return the keyword value. + * @stable ICU 63 + */ + template<typename StringClass> + inline StringClass getUnicodeKeywordValue(StringPiece keywordName, UErrorCode& status) const; + + /** + * Sets or removes the value for a keyword. + * + * For removing all keywords, use getBaseName(), + * and construct a new Locale if it differs from getName(). + * + * This uses legacy keyword=value pairs, like "collation=phonebook". + * + * ICU4C doesn't do automatic conversion between legacy and Unicode + * keywords and values in getters and setters (as opposed to ICU4J). + * + * @param keywordName name of the keyword to be set. Case insensitive. + * @param keywordValue value of the keyword to be set. If 0-length or + * NULL, will result in the keyword being removed. No error is given if + * that keyword does not exist. + * @param status Returns any error information while performing this operation. + * + * @stable ICU 49 + */ + void setKeywordValue(const char* keywordName, const char* keywordValue, UErrorCode &status); + + /** + * Sets or removes the value for a keyword. + * + * For removing all keywords, use getBaseName(), + * and construct a new Locale if it differs from getName(). + * + * This uses legacy keyword=value pairs, like "collation=phonebook". + * + * ICU4C doesn't do automatic conversion between legacy and Unicode + * keywords and values in getters and setters (as opposed to ICU4J). + * + * @param keywordName name of the keyword to be set. + * @param keywordValue value of the keyword to be set. If 0-length or + * NULL, will result in the keyword being removed. No error is given if + * that keyword does not exist. + * @param status Returns any error information while performing this operation. + * @stable ICU 63 + */ + void setKeywordValue(StringPiece keywordName, StringPiece keywordValue, UErrorCode& status); + + /** + * Sets or removes the Unicode value for a Unicode keyword. + * + * For removing all keywords, use getBaseName(), + * and construct a new Locale if it differs from getName(). + * + * This uses Unicode key-value pairs, like "co-phonebk". + * + * ICU4C doesn't do automatic conversion between legacy and Unicode + * keywords and values in getters and setters (as opposed to ICU4J). + * + * @param keywordName name of the keyword to be set. + * @param keywordValue value of the keyword to be set. If 0-length or + * NULL, will result in the keyword being removed. No error is given if + * that keyword does not exist. + * @param status Returns any error information while performing this operation. + * @stable ICU 63 + */ + void setUnicodeKeywordValue(StringPiece keywordName, StringPiece keywordValue, UErrorCode& status); + + /** + * returns the locale's three-letter language code, as specified + * in ISO draft standard ISO-639-2. + * @return An alias to the code, or an empty string + * @stable ICU 2.0 + */ + const char * getISO3Language() const; + + /** + * Fills in "name" with the locale's three-letter ISO-3166 country code. + * @return An alias to the code, or an empty string + * @stable ICU 2.0 + */ + const char * getISO3Country() const; + + /** + * Returns the Windows LCID value corresponding to this locale. + * This value is stored in the resource data for the locale as a one-to-four-digit + * hexadecimal number. If the resource is missing, in the wrong format, or + * there is no Windows LCID value that corresponds to this locale, returns 0. + * @stable ICU 2.0 + */ + uint32_t getLCID(void) const; + + /** + * Returns whether this locale's script is written right-to-left. + * If there is no script subtag, then the likely script is used, see uloc_addLikelySubtags(). + * If no likely script is known, then false is returned. + * + * A script is right-to-left according to the CLDR script metadata + * which corresponds to whether the script's letters have Bidi_Class=R or AL. + * + * Returns true for "ar" and "en-Hebr", false for "zh" and "fa-Cyrl". + * + * @return true if the locale's script is written right-to-left + * @stable ICU 54 + */ + UBool isRightToLeft() const; + + /** + * Fills in "dispLang" with the name of this locale's language in a format suitable for + * user display in the default locale. For example, if the locale's language code is + * "fr" and the default locale's language code is "en", this function would set + * dispLang to "French". + * @param dispLang Receives the language's display name. + * @return A reference to "dispLang". + * @stable ICU 2.0 + */ + UnicodeString& getDisplayLanguage(UnicodeString& dispLang) const; + + /** + * Fills in "dispLang" with the name of this locale's language in a format suitable for + * user display in the locale specified by "displayLocale". For example, if the locale's + * language code is "en" and displayLocale's language code is "fr", this function would set + * dispLang to "Anglais". + * @param displayLocale Specifies the locale to be used to display the name. In other words, + * if the locale's language code is "en", passing Locale::getFrench() for + * displayLocale would result in "Anglais", while passing Locale::getGerman() + * for displayLocale would result in "Englisch". + * @param dispLang Receives the language's display name. + * @return A reference to "dispLang". + * @stable ICU 2.0 + */ + UnicodeString& getDisplayLanguage( const Locale& displayLocale, + UnicodeString& dispLang) const; + + /** + * Fills in "dispScript" with the name of this locale's script in a format suitable + * for user display in the default locale. For example, if the locale's script code + * is "LATN" and the default locale's language code is "en", this function would set + * dispScript to "Latin". + * @param dispScript Receives the scripts's display name. + * @return A reference to "dispScript". + * @stable ICU 2.8 + */ + UnicodeString& getDisplayScript( UnicodeString& dispScript) const; + + /** + * Fills in "dispScript" with the name of this locale's country in a format suitable + * for user display in the locale specified by "displayLocale". For example, if the locale's + * script code is "LATN" and displayLocale's language code is "en", this function would set + * dispScript to "Latin". + * @param displayLocale Specifies the locale to be used to display the name. In other + * words, if the locale's script code is "LATN", passing + * Locale::getFrench() for displayLocale would result in "", while + * passing Locale::getGerman() for displayLocale would result in + * "". + * @param dispScript Receives the scripts's display name. + * @return A reference to "dispScript". + * @stable ICU 2.8 + */ + UnicodeString& getDisplayScript( const Locale& displayLocale, + UnicodeString& dispScript) const; + + /** + * Fills in "dispCountry" with the name of this locale's country in a format suitable + * for user display in the default locale. For example, if the locale's country code + * is "FR" and the default locale's language code is "en", this function would set + * dispCountry to "France". + * @param dispCountry Receives the country's display name. + * @return A reference to "dispCountry". + * @stable ICU 2.0 + */ + UnicodeString& getDisplayCountry( UnicodeString& dispCountry) const; + + /** + * Fills in "dispCountry" with the name of this locale's country in a format suitable + * for user display in the locale specified by "displayLocale". For example, if the locale's + * country code is "US" and displayLocale's language code is "fr", this function would set + * dispCountry to "États-Unis". + * @param displayLocale Specifies the locale to be used to display the name. In other + * words, if the locale's country code is "US", passing + * Locale::getFrench() for displayLocale would result in "États-Unis", while + * passing Locale::getGerman() for displayLocale would result in + * "Vereinigte Staaten". + * @param dispCountry Receives the country's display name. + * @return A reference to "dispCountry". + * @stable ICU 2.0 + */ + UnicodeString& getDisplayCountry( const Locale& displayLocale, + UnicodeString& dispCountry) const; + + /** + * Fills in "dispVar" with the name of this locale's variant code in a format suitable + * for user display in the default locale. + * @param dispVar Receives the variant's name. + * @return A reference to "dispVar". + * @stable ICU 2.0 + */ + UnicodeString& getDisplayVariant( UnicodeString& dispVar) const; + + /** + * Fills in "dispVar" with the name of this locale's variant code in a format + * suitable for user display in the locale specified by "displayLocale". + * @param displayLocale Specifies the locale to be used to display the name. + * @param dispVar Receives the variant's display name. + * @return A reference to "dispVar". + * @stable ICU 2.0 + */ + UnicodeString& getDisplayVariant( const Locale& displayLocale, + UnicodeString& dispVar) const; + + /** + * Fills in "name" with the name of this locale in a format suitable for user display + * in the default locale. This function uses getDisplayLanguage(), getDisplayCountry(), + * and getDisplayVariant() to do its work, and outputs the display name in the format + * "language (country[,variant])". For example, if the default locale is en_US, then + * fr_FR's display name would be "French (France)", and es_MX_Traditional's display name + * would be "Spanish (Mexico,Traditional)". + * @param name Receives the locale's display name. + * @return A reference to "name". + * @stable ICU 2.0 + */ + UnicodeString& getDisplayName( UnicodeString& name) const; + + /** + * Fills in "name" with the name of this locale in a format suitable for user display + * in the locale specified by "displayLocale". This function uses getDisplayLanguage(), + * getDisplayCountry(), and getDisplayVariant() to do its work, and outputs the display + * name in the format "language (country[,variant])". For example, if displayLocale is + * fr_FR, then en_US's display name would be "Anglais (États-Unis)", and no_NO_NY's + * display name would be "norvégien (Norvège,NY)". + * @param displayLocale Specifies the locale to be used to display the name. + * @param name Receives the locale's display name. + * @return A reference to "name". + * @stable ICU 2.0 + */ + UnicodeString& getDisplayName( const Locale& displayLocale, + UnicodeString& name) const; + + /** + * Generates a hash code for the locale. + * @stable ICU 2.0 + */ + int32_t hashCode(void) const; + + /** + * Sets the locale to bogus + * A bogus locale represents a non-existing locale associated + * with services that can be instantiated from non-locale data + * in addition to locale (for example, collation can be + * instantiated from a locale and from a rule set). + * @stable ICU 2.1 + */ + void setToBogus(); + + /** + * Gets the bogus state. Locale object can be bogus if it doesn't exist + * @return false if it is a real locale, true if it is a bogus locale + * @stable ICU 2.1 + */ + inline UBool isBogus(void) const; + + /** + * Returns a list of all installed locales. + * @param count Receives the number of locales in the list. + * @return A pointer to an array of Locale objects. This array is the list + * of all locales with installed resource files. The called does NOT + * get ownership of this list, and must NOT delete it. + * @stable ICU 2.0 + */ + static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count); + + /** + * Gets a list of all available 2-letter country codes defined in ISO 3166. This is a + * pointer to an array of pointers to arrays of char. All of these pointers are + * owned by ICU-- do not delete them, and do not write through them. The array is + * terminated with a null pointer. + * @return a list of all available country codes + * @stable ICU 2.0 + */ + static const char* const* U_EXPORT2 getISOCountries(); + + /** + * Gets a list of all available language codes defined in ISO 639. This is a pointer + * to an array of pointers to arrays of char. All of these pointers are owned + * by ICU-- do not delete them, and do not write through them. The array is + * terminated with a null pointer. + * @return a list of all available language codes + * @stable ICU 2.0 + */ + static const char* const* U_EXPORT2 getISOLanguages(); + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + /** + * A Locale iterator interface similar to a Java Iterator<Locale>. + * @stable ICU 65 + */ + class U_COMMON_API Iterator /* not : public UObject because this is an interface/mixin class */ { + public: + /** @stable ICU 65 */ + virtual ~Iterator(); + + /** + * @return true if next() can be called again. + * @stable ICU 65 + */ + virtual UBool hasNext() const = 0; + + /** + * @return the next locale. + * @stable ICU 65 + */ + virtual const Locale &next() = 0; + }; + + /** + * A generic Locale iterator implementation over Locale input iterators. + * @stable ICU 65 + */ + template<typename Iter> + class RangeIterator : public Iterator, public UMemory { + public: + /** + * Constructs an iterator from a begin/end range. + * Each of the iterator parameter values must be an + * input iterator whose value is convertible to const Locale &. + * + * @param begin Start of range. + * @param end Exclusive end of range. + * @stable ICU 65 + */ + RangeIterator(Iter begin, Iter end) : it_(begin), end_(end) {} + + /** + * @return true if next() can be called again. + * @stable ICU 65 + */ + UBool hasNext() const override { return it_ != end_; } + + /** + * @return the next locale. + * @stable ICU 65 + */ + const Locale &next() override { return *it_++; } + + private: + Iter it_; + const Iter end_; + }; + + /** + * A generic Locale iterator implementation over Locale input iterators. + * Calls the converter to convert each *begin to a const Locale &. + * @stable ICU 65 + */ + template<typename Iter, typename Conv> + class ConvertingIterator : public Iterator, public UMemory { + public: + /** + * Constructs an iterator from a begin/end range. + * Each of the iterator parameter values must be an + * input iterator whose value the converter converts to const Locale &. + * + * @param begin Start of range. + * @param end Exclusive end of range. + * @param converter Converter from *begin to const Locale & or compatible. + * @stable ICU 65 + */ + ConvertingIterator(Iter begin, Iter end, Conv converter) : + it_(begin), end_(end), converter_(converter) {} + + /** + * @return true if next() can be called again. + * @stable ICU 65 + */ + UBool hasNext() const override { return it_ != end_; } + + /** + * @return the next locale. + * @stable ICU 65 + */ + const Locale &next() override { return converter_(*it_++); } + + private: + Iter it_; + const Iter end_; + Conv converter_; + }; + +protected: /* only protected for testing purposes. DO NOT USE. */ +#ifndef U_HIDE_INTERNAL_API + /** + * Set this from a single POSIX style locale string. + * @internal + */ + void setFromPOSIXID(const char *posixID); +#endif /* U_HIDE_INTERNAL_API */ + +private: + /** + * Initialize the locale object with a new name. + * Was deprecated - used in implementation - moved internal + * + * @param cLocaleID The new locale name. + * @param canonicalize whether to call uloc_canonicalize on cLocaleID + */ + Locale& init(const char* cLocaleID, UBool canonicalize); + + /* + * Internal constructor to allow construction of a locale object with + * NO side effects. (Default constructor tries to get + * the default locale.) + */ + enum ELocaleType { + eBOGUS + }; + Locale(ELocaleType); + + /** + * Initialize the locale cache for commonly used locales + */ + static Locale *getLocaleCache(void); + + char language[ULOC_LANG_CAPACITY]; + char script[ULOC_SCRIPT_CAPACITY]; + char country[ULOC_COUNTRY_CAPACITY]; + int32_t variantBegin; + char* fullName; + char fullNameBuffer[ULOC_FULLNAME_CAPACITY]; + // name without keywords + char* baseName; + void initBaseName(UErrorCode& status); + + UBool fIsBogus; + + static const Locale &getLocale(int locid); + + /** + * A friend to allow the default locale to be set by either the C or C++ API. + * @internal (private) + */ + friend Locale *locale_set_default_internal(const char *, UErrorCode& status); + + /** + * @internal (private) + */ + friend void U_CALLCONV locale_available_init(); +}; + +inline UBool +Locale::operator!=(const Locale& other) const +{ + return !operator==(other); +} + +template<typename StringClass> inline StringClass +Locale::toLanguageTag(UErrorCode& status) const +{ + StringClass result; + StringByteSink<StringClass> sink(&result); + toLanguageTag(sink, status); + return result; +} + +inline const char * +Locale::getCountry() const +{ + return country; +} + +inline const char * +Locale::getLanguage() const +{ + return language; +} + +inline const char * +Locale::getScript() const +{ + return script; +} + +inline const char * +Locale::getVariant() const +{ + return &baseName[variantBegin]; +} + +inline const char * +Locale::getName() const +{ + return fullName; +} + +template<typename StringClass, typename OutputIterator> inline void +Locale::getKeywords(OutputIterator iterator, UErrorCode& status) const +{ + LocalPointer<StringEnumeration> keys(createKeywords(status)); + if (U_FAILURE(status) || keys.isNull()) { + return; + } + for (;;) { + int32_t resultLength; + const char* buffer = keys->next(&resultLength, status); + if (U_FAILURE(status) || buffer == nullptr) { + return; + } + *iterator++ = StringClass(buffer, resultLength); + } +} + +template<typename StringClass, typename OutputIterator> inline void +Locale::getUnicodeKeywords(OutputIterator iterator, UErrorCode& status) const +{ + LocalPointer<StringEnumeration> keys(createUnicodeKeywords(status)); + if (U_FAILURE(status) || keys.isNull()) { + return; + } + for (;;) { + int32_t resultLength; + const char* buffer = keys->next(&resultLength, status); + if (U_FAILURE(status) || buffer == nullptr) { + return; + } + *iterator++ = StringClass(buffer, resultLength); + } +} + +template<typename StringClass> inline StringClass +Locale::getKeywordValue(StringPiece keywordName, UErrorCode& status) const +{ + StringClass result; + StringByteSink<StringClass> sink(&result); + getKeywordValue(keywordName, sink, status); + return result; +} + +template<typename StringClass> inline StringClass +Locale::getUnicodeKeywordValue(StringPiece keywordName, UErrorCode& status) const +{ + StringClass result; + StringByteSink<StringClass> sink(&result); + getUnicodeKeywordValue(keywordName, sink, status); + return result; +} + +inline UBool +Locale::isBogus(void) const { + return fIsBogus; +} + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/messagepattern.h b/thirdparty/icu4c/common/unicode/messagepattern.h new file mode 100644 index 0000000000..98e7b70b1f --- /dev/null +++ b/thirdparty/icu4c/common/unicode/messagepattern.h @@ -0,0 +1,949 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2011-2013, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: messagepattern.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2011mar14 +* created by: Markus W. Scherer +*/ + +#ifndef __MESSAGEPATTERN_H__ +#define __MESSAGEPATTERN_H__ + +/** + * \file + * \brief C++ API: MessagePattern class: Parses and represents ICU MessageFormat patterns. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#if !UCONFIG_NO_FORMATTING + +#include "unicode/parseerr.h" +#include "unicode/unistr.h" + +/** + * Mode for when an apostrophe starts quoted literal text for MessageFormat output. + * The default is DOUBLE_OPTIONAL unless overridden via uconfig.h + * (UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE). + * <p> + * A pair of adjacent apostrophes always results in a single apostrophe in the output, + * even when the pair is between two single, text-quoting apostrophes. + * <p> + * The following table shows examples of desired MessageFormat.format() output + * with the pattern strings that yield that output. + * <p> + * <table> + * <tr> + * <th>Desired output</th> + * <th>DOUBLE_OPTIONAL</th> + * <th>DOUBLE_REQUIRED</th> + * </tr> + * <tr> + * <td>I see {many}</td> + * <td>I see '{many}'</td> + * <td>(same)</td> + * </tr> + * <tr> + * <td>I said {'Wow!'}</td> + * <td>I said '{''Wow!''}'</td> + * <td>(same)</td> + * </tr> + * <tr> + * <td>I don't know</td> + * <td>I don't know OR<br> I don''t know</td> + * <td>I don''t know</td> + * </tr> + * </table> + * @stable ICU 4.8 + * @see UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE + */ +enum UMessagePatternApostropheMode { + /** + * A literal apostrophe is represented by + * either a single or a double apostrophe pattern character. + * Within a MessageFormat pattern, a single apostrophe only starts quoted literal text + * if it immediately precedes a curly brace {}, + * or a pipe symbol | if inside a choice format, + * or a pound symbol # if inside a plural format. + * <p> + * This is the default behavior starting with ICU 4.8. + * @stable ICU 4.8 + */ + UMSGPAT_APOS_DOUBLE_OPTIONAL, + /** + * A literal apostrophe must be represented by + * a double apostrophe pattern character. + * A single apostrophe always starts quoted literal text. + * <p> + * This is the behavior of ICU 4.6 and earlier, and of the JDK. + * @stable ICU 4.8 + */ + UMSGPAT_APOS_DOUBLE_REQUIRED +}; +/** + * @stable ICU 4.8 + */ +typedef enum UMessagePatternApostropheMode UMessagePatternApostropheMode; + +/** + * MessagePattern::Part type constants. + * @stable ICU 4.8 + */ +enum UMessagePatternPartType { + /** + * Start of a message pattern (main or nested). + * The length is 0 for the top-level message + * and for a choice argument sub-message, otherwise 1 for the '{'. + * The value indicates the nesting level, starting with 0 for the main message. + * <p> + * There is always a later MSG_LIMIT part. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_MSG_START, + /** + * End of a message pattern (main or nested). + * The length is 0 for the top-level message and + * the last sub-message of a choice argument, + * otherwise 1 for the '}' or (in a choice argument style) the '|'. + * The value indicates the nesting level, starting with 0 for the main message. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_MSG_LIMIT, + /** + * Indicates a substring of the pattern string which is to be skipped when formatting. + * For example, an apostrophe that begins or ends quoted text + * would be indicated with such a part. + * The value is undefined and currently always 0. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_SKIP_SYNTAX, + /** + * Indicates that a syntax character needs to be inserted for auto-quoting. + * The length is 0. + * The value is the character code of the insertion character. (U+0027=APOSTROPHE) + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_INSERT_CHAR, + /** + * Indicates a syntactic (non-escaped) # symbol in a plural variant. + * When formatting, replace this part's substring with the + * (value-offset) for the plural argument value. + * The value is undefined and currently always 0. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_REPLACE_NUMBER, + /** + * Start of an argument. + * The length is 1 for the '{'. + * The value is the ordinal value of the ArgType. Use getArgType(). + * <p> + * This part is followed by either an ARG_NUMBER or ARG_NAME, + * followed by optional argument sub-parts (see UMessagePatternArgType constants) + * and finally an ARG_LIMIT part. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_START, + /** + * End of an argument. + * The length is 1 for the '}'. + * The value is the ordinal value of the ArgType. Use getArgType(). + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_LIMIT, + /** + * The argument number, provided by the value. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_NUMBER, + /** + * The argument name. + * The value is undefined and currently always 0. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_NAME, + /** + * The argument type. + * The value is undefined and currently always 0. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_TYPE, + /** + * The argument style text. + * The value is undefined and currently always 0. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_STYLE, + /** + * A selector substring in a "complex" argument style. + * The value is undefined and currently always 0. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_SELECTOR, + /** + * An integer value, for example the offset or an explicit selector value + * in a PluralFormat style. + * The part value is the integer value. + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_INT, + /** + * A numeric value, for example the offset or an explicit selector value + * in a PluralFormat style. + * The part value is an index into an internal array of numeric values; + * use getNumericValue(). + * @stable ICU 4.8 + */ + UMSGPAT_PART_TYPE_ARG_DOUBLE +}; +/** + * @stable ICU 4.8 + */ +typedef enum UMessagePatternPartType UMessagePatternPartType; + +/** + * Argument type constants. + * Returned by Part.getArgType() for ARG_START and ARG_LIMIT parts. + * + * Messages nested inside an argument are each delimited by MSG_START and MSG_LIMIT, + * with a nesting level one greater than the surrounding message. + * @stable ICU 4.8 + */ +enum UMessagePatternArgType { + /** + * The argument has no specified type. + * @stable ICU 4.8 + */ + UMSGPAT_ARG_TYPE_NONE, + /** + * The argument has a "simple" type which is provided by the ARG_TYPE part. + * An ARG_STYLE part might follow that. + * @stable ICU 4.8 + */ + UMSGPAT_ARG_TYPE_SIMPLE, + /** + * The argument is a ChoiceFormat with one or more + * ((ARG_INT | ARG_DOUBLE), ARG_SELECTOR, message) tuples. + * @stable ICU 4.8 + */ + UMSGPAT_ARG_TYPE_CHOICE, + /** + * The argument is a cardinal-number PluralFormat with an optional ARG_INT or ARG_DOUBLE offset + * (e.g., offset:1) + * and one or more (ARG_SELECTOR [explicit-value] message) tuples. + * If the selector has an explicit value (e.g., =2), then + * that value is provided by the ARG_INT or ARG_DOUBLE part preceding the message. + * Otherwise the message immediately follows the ARG_SELECTOR. + * @stable ICU 4.8 + */ + UMSGPAT_ARG_TYPE_PLURAL, + /** + * The argument is a SelectFormat with one or more (ARG_SELECTOR, message) pairs. + * @stable ICU 4.8 + */ + UMSGPAT_ARG_TYPE_SELECT, + /** + * The argument is an ordinal-number PluralFormat + * with the same style parts sequence and semantics as UMSGPAT_ARG_TYPE_PLURAL. + * @stable ICU 50 + */ + UMSGPAT_ARG_TYPE_SELECTORDINAL +}; +/** + * @stable ICU 4.8 + */ +typedef enum UMessagePatternArgType UMessagePatternArgType; + +/** + * \def UMSGPAT_ARG_TYPE_HAS_PLURAL_STYLE + * Returns true if the argument type has a plural style part sequence and semantics, + * for example UMSGPAT_ARG_TYPE_PLURAL and UMSGPAT_ARG_TYPE_SELECTORDINAL. + * @stable ICU 50 + */ +#define UMSGPAT_ARG_TYPE_HAS_PLURAL_STYLE(argType) \ + ((argType)==UMSGPAT_ARG_TYPE_PLURAL || (argType)==UMSGPAT_ARG_TYPE_SELECTORDINAL) + +enum { + /** + * Return value from MessagePattern.validateArgumentName() for when + * the string is a valid "pattern identifier" but not a number. + * @stable ICU 4.8 + */ + UMSGPAT_ARG_NAME_NOT_NUMBER=-1, + + /** + * Return value from MessagePattern.validateArgumentName() for when + * the string is invalid. + * It might not be a valid "pattern identifier", + * or it have only ASCII digits but there is a leading zero or the number is too large. + * @stable ICU 4.8 + */ + UMSGPAT_ARG_NAME_NOT_VALID=-2 +}; + +/** + * Special value that is returned by getNumericValue(Part) when no + * numeric value is defined for a part. + * @see MessagePattern.getNumericValue() + * @stable ICU 4.8 + */ +#define UMSGPAT_NO_NUMERIC_VALUE ((double)(-123456789)) + +U_NAMESPACE_BEGIN + +class MessagePatternDoubleList; +class MessagePatternPartsList; + +/** + * Parses and represents ICU MessageFormat patterns. + * Also handles patterns for ChoiceFormat, PluralFormat and SelectFormat. + * Used in the implementations of those classes as well as in tools + * for message validation, translation and format conversion. + * <p> + * The parser handles all syntax relevant for identifying message arguments. + * This includes "complex" arguments whose style strings contain + * nested MessageFormat pattern substrings. + * For "simple" arguments (with no nested MessageFormat pattern substrings), + * the argument style is not parsed any further. + * <p> + * The parser handles named and numbered message arguments and allows both in one message. + * <p> + * Once a pattern has been parsed successfully, iterate through the parsed data + * with countParts(), getPart() and related methods. + * <p> + * The data logically represents a parse tree, but is stored and accessed + * as a list of "parts" for fast and simple parsing and to minimize object allocations. + * Arguments and nested messages are best handled via recursion. + * For every _START "part", MessagePattern.getLimitPartIndex() efficiently returns + * the index of the corresponding _LIMIT "part". + * <p> + * List of "parts": + * <pre> + * message = MSG_START (SKIP_SYNTAX | INSERT_CHAR | REPLACE_NUMBER | argument)* MSG_LIMIT + * argument = noneArg | simpleArg | complexArg + * complexArg = choiceArg | pluralArg | selectArg + * + * noneArg = ARG_START.NONE (ARG_NAME | ARG_NUMBER) ARG_LIMIT.NONE + * simpleArg = ARG_START.SIMPLE (ARG_NAME | ARG_NUMBER) ARG_TYPE [ARG_STYLE] ARG_LIMIT.SIMPLE + * choiceArg = ARG_START.CHOICE (ARG_NAME | ARG_NUMBER) choiceStyle ARG_LIMIT.CHOICE + * pluralArg = ARG_START.PLURAL (ARG_NAME | ARG_NUMBER) pluralStyle ARG_LIMIT.PLURAL + * selectArg = ARG_START.SELECT (ARG_NAME | ARG_NUMBER) selectStyle ARG_LIMIT.SELECT + * + * choiceStyle = ((ARG_INT | ARG_DOUBLE) ARG_SELECTOR message)+ + * pluralStyle = [ARG_INT | ARG_DOUBLE] (ARG_SELECTOR [ARG_INT | ARG_DOUBLE] message)+ + * selectStyle = (ARG_SELECTOR message)+ + * </pre> + * <ul> + * <li>Literal output text is not represented directly by "parts" but accessed + * between parts of a message, from one part's getLimit() to the next part's getIndex(). + * <li><code>ARG_START.CHOICE</code> stands for an ARG_START Part with ArgType CHOICE. + * <li>In the choiceStyle, the ARG_SELECTOR has the '<', the '#' or + * the less-than-or-equal-to sign (U+2264). + * <li>In the pluralStyle, the first, optional numeric Part has the "offset:" value. + * The optional numeric Part between each (ARG_SELECTOR, message) pair + * is the value of an explicit-number selector like "=2", + * otherwise the selector is a non-numeric identifier. + * <li>The REPLACE_NUMBER Part can occur only in an immediate sub-message of the pluralStyle. + * </ul> + * <p> + * This class is not intended for public subclassing. + * + * @stable ICU 4.8 + */ +class U_COMMON_API MessagePattern : public UObject { +public: + /** + * Constructs an empty MessagePattern with default UMessagePatternApostropheMode. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @stable ICU 4.8 + */ + MessagePattern(UErrorCode &errorCode); + + /** + * Constructs an empty MessagePattern. + * @param mode Explicit UMessagePatternApostropheMode. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @stable ICU 4.8 + */ + MessagePattern(UMessagePatternApostropheMode mode, UErrorCode &errorCode); + + /** + * Constructs a MessagePattern with default UMessagePatternApostropheMode and + * parses the MessageFormat pattern string. + * @param pattern a MessageFormat pattern string + * @param parseError Struct to receive information on the position + * of an error within the pattern. + * Can be NULL. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * TODO: turn @throws into UErrorCode specifics? + * @throws IllegalArgumentException for syntax errors in the pattern string + * @throws IndexOutOfBoundsException if certain limits are exceeded + * (e.g., argument number too high, argument name too long, etc.) + * @throws NumberFormatException if a number could not be parsed + * @stable ICU 4.8 + */ + MessagePattern(const UnicodeString &pattern, UParseError *parseError, UErrorCode &errorCode); + + /** + * Copy constructor. + * @param other Object to copy. + * @stable ICU 4.8 + */ + MessagePattern(const MessagePattern &other); + + /** + * Assignment operator. + * @param other Object to copy. + * @return *this=other + * @stable ICU 4.8 + */ + MessagePattern &operator=(const MessagePattern &other); + + /** + * Destructor. + * @stable ICU 4.8 + */ + virtual ~MessagePattern(); + + /** + * Parses a MessageFormat pattern string. + * @param pattern a MessageFormat pattern string + * @param parseError Struct to receive information on the position + * of an error within the pattern. + * Can be NULL. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return *this + * @throws IllegalArgumentException for syntax errors in the pattern string + * @throws IndexOutOfBoundsException if certain limits are exceeded + * (e.g., argument number too high, argument name too long, etc.) + * @throws NumberFormatException if a number could not be parsed + * @stable ICU 4.8 + */ + MessagePattern &parse(const UnicodeString &pattern, + UParseError *parseError, UErrorCode &errorCode); + + /** + * Parses a ChoiceFormat pattern string. + * @param pattern a ChoiceFormat pattern string + * @param parseError Struct to receive information on the position + * of an error within the pattern. + * Can be NULL. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return *this + * @throws IllegalArgumentException for syntax errors in the pattern string + * @throws IndexOutOfBoundsException if certain limits are exceeded + * (e.g., argument number too high, argument name too long, etc.) + * @throws NumberFormatException if a number could not be parsed + * @stable ICU 4.8 + */ + MessagePattern &parseChoiceStyle(const UnicodeString &pattern, + UParseError *parseError, UErrorCode &errorCode); + + /** + * Parses a PluralFormat pattern string. + * @param pattern a PluralFormat pattern string + * @param parseError Struct to receive information on the position + * of an error within the pattern. + * Can be NULL. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return *this + * @throws IllegalArgumentException for syntax errors in the pattern string + * @throws IndexOutOfBoundsException if certain limits are exceeded + * (e.g., argument number too high, argument name too long, etc.) + * @throws NumberFormatException if a number could not be parsed + * @stable ICU 4.8 + */ + MessagePattern &parsePluralStyle(const UnicodeString &pattern, + UParseError *parseError, UErrorCode &errorCode); + + /** + * Parses a SelectFormat pattern string. + * @param pattern a SelectFormat pattern string + * @param parseError Struct to receive information on the position + * of an error within the pattern. + * Can be NULL. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return *this + * @throws IllegalArgumentException for syntax errors in the pattern string + * @throws IndexOutOfBoundsException if certain limits are exceeded + * (e.g., argument number too high, argument name too long, etc.) + * @throws NumberFormatException if a number could not be parsed + * @stable ICU 4.8 + */ + MessagePattern &parseSelectStyle(const UnicodeString &pattern, + UParseError *parseError, UErrorCode &errorCode); + + /** + * Clears this MessagePattern. + * countParts() will return 0. + * @stable ICU 4.8 + */ + void clear(); + + /** + * Clears this MessagePattern and sets the UMessagePatternApostropheMode. + * countParts() will return 0. + * @param mode The new UMessagePatternApostropheMode. + * @stable ICU 4.8 + */ + void clearPatternAndSetApostropheMode(UMessagePatternApostropheMode mode) { + clear(); + aposMode=mode; + } + + /** + * @param other another object to compare with. + * @return true if this object is equivalent to the other one. + * @stable ICU 4.8 + */ + UBool operator==(const MessagePattern &other) const; + + /** + * @param other another object to compare with. + * @return false if this object is equivalent to the other one. + * @stable ICU 4.8 + */ + inline UBool operator!=(const MessagePattern &other) const { + return !operator==(other); + } + + /** + * @return A hash code for this object. + * @stable ICU 4.8 + */ + int32_t hashCode() const; + + /** + * @return this instance's UMessagePatternApostropheMode. + * @stable ICU 4.8 + */ + UMessagePatternApostropheMode getApostropheMode() const { + return aposMode; + } + + // Java has package-private jdkAposMode() here. + // In C++, this is declared in the MessageImpl class. + + /** + * @return the parsed pattern string (null if none was parsed). + * @stable ICU 4.8 + */ + const UnicodeString &getPatternString() const { + return msg; + } + + /** + * Does the parsed pattern have named arguments like {first_name}? + * @return true if the parsed pattern has at least one named argument. + * @stable ICU 4.8 + */ + UBool hasNamedArguments() const { + return hasArgNames; + } + + /** + * Does the parsed pattern have numbered arguments like {2}? + * @return true if the parsed pattern has at least one numbered argument. + * @stable ICU 4.8 + */ + UBool hasNumberedArguments() const { + return hasArgNumbers; + } + + /** + * Validates and parses an argument name or argument number string. + * An argument name must be a "pattern identifier", that is, it must contain + * no Unicode Pattern_Syntax or Pattern_White_Space characters. + * If it only contains ASCII digits, then it must be a small integer with no leading zero. + * @param name Input string. + * @return >=0 if the name is a valid number, + * ARG_NAME_NOT_NUMBER (-1) if it is a "pattern identifier" but not all ASCII digits, + * ARG_NAME_NOT_VALID (-2) if it is neither. + * @stable ICU 4.8 + */ + static int32_t validateArgumentName(const UnicodeString &name); + + /** + * Returns a version of the parsed pattern string where each ASCII apostrophe + * is doubled (escaped) if it is not already, and if it is not interpreted as quoting syntax. + * <p> + * For example, this turns "I don't '{know}' {gender,select,female{h''er}other{h'im}}." + * into "I don''t '{know}' {gender,select,female{h''er}other{h''im}}." + * @return the deep-auto-quoted version of the parsed pattern string. + * @see MessageFormat.autoQuoteApostrophe() + * @stable ICU 4.8 + */ + UnicodeString autoQuoteApostropheDeep() const; + + class Part; + + /** + * Returns the number of "parts" created by parsing the pattern string. + * Returns 0 if no pattern has been parsed or clear() was called. + * @return the number of pattern parts. + * @stable ICU 4.8 + */ + int32_t countParts() const { + return partsLength; + } + + /** + * Gets the i-th pattern "part". + * @param i The index of the Part data. (0..countParts()-1) + * @return the i-th pattern "part". + * @stable ICU 4.8 + */ + const Part &getPart(int32_t i) const { + return parts[i]; + } + + /** + * Returns the UMessagePatternPartType of the i-th pattern "part". + * Convenience method for getPart(i).getType(). + * @param i The index of the Part data. (0..countParts()-1) + * @return The UMessagePatternPartType of the i-th Part. + * @stable ICU 4.8 + */ + UMessagePatternPartType getPartType(int32_t i) const { + return getPart(i).type; + } + + /** + * Returns the pattern index of the specified pattern "part". + * Convenience method for getPart(partIndex).getIndex(). + * @param partIndex The index of the Part data. (0..countParts()-1) + * @return The pattern index of this Part. + * @stable ICU 4.8 + */ + int32_t getPatternIndex(int32_t partIndex) const { + return getPart(partIndex).index; + } + + /** + * Returns the substring of the pattern string indicated by the Part. + * Convenience method for getPatternString().substring(part.getIndex(), part.getLimit()). + * @param part a part of this MessagePattern. + * @return the substring associated with part. + * @stable ICU 4.8 + */ + UnicodeString getSubstring(const Part &part) const { + return msg.tempSubString(part.index, part.length); + } + + /** + * Compares the part's substring with the input string s. + * @param part a part of this MessagePattern. + * @param s a string. + * @return true if getSubstring(part).equals(s). + * @stable ICU 4.8 + */ + UBool partSubstringMatches(const Part &part, const UnicodeString &s) const { + return 0==msg.compare(part.index, part.length, s); + } + + /** + * Returns the numeric value associated with an ARG_INT or ARG_DOUBLE. + * @param part a part of this MessagePattern. + * @return the part's numeric value, or UMSGPAT_NO_NUMERIC_VALUE if this is not a numeric part. + * @stable ICU 4.8 + */ + double getNumericValue(const Part &part) const; + + /** + * Returns the "offset:" value of a PluralFormat argument, or 0 if none is specified. + * @param pluralStart the index of the first PluralFormat argument style part. (0..countParts()-1) + * @return the "offset:" value. + * @stable ICU 4.8 + */ + double getPluralOffset(int32_t pluralStart) const; + + /** + * Returns the index of the ARG|MSG_LIMIT part corresponding to the ARG|MSG_START at start. + * @param start The index of some Part data (0..countParts()-1); + * this Part should be of Type ARG_START or MSG_START. + * @return The first i>start where getPart(i).getType()==ARG|MSG_LIMIT at the same nesting level, + * or start itself if getPartType(msgStart)!=ARG|MSG_START. + * @stable ICU 4.8 + */ + int32_t getLimitPartIndex(int32_t start) const { + int32_t limit=getPart(start).limitPartIndex; + if(limit<start) { + return start; + } + return limit; + } + + /** + * A message pattern "part", representing a pattern parsing event. + * There is a part for the start and end of a message or argument, + * for quoting and escaping of and with ASCII apostrophes, + * and for syntax elements of "complex" arguments. + * @stable ICU 4.8 + */ + class Part : public UMemory { + public: + /** + * Default constructor, do not use. + * @internal + */ + Part() {} + + /** + * Returns the type of this part. + * @return the part type. + * @stable ICU 4.8 + */ + UMessagePatternPartType getType() const { + return type; + } + + /** + * Returns the pattern string index associated with this Part. + * @return this part's pattern string index. + * @stable ICU 4.8 + */ + int32_t getIndex() const { + return index; + } + + /** + * Returns the length of the pattern substring associated with this Part. + * This is 0 for some parts. + * @return this part's pattern substring length. + * @stable ICU 4.8 + */ + int32_t getLength() const { + return length; + } + + /** + * Returns the pattern string limit (exclusive-end) index associated with this Part. + * Convenience method for getIndex()+getLength(). + * @return this part's pattern string limit index, same as getIndex()+getLength(). + * @stable ICU 4.8 + */ + int32_t getLimit() const { + return index+length; + } + + /** + * Returns a value associated with this part. + * See the documentation of each part type for details. + * @return the part value. + * @stable ICU 4.8 + */ + int32_t getValue() const { + return value; + } + + /** + * Returns the argument type if this part is of type ARG_START or ARG_LIMIT, + * otherwise UMSGPAT_ARG_TYPE_NONE. + * @return the argument type for this part. + * @stable ICU 4.8 + */ + UMessagePatternArgType getArgType() const { + UMessagePatternPartType msgType=getType(); + if(msgType ==UMSGPAT_PART_TYPE_ARG_START || msgType ==UMSGPAT_PART_TYPE_ARG_LIMIT) { + return (UMessagePatternArgType)value; + } else { + return UMSGPAT_ARG_TYPE_NONE; + } + } + + /** + * Indicates whether the Part type has a numeric value. + * If so, then that numeric value can be retrieved via MessagePattern.getNumericValue(). + * @param type The Part type to be tested. + * @return true if the Part type has a numeric value. + * @stable ICU 4.8 + */ + static UBool hasNumericValue(UMessagePatternPartType type) { + return type==UMSGPAT_PART_TYPE_ARG_INT || type==UMSGPAT_PART_TYPE_ARG_DOUBLE; + } + + /** + * @param other another object to compare with. + * @return true if this object is equivalent to the other one. + * @stable ICU 4.8 + */ + UBool operator==(const Part &other) const; + + /** + * @param other another object to compare with. + * @return false if this object is equivalent to the other one. + * @stable ICU 4.8 + */ + inline UBool operator!=(const Part &other) const { + return !operator==(other); + } + + /** + * @return A hash code for this object. + * @stable ICU 4.8 + */ + int32_t hashCode() const { + return ((type*37+index)*37+length)*37+value; + } + + private: + friend class MessagePattern; + + static const int32_t MAX_LENGTH=0xffff; + static const int32_t MAX_VALUE=0x7fff; + + // Some fields are not final because they are modified during pattern parsing. + // After pattern parsing, the parts are effectively immutable. + UMessagePatternPartType type; + int32_t index; + uint16_t length; + int16_t value; + int32_t limitPartIndex; + }; + +private: + void preParse(const UnicodeString &pattern, UParseError *parseError, UErrorCode &errorCode); + + void postParse(); + + int32_t parseMessage(int32_t index, int32_t msgStartLength, + int32_t nestingLevel, UMessagePatternArgType parentType, + UParseError *parseError, UErrorCode &errorCode); + + int32_t parseArg(int32_t index, int32_t argStartLength, int32_t nestingLevel, + UParseError *parseError, UErrorCode &errorCode); + + int32_t parseSimpleStyle(int32_t index, UParseError *parseError, UErrorCode &errorCode); + + int32_t parseChoiceStyle(int32_t index, int32_t nestingLevel, + UParseError *parseError, UErrorCode &errorCode); + + int32_t parsePluralOrSelectStyle(UMessagePatternArgType argType, int32_t index, int32_t nestingLevel, + UParseError *parseError, UErrorCode &errorCode); + + /** + * Validates and parses an argument name or argument number string. + * This internal method assumes that the input substring is a "pattern identifier". + * @return >=0 if the name is a valid number, + * ARG_NAME_NOT_NUMBER (-1) if it is a "pattern identifier" but not all ASCII digits, + * ARG_NAME_NOT_VALID (-2) if it is neither. + * @see #validateArgumentName(String) + */ + static int32_t parseArgNumber(const UnicodeString &s, int32_t start, int32_t limit); + + int32_t parseArgNumber(int32_t start, int32_t limit) { + return parseArgNumber(msg, start, limit); + } + + /** + * Parses a number from the specified message substring. + * @param start start index into the message string + * @param limit limit index into the message string, must be start<limit + * @param allowInfinity true if U+221E is allowed (for ChoiceFormat) + * @param parseError + * @param errorCode + */ + void parseDouble(int32_t start, int32_t limit, UBool allowInfinity, + UParseError *parseError, UErrorCode &errorCode); + + // Java has package-private appendReducedApostrophes() here. + // In C++, this is declared in the MessageImpl class. + + int32_t skipWhiteSpace(int32_t index); + + int32_t skipIdentifier(int32_t index); + + /** + * Skips a sequence of characters that could occur in a double value. + * Does not fully parse or validate the value. + */ + int32_t skipDouble(int32_t index); + + static UBool isArgTypeChar(UChar32 c); + + UBool isChoice(int32_t index); + + UBool isPlural(int32_t index); + + UBool isSelect(int32_t index); + + UBool isOrdinal(int32_t index); + + /** + * @return true if we are inside a MessageFormat (sub-)pattern, + * as opposed to inside a top-level choice/plural/select pattern. + */ + UBool inMessageFormatPattern(int32_t nestingLevel); + + /** + * @return true if we are in a MessageFormat sub-pattern + * of a top-level ChoiceFormat pattern. + */ + UBool inTopLevelChoiceMessage(int32_t nestingLevel, UMessagePatternArgType parentType); + + void addPart(UMessagePatternPartType type, int32_t index, int32_t length, + int32_t value, UErrorCode &errorCode); + + void addLimitPart(int32_t start, + UMessagePatternPartType type, int32_t index, int32_t length, + int32_t value, UErrorCode &errorCode); + + void addArgDoublePart(double numericValue, int32_t start, int32_t length, UErrorCode &errorCode); + + void setParseError(UParseError *parseError, int32_t index); + + UBool init(UErrorCode &errorCode); + UBool copyStorage(const MessagePattern &other, UErrorCode &errorCode); + + UMessagePatternApostropheMode aposMode; + UnicodeString msg; + // ArrayList<Part> parts=new ArrayList<Part>(); + MessagePatternPartsList *partsList; + Part *parts; + int32_t partsLength; + // ArrayList<Double> numericValues; + MessagePatternDoubleList *numericValuesList; + double *numericValues; + int32_t numericValuesLength; + UBool hasArgNames; + UBool hasArgNumbers; + UBool needsAutoQuoting; +}; + +U_NAMESPACE_END + +#endif // !UCONFIG_NO_FORMATTING + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __MESSAGEPATTERN_H__ diff --git a/thirdparty/icu4c/common/unicode/normalizer2.h b/thirdparty/icu4c/common/unicode/normalizer2.h new file mode 100644 index 0000000000..5eb1d95caf --- /dev/null +++ b/thirdparty/icu4c/common/unicode/normalizer2.h @@ -0,0 +1,779 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2009-2013, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: normalizer2.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2009nov22 +* created by: Markus W. Scherer +*/ + +#ifndef __NORMALIZER2_H__ +#define __NORMALIZER2_H__ + +/** + * \file + * \brief C++ API: New API for Unicode Normalization. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#if !UCONFIG_NO_NORMALIZATION + +#include "unicode/stringpiece.h" +#include "unicode/uniset.h" +#include "unicode/unistr.h" +#include "unicode/unorm2.h" + +U_NAMESPACE_BEGIN + +class ByteSink; + +/** + * Unicode normalization functionality for standard Unicode normalization or + * for using custom mapping tables. + * All instances of this class are unmodifiable/immutable. + * Instances returned by getInstance() are singletons that must not be deleted by the caller. + * The Normalizer2 class is not intended for public subclassing. + * + * The primary functions are to produce a normalized string and to detect whether + * a string is already normalized. + * The most commonly used normalization forms are those defined in + * http://www.unicode.org/unicode/reports/tr15/ + * However, this API supports additional normalization forms for specialized purposes. + * For example, NFKC_Casefold is provided via getInstance("nfkc_cf", COMPOSE) + * and can be used in implementations of UTS #46. + * + * Not only are the standard compose and decompose modes supplied, + * but additional modes are provided as documented in the Mode enum. + * + * Some of the functions in this class identify normalization boundaries. + * At a normalization boundary, the portions of the string + * before it and starting from it do not interact and can be handled independently. + * + * The spanQuickCheckYes() stops at a normalization boundary. + * When the goal is a normalized string, then the text before the boundary + * can be copied, and the remainder can be processed with normalizeSecondAndAppend(). + * + * The hasBoundaryBefore(), hasBoundaryAfter() and isInert() functions test whether + * a character is guaranteed to be at a normalization boundary, + * regardless of context. + * This is used for moving from one normalization boundary to the next + * or preceding boundary, and for performing iterative normalization. + * + * Iterative normalization is useful when only a small portion of a + * longer string needs to be processed. + * For example, in ICU, iterative normalization is used by the NormalizationTransliterator + * (to avoid replacing already-normalized text) and ucol_nextSortKeyPart() + * (to process only the substring for which sort key bytes are computed). + * + * The set of normalization boundaries returned by these functions may not be + * complete: There may be more boundaries that could be returned. + * Different functions may return different boundaries. + * @stable ICU 4.4 + */ +class U_COMMON_API Normalizer2 : public UObject { +public: + /** + * Destructor. + * @stable ICU 4.4 + */ + ~Normalizer2(); + + /** + * Returns a Normalizer2 instance for Unicode NFC normalization. + * Same as getInstance(NULL, "nfc", UNORM2_COMPOSE, errorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ + static const Normalizer2 * + getNFCInstance(UErrorCode &errorCode); + + /** + * Returns a Normalizer2 instance for Unicode NFD normalization. + * Same as getInstance(NULL, "nfc", UNORM2_DECOMPOSE, errorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ + static const Normalizer2 * + getNFDInstance(UErrorCode &errorCode); + + /** + * Returns a Normalizer2 instance for Unicode NFKC normalization. + * Same as getInstance(NULL, "nfkc", UNORM2_COMPOSE, errorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ + static const Normalizer2 * + getNFKCInstance(UErrorCode &errorCode); + + /** + * Returns a Normalizer2 instance for Unicode NFKD normalization. + * Same as getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, errorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ + static const Normalizer2 * + getNFKDInstance(UErrorCode &errorCode); + + /** + * Returns a Normalizer2 instance for Unicode NFKC_Casefold normalization. + * Same as getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, errorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ + static const Normalizer2 * + getNFKCCasefoldInstance(UErrorCode &errorCode); + + /** + * Returns a Normalizer2 instance which uses the specified data file + * (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle) + * and which composes or decomposes text according to the specified mode. + * Returns an unmodifiable singleton instance. Do not delete it. + * + * Use packageName=NULL for data files that are part of ICU's own data. + * Use name="nfc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFC/NFD. + * Use name="nfkc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFKC/NFKD. + * Use name="nfkc_cf" and UNORM2_COMPOSE for Unicode standard NFKC_CF=NFKC_Casefold. + * + * @param packageName NULL for ICU built-in data, otherwise application data package name + * @param name "nfc" or "nfkc" or "nfkc_cf" or name of custom data file + * @param mode normalization mode (compose or decompose etc.) + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 4.4 + */ + static const Normalizer2 * + getInstance(const char *packageName, + const char *name, + UNormalization2Mode mode, + UErrorCode &errorCode); + + /** + * Returns the normalized form of the source string. + * @param src source string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return normalized src + * @stable ICU 4.4 + */ + UnicodeString + normalize(const UnicodeString &src, UErrorCode &errorCode) const { + UnicodeString result; + normalize(src, result, errorCode); + return result; + } + /** + * Writes the normalized form of the source string to the destination string + * (replacing its contents) and returns the destination string. + * The source and destination strings must be different objects. + * @param src source string + * @param dest destination string; its contents is replaced with normalized src + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.4 + */ + virtual UnicodeString & + normalize(const UnicodeString &src, + UnicodeString &dest, + UErrorCode &errorCode) const = 0; + + /** + * Normalizes a UTF-8 string and optionally records how source substrings + * relate to changed and unchanged result substrings. + * + * Currently implemented completely only for "compose" modes, + * such as for NFC, NFKC, and NFKC_Casefold + * (UNORM2_COMPOSE and UNORM2_COMPOSE_CONTIGUOUS). + * Otherwise currently converts to & from UTF-16 and does not support edits. + * + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src Source UTF-8 string. + * @param sink A ByteSink to which the normalized UTF-8 result string is written. + * sink.Flush() is called at the end. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be nullptr. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @stable ICU 60 + */ + virtual void + normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink, + Edits *edits, UErrorCode &errorCode) const; + + /** + * Appends the normalized form of the second string to the first string + * (merging them at the boundary) and returns the first string. + * The result is normalized if the first string was normalized. + * The first and second strings must be different objects. + * @param first string, should be normalized + * @param second string, will be normalized + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return first + * @stable ICU 4.4 + */ + virtual UnicodeString & + normalizeSecondAndAppend(UnicodeString &first, + const UnicodeString &second, + UErrorCode &errorCode) const = 0; + /** + * Appends the second string to the first string + * (merging them at the boundary) and returns the first string. + * The result is normalized if both the strings were normalized. + * The first and second strings must be different objects. + * @param first string, should be normalized + * @param second string, should be normalized + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return first + * @stable ICU 4.4 + */ + virtual UnicodeString & + append(UnicodeString &first, + const UnicodeString &second, + UErrorCode &errorCode) const = 0; + + /** + * Gets the decomposition mapping of c. + * Roughly equivalent to normalizing the String form of c + * on a UNORM2_DECOMPOSE Normalizer2 instance, but much faster, and except that this function + * returns false and does not write a string + * if c does not have a decomposition mapping in this instance's data. + * This function is independent of the mode of the Normalizer2. + * @param c code point + * @param decomposition String object which will be set to c's + * decomposition mapping, if there is one. + * @return true if c has a decomposition, otherwise false + * @stable ICU 4.6 + */ + virtual UBool + getDecomposition(UChar32 c, UnicodeString &decomposition) const = 0; + + /** + * Gets the raw decomposition mapping of c. + * + * This is similar to the getDecomposition() method but returns the + * raw decomposition mapping as specified in UnicodeData.txt or + * (for custom data) in the mapping files processed by the gennorm2 tool. + * By contrast, getDecomposition() returns the processed, + * recursively-decomposed version of this mapping. + * + * When used on a standard NFKC Normalizer2 instance, + * getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property. + * + * When used on a standard NFC Normalizer2 instance, + * it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can); + * in this case, the result contains either one or two code points (=1..4 char16_ts). + * + * This function is independent of the mode of the Normalizer2. + * The default implementation returns false. + * @param c code point + * @param decomposition String object which will be set to c's + * raw decomposition mapping, if there is one. + * @return true if c has a decomposition, otherwise false + * @stable ICU 49 + */ + virtual UBool + getRawDecomposition(UChar32 c, UnicodeString &decomposition) const; + + /** + * Performs pairwise composition of a & b and returns the composite if there is one. + * + * Returns a composite code point c only if c has a two-way mapping to a+b. + * In standard Unicode normalization, this means that + * c has a canonical decomposition to a+b + * and c does not have the Full_Composition_Exclusion property. + * + * This function is independent of the mode of the Normalizer2. + * The default implementation returns a negative value. + * @param a A (normalization starter) code point. + * @param b Another code point. + * @return The non-negative composite code point if there is one; otherwise a negative value. + * @stable ICU 49 + */ + virtual UChar32 + composePair(UChar32 a, UChar32 b) const; + + /** + * Gets the combining class of c. + * The default implementation returns 0 + * but all standard implementations return the Unicode Canonical_Combining_Class value. + * @param c code point + * @return c's combining class + * @stable ICU 49 + */ + virtual uint8_t + getCombiningClass(UChar32 c) const; + + /** + * Tests if the string is normalized. + * Internally, in cases where the quickCheck() method would return "maybe" + * (which is only possible for the two COMPOSE modes) this method + * resolves to "yes" or "no" to provide a definitive result, + * at the cost of doing more work in those cases. + * @param s input string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return true if s is normalized + * @stable ICU 4.4 + */ + virtual UBool + isNormalized(const UnicodeString &s, UErrorCode &errorCode) const = 0; + /** + * Tests if the UTF-8 string is normalized. + * Internally, in cases where the quickCheck() method would return "maybe" + * (which is only possible for the two COMPOSE modes) this method + * resolves to "yes" or "no" to provide a definitive result, + * at the cost of doing more work in those cases. + * + * This works for all normalization modes, + * but it is currently optimized for UTF-8 only for "compose" modes, + * such as for NFC, NFKC, and NFKC_Casefold + * (UNORM2_COMPOSE and UNORM2_COMPOSE_CONTIGUOUS). + * For other modes it currently converts to UTF-16 and calls isNormalized(). + * + * @param s UTF-8 input string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return true if s is normalized + * @stable ICU 60 + */ + virtual UBool + isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const; + + + /** + * Tests if the string is normalized. + * For the two COMPOSE modes, the result could be "maybe" in cases that + * would take a little more work to resolve definitively. + * Use spanQuickCheckYes() and normalizeSecondAndAppend() for a faster + * combination of quick check + normalization, to avoid + * re-checking the "yes" prefix. + * @param s input string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return UNormalizationCheckResult + * @stable ICU 4.4 + */ + virtual UNormalizationCheckResult + quickCheck(const UnicodeString &s, UErrorCode &errorCode) const = 0; + + /** + * Returns the end of the normalized substring of the input string. + * In other words, with <code>end=spanQuickCheckYes(s, ec);</code> + * the substring <code>UnicodeString(s, 0, end)</code> + * will pass the quick check with a "yes" result. + * + * The returned end index is usually one or more characters before the + * "no" or "maybe" character: The end index is at a normalization boundary. + * (See the class documentation for more about normalization boundaries.) + * + * When the goal is a normalized string and most input strings are expected + * to be normalized already, then call this method, + * and if it returns a prefix shorter than the input string, + * copy that prefix and use normalizeSecondAndAppend() for the remainder. + * @param s input string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return "yes" span end index + * @stable ICU 4.4 + */ + virtual int32_t + spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const = 0; + + /** + * Tests if the character always has a normalization boundary before it, + * regardless of context. + * If true, then the character does not normalization-interact with + * preceding characters. + * In other words, a string containing this character can be normalized + * by processing portions before this character and starting from this + * character independently. + * This is used for iterative normalization. See the class documentation for details. + * @param c character to test + * @return true if c has a normalization boundary before it + * @stable ICU 4.4 + */ + virtual UBool hasBoundaryBefore(UChar32 c) const = 0; + + /** + * Tests if the character always has a normalization boundary after it, + * regardless of context. + * If true, then the character does not normalization-interact with + * following characters. + * In other words, a string containing this character can be normalized + * by processing portions up to this character and after this + * character independently. + * This is used for iterative normalization. See the class documentation for details. + * Note that this operation may be significantly slower than hasBoundaryBefore(). + * @param c character to test + * @return true if c has a normalization boundary after it + * @stable ICU 4.4 + */ + virtual UBool hasBoundaryAfter(UChar32 c) const = 0; + + /** + * Tests if the character is normalization-inert. + * If true, then the character does not change, nor normalization-interact with + * preceding or following characters. + * In other words, a string containing this character can be normalized + * by processing portions before this character and after this + * character independently. + * This is used for iterative normalization. See the class documentation for details. + * Note that this operation may be significantly slower than hasBoundaryBefore(). + * @param c character to test + * @return true if c is normalization-inert + * @stable ICU 4.4 + */ + virtual UBool isInert(UChar32 c) const = 0; +}; + +/** + * Normalization filtered by a UnicodeSet. + * Normalizes portions of the text contained in the filter set and leaves + * portions not contained in the filter set unchanged. + * Filtering is done via UnicodeSet::span(..., USET_SPAN_SIMPLE). + * Not-in-the-filter text is treated as "is normalized" and "quick check yes". + * This class implements all of (and only) the Normalizer2 API. + * An instance of this class is unmodifiable/immutable but is constructed and + * must be destructed by the owner. + * @stable ICU 4.4 + */ +class U_COMMON_API FilteredNormalizer2 : public Normalizer2 { +public: + /** + * Constructs a filtered normalizer wrapping any Normalizer2 instance + * and a filter set. + * Both are aliased and must not be modified or deleted while this object + * is used. + * The filter set should be frozen; otherwise the performance will suffer greatly. + * @param n2 wrapped Normalizer2 instance + * @param filterSet UnicodeSet which determines the characters to be normalized + * @stable ICU 4.4 + */ + FilteredNormalizer2(const Normalizer2 &n2, const UnicodeSet &filterSet) : + norm2(n2), set(filterSet) {} + + /** + * Destructor. + * @stable ICU 4.4 + */ + ~FilteredNormalizer2(); + + /** + * Writes the normalized form of the source string to the destination string + * (replacing its contents) and returns the destination string. + * The source and destination strings must be different objects. + * @param src source string + * @param dest destination string; its contents is replaced with normalized src + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.4 + */ + virtual UnicodeString & + normalize(const UnicodeString &src, + UnicodeString &dest, + UErrorCode &errorCode) const U_OVERRIDE; + + /** + * Normalizes a UTF-8 string and optionally records how source substrings + * relate to changed and unchanged result substrings. + * + * Currently implemented completely only for "compose" modes, + * such as for NFC, NFKC, and NFKC_Casefold + * (UNORM2_COMPOSE and UNORM2_COMPOSE_CONTIGUOUS). + * Otherwise currently converts to & from UTF-16 and does not support edits. + * + * @param options Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET. + * @param src Source UTF-8 string. + * @param sink A ByteSink to which the normalized UTF-8 result string is written. + * sink.Flush() is called at the end. + * @param edits Records edits for index mapping, working with styled text, + * and getting only changes (if any). + * The Edits contents is undefined if any error occurs. + * This function calls edits->reset() first unless + * options includes U_EDITS_NO_RESET. edits can be nullptr. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @stable ICU 60 + */ + virtual void + normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink, + Edits *edits, UErrorCode &errorCode) const U_OVERRIDE; + + /** + * Appends the normalized form of the second string to the first string + * (merging them at the boundary) and returns the first string. + * The result is normalized if the first string was normalized. + * The first and second strings must be different objects. + * @param first string, should be normalized + * @param second string, will be normalized + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return first + * @stable ICU 4.4 + */ + virtual UnicodeString & + normalizeSecondAndAppend(UnicodeString &first, + const UnicodeString &second, + UErrorCode &errorCode) const U_OVERRIDE; + /** + * Appends the second string to the first string + * (merging them at the boundary) and returns the first string. + * The result is normalized if both the strings were normalized. + * The first and second strings must be different objects. + * @param first string, should be normalized + * @param second string, should be normalized + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return first + * @stable ICU 4.4 + */ + virtual UnicodeString & + append(UnicodeString &first, + const UnicodeString &second, + UErrorCode &errorCode) const U_OVERRIDE; + + /** + * Gets the decomposition mapping of c. + * For details see the base class documentation. + * + * This function is independent of the mode of the Normalizer2. + * @param c code point + * @param decomposition String object which will be set to c's + * decomposition mapping, if there is one. + * @return true if c has a decomposition, otherwise false + * @stable ICU 4.6 + */ + virtual UBool + getDecomposition(UChar32 c, UnicodeString &decomposition) const U_OVERRIDE; + + /** + * Gets the raw decomposition mapping of c. + * For details see the base class documentation. + * + * This function is independent of the mode of the Normalizer2. + * @param c code point + * @param decomposition String object which will be set to c's + * raw decomposition mapping, if there is one. + * @return true if c has a decomposition, otherwise false + * @stable ICU 49 + */ + virtual UBool + getRawDecomposition(UChar32 c, UnicodeString &decomposition) const U_OVERRIDE; + + /** + * Performs pairwise composition of a & b and returns the composite if there is one. + * For details see the base class documentation. + * + * This function is independent of the mode of the Normalizer2. + * @param a A (normalization starter) code point. + * @param b Another code point. + * @return The non-negative composite code point if there is one; otherwise a negative value. + * @stable ICU 49 + */ + virtual UChar32 + composePair(UChar32 a, UChar32 b) const U_OVERRIDE; + + /** + * Gets the combining class of c. + * The default implementation returns 0 + * but all standard implementations return the Unicode Canonical_Combining_Class value. + * @param c code point + * @return c's combining class + * @stable ICU 49 + */ + virtual uint8_t + getCombiningClass(UChar32 c) const U_OVERRIDE; + + /** + * Tests if the string is normalized. + * For details see the Normalizer2 base class documentation. + * @param s input string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return true if s is normalized + * @stable ICU 4.4 + */ + virtual UBool + isNormalized(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE; + /** + * Tests if the UTF-8 string is normalized. + * Internally, in cases where the quickCheck() method would return "maybe" + * (which is only possible for the two COMPOSE modes) this method + * resolves to "yes" or "no" to provide a definitive result, + * at the cost of doing more work in those cases. + * + * This works for all normalization modes, + * but it is currently optimized for UTF-8 only for "compose" modes, + * such as for NFC, NFKC, and NFKC_Casefold + * (UNORM2_COMPOSE and UNORM2_COMPOSE_CONTIGUOUS). + * For other modes it currently converts to UTF-16 and calls isNormalized(). + * + * @param s UTF-8 input string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return true if s is normalized + * @stable ICU 60 + */ + virtual UBool + isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const U_OVERRIDE; + /** + * Tests if the string is normalized. + * For details see the Normalizer2 base class documentation. + * @param s input string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return UNormalizationCheckResult + * @stable ICU 4.4 + */ + virtual UNormalizationCheckResult + quickCheck(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE; + /** + * Returns the end of the normalized substring of the input string. + * For details see the Normalizer2 base class documentation. + * @param s input string + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return "yes" span end index + * @stable ICU 4.4 + */ + virtual int32_t + spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE; + + /** + * Tests if the character always has a normalization boundary before it, + * regardless of context. + * For details see the Normalizer2 base class documentation. + * @param c character to test + * @return true if c has a normalization boundary before it + * @stable ICU 4.4 + */ + virtual UBool hasBoundaryBefore(UChar32 c) const U_OVERRIDE; + + /** + * Tests if the character always has a normalization boundary after it, + * regardless of context. + * For details see the Normalizer2 base class documentation. + * @param c character to test + * @return true if c has a normalization boundary after it + * @stable ICU 4.4 + */ + virtual UBool hasBoundaryAfter(UChar32 c) const U_OVERRIDE; + + /** + * Tests if the character is normalization-inert. + * For details see the Normalizer2 base class documentation. + * @param c character to test + * @return true if c is normalization-inert + * @stable ICU 4.4 + */ + virtual UBool isInert(UChar32 c) const U_OVERRIDE; +private: + UnicodeString & + normalize(const UnicodeString &src, + UnicodeString &dest, + USetSpanCondition spanCondition, + UErrorCode &errorCode) const; + + void + normalizeUTF8(uint32_t options, const char *src, int32_t length, + ByteSink &sink, Edits *edits, + USetSpanCondition spanCondition, + UErrorCode &errorCode) const; + + UnicodeString & + normalizeSecondAndAppend(UnicodeString &first, + const UnicodeString &second, + UBool doNormalize, + UErrorCode &errorCode) const; + + const Normalizer2 &norm2; + const UnicodeSet &set; +}; + +U_NAMESPACE_END + +#endif // !UCONFIG_NO_NORMALIZATION + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __NORMALIZER2_H__ diff --git a/thirdparty/icu4c/common/unicode/normlzr.h b/thirdparty/icu4c/common/unicode/normlzr.h new file mode 100644 index 0000000000..3352983cdc --- /dev/null +++ b/thirdparty/icu4c/common/unicode/normlzr.h @@ -0,0 +1,816 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* + ******************************************************************** + * COPYRIGHT: + * Copyright (c) 1996-2015, International Business Machines Corporation and + * others. All Rights Reserved. + ******************************************************************** + */ + +#ifndef NORMLZR_H +#define NORMLZR_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +/** + * \file + * \brief C++ API: Unicode Normalization + */ + +#if !UCONFIG_NO_NORMALIZATION + +#include "unicode/chariter.h" +#include "unicode/normalizer2.h" +#include "unicode/unistr.h" +#include "unicode/unorm.h" +#include "unicode/uobject.h" + +U_NAMESPACE_BEGIN +/** + * Old Unicode normalization API. + * + * This API has been replaced by the Normalizer2 class and is only available + * for backward compatibility. This class simply delegates to the Normalizer2 class. + * There is one exception: The new API does not provide a replacement for Normalizer::compare(). + * + * The Normalizer class supports the standard normalization forms described in + * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> + * Unicode Standard Annex #15: Unicode Normalization Forms</a>. + * + * The Normalizer class consists of two parts: + * - static functions that normalize strings or test if strings are normalized + * - a Normalizer object is an iterator that takes any kind of text and + * provides iteration over its normalized form + * + * The Normalizer class is not suitable for subclassing. + * + * For basic information about normalization forms and details about the C API + * please see the documentation in unorm.h. + * + * The iterator API with the Normalizer constructors and the non-static functions + * use a CharacterIterator as input. It is possible to pass a string which + * is then internally wrapped in a CharacterIterator. + * The input text is not normalized all at once, but incrementally where needed + * (providing efficient random access). + * This allows to pass in a large text but spend only a small amount of time + * normalizing a small part of that text. + * However, if the entire text is normalized, then the iterator will be + * slower than normalizing the entire text at once and iterating over the result. + * A possible use of the Normalizer iterator is also to report an index into the + * original text that is close to where the normalized characters come from. + * + * <em>Important:</em> The iterator API was cleaned up significantly for ICU 2.0. + * The earlier implementation reported the getIndex() inconsistently, + * and previous() could not be used after setIndex(), next(), first(), and current(). + * + * Normalizer allows to start normalizing from anywhere in the input text by + * calling setIndexOnly(), first(), or last(). + * Without calling any of these, the iterator will start at the beginning of the text. + * + * At any time, next() returns the next normalized code point (UChar32), + * with post-increment semantics (like CharacterIterator::next32PostInc()). + * previous() returns the previous normalized code point (UChar32), + * with pre-decrement semantics (like CharacterIterator::previous32()). + * + * current() returns the current code point + * (respectively the one at the newly set index) without moving + * the getIndex(). Note that if the text at the current position + * needs to be normalized, then these functions will do that. + * (This is why current() is not const.) + * It is more efficient to call setIndexOnly() instead, which does not + * normalize. + * + * getIndex() always refers to the position in the input text where the normalized + * code points are returned from. It does not always change with each returned + * code point. + * The code point that is returned from any of the functions + * corresponds to text at or after getIndex(), according to the + * function's iteration semantics (post-increment or pre-decrement). + * + * next() returns a code point from at or after the getIndex() + * from before the next() call. After the next() call, the getIndex() + * might have moved to where the next code point will be returned from + * (from a next() or current() call). + * This is semantically equivalent to array access with array[index++] + * (post-increment semantics). + * + * previous() returns a code point from at or after the getIndex() + * from after the previous() call. + * This is semantically equivalent to array access with array[--index] + * (pre-decrement semantics). + * + * Internally, the Normalizer iterator normalizes a small piece of text + * starting at the getIndex() and ending at a following "safe" index. + * The normalized results is stored in an internal string buffer, and + * the code points are iterated from there. + * With multiple iteration calls, this is repeated until the next piece + * of text needs to be normalized, and the getIndex() needs to be moved. + * + * The following "safe" index, the internal buffer, and the secondary + * iteration index into that buffer are not exposed on the API. + * This also means that it is currently not practical to return to + * a particular, arbitrary position in the text because one would need to + * know, and be able to set, in addition to the getIndex(), at least also the + * current index into the internal buffer. + * It is currently only possible to observe when getIndex() changes + * (with careful consideration of the iteration semantics), + * at which time the internal index will be 0. + * For example, if getIndex() is different after next() than before it, + * then the internal index is 0 and one can return to this getIndex() + * later with setIndexOnly(). + * + * Note: While the setIndex() and getIndex() refer to indices in the + * underlying Unicode input text, the next() and previous() methods + * iterate through characters in the normalized output. + * This means that there is not necessarily a one-to-one correspondence + * between characters returned by next() and previous() and the indices + * passed to and returned from setIndex() and getIndex(). + * It is for this reason that Normalizer does not implement the CharacterIterator interface. + * + * @author Laura Werner, Mark Davis, Markus Scherer + * @stable ICU 2.0 + */ +class U_COMMON_API Normalizer : public UObject { +public: +#ifndef U_HIDE_DEPRECATED_API + /** + * If DONE is returned from an iteration function that returns a code point, + * then there are no more normalization results available. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + enum { + DONE=0xffff + }; + + // Constructors + + /** + * Creates a new <code>Normalizer</code> object for iterating over the + * normalized form of a given string. + * <p> + * @param str The string to be normalized. The normalization + * will start at the beginning of the string. + * + * @param mode The normalization mode. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + Normalizer(const UnicodeString& str, UNormalizationMode mode); + + /** + * Creates a new <code>Normalizer</code> object for iterating over the + * normalized form of a given string. + * <p> + * @param str The string to be normalized. The normalization + * will start at the beginning of the string. + * + * @param length Length of the string, or -1 if NUL-terminated. + * @param mode The normalization mode. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + Normalizer(ConstChar16Ptr str, int32_t length, UNormalizationMode mode); + + /** + * Creates a new <code>Normalizer</code> object for iterating over the + * normalized form of the given text. + * <p> + * @param iter The input text to be normalized. The normalization + * will start at the beginning of the string. + * + * @param mode The normalization mode. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + Normalizer(const CharacterIterator& iter, UNormalizationMode mode); +#endif /* U_HIDE_DEPRECATED_API */ + +#ifndef U_FORCE_HIDE_DEPRECATED_API + /** + * Copy constructor. + * @param copy The object to be copied. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + Normalizer(const Normalizer& copy); + + /** + * Destructor + * @deprecated ICU 56 Use Normalizer2 instead. + */ + virtual ~Normalizer(); +#endif // U_FORCE_HIDE_DEPRECATED_API + + //------------------------------------------------------------------------- + // Static utility methods + //------------------------------------------------------------------------- + +#ifndef U_HIDE_DEPRECATED_API + /** + * Normalizes a <code>UnicodeString</code> according to the specified normalization mode. + * This is a wrapper for unorm_normalize(), using UnicodeString's. + * + * The <code>options</code> parameter specifies which optional + * <code>Normalizer</code> features are to be enabled for this operation. + * + * @param source the input string to be normalized. + * @param mode the normalization mode + * @param options the optional features to be enabled (0 for no options) + * @param result The normalized string (on output). + * @param status The error code. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static void U_EXPORT2 normalize(const UnicodeString& source, + UNormalizationMode mode, int32_t options, + UnicodeString& result, + UErrorCode &status); + + /** + * Compose a <code>UnicodeString</code>. + * This is equivalent to normalize() with mode UNORM_NFC or UNORM_NFKC. + * This is a wrapper for unorm_normalize(), using UnicodeString's. + * + * The <code>options</code> parameter specifies which optional + * <code>Normalizer</code> features are to be enabled for this operation. + * + * @param source the string to be composed. + * @param compat Perform compatibility decomposition before composition. + * If this argument is <code>false</code>, only canonical + * decomposition will be performed. + * @param options the optional features to be enabled (0 for no options) + * @param result The composed string (on output). + * @param status The error code. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static void U_EXPORT2 compose(const UnicodeString& source, + UBool compat, int32_t options, + UnicodeString& result, + UErrorCode &status); + + /** + * Static method to decompose a <code>UnicodeString</code>. + * This is equivalent to normalize() with mode UNORM_NFD or UNORM_NFKD. + * This is a wrapper for unorm_normalize(), using UnicodeString's. + * + * The <code>options</code> parameter specifies which optional + * <code>Normalizer</code> features are to be enabled for this operation. + * + * @param source the string to be decomposed. + * @param compat Perform compatibility decomposition. + * If this argument is <code>false</code>, only canonical + * decomposition will be performed. + * @param options the optional features to be enabled (0 for no options) + * @param result The decomposed string (on output). + * @param status The error code. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static void U_EXPORT2 decompose(const UnicodeString& source, + UBool compat, int32_t options, + UnicodeString& result, + UErrorCode &status); + + /** + * Performing quick check on a string, to quickly determine if the string is + * in a particular normalization format. + * This is a wrapper for unorm_quickCheck(), using a UnicodeString. + * + * Three types of result can be returned UNORM_YES, UNORM_NO or + * UNORM_MAYBE. Result UNORM_YES indicates that the argument + * string is in the desired normalized format, UNORM_NO determines that + * argument string is not in the desired normalized format. A + * UNORM_MAYBE result indicates that a more thorough check is required, + * the user may have to put the string in its normalized form and compare the + * results. + * @param source string for determining if it is in a normalized format + * @param mode normalization format + * @param status A reference to a UErrorCode to receive any errors + * @return UNORM_YES, UNORM_NO or UNORM_MAYBE + * + * @see isNormalized + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static inline UNormalizationCheckResult + quickCheck(const UnicodeString &source, UNormalizationMode mode, UErrorCode &status); + + /** + * Performing quick check on a string; same as the other version of quickCheck + * but takes an extra options parameter like most normalization functions. + * + * @param source string for determining if it is in a normalized format + * @param mode normalization format + * @param options the optional features to be enabled (0 for no options) + * @param status A reference to a UErrorCode to receive any errors + * @return UNORM_YES, UNORM_NO or UNORM_MAYBE + * + * @see isNormalized + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static UNormalizationCheckResult + quickCheck(const UnicodeString &source, UNormalizationMode mode, int32_t options, UErrorCode &status); + + /** + * Test if a string is in a given normalization form. + * This is semantically equivalent to source.equals(normalize(source, mode)) . + * + * Unlike unorm_quickCheck(), this function returns a definitive result, + * never a "maybe". + * For NFD, NFKD, and FCD, both functions work exactly the same. + * For NFC and NFKC where quickCheck may return "maybe", this function will + * perform further tests to arrive at a true/false result. + * + * @param src String that is to be tested if it is in a normalization format. + * @param mode Which normalization form to test for. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Boolean value indicating whether the source string is in the + * "mode" normalization form. + * + * @see quickCheck + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static inline UBool + isNormalized(const UnicodeString &src, UNormalizationMode mode, UErrorCode &errorCode); + + /** + * Test if a string is in a given normalization form; same as the other version of isNormalized + * but takes an extra options parameter like most normalization functions. + * + * @param src String that is to be tested if it is in a normalization format. + * @param mode Which normalization form to test for. + * @param options the optional features to be enabled (0 for no options) + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Boolean value indicating whether the source string is in the + * "mode" normalization form. + * + * @see quickCheck + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static UBool + isNormalized(const UnicodeString &src, UNormalizationMode mode, int32_t options, UErrorCode &errorCode); + + /** + * Concatenate normalized strings, making sure that the result is normalized as well. + * + * If both the left and the right strings are in + * the normalization form according to "mode/options", + * then the result will be + * + * \code + * dest=normalize(left+right, mode, options) + * \endcode + * + * For details see unorm_concatenate in unorm.h. + * + * @param left Left source string. + * @param right Right source string. + * @param result The output string. + * @param mode The normalization mode. + * @param options A bit set of normalization options. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return result + * + * @see unorm_concatenate + * @see normalize + * @see unorm_next + * @see unorm_previous + * + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static UnicodeString & + U_EXPORT2 concatenate(const UnicodeString &left, const UnicodeString &right, + UnicodeString &result, + UNormalizationMode mode, int32_t options, + UErrorCode &errorCode); +#endif /* U_HIDE_DEPRECATED_API */ + + /** + * Compare two strings for canonical equivalence. + * Further options include case-insensitive comparison and + * code point order (as opposed to code unit order). + * + * Canonical equivalence between two strings is defined as their normalized + * forms (NFD or NFC) being identical. + * This function compares strings incrementally instead of normalizing + * (and optionally case-folding) both strings entirely, + * improving performance significantly. + * + * Bulk normalization is only necessary if the strings do not fulfill the FCD + * conditions. Only in this case, and only if the strings are relatively long, + * is memory allocated temporarily. + * For FCD strings and short non-FCD strings there is no memory allocation. + * + * Semantically, this is equivalent to + * strcmp[CodePointOrder](NFD(foldCase(s1)), NFD(foldCase(s2))) + * where code point order and foldCase are all optional. + * + * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match + * the case folding must be performed first, then the normalization. + * + * @param s1 First source string. + * @param s2 Second source string. + * + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Case-sensitive comparison in code unit order, and the input strings + * are quick-checked for FCD. + * + * - UNORM_INPUT_IS_FCD + * Set if the caller knows that both s1 and s2 fulfill the FCD conditions. + * If not set, the function will quickCheck for FCD + * and normalize if necessary. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_COMPARE_IGNORE_CASE + * Set to compare strings case-insensitively using case folding, + * instead of case-sensitively. + * If set, then the following case folding options are used. + * + * - Options as used with case-insensitive comparisons, currently: + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * (see u_strCaseCompare for details) + * + * - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT + * + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return <0 or 0 or >0 as usual for string comparisons + * + * @see unorm_compare + * @see normalize + * @see UNORM_FCD + * @see u_strCompare + * @see u_strCaseCompare + * + * @stable ICU 2.2 + */ + static inline int32_t + compare(const UnicodeString &s1, const UnicodeString &s2, + uint32_t options, + UErrorCode &errorCode); + +#ifndef U_HIDE_DEPRECATED_API + //------------------------------------------------------------------------- + // Iteration API + //------------------------------------------------------------------------- + + /** + * Return the current character in the normalized text. + * current() may need to normalize some text at getIndex(). + * The getIndex() is not changed. + * + * @return the current normalized code point + * @deprecated ICU 56 Use Normalizer2 instead. + */ + UChar32 current(void); + + /** + * Return the first character in the normalized text. + * This is equivalent to setIndexOnly(startIndex()) followed by next(). + * (Post-increment semantics.) + * + * @return the first normalized code point + * @deprecated ICU 56 Use Normalizer2 instead. + */ + UChar32 first(void); + + /** + * Return the last character in the normalized text. + * This is equivalent to setIndexOnly(endIndex()) followed by previous(). + * (Pre-decrement semantics.) + * + * @return the last normalized code point + * @deprecated ICU 56 Use Normalizer2 instead. + */ + UChar32 last(void); + + /** + * Return the next character in the normalized text. + * (Post-increment semantics.) + * If the end of the text has already been reached, DONE is returned. + * The DONE value could be confused with a U+FFFF non-character code point + * in the text. If this is possible, you can test getIndex()<endIndex() + * before calling next(), or (getIndex()<endIndex() || last()!=DONE) + * after calling next(). (Calling last() will change the iterator state!) + * + * The C API unorm_next() is more efficient and does not have this ambiguity. + * + * @return the next normalized code point + * @deprecated ICU 56 Use Normalizer2 instead. + */ + UChar32 next(void); + + /** + * Return the previous character in the normalized text and decrement. + * (Pre-decrement semantics.) + * If the beginning of the text has already been reached, DONE is returned. + * The DONE value could be confused with a U+FFFF non-character code point + * in the text. If this is possible, you can test + * (getIndex()>startIndex() || first()!=DONE). (Calling first() will change + * the iterator state!) + * + * The C API unorm_previous() is more efficient and does not have this ambiguity. + * + * @return the previous normalized code point + * @deprecated ICU 56 Use Normalizer2 instead. + */ + UChar32 previous(void); + + /** + * Set the iteration position in the input text that is being normalized, + * without any immediate normalization. + * After setIndexOnly(), getIndex() will return the same index that is + * specified here. + * + * @param index the desired index in the input text. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + void setIndexOnly(int32_t index); + + /** + * Reset the index to the beginning of the text. + * This is equivalent to setIndexOnly(startIndex)). + * @deprecated ICU 56 Use Normalizer2 instead. + */ + void reset(void); + + /** + * Retrieve the current iteration position in the input text that is + * being normalized. + * + * A following call to next() will return a normalized code point from + * the input text at or after this index. + * + * After a call to previous(), getIndex() will point at or before the + * position in the input text where the normalized code point + * was returned from with previous(). + * + * @return the current index in the input text + * @deprecated ICU 56 Use Normalizer2 instead. + */ + int32_t getIndex(void) const; + + /** + * Retrieve the index of the start of the input text. This is the begin index + * of the <code>CharacterIterator</code> or the start (i.e. index 0) of the string + * over which this <code>Normalizer</code> is iterating. + * + * @return the smallest index in the input text where the Normalizer operates + * @deprecated ICU 56 Use Normalizer2 instead. + */ + int32_t startIndex(void) const; + + /** + * Retrieve the index of the end of the input text. This is the end index + * of the <code>CharacterIterator</code> or the length of the string + * over which this <code>Normalizer</code> is iterating. + * This end index is exclusive, i.e., the Normalizer operates only on characters + * before this index. + * + * @return the first index in the input text where the Normalizer does not operate + * @deprecated ICU 56 Use Normalizer2 instead. + */ + int32_t endIndex(void) const; + + /** + * Returns true when both iterators refer to the same character in the same + * input text. + * + * @param that a Normalizer object to compare this one to + * @return comparison result + * @deprecated ICU 56 Use Normalizer2 instead. + */ + UBool operator==(const Normalizer& that) const; + + /** + * Returns false when both iterators refer to the same character in the same + * input text. + * + * @param that a Normalizer object to compare this one to + * @return comparison result + * @deprecated ICU 56 Use Normalizer2 instead. + */ + inline UBool operator!=(const Normalizer& that) const; + + /** + * Returns a pointer to a new Normalizer that is a clone of this one. + * The caller is responsible for deleting the new clone. + * @return a pointer to a new Normalizer + * @deprecated ICU 56 Use Normalizer2 instead. + */ + Normalizer* clone() const; + + /** + * Generates a hash code for this iterator. + * + * @return the hash code + * @deprecated ICU 56 Use Normalizer2 instead. + */ + int32_t hashCode(void) const; + + //------------------------------------------------------------------------- + // Property access methods + //------------------------------------------------------------------------- + + /** + * Set the normalization mode for this object. + * <p> + * <b>Note:</b>If the normalization mode is changed while iterating + * over a string, calls to {@link #next() } and {@link #previous() } may + * return previously buffers characters in the old normalization mode + * until the iteration is able to re-sync at the next base character. + * It is safest to call {@link #setIndexOnly }, {@link #reset() }, + * {@link #setText }, {@link #first() }, + * {@link #last() }, etc. after calling <code>setMode</code>. + * <p> + * @param newMode the new mode for this <code>Normalizer</code>. + * @see #getUMode + * @deprecated ICU 56 Use Normalizer2 instead. + */ + void setMode(UNormalizationMode newMode); + + /** + * Return the normalization mode for this object. + * + * This is an unusual name because there used to be a getMode() that + * returned a different type. + * + * @return the mode for this <code>Normalizer</code> + * @see #setMode + * @deprecated ICU 56 Use Normalizer2 instead. + */ + UNormalizationMode getUMode(void) const; + + /** + * Set options that affect this <code>Normalizer</code>'s operation. + * Options do not change the basic composition or decomposition operation + * that is being performed, but they control whether + * certain optional portions of the operation are done. + * Currently the only available option is obsolete. + * + * It is possible to specify multiple options that are all turned on or off. + * + * @param option the option(s) whose value is/are to be set. + * @param value the new setting for the option. Use <code>true</code> to + * turn the option(s) on and <code>false</code> to turn it/them off. + * + * @see #getOption + * @deprecated ICU 56 Use Normalizer2 instead. + */ + void setOption(int32_t option, + UBool value); + + /** + * Determine whether an option is turned on or off. + * If multiple options are specified, then the result is true if any + * of them are set. + * <p> + * @param option the option(s) that are to be checked + * @return true if any of the option(s) are set + * @see #setOption + * @deprecated ICU 56 Use Normalizer2 instead. + */ + UBool getOption(int32_t option) const; + + /** + * Set the input text over which this <code>Normalizer</code> will iterate. + * The iteration position is set to the beginning. + * + * @param newText a string that replaces the current input text + * @param status a UErrorCode + * @deprecated ICU 56 Use Normalizer2 instead. + */ + void setText(const UnicodeString& newText, + UErrorCode &status); + + /** + * Set the input text over which this <code>Normalizer</code> will iterate. + * The iteration position is set to the beginning. + * + * @param newText a CharacterIterator object that replaces the current input text + * @param status a UErrorCode + * @deprecated ICU 56 Use Normalizer2 instead. + */ + void setText(const CharacterIterator& newText, + UErrorCode &status); + + /** + * Set the input text over which this <code>Normalizer</code> will iterate. + * The iteration position is set to the beginning. + * + * @param newText a string that replaces the current input text + * @param length the length of the string, or -1 if NUL-terminated + * @param status a UErrorCode + * @deprecated ICU 56 Use Normalizer2 instead. + */ + void setText(ConstChar16Ptr newText, + int32_t length, + UErrorCode &status); + /** + * Copies the input text into the UnicodeString argument. + * + * @param result Receives a copy of the text under iteration. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + void getText(UnicodeString& result); + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * @returns a UClassID for this class. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + static UClassID U_EXPORT2 getStaticClassID(); +#endif /* U_HIDE_DEPRECATED_API */ + +#ifndef U_FORCE_HIDE_DEPRECATED_API + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * @return a UClassID for the actual class. + * @deprecated ICU 56 Use Normalizer2 instead. + */ + virtual UClassID getDynamicClassID() const; +#endif // U_FORCE_HIDE_DEPRECATED_API + +private: + //------------------------------------------------------------------------- + // Private functions + //------------------------------------------------------------------------- + + Normalizer(); // default constructor not implemented + Normalizer &operator=(const Normalizer &that); // assignment operator not implemented + + // Private utility methods for iteration + // For documentation, see the source code + UBool nextNormalize(); + UBool previousNormalize(); + + void init(); + void clearBuffer(void); + + //------------------------------------------------------------------------- + // Private data + //------------------------------------------------------------------------- + + FilteredNormalizer2*fFilteredNorm2; // owned if not NULL + const Normalizer2 *fNorm2; // not owned; may be equal to fFilteredNorm2 + UNormalizationMode fUMode; // deprecated + int32_t fOptions; + + // The input text and our position in it + CharacterIterator *text; + + // The normalization buffer is the result of normalization + // of the source in [currentIndex..nextIndex[ . + int32_t currentIndex, nextIndex; + + // A buffer for holding intermediate results + UnicodeString buffer; + int32_t bufferPos; +}; + +//------------------------------------------------------------------------- +// Inline implementations +//------------------------------------------------------------------------- + +#ifndef U_HIDE_DEPRECATED_API +inline UBool +Normalizer::operator!= (const Normalizer& other) const +{ return ! operator==(other); } + +inline UNormalizationCheckResult +Normalizer::quickCheck(const UnicodeString& source, + UNormalizationMode mode, + UErrorCode &status) { + return quickCheck(source, mode, 0, status); +} + +inline UBool +Normalizer::isNormalized(const UnicodeString& source, + UNormalizationMode mode, + UErrorCode &status) { + return isNormalized(source, mode, 0, status); +} +#endif /* U_HIDE_DEPRECATED_API */ + +inline int32_t +Normalizer::compare(const UnicodeString &s1, const UnicodeString &s2, + uint32_t options, + UErrorCode &errorCode) { + // all argument checking is done in unorm_compare + return unorm_compare(toUCharPtr(s1.getBuffer()), s1.length(), + toUCharPtr(s2.getBuffer()), s2.length(), + options, + &errorCode); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_NORMALIZATION */ + +#endif // NORMLZR_H + +#endif /* U_SHOW_CPLUSPLUS_API */ diff --git a/thirdparty/icu4c/common/unicode/parseerr.h b/thirdparty/icu4c/common/unicode/parseerr.h new file mode 100644 index 0000000000..c23cc273b8 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/parseerr.h @@ -0,0 +1,94 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1999-2005, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Date Name Description +* 03/14/00 aliu Creation. +* 06/27/00 aliu Change from C++ class to C struct +********************************************************************** +*/ +#ifndef PARSEERR_H +#define PARSEERR_H + +#include "unicode/utypes.h" + + +/** + * \file + * \brief C API: Parse Error Information + */ +/** + * The capacity of the context strings in UParseError. + * @stable ICU 2.0 + */ +enum { U_PARSE_CONTEXT_LEN = 16 }; + +/** + * A UParseError struct is used to returned detailed information about + * parsing errors. It is used by ICU parsing engines that parse long + * rules, patterns, or programs, where the text being parsed is long + * enough that more information than a UErrorCode is needed to + * localize the error. + * + * <p>The line, offset, and context fields are optional; parsing + * engines may choose not to use to use them. + * + * <p>The preContext and postContext strings include some part of the + * context surrounding the error. If the source text is "let for=7" + * and "for" is the error (e.g., because it is a reserved word), then + * some examples of what a parser might produce are the following: + * + * <pre> + * preContext postContext + * "" "" The parser does not support context + * "let " "=7" Pre- and post-context only + * "let " "for=7" Pre- and post-context and error text + * "" "for" Error text only + * </pre> + * + * <p>Examples of engines which use UParseError (or may use it in the + * future) are Transliterator, RuleBasedBreakIterator, and + * RegexPattern. + * + * @stable ICU 2.0 + */ +typedef struct UParseError { + + /** + * The line on which the error occurred. If the parser uses this + * field, it sets it to the line number of the source text line on + * which the error appears, which will be a value >= 1. If the + * parse does not support line numbers, the value will be <= 0. + * @stable ICU 2.0 + */ + int32_t line; + + /** + * The character offset to the error. If the line field is >= 1, + * then this is the offset from the start of the line. Otherwise, + * this is the offset from the start of the text. If the parser + * does not support this field, it will have a value < 0. + * @stable ICU 2.0 + */ + int32_t offset; + + /** + * Textual context before the error. Null-terminated. The empty + * string if not supported by parser. + * @stable ICU 2.0 + */ + UChar preContext[U_PARSE_CONTEXT_LEN]; + + /** + * The error itself and/or textual context after the error. + * Null-terminated. The empty string if not supported by parser. + * @stable ICU 2.0 + */ + UChar postContext[U_PARSE_CONTEXT_LEN]; + +} UParseError; + +#endif diff --git a/thirdparty/icu4c/common/unicode/parsepos.h b/thirdparty/icu4c/common/unicode/parsepos.h new file mode 100644 index 0000000000..260ed4cbb8 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/parsepos.h @@ -0,0 +1,237 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +* Copyright (C) 1997-2005, International Business Machines Corporation and others. All Rights Reserved. +******************************************************************************* +* +* File PARSEPOS.H +* +* Modification History: +* +* Date Name Description +* 07/09/97 helena Converted from java. +* 07/17/98 stephen Added errorIndex support. +* 05/11/99 stephen Cleaned up. +******************************************************************************* +*/ + +#ifndef PARSEPOS_H +#define PARSEPOS_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + + +U_NAMESPACE_BEGIN + +/** + * \file + * \brief C++ API: Canonical Iterator + */ +/** + * <code>ParsePosition</code> is a simple class used by <code>Format</code> + * and its subclasses to keep track of the current position during parsing. + * The <code>parseObject</code> method in the various <code>Format</code> + * classes requires a <code>ParsePosition</code> object as an argument. + * + * <p> + * By design, as you parse through a string with different formats, + * you can use the same <code>ParsePosition</code>, since the index parameter + * records the current position. + * + * The ParsePosition class is not suitable for subclassing. + * + * @version 1.3 10/30/97 + * @author Mark Davis, Helena Shih + * @see java.text.Format + */ + +class U_COMMON_API ParsePosition : public UObject { +public: + /** + * Default constructor, the index starts with 0 as default. + * @stable ICU 2.0 + */ + ParsePosition() + : UObject(), + index(0), + errorIndex(-1) + {} + + /** + * Create a new ParsePosition with the given initial index. + * @param newIndex the new text offset. + * @stable ICU 2.0 + */ + ParsePosition(int32_t newIndex) + : UObject(), + index(newIndex), + errorIndex(-1) + {} + + /** + * Copy constructor + * @param copy the object to be copied from. + * @stable ICU 2.0 + */ + ParsePosition(const ParsePosition& copy) + : UObject(copy), + index(copy.index), + errorIndex(copy.errorIndex) + {} + + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~ParsePosition(); + + /** + * Assignment operator + * @stable ICU 2.0 + */ + inline ParsePosition& operator=(const ParsePosition& copy); + + /** + * Equality operator. + * @return true if the two parse positions are equal, false otherwise. + * @stable ICU 2.0 + */ + inline UBool operator==(const ParsePosition& that) const; + + /** + * Equality operator. + * @return true if the two parse positions are not equal, false otherwise. + * @stable ICU 2.0 + */ + inline UBool operator!=(const ParsePosition& that) const; + + /** + * Clone this object. + * Clones can be used concurrently in multiple threads. + * If an error occurs, then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see getDynamicClassID + * @stable ICU 2.8 + */ + ParsePosition *clone() const; + + /** + * Retrieve the current parse position. On input to a parse method, this + * is the index of the character at which parsing will begin; on output, it + * is the index of the character following the last character parsed. + * @return the current index. + * @stable ICU 2.0 + */ + inline int32_t getIndex(void) const; + + /** + * Set the current parse position. + * @param index the new index. + * @stable ICU 2.0 + */ + inline void setIndex(int32_t index); + + /** + * Set the index at which a parse error occurred. Formatters + * should set this before returning an error code from their + * parseObject method. The default value is -1 if this is not + * set. + * @stable ICU 2.0 + */ + inline void setErrorIndex(int32_t ei); + + /** + * Retrieve the index at which an error occurred, or -1 if the + * error index has not been set. + * @stable ICU 2.0 + */ + inline int32_t getErrorIndex(void) const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + +private: + /** + * Input: the place you start parsing. + * <br>Output: position where the parse stopped. + * This is designed to be used serially, + * with each call setting index up for the next one. + */ + int32_t index; + + /** + * The index at which a parse error occurred. + */ + int32_t errorIndex; + +}; + +inline ParsePosition& +ParsePosition::operator=(const ParsePosition& copy) +{ + index = copy.index; + errorIndex = copy.errorIndex; + return *this; +} + +inline UBool +ParsePosition::operator==(const ParsePosition& copy) const +{ + if(index != copy.index || errorIndex != copy.errorIndex) + return false; + else + return true; +} + +inline UBool +ParsePosition::operator!=(const ParsePosition& copy) const +{ + return !operator==(copy); +} + +inline int32_t +ParsePosition::getIndex() const +{ + return index; +} + +inline void +ParsePosition::setIndex(int32_t offset) +{ + this->index = offset; +} + +inline int32_t +ParsePosition::getErrorIndex() const +{ + return errorIndex; +} + +inline void +ParsePosition::setErrorIndex(int32_t ei) +{ + this->errorIndex = ei; +} +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/platform.h b/thirdparty/icu4c/common/unicode/platform.h new file mode 100644 index 0000000000..2bb2f8b318 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/platform.h @@ -0,0 +1,885 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1997-2016, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* +* FILE NAME : platform.h +* +* Date Name Description +* 05/13/98 nos Creation (content moved here from ptypes.h). +* 03/02/99 stephen Added AS400 support. +* 03/30/99 stephen Added Linux support. +* 04/13/99 stephen Reworked for autoconf. +****************************************************************************** +*/ + +#ifndef _PLATFORM_H +#define _PLATFORM_H + +#include "unicode/uconfig.h" +#include "unicode/uvernum.h" + +/** + * \file + * \brief Basic types for the platform. + * + * This file used to be generated by autoconf/configure. + * Starting with ICU 49, platform.h is a normal source file, + * to simplify cross-compiling and working with non-autoconf/make build systems. + * + * When a value in this file does not work on a platform, then please + * try to derive it from the U_PLATFORM value + * (for which we might need a new value constant in rare cases) + * and/or from other macros that are predefined by the compiler + * or defined in standard (POSIX or platform or compiler) headers. + * + * As a temporary workaround, you can add an explicit \#define for some macros + * before it is first tested, or add an equivalent -D macro definition + * to the compiler's command line. + * + * Note: Some compilers provide ways to show the predefined macros. + * For example, with gcc you can compile an empty .c file and have the compiler + * print the predefined macros with + * \code + * gcc -E -dM -x c /dev/null | sort + * \endcode + * (You can provide an actual empty .c file rather than /dev/null. + * <code>-x c++</code> is for C++.) + */ + +/** + * Define some things so that they can be documented. + * @internal + */ +#ifdef U_IN_DOXYGEN +/* + * Problem: "platform.h:335: warning: documentation for unknown define U_HAVE_STD_STRING found." means that U_HAVE_STD_STRING is not documented. + * Solution: #define any defines for non @internal API here, so that they are visible in the docs. If you just set PREDEFINED in Doxyfile.in, they won't be documented. + */ + +/* None for now. */ +#endif + +/** + * \def U_PLATFORM + * The U_PLATFORM macro defines the platform we're on. + * + * We used to define one different, value-less macro per platform. + * That made it hard to know the set of relevant platforms and macros, + * and hard to deal with variants of platforms. + * + * Starting with ICU 49, we define platforms as numeric macros, + * with ranges of values for related platforms and their variants. + * The U_PLATFORM macro is set to one of these values. + * + * Historical note from the Solaris Wikipedia article: + * AT&T and Sun collaborated on a project to merge the most popular Unix variants + * on the market at that time: BSD, System V, and Xenix. + * This became Unix System V Release 4 (SVR4). + * + * @internal + */ + +/** Unknown platform. @internal */ +#define U_PF_UNKNOWN 0 +/** Windows @internal */ +#define U_PF_WINDOWS 1000 +/** MinGW. Windows, calls to Win32 API, but using GNU gcc and binutils. @internal */ +#define U_PF_MINGW 1800 +/** + * Cygwin. Windows, calls to cygwin1.dll for Posix functions, + * using MSVC or GNU gcc and binutils. + * @internal + */ +#define U_PF_CYGWIN 1900 +/* Reserve 2000 for U_PF_UNIX? */ +/** HP-UX is based on UNIX System V. @internal */ +#define U_PF_HPUX 2100 +/** Solaris is a Unix operating system based on SVR4. @internal */ +#define U_PF_SOLARIS 2600 +/** BSD is a UNIX operating system derivative. @internal */ +#define U_PF_BSD 3000 +/** AIX is based on UNIX System V Releases and 4.3 BSD. @internal */ +#define U_PF_AIX 3100 +/** IRIX is based on UNIX System V with BSD extensions. @internal */ +#define U_PF_IRIX 3200 +/** + * Darwin is a POSIX-compliant operating system, composed of code developed by Apple, + * as well as code derived from NeXTSTEP, BSD, and other projects, + * built around the Mach kernel. + * Darwin forms the core set of components upon which Mac OS X, Apple TV, and iOS are based. + * (Original description modified from WikiPedia.) + * @internal + */ +#define U_PF_DARWIN 3500 +/** iPhone OS (iOS) is a derivative of Mac OS X. @internal */ +#define U_PF_IPHONE 3550 +/** QNX is a commercial Unix-like real-time operating system related to BSD. @internal */ +#define U_PF_QNX 3700 +/** Linux is a Unix-like operating system. @internal */ +#define U_PF_LINUX 4000 +/** + * Native Client is pretty close to Linux. + * See https://developer.chrome.com/native-client and + * http://www.chromium.org/nativeclient + * @internal + */ +#define U_PF_BROWSER_NATIVE_CLIENT 4020 +/** Android is based on Linux. @internal */ +#define U_PF_ANDROID 4050 +/** Fuchsia is a POSIX-ish platform. @internal */ +#define U_PF_FUCHSIA 4100 +/* Maximum value for Linux-based platform is 4499 */ +/** + * Emscripten is a C++ transpiler for the Web that can target asm.js or + * WebAssembly. It provides some POSIX-compatible wrappers and stubs and + * some Linux-like functionality, but is not fully compatible with + * either. + * @internal + */ +#define U_PF_EMSCRIPTEN 5010 +/** z/OS is the successor to OS/390 which was the successor to MVS. @internal */ +#define U_PF_OS390 9000 +/** "IBM i" is the current name of what used to be i5/OS and earlier OS/400. @internal */ +#define U_PF_OS400 9400 + +#ifdef U_PLATFORM + /* Use the predefined value. */ +#elif defined(__MINGW32__) +# define U_PLATFORM U_PF_MINGW +#elif defined(__CYGWIN__) +# define U_PLATFORM U_PF_CYGWIN +#elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64) +# define U_PLATFORM U_PF_WINDOWS +#elif defined(__ANDROID__) +# define U_PLATFORM U_PF_ANDROID + /* Android wchar_t support depends on the API level. */ +# include <android/api-level.h> +#elif defined(__pnacl__) || defined(__native_client__) +# define U_PLATFORM U_PF_BROWSER_NATIVE_CLIENT +#elif defined(__Fuchsia__) +# define U_PLATFORM U_PF_FUCHSIA +#elif defined(linux) || defined(__linux__) || defined(__linux) +# define U_PLATFORM U_PF_LINUX +#elif defined(__APPLE__) && defined(__MACH__) +# include <TargetConditionals.h> +# if defined(TARGET_OS_IPHONE) && TARGET_OS_IPHONE /* variant of TARGET_OS_MAC */ +# define U_PLATFORM U_PF_IPHONE +# else +# define U_PLATFORM U_PF_DARWIN +# endif +#elif defined(BSD) || defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__MirBSD__) +# if defined(__FreeBSD__) +# include <sys/endian.h> +# endif +# define U_PLATFORM U_PF_BSD +#elif defined(sun) || defined(__sun) + /* Check defined(__SVR4) || defined(__svr4__) to distinguish Solaris from SunOS? */ +# define U_PLATFORM U_PF_SOLARIS +# if defined(__GNUC__) + /* Solaris/GCC needs this header file to get the proper endianness. Normally, this + * header file is included with stddef.h but on Solairs/GCC, the GCC version of stddef.h + * is included which does not include this header file. + */ +# include <sys/isa_defs.h> +# endif +#elif defined(_AIX) || defined(__TOS_AIX__) +# define U_PLATFORM U_PF_AIX +#elif defined(_hpux) || defined(hpux) || defined(__hpux) +# define U_PLATFORM U_PF_HPUX +#elif defined(sgi) || defined(__sgi) +# define U_PLATFORM U_PF_IRIX +#elif defined(__QNX__) || defined(__QNXNTO__) +# define U_PLATFORM U_PF_QNX +#elif defined(__TOS_MVS__) +# define U_PLATFORM U_PF_OS390 +#elif defined(__OS400__) || defined(__TOS_OS400__) +# define U_PLATFORM U_PF_OS400 +#elif defined(__EMSCRIPTEN__) +# define U_PLATFORM U_PF_EMSCRIPTEN +#else +# define U_PLATFORM U_PF_UNKNOWN +#endif + +/** + * \def CYGWINMSVC + * Defined if this is Windows with Cygwin, but using MSVC rather than gcc. + * Otherwise undefined. + * @internal + */ +/* Commented out because this is already set in mh-cygwin-msvc +#if U_PLATFORM == U_PF_CYGWIN && defined(_MSC_VER) +# define CYGWINMSVC +#endif +*/ +#ifdef U_IN_DOXYGEN +# define CYGWINMSVC +#endif + +/** + * \def U_PLATFORM_USES_ONLY_WIN32_API + * Defines whether the platform uses only the Win32 API. + * Set to 1 for Windows/MSVC and MinGW but not Cygwin. + * @internal + */ +#ifdef U_PLATFORM_USES_ONLY_WIN32_API + /* Use the predefined value. */ +#elif (U_PF_WINDOWS <= U_PLATFORM && U_PLATFORM <= U_PF_MINGW) || defined(CYGWINMSVC) +# define U_PLATFORM_USES_ONLY_WIN32_API 1 +#else + /* Cygwin implements POSIX. */ +# define U_PLATFORM_USES_ONLY_WIN32_API 0 +#endif + +/** + * \def U_PLATFORM_HAS_WIN32_API + * Defines whether the Win32 API is available on the platform. + * Set to 1 for Windows/MSVC, MinGW and Cygwin. + * @internal + */ +#ifdef U_PLATFORM_HAS_WIN32_API + /* Use the predefined value. */ +#elif U_PF_WINDOWS <= U_PLATFORM && U_PLATFORM <= U_PF_CYGWIN +# define U_PLATFORM_HAS_WIN32_API 1 +#else +# define U_PLATFORM_HAS_WIN32_API 0 +#endif + +/** + * \def U_PLATFORM_HAS_WINUWP_API + * Defines whether target is intended for Universal Windows Platform API + * Set to 1 for Windows10 Release Solution Configuration + * @internal + */ +#ifdef U_PLATFORM_HAS_WINUWP_API + /* Use the predefined value. */ +#else +# define U_PLATFORM_HAS_WINUWP_API 0 +#endif + +/** + * \def U_PLATFORM_IMPLEMENTS_POSIX + * Defines whether the platform implements (most of) the POSIX API. + * Set to 1 for Cygwin and most other platforms. + * @internal + */ +#ifdef U_PLATFORM_IMPLEMENTS_POSIX + /* Use the predefined value. */ +#elif U_PLATFORM_USES_ONLY_WIN32_API +# define U_PLATFORM_IMPLEMENTS_POSIX 0 +#else +# define U_PLATFORM_IMPLEMENTS_POSIX 1 +#endif + +/** + * \def U_PLATFORM_IS_LINUX_BASED + * Defines whether the platform is Linux or one of its derivatives. + * @internal + */ +#ifdef U_PLATFORM_IS_LINUX_BASED + /* Use the predefined value. */ +#elif U_PF_LINUX <= U_PLATFORM && U_PLATFORM <= 4499 +# define U_PLATFORM_IS_LINUX_BASED 1 +#else +# define U_PLATFORM_IS_LINUX_BASED 0 +#endif + +/** + * \def U_PLATFORM_IS_DARWIN_BASED + * Defines whether the platform is Darwin or one of its derivatives. + * @internal + */ +#ifdef U_PLATFORM_IS_DARWIN_BASED + /* Use the predefined value. */ +#elif U_PF_DARWIN <= U_PLATFORM && U_PLATFORM <= U_PF_IPHONE +# define U_PLATFORM_IS_DARWIN_BASED 1 +#else +# define U_PLATFORM_IS_DARWIN_BASED 0 +#endif + +/** + * \def U_HAVE_STDINT_H + * Defines whether stdint.h is available. It is a C99 standard header. + * We used to include inttypes.h which includes stdint.h but we usually do not need + * the additional definitions from inttypes.h. + * @internal + */ +#ifdef U_HAVE_STDINT_H + /* Use the predefined value. */ +#elif U_PLATFORM_USES_ONLY_WIN32_API +# if defined(__BORLANDC__) || U_PLATFORM == U_PF_MINGW || (defined(_MSC_VER) && _MSC_VER>=1600) + /* Windows Visual Studio 9 and below do not have stdint.h & inttypes.h, but VS 2010 adds them. */ +# define U_HAVE_STDINT_H 1 +# else +# define U_HAVE_STDINT_H 0 +# endif +#elif U_PLATFORM == U_PF_SOLARIS + /* Solaris has inttypes.h but not stdint.h. */ +# define U_HAVE_STDINT_H 0 +#elif U_PLATFORM == U_PF_AIX && !defined(_AIX51) && defined(_POWER) + /* PPC AIX <= 4.3 has inttypes.h but not stdint.h. */ +# define U_HAVE_STDINT_H 0 +#else +# define U_HAVE_STDINT_H 1 +#endif + +/** + * \def U_HAVE_INTTYPES_H + * Defines whether inttypes.h is available. It is a C99 standard header. + * We include inttypes.h where it is available but stdint.h is not. + * @internal + */ +#ifdef U_HAVE_INTTYPES_H + /* Use the predefined value. */ +#elif U_PLATFORM == U_PF_SOLARIS + /* Solaris has inttypes.h but not stdint.h. */ +# define U_HAVE_INTTYPES_H 1 +#elif U_PLATFORM == U_PF_AIX && !defined(_AIX51) && defined(_POWER) + /* PPC AIX <= 4.3 has inttypes.h but not stdint.h. */ +# define U_HAVE_INTTYPES_H 1 +#else + /* Most platforms have both inttypes.h and stdint.h, or neither. */ +# define U_HAVE_INTTYPES_H U_HAVE_STDINT_H +#endif + +/*===========================================================================*/ +/** @{ Compiler and environment features */ +/*===========================================================================*/ + +/** + * \def U_GCC_MAJOR_MINOR + * Indicates whether the compiler is gcc (test for != 0), + * and if so, contains its major (times 100) and minor version numbers. + * If the compiler is not gcc, then U_GCC_MAJOR_MINOR == 0. + * + * For example, for testing for whether we have gcc, and whether it's 4.6 or higher, + * use "#if U_GCC_MAJOR_MINOR >= 406". + * @internal + */ +#ifdef __GNUC__ +# define U_GCC_MAJOR_MINOR (__GNUC__ * 100 + __GNUC_MINOR__) +#else +# define U_GCC_MAJOR_MINOR 0 +#endif + +/** + * \def U_IS_BIG_ENDIAN + * Determines the endianness of the platform. + * @internal + */ +#ifdef U_IS_BIG_ENDIAN + /* Use the predefined value. */ +#elif defined(BYTE_ORDER) && defined(BIG_ENDIAN) +# define U_IS_BIG_ENDIAN (BYTE_ORDER == BIG_ENDIAN) +#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) + /* gcc */ +# define U_IS_BIG_ENDIAN (__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__) +#elif defined(__BIG_ENDIAN__) || defined(_BIG_ENDIAN) +# define U_IS_BIG_ENDIAN 1 +#elif defined(__LITTLE_ENDIAN__) || defined(_LITTLE_ENDIAN) +# define U_IS_BIG_ENDIAN 0 +#elif U_PLATFORM == U_PF_OS390 || U_PLATFORM == U_PF_OS400 || defined(__s390__) || defined(__s390x__) + /* These platforms do not appear to predefine any endianness macros. */ +# define U_IS_BIG_ENDIAN 1 +#elif defined(_PA_RISC1_0) || defined(_PA_RISC1_1) || defined(_PA_RISC2_0) + /* HPPA do not appear to predefine any endianness macros. */ +# define U_IS_BIG_ENDIAN 1 +#elif defined(sparc) || defined(__sparc) || defined(__sparc__) + /* Some sparc based systems (e.g. Linux) do not predefine any endianness macros. */ +# define U_IS_BIG_ENDIAN 1 +#else +# define U_IS_BIG_ENDIAN 0 +#endif + +/** + * \def U_HAVE_PLACEMENT_NEW + * Determines whether to override placement new and delete for STL. + * @stable ICU 2.6 + */ +#ifdef U_HAVE_PLACEMENT_NEW + /* Use the predefined value. */ +#elif defined(__BORLANDC__) +# define U_HAVE_PLACEMENT_NEW 0 +#else +# define U_HAVE_PLACEMENT_NEW 1 +#endif + +/** + * \def U_HAVE_DEBUG_LOCATION_NEW + * Define this to define the MFC debug version of the operator new. + * + * @stable ICU 3.4 + */ +#ifdef U_HAVE_DEBUG_LOCATION_NEW + /* Use the predefined value. */ +#elif defined(_MSC_VER) +# define U_HAVE_DEBUG_LOCATION_NEW 1 +#else +# define U_HAVE_DEBUG_LOCATION_NEW 0 +#endif + +/* Compatibility with compilers other than clang: http://clang.llvm.org/docs/LanguageExtensions.html */ +#ifdef __has_attribute +# define UPRV_HAS_ATTRIBUTE(x) __has_attribute(x) +#else +# define UPRV_HAS_ATTRIBUTE(x) 0 +#endif +#ifdef __has_cpp_attribute +# define UPRV_HAS_CPP_ATTRIBUTE(x) __has_cpp_attribute(x) +#else +# define UPRV_HAS_CPP_ATTRIBUTE(x) 0 +#endif +#ifdef __has_declspec_attribute +# define UPRV_HAS_DECLSPEC_ATTRIBUTE(x) __has_declspec_attribute(x) +#else +# define UPRV_HAS_DECLSPEC_ATTRIBUTE(x) 0 +#endif +#ifdef __has_builtin +# define UPRV_HAS_BUILTIN(x) __has_builtin(x) +#else +# define UPRV_HAS_BUILTIN(x) 0 +#endif +#ifdef __has_feature +# define UPRV_HAS_FEATURE(x) __has_feature(x) +#else +# define UPRV_HAS_FEATURE(x) 0 +#endif +#ifdef __has_extension +# define UPRV_HAS_EXTENSION(x) __has_extension(x) +#else +# define UPRV_HAS_EXTENSION(x) 0 +#endif +#ifdef __has_warning +# define UPRV_HAS_WARNING(x) __has_warning(x) +#else +# define UPRV_HAS_WARNING(x) 0 +#endif + +/** + * \def U_MALLOC_ATTR + * Attribute to mark functions as malloc-like + * @internal + */ +#if defined(__GNUC__) && __GNUC__>=3 +# define U_MALLOC_ATTR __attribute__ ((__malloc__)) +#else +# define U_MALLOC_ATTR +#endif + +/** + * \def U_ALLOC_SIZE_ATTR + * Attribute to specify the size of the allocated buffer for malloc-like functions + * @internal + */ +#if (defined(__GNUC__) && \ + (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))) || \ + UPRV_HAS_ATTRIBUTE(alloc_size) +# define U_ALLOC_SIZE_ATTR(X) __attribute__ ((alloc_size(X))) +# define U_ALLOC_SIZE_ATTR2(X,Y) __attribute__ ((alloc_size(X,Y))) +#else +# define U_ALLOC_SIZE_ATTR(X) +# define U_ALLOC_SIZE_ATTR2(X,Y) +#endif + +/** + * \def U_CPLUSPLUS_VERSION + * 0 if no C++; 1, 11, 14, ... if C++. + * Support for specific features cannot always be determined by the C++ version alone. + * @internal + */ +#ifdef U_CPLUSPLUS_VERSION +# if U_CPLUSPLUS_VERSION != 0 && !defined(__cplusplus) +# undef U_CPLUSPLUS_VERSION +# define U_CPLUSPLUS_VERSION 0 +# endif + /* Otherwise use the predefined value. */ +#elif !defined(__cplusplus) +# define U_CPLUSPLUS_VERSION 0 +#elif __cplusplus >= 201402L || (defined(_MSVC_LANG) && _MSVC_LANG >= 201402L) +# define U_CPLUSPLUS_VERSION 14 +#elif __cplusplus >= 201103L || (defined(_MSVC_LANG) && _MSVC_LANG >= 201103L) +# define U_CPLUSPLUS_VERSION 11 +#else + // C++98 or C++03 +# define U_CPLUSPLUS_VERSION 1 +#endif + +#if (U_PLATFORM == U_PF_AIX || U_PLATFORM == U_PF_OS390) && defined(__cplusplus) &&(U_CPLUSPLUS_VERSION < 11) +// add in std::nullptr_t +namespace std { + typedef decltype(nullptr) nullptr_t; +}; +#endif + +/** + * \def U_NOEXCEPT + * "noexcept" if supported, otherwise empty. + * Some code, especially STL containers, uses move semantics of objects only + * if the move constructor and the move operator are declared as not throwing exceptions. + * @internal + */ +#ifdef U_NOEXCEPT + /* Use the predefined value. */ +#else +# define U_NOEXCEPT noexcept +#endif + +/** + * \def U_FALLTHROUGH + * Annotate intentional fall-through between switch labels. + * http://clang.llvm.org/docs/AttributeReference.html#fallthrough-clang-fallthrough + * @internal + */ +#ifndef __cplusplus + // Not for C. +#elif defined(U_FALLTHROUGH) + // Use the predefined value. +#elif defined(__clang__) + // Test for compiler vs. feature separately. + // Other compilers might choke on the feature test. +# if UPRV_HAS_CPP_ATTRIBUTE(clang::fallthrough) || \ + (UPRV_HAS_FEATURE(cxx_attributes) && \ + UPRV_HAS_WARNING("-Wimplicit-fallthrough")) +# define U_FALLTHROUGH [[clang::fallthrough]] +# endif +#elif defined(__GNUC__) && (__GNUC__ >= 7) +# define U_FALLTHROUGH __attribute__((fallthrough)) +#endif + +#ifndef U_FALLTHROUGH +# define U_FALLTHROUGH +#endif + +/** @} */ + +/*===========================================================================*/ +/** @{ Character data types */ +/*===========================================================================*/ + +/** + * U_CHARSET_FAMILY is equal to this value when the platform is an ASCII based platform. + * @stable ICU 2.0 + */ +#define U_ASCII_FAMILY 0 + +/** + * U_CHARSET_FAMILY is equal to this value when the platform is an EBCDIC based platform. + * @stable ICU 2.0 + */ +#define U_EBCDIC_FAMILY 1 + +/** + * \def U_CHARSET_FAMILY + * + * <p>These definitions allow to specify the encoding of text + * in the char data type as defined by the platform and the compiler. + * It is enough to determine the code point values of "invariant characters", + * which are the ones shared by all encodings that are in use + * on a given platform.</p> + * + * <p>Those "invariant characters" should be all the uppercase and lowercase + * latin letters, the digits, the space, and "basic punctuation". + * Also, '\\n', '\\r', '\\t' should be available.</p> + * + * <p>The list of "invariant characters" is:<br> + * \code + * A-Z a-z 0-9 SPACE " % & ' ( ) * + , - . / : ; < = > ? _ + * \endcode + * <br> + * (52 letters + 10 numbers + 20 punc/sym/space = 82 total)</p> + * + * <p>This matches the IBM Syntactic Character Set (CS 640).</p> + * + * <p>In other words, all the graphic characters in 7-bit ASCII should + * be safely accessible except the following:</p> + * + * \code + * '\' <backslash> + * '[' <left bracket> + * ']' <right bracket> + * '{' <left brace> + * '}' <right brace> + * '^' <circumflex> + * '~' <tilde> + * '!' <exclamation mark> + * '#' <number sign> + * '|' <vertical line> + * '$' <dollar sign> + * '@' <commercial at> + * '`' <grave accent> + * \endcode + * @stable ICU 2.0 + */ +#ifdef U_CHARSET_FAMILY + /* Use the predefined value. */ +#elif U_PLATFORM == U_PF_OS390 && (!defined(__CHARSET_LIB) || !__CHARSET_LIB) +# define U_CHARSET_FAMILY U_EBCDIC_FAMILY +#elif U_PLATFORM == U_PF_OS400 && !defined(__UTF32__) +# define U_CHARSET_FAMILY U_EBCDIC_FAMILY +#else +# define U_CHARSET_FAMILY U_ASCII_FAMILY +#endif + +/** + * \def U_CHARSET_IS_UTF8 + * + * Hardcode the default charset to UTF-8. + * + * If this is set to 1, then + * - ICU will assume that all non-invariant char*, StringPiece, std::string etc. + * contain UTF-8 text, regardless of what the system API uses + * - some ICU code will use fast functions like u_strFromUTF8() + * rather than the more general and more heavy-weight conversion API (ucnv.h) + * - ucnv_getDefaultName() always returns "UTF-8" + * - ucnv_setDefaultName() is disabled and will not change the default charset + * - static builds of ICU are smaller + * - more functionality is available with the UCONFIG_NO_CONVERSION build-time + * configuration option (see unicode/uconfig.h) + * - the UCONFIG_NO_CONVERSION build option in uconfig.h is more usable + * + * @stable ICU 4.2 + * @see UCONFIG_NO_CONVERSION + */ +#ifdef U_CHARSET_IS_UTF8 + /* Use the predefined value. */ +#elif U_PLATFORM_IS_LINUX_BASED || U_PLATFORM_IS_DARWIN_BASED || \ + U_PLATFORM == U_PF_EMSCRIPTEN +# define U_CHARSET_IS_UTF8 1 +#else +# define U_CHARSET_IS_UTF8 0 +#endif + +/** @} */ + +/*===========================================================================*/ +/** @{ Information about wchar support */ +/*===========================================================================*/ + +/** + * \def U_HAVE_WCHAR_H + * Indicates whether <wchar.h> is available (1) or not (0). Set to 1 by default. + * + * @stable ICU 2.0 + */ +#ifdef U_HAVE_WCHAR_H + /* Use the predefined value. */ +#elif U_PLATFORM == U_PF_ANDROID && __ANDROID_API__ < 9 + /* + * Android before Gingerbread (Android 2.3, API level 9) did not support wchar_t. + * The type and header existed, but the library functions did not work as expected. + * The size of wchar_t was 1 but L"xyz" string literals had 32-bit units anyway. + */ +# define U_HAVE_WCHAR_H 0 +#else +# define U_HAVE_WCHAR_H 1 +#endif + +/** + * \def U_SIZEOF_WCHAR_T + * U_SIZEOF_WCHAR_T==sizeof(wchar_t) + * + * @stable ICU 2.0 + */ +#ifdef U_SIZEOF_WCHAR_T + /* Use the predefined value. */ +#elif (U_PLATFORM == U_PF_ANDROID && __ANDROID_API__ < 9) + /* + * Classic Mac OS and Mac OS X before 10.3 (Panther) did not support wchar_t or wstring. + * Newer Mac OS X has size 4. + */ +# define U_SIZEOF_WCHAR_T 1 +#elif U_PLATFORM_HAS_WIN32_API || U_PLATFORM == U_PF_CYGWIN +# define U_SIZEOF_WCHAR_T 2 +#elif U_PLATFORM == U_PF_AIX + /* + * AIX 6.1 information, section "Wide character data representation": + * "... the wchar_t datatype is 32-bit in the 64-bit environment and + * 16-bit in the 32-bit environment." + * and + * "All locales use Unicode for their wide character code values (process code), + * except the IBM-eucTW codeset." + */ +# ifdef __64BIT__ +# define U_SIZEOF_WCHAR_T 4 +# else +# define U_SIZEOF_WCHAR_T 2 +# endif +#elif U_PLATFORM == U_PF_OS390 + /* + * z/OS V1R11 information center, section "LP64 | ILP32": + * "In 31-bit mode, the size of long and pointers is 4 bytes and the size of wchar_t is 2 bytes. + * Under LP64, the size of long and pointer is 8 bytes and the size of wchar_t is 4 bytes." + */ +# ifdef _LP64 +# define U_SIZEOF_WCHAR_T 4 +# else +# define U_SIZEOF_WCHAR_T 2 +# endif +#elif U_PLATFORM == U_PF_OS400 +# if defined(__UTF32__) + /* + * LOCALETYPE(*LOCALEUTF) is specified. + * Wide-character strings are in UTF-32, + * narrow-character strings are in UTF-8. + */ +# define U_SIZEOF_WCHAR_T 4 +# elif defined(__UCS2__) + /* + * LOCALETYPE(*LOCALEUCS2) is specified. + * Wide-character strings are in UCS-2, + * narrow-character strings are in EBCDIC. + */ +# define U_SIZEOF_WCHAR_T 2 +# else + /* + * LOCALETYPE(*CLD) or LOCALETYPE(*LOCALE) is specified. + * Wide-character strings are in 16-bit EBCDIC, + * narrow-character strings are in EBCDIC. + */ +# define U_SIZEOF_WCHAR_T 2 +# endif +#else +# define U_SIZEOF_WCHAR_T 4 +#endif + +#ifndef U_HAVE_WCSCPY +#define U_HAVE_WCSCPY U_HAVE_WCHAR_H +#endif + +/** @} */ + +/** + * \def U_HAVE_CHAR16_T + * Defines whether the char16_t type is available for UTF-16 + * and u"abc" UTF-16 string literals are supported. + * This is a new standard type and standard string literal syntax in C++0x + * but has been available in some compilers before. + * @internal + */ +#ifdef U_HAVE_CHAR16_T + /* Use the predefined value. */ +#else + /* + * Notes: + * Visual Studio 2010 (_MSC_VER==1600) defines char16_t as a typedef + * and does not support u"abc" string literals. + * Visual Studio 2015 (_MSC_VER>=1900) and above adds support for + * both char16_t and u"abc" string literals. + * gcc 4.4 defines the __CHAR16_TYPE__ macro to a usable type but + * does not support u"abc" string literals. + * C++11 and C11 require support for UTF-16 literals + * TODO: Fix for plain C. Doesn't work on Mac. + */ +# if U_CPLUSPLUS_VERSION >= 11 || (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L) +# define U_HAVE_CHAR16_T 1 +# else +# define U_HAVE_CHAR16_T 0 +# endif +#endif + +/** + * @{ + * \def U_DECLARE_UTF16 + * Do not use this macro because it is not defined on all platforms. + * Use the UNICODE_STRING or U_STRING_DECL macros instead. + * @internal + */ +#ifdef U_DECLARE_UTF16 + /* Use the predefined value. */ +#elif U_HAVE_CHAR16_T \ + || (defined(__xlC__) && defined(__IBM_UTF_LITERAL) && U_SIZEOF_WCHAR_T != 2) \ + || (defined(__HP_aCC) && __HP_aCC >= 035000) \ + || (defined(__HP_cc) && __HP_cc >= 111106) \ + || (defined(U_IN_DOXYGEN)) +# define U_DECLARE_UTF16(string) u ## string +#elif U_SIZEOF_WCHAR_T == 2 \ + && (U_CHARSET_FAMILY == 0 || (U_PF_OS390 <= U_PLATFORM && U_PLATFORM <= U_PF_OS400 && defined(__UCS2__))) +# define U_DECLARE_UTF16(string) L ## string +#else + /* Leave U_DECLARE_UTF16 undefined. See unistr.h. */ +#endif + +/** @} */ + +/*===========================================================================*/ +/** @{ Symbol import-export control */ +/*===========================================================================*/ + +#ifdef U_EXPORT + /* Use the predefined value. */ +#elif defined(U_STATIC_IMPLEMENTATION) +# define U_EXPORT +#elif defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(dllexport) && \ + UPRV_HAS_DECLSPEC_ATTRIBUTE(dllimport)) +# define U_EXPORT __declspec(dllexport) +#elif defined(__GNUC__) +# define U_EXPORT __attribute__((visibility("default"))) +#elif (defined(__SUNPRO_CC) && __SUNPRO_CC >= 0x550) \ + || (defined(__SUNPRO_C) && __SUNPRO_C >= 0x550) +# define U_EXPORT __global +/*#elif defined(__HP_aCC) || defined(__HP_cc) +# define U_EXPORT __declspec(dllexport)*/ +#else +# define U_EXPORT +#endif + +/* U_CALLCONV is related to U_EXPORT2 */ +#ifdef U_EXPORT2 + /* Use the predefined value. */ +#elif defined(_MSC_VER) +# define U_EXPORT2 __cdecl +#else +# define U_EXPORT2 +#endif + +#ifdef U_IMPORT + /* Use the predefined value. */ +#elif defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(dllexport) && \ + UPRV_HAS_DECLSPEC_ATTRIBUTE(dllimport)) + /* Windows needs to export/import data. */ +# define U_IMPORT __declspec(dllimport) +#else +# define U_IMPORT +#endif + +/** + * \def U_CALLCONV + * Similar to U_CDECL_BEGIN/U_CDECL_END, this qualifier is necessary + * in callback function typedefs to make sure that the calling convention + * is compatible. + * + * This is only used for non-ICU-API functions. + * When a function is a public ICU API, + * you must use the U_CAPI and U_EXPORT2 qualifiers. + * + * Please note, you need to use U_CALLCONV after the *. + * + * NO : "static const char U_CALLCONV *func( . . . )" + * YES: "static const char* U_CALLCONV func( . . . )" + * + * @stable ICU 2.0 + */ +#if U_PLATFORM == U_PF_OS390 && defined(__cplusplus) +# define U_CALLCONV __cdecl +#else +# define U_CALLCONV U_EXPORT2 +#endif + +/** + * \def U_CALLCONV_FPTR + * Similar to U_CALLCONV, but only used on function pointers. + * @internal + */ +#if U_PLATFORM == U_PF_OS390 && defined(__cplusplus) +# define U_CALLCONV_FPTR U_CALLCONV +#else +# define U_CALLCONV_FPTR +#endif +/* @} */ + +#endif // _PLATFORM_H diff --git a/thirdparty/icu4c/common/unicode/ptypes.h b/thirdparty/icu4c/common/unicode/ptypes.h new file mode 100644 index 0000000000..70324ffee3 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ptypes.h @@ -0,0 +1,130 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1997-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* +* FILE NAME : ptypes.h +* +* Date Name Description +* 05/13/98 nos Creation (content moved here from ptypes.h). +* 03/02/99 stephen Added AS400 support. +* 03/30/99 stephen Added Linux support. +* 04/13/99 stephen Reworked for autoconf. +* 09/18/08 srl Moved basic types back to ptypes.h from platform.h +****************************************************************************** +*/ + +/** + * \file + * \brief C API: Definitions of integer types of various widths + */ + +#ifndef _PTYPES_H +#define _PTYPES_H + +/** + * \def __STDC_LIMIT_MACROS + * According to the Linux stdint.h, the ISO C99 standard specifies that in C++ implementations + * macros like INT32_MIN and UINTPTR_MAX should only be defined if explicitly requested. + * We need to define __STDC_LIMIT_MACROS before including stdint.h in C++ code + * that uses such limit macros. + * @internal + */ +#ifndef __STDC_LIMIT_MACROS +#define __STDC_LIMIT_MACROS +#endif + +/* NULL, size_t, wchar_t */ +#include <stddef.h> + +/* + * If all compilers provided all of the C99 headers and types, + * we would just unconditionally #include <stdint.h> here + * and not need any of the stuff after including platform.h. + */ + +/* Find out if we have stdint.h etc. */ +#include "unicode/platform.h" + +/*===========================================================================*/ +/* Generic data types */ +/*===========================================================================*/ + +/* If your platform does not have the <stdint.h> header, you may + need to edit the typedefs in the #else section below. + Use #if...#else...#endif with predefined compiler macros if possible. */ +#if U_HAVE_STDINT_H + +/* + * We mostly need <stdint.h> (which defines the standard integer types) but not <inttypes.h>. + * <inttypes.h> includes <stdint.h> and adds the printf/scanf helpers PRId32, SCNx16 etc. + * which we almost never use, plus stuff like imaxabs() which we never use. + */ +#include <stdint.h> + +#if U_PLATFORM == U_PF_OS390 +/* The features header is needed to get (u)int64_t sometimes. */ +#include <features.h> +/* z/OS has <stdint.h>, but some versions are missing uint8_t (APAR PK62248). */ +#if !defined(__uint8_t) +#define __uint8_t 1 +typedef unsigned char uint8_t; +#endif +#endif /* U_PLATFORM == U_PF_OS390 */ + +#elif U_HAVE_INTTYPES_H + +# include <inttypes.h> + +#else /* neither U_HAVE_STDINT_H nor U_HAVE_INTTYPES_H */ + +/// \cond +#if ! U_HAVE_INT8_T +typedef signed char int8_t; +#endif + +#if ! U_HAVE_UINT8_T +typedef unsigned char uint8_t; +#endif + +#if ! U_HAVE_INT16_T +typedef signed short int16_t; +#endif + +#if ! U_HAVE_UINT16_T +typedef unsigned short uint16_t; +#endif + +#if ! U_HAVE_INT32_T +typedef signed int int32_t; +#endif + +#if ! U_HAVE_UINT32_T +typedef unsigned int uint32_t; +#endif + +#if ! U_HAVE_INT64_T +#ifdef _MSC_VER + typedef signed __int64 int64_t; +#else + typedef signed long long int64_t; +#endif +#endif + +#if ! U_HAVE_UINT64_T +#ifdef _MSC_VER + typedef unsigned __int64 uint64_t; +#else + typedef unsigned long long uint64_t; +#endif +#endif +/// \endcond + +#endif /* U_HAVE_STDINT_H / U_HAVE_INTTYPES_H */ + +#endif /* _PTYPES_H */ diff --git a/thirdparty/icu4c/common/unicode/putil.h b/thirdparty/icu4c/common/unicode/putil.h new file mode 100644 index 0000000000..500c21252f --- /dev/null +++ b/thirdparty/icu4c/common/unicode/putil.h @@ -0,0 +1,183 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1997-2014, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* +* FILE NAME : putil.h +* +* Date Name Description +* 05/14/98 nos Creation (content moved here from utypes.h). +* 06/17/99 erm Added IEEE_754 +* 07/22/98 stephen Added IEEEremainder, max, min, trunc +* 08/13/98 stephen Added isNegativeInfinity, isPositiveInfinity +* 08/24/98 stephen Added longBitsFromDouble +* 03/02/99 stephen Removed openFile(). Added AS400 support. +* 04/15/99 stephen Converted to C +* 11/15/99 helena Integrated S/390 changes for IEEE support. +* 01/11/00 helena Added u_getVersion. +****************************************************************************** +*/ + +#ifndef PUTIL_H +#define PUTIL_H + +#include "unicode/utypes.h" + /** + * \file + * \brief C API: Platform Utilities + */ + +/*==========================================================================*/ +/* Platform utilities */ +/*==========================================================================*/ + +/** + * Platform utilities isolates the platform dependencies of the + * library. For each platform which this code is ported to, these + * functions may have to be re-implemented. + */ + +/** + * Return the ICU data directory. + * The data directory is where common format ICU data files (.dat files) + * are loaded from. Note that normal use of the built-in ICU + * facilities does not require loading of an external data file; + * unless you are adding custom data to ICU, the data directory + * does not need to be set. + * + * The data directory is determined as follows: + * If u_setDataDirectory() has been called, that is it, otherwise + * if the ICU_DATA environment variable is set, use that, otherwise + * If a data directory was specified at ICU build time + * <code> + * \code + * #define ICU_DATA_DIR "path" + * \endcode + * </code> use that, + * otherwise no data directory is available. + * + * @return the data directory, or an empty string ("") if no data directory has + * been specified. + * + * @stable ICU 2.0 + */ +U_CAPI const char* U_EXPORT2 u_getDataDirectory(void); + + +/** + * Set the ICU data directory. + * The data directory is where common format ICU data files (.dat files) + * are loaded from. Note that normal use of the built-in ICU + * facilities does not require loading of an external data file; + * unless you are adding custom data to ICU, the data directory + * does not need to be set. + * + * This function should be called at most once in a process, before the + * first ICU operation (e.g., u_init()) that will require the loading of an + * ICU data file. + * This function is not thread-safe. Use it before calling ICU APIs from + * multiple threads. + * + * @param directory The directory to be set. + * + * @see u_init + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 u_setDataDirectory(const char *directory); + +#ifndef U_HIDE_INTERNAL_API +/** + * Return the time zone files override directory, or an empty string if + * no directory was specified. Certain time zone resources will be preferentially + * loaded from individual files in this directory. + * + * @return the time zone data override directory. + * @internal + */ +U_CAPI const char * U_EXPORT2 u_getTimeZoneFilesDirectory(UErrorCode *status); + +/** + * Set the time zone files override directory. + * This function is not thread safe; it must not be called concurrently with + * u_getTimeZoneFilesDirectory() or any other use of ICU time zone functions. + * This function should only be called before using any ICU service that + * will access the time zone data. + * @internal + */ +U_CAPI void U_EXPORT2 u_setTimeZoneFilesDirectory(const char *path, UErrorCode *status); +#endif /* U_HIDE_INTERNAL_API */ + + +/** + * @{ + * Filesystem file and path separator characters. + * Example: '/' and ':' on Unix, '\\' and ';' on Windows. + * @stable ICU 2.0 + */ +#if U_PLATFORM_USES_ONLY_WIN32_API +# define U_FILE_SEP_CHAR '\\' +# define U_FILE_ALT_SEP_CHAR '/' +# define U_PATH_SEP_CHAR ';' +# define U_FILE_SEP_STRING "\\" +# define U_FILE_ALT_SEP_STRING "/" +# define U_PATH_SEP_STRING ";" +#else +# define U_FILE_SEP_CHAR '/' +# define U_FILE_ALT_SEP_CHAR '/' +# define U_PATH_SEP_CHAR ':' +# define U_FILE_SEP_STRING "/" +# define U_FILE_ALT_SEP_STRING "/" +# define U_PATH_SEP_STRING ":" +#endif + +/** @} */ + +/** + * Convert char characters to UChar characters. + * This utility function is useful only for "invariant characters" + * that are encoded in the platform default encoding. + * They are a small, constant subset of the encoding and include + * just the latin letters, digits, and some punctuation. + * For details, see U_CHARSET_FAMILY. + * + * @param cs Input string, points to <code>length</code> + * character bytes from a subset of the platform encoding. + * @param us Output string, points to memory for <code>length</code> + * Unicode characters. + * @param length The number of characters to convert; this may + * include the terminating <code>NUL</code>. + * + * @see U_CHARSET_FAMILY + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +u_charsToUChars(const char *cs, UChar *us, int32_t length); + +/** + * Convert UChar characters to char characters. + * This utility function is useful only for "invariant characters" + * that can be encoded in the platform default encoding. + * They are a small, constant subset of the encoding and include + * just the latin letters, digits, and some punctuation. + * For details, see U_CHARSET_FAMILY. + * + * @param us Input string, points to <code>length</code> + * Unicode characters that can be encoded with the + * codepage-invariant subset of the platform encoding. + * @param cs Output string, points to memory for <code>length</code> + * character bytes. + * @param length The number of characters to convert; this may + * include the terminating <code>NUL</code>. + * + * @see U_CHARSET_FAMILY + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +u_UCharsToChars(const UChar *us, char *cs, int32_t length); + +#endif diff --git a/thirdparty/icu4c/common/unicode/rbbi.h b/thirdparty/icu4c/common/unicode/rbbi.h new file mode 100644 index 0000000000..65117f616c --- /dev/null +++ b/thirdparty/icu4c/common/unicode/rbbi.h @@ -0,0 +1,732 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +*************************************************************************** +* Copyright (C) 1999-2016 International Business Machines Corporation * +* and others. All rights reserved. * +*************************************************************************** + +********************************************************************** +* Date Name Description +* 10/22/99 alan Creation. +* 11/11/99 rgillam Complete port from Java. +********************************************************************** +*/ + +#ifndef RBBI_H +#define RBBI_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +/** + * \file + * \brief C++ API: Rule Based Break Iterator + */ + +#if !UCONFIG_NO_BREAK_ITERATION + +#include "unicode/brkiter.h" +#include "unicode/udata.h" +#include "unicode/parseerr.h" +#include "unicode/schriter.h" + +struct UCPTrie; + +U_NAMESPACE_BEGIN + +/** @internal */ +class LanguageBreakEngine; +struct RBBIDataHeader; +class RBBIDataWrapper; +class UnhandledEngine; +class UStack; + +/** + * + * A subclass of BreakIterator whose behavior is specified using a list of rules. + * <p>Instances of this class are most commonly created by the factory methods of + * BreakIterator::createWordInstance(), BreakIterator::createLineInstance(), etc., + * and then used via the abstract API in class BreakIterator</p> + * + * <p>See the ICU User Guide for information on Break Iterator Rules.</p> + * + * <p>This class is not intended to be subclassed.</p> + */ +class U_COMMON_API RuleBasedBreakIterator /*U_FINAL*/ : public BreakIterator { + +private: + /** + * The UText through which this BreakIterator accesses the text + * @internal (private) + */ + UText fText; + +#ifndef U_HIDE_INTERNAL_API +public: +#endif /* U_HIDE_INTERNAL_API */ + /** + * The rule data for this BreakIterator instance. + * Not for general use; Public only for testing purposes. + * @internal + */ + RBBIDataWrapper *fData; +private: + + /** + * The current position of the iterator. Pinned, 0 < fPosition <= text.length. + * Never has the value UBRK_DONE (-1). + */ + int32_t fPosition; + + /** + * TODO: + */ + int32_t fRuleStatusIndex; + + /** + * Cache of previously determined boundary positions. + */ + class BreakCache; + BreakCache *fBreakCache; + + /** + * Cache of boundary positions within a region of text that has been + * sub-divided by dictionary based breaking. + */ + class DictionaryCache; + DictionaryCache *fDictionaryCache; + + /** + * + * If present, UStack of LanguageBreakEngine objects that might handle + * dictionary characters. Searched from top to bottom to find an object to + * handle a given character. + * @internal (private) + */ + UStack *fLanguageBreakEngines; + + /** + * + * If present, the special LanguageBreakEngine used for handling + * characters that are in the dictionary set, but not handled by any + * LanguageBreakEngine. + * @internal (private) + */ + UnhandledEngine *fUnhandledBreakEngine; + + /** + * Counter for the number of characters encountered with the "dictionary" + * flag set. + * @internal (private) + */ + uint32_t fDictionaryCharCount; + + /** + * A character iterator that refers to the same text as the UText, above. + * Only included for compatibility with old API, which was based on CharacterIterators. + * Value may be adopted from outside, or one of fSCharIter or fDCharIter, below. + */ + CharacterIterator *fCharIter; + + /** + * When the input text is provided by a UnicodeString, this will point to + * a characterIterator that wraps that data. Needed only for the + * implementation of getText(), a backwards compatibility issue. + */ + StringCharacterIterator fSCharIter; + + /** + * True when iteration has run off the end, and iterator functions should return UBRK_DONE. + */ + UBool fDone; + + /** + * Array of look-ahead tentative results. + */ + int32_t *fLookAheadMatches; + + //======================================================================= + // constructors + //======================================================================= + + /** + * Constructor from a flattened set of RBBI data in malloced memory. + * RulesBasedBreakIterators built from a custom set of rules + * are created via this constructor; the rules are compiled + * into memory, then the break iterator is constructed here. + * + * The break iterator adopts the memory, and will + * free it when done. + * @internal (private) + */ + RuleBasedBreakIterator(RBBIDataHeader* data, UErrorCode &status); + + /** @internal */ + friend class RBBIRuleBuilder; + /** @internal */ + friend class BreakIterator; + +public: + + /** Default constructor. Creates an empty shell of an iterator, with no + * rules or text to iterate over. Object can subsequently be assigned to. + * @stable ICU 2.2 + */ + RuleBasedBreakIterator(); + + /** + * Copy constructor. Will produce a break iterator with the same behavior, + * and which iterates over the same text, as the one passed in. + * @param that The RuleBasedBreakIterator passed to be copied + * @stable ICU 2.0 + */ + RuleBasedBreakIterator(const RuleBasedBreakIterator& that); + + /** + * Construct a RuleBasedBreakIterator from a set of rules supplied as a string. + * @param rules The break rules to be used. + * @param parseError In the event of a syntax error in the rules, provides the location + * within the rules of the problem. + * @param status Information on any errors encountered. + * @stable ICU 2.2 + */ + RuleBasedBreakIterator( const UnicodeString &rules, + UParseError &parseError, + UErrorCode &status); + + /** + * Construct a RuleBasedBreakIterator from a set of precompiled binary rules. + * Binary rules are obtained from RulesBasedBreakIterator::getBinaryRules(). + * Construction of a break iterator in this way is substantially faster than + * construction from source rules. + * + * Ownership of the storage containing the compiled rules remains with the + * caller of this function. The compiled rules must not be modified or + * deleted during the life of the break iterator. + * + * The compiled rules are not compatible across different major versions of ICU. + * The compiled rules are compatible only between machines with the same + * byte ordering (little or big endian) and the same base character set family + * (ASCII or EBCDIC). + * + * @see #getBinaryRules + * @param compiledRules A pointer to the compiled break rules to be used. + * @param ruleLength The length of the compiled break rules, in bytes. This + * corresponds to the length value produced by getBinaryRules(). + * @param status Information on any errors encountered, including invalid + * binary rules. + * @stable ICU 4.8 + */ + RuleBasedBreakIterator(const uint8_t *compiledRules, + uint32_t ruleLength, + UErrorCode &status); + + /** + * This constructor uses the udata interface to create a BreakIterator + * whose internal tables live in a memory-mapped file. "image" is an + * ICU UDataMemory handle for the pre-compiled break iterator tables. + * @param image handle to the memory image for the break iterator data. + * Ownership of the UDataMemory handle passes to the Break Iterator, + * which will be responsible for closing it when it is no longer needed. + * @param status Information on any errors encountered. + * @see udata_open + * @see #getBinaryRules + * @stable ICU 2.8 + */ + RuleBasedBreakIterator(UDataMemory* image, UErrorCode &status); + + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~RuleBasedBreakIterator(); + + /** + * Assignment operator. Sets this iterator to have the same behavior, + * and iterate over the same text, as the one passed in. + * @param that The RuleBasedBreakItertor passed in + * @return the newly created RuleBasedBreakIterator + * @stable ICU 2.0 + */ + RuleBasedBreakIterator& operator=(const RuleBasedBreakIterator& that); + + /** + * Equality operator. Returns true if both BreakIterators are of the + * same class, have the same behavior, and iterate over the same text. + * @param that The BreakIterator to be compared for equality + * @return true if both BreakIterators are of the + * same class, have the same behavior, and iterate over the same text. + * @stable ICU 2.0 + */ + virtual UBool operator==(const BreakIterator& that) const; + + /** + * Not-equal operator. If operator== returns true, this returns false, + * and vice versa. + * @param that The BreakIterator to be compared for inequality + * @return true if both BreakIterators are not same. + * @stable ICU 2.0 + */ + inline UBool operator!=(const BreakIterator& that) const; + + /** + * Returns a newly-constructed RuleBasedBreakIterator with the same + * behavior, and iterating over the same text, as this one. + * Differs from the copy constructor in that it is polymorphic, and + * will correctly clone (copy) a derived class. + * clone() is thread safe. Multiple threads may simultaneously + * clone the same source break iterator. + * @return a newly-constructed RuleBasedBreakIterator + * @stable ICU 2.0 + */ + virtual RuleBasedBreakIterator* clone() const; + + /** + * Compute a hash code for this BreakIterator + * @return A hash code + * @stable ICU 2.0 + */ + virtual int32_t hashCode(void) const; + + /** + * Returns the description used to create this iterator + * @return the description used to create this iterator + * @stable ICU 2.0 + */ + virtual const UnicodeString& getRules(void) const; + + //======================================================================= + // BreakIterator overrides + //======================================================================= + + /** + * <p> + * Return a CharacterIterator over the text being analyzed. + * The returned character iterator is owned by the break iterator, and must + * not be deleted by the caller. Repeated calls to this function may + * return the same CharacterIterator. + * </p> + * <p> + * The returned character iterator must not be used concurrently with + * the break iterator. If concurrent operation is needed, clone the + * returned character iterator first and operate on the clone. + * </p> + * <p> + * When the break iterator is operating on text supplied via a UText, + * this function will fail. Lacking any way to signal failures, it + * returns an CharacterIterator containing no text. + * The function getUText() provides similar functionality, + * is reliable, and is more efficient. + * </p> + * + * TODO: deprecate this function? + * + * @return An iterator over the text being analyzed. + * @stable ICU 2.0 + */ + virtual CharacterIterator& getText(void) const; + + + /** + * Get a UText for the text being analyzed. + * The returned UText is a shallow clone of the UText used internally + * by the break iterator implementation. It can safely be used to + * access the text without impacting any break iterator operations, + * but the underlying text itself must not be altered. + * + * @param fillIn A UText to be filled in. If NULL, a new UText will be + * allocated to hold the result. + * @param status receives any error codes. + * @return The current UText for this break iterator. If an input + * UText was provided, it will always be returned. + * @stable ICU 3.4 + */ + virtual UText *getUText(UText *fillIn, UErrorCode &status) const; + + /** + * Set the iterator to analyze a new piece of text. This function resets + * the current iteration position to the beginning of the text. + * @param newText An iterator over the text to analyze. The BreakIterator + * takes ownership of the character iterator. The caller MUST NOT delete it! + * @stable ICU 2.0 + */ + virtual void adoptText(CharacterIterator* newText); + + /** + * Set the iterator to analyze a new piece of text. This function resets + * the current iteration position to the beginning of the text. + * + * The BreakIterator will retain a reference to the supplied string. + * The caller must not modify or delete the text while the BreakIterator + * retains the reference. + * + * @param newText The text to analyze. + * @stable ICU 2.0 + */ + virtual void setText(const UnicodeString& newText); + + /** + * Reset the break iterator to operate over the text represented by + * the UText. The iterator position is reset to the start. + * + * This function makes a shallow clone of the supplied UText. This means + * that the caller is free to immediately close or otherwise reuse the + * Utext that was passed as a parameter, but that the underlying text itself + * must not be altered while being referenced by the break iterator. + * + * @param text The UText used to change the text. + * @param status Receives any error codes. + * @stable ICU 3.4 + */ + virtual void setText(UText *text, UErrorCode &status); + + /** + * Sets the current iteration position to the beginning of the text, position zero. + * @return The offset of the beginning of the text, zero. + * @stable ICU 2.0 + */ + virtual int32_t first(void); + + /** + * Sets the current iteration position to the end of the text. + * @return The text's past-the-end offset. + * @stable ICU 2.0 + */ + virtual int32_t last(void); + + /** + * Advances the iterator either forward or backward the specified number of steps. + * Negative values move backward, and positive values move forward. This is + * equivalent to repeatedly calling next() or previous(). + * @param n The number of steps to move. The sign indicates the direction + * (negative is backwards, and positive is forwards). + * @return The character offset of the boundary position n boundaries away from + * the current one. + * @stable ICU 2.0 + */ + virtual int32_t next(int32_t n); + + /** + * Advances the iterator to the next boundary position. + * @return The position of the first boundary after this one. + * @stable ICU 2.0 + */ + virtual int32_t next(void); + + /** + * Moves the iterator backwards, to the last boundary preceding this one. + * @return The position of the last boundary position preceding this one. + * @stable ICU 2.0 + */ + virtual int32_t previous(void); + + /** + * Sets the iterator to refer to the first boundary position following + * the specified position. + * @param offset The position from which to begin searching for a break position. + * @return The position of the first break after the current position. + * @stable ICU 2.0 + */ + virtual int32_t following(int32_t offset); + + /** + * Sets the iterator to refer to the last boundary position before the + * specified position. + * @param offset The position to begin searching for a break from. + * @return The position of the last boundary before the starting position. + * @stable ICU 2.0 + */ + virtual int32_t preceding(int32_t offset); + + /** + * Returns true if the specified position is a boundary position. As a side + * effect, leaves the iterator pointing to the first boundary position at + * or after "offset". + * @param offset the offset to check. + * @return True if "offset" is a boundary position. + * @stable ICU 2.0 + */ + virtual UBool isBoundary(int32_t offset); + + /** + * Returns the current iteration position. Note that UBRK_DONE is never + * returned from this function; if iteration has run to the end of a + * string, current() will return the length of the string while + * next() will return UBRK_DONE). + * @return The current iteration position. + * @stable ICU 2.0 + */ + virtual int32_t current(void) const; + + + /** + * Return the status tag from the break rule that determined the boundary at + * the current iteration position. For break rules that do not specify a + * status, a default value of 0 is returned. If more than one break rule + * would cause a boundary to be located at some position in the text, + * the numerically largest of the applicable status values is returned. + * <p> + * Of the standard types of ICU break iterators, only word break and + * line break provide status values. The values are defined in + * the header file ubrk.h. For Word breaks, the status allows distinguishing between words + * that contain alphabetic letters, "words" that appear to be numbers, + * punctuation and spaces, words containing ideographic characters, and + * more. For Line Break, the status distinguishes between hard (mandatory) breaks + * and soft (potential) break positions. + * <p> + * <code>getRuleStatus()</code> can be called after obtaining a boundary + * position from <code>next()</code>, <code>previous()</code>, or + * any other break iterator functions that returns a boundary position. + * <p> + * Note that <code>getRuleStatus()</code> returns the value corresponding to + * <code>current()</code> index even after <code>next()</code> has returned DONE. + * <p> + * When creating custom break rules, one is free to define whatever + * status values may be convenient for the application. + * <p> + * @return the status from the break rule that determined the boundary + * at the current iteration position. + * + * @see UWordBreak + * @stable ICU 2.2 + */ + virtual int32_t getRuleStatus() const; + + /** + * Get the status (tag) values from the break rule(s) that determined the boundary + * at the current iteration position. + * <p> + * The returned status value(s) are stored into an array provided by the caller. + * The values are stored in sorted (ascending) order. + * If the capacity of the output array is insufficient to hold the data, + * the output will be truncated to the available length, and a + * U_BUFFER_OVERFLOW_ERROR will be signaled. + * + * @param fillInVec an array to be filled in with the status values. + * @param capacity the length of the supplied vector. A length of zero causes + * the function to return the number of status values, in the + * normal way, without attempting to store any values. + * @param status receives error codes. + * @return The number of rule status values from the rules that determined + * the boundary at the current iteration position. + * In the event of a U_BUFFER_OVERFLOW_ERROR, the return value + * is the total number of status values that were available, + * not the reduced number that were actually returned. + * @see getRuleStatus + * @stable ICU 3.0 + */ + virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status); + + /** + * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. + * This method is to implement a simple version of RTTI, since not all + * C++ compilers support genuine RTTI. Polymorphic operator==() and + * clone() methods call this method. + * + * @return The class ID for this object. All objects of a + * given class have the same class ID. Objects of + * other classes have different class IDs. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + + /** + * Returns the class ID for this class. This is useful only for + * comparing to a return value from getDynamicClassID(). For example: + * + * Base* polymorphic_pointer = createPolymorphicObject(); + * if (polymorphic_pointer->getDynamicClassID() == + * Derived::getStaticClassID()) ... + * + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + +#ifndef U_FORCE_HIDE_DEPRECATED_API + /** + * Deprecated functionality. Use clone() instead. + * + * Create a clone (copy) of this break iterator in memory provided + * by the caller. The idea is to increase performance by avoiding + * a storage allocation. Use of this function is NOT RECOMMENDED. + * Performance gains are minimal, and correct buffer management is + * tricky. Use clone() instead. + * + * @param stackBuffer The pointer to the memory into which the cloned object + * should be placed. If NULL, allocate heap memory + * for the cloned object. + * @param BufferSize The size of the buffer. If zero, return the required + * buffer size, but do not clone the object. If the + * size was too small (but not zero), allocate heap + * storage for the cloned object. + * + * @param status Error status. U_SAFECLONE_ALLOCATED_WARNING will be + * returned if the provided buffer was too small, and + * the clone was therefore put on the heap. + * + * @return Pointer to the clone object. This may differ from the stackBuffer + * address if the byte alignment of the stack buffer was not suitable + * or if the stackBuffer was too small to hold the clone. + * @deprecated ICU 52. Use clone() instead. + */ + virtual RuleBasedBreakIterator *createBufferClone(void *stackBuffer, + int32_t &BufferSize, + UErrorCode &status); +#endif // U_FORCE_HIDE_DEPRECATED_API + + /** + * Return the binary form of compiled break rules, + * which can then be used to create a new break iterator at some + * time in the future. Creating a break iterator from pre-compiled rules + * is much faster than building one from the source form of the + * break rules. + * + * The binary data can only be used with the same version of ICU + * and on the same platform type (processor endian-ness) + * + * @param length Returns the length of the binary data. (Out parameter.) + * + * @return A pointer to the binary (compiled) rule data. The storage + * belongs to the RulesBasedBreakIterator object, not the + * caller, and must not be modified or deleted. + * @stable ICU 4.8 + */ + virtual const uint8_t *getBinaryRules(uint32_t &length); + + /** + * Set the subject text string upon which the break iterator is operating + * without changing any other aspect of the matching state. + * The new and previous text strings must have the same content. + * + * This function is intended for use in environments where ICU is operating on + * strings that may move around in memory. It provides a mechanism for notifying + * ICU that the string has been relocated, and providing a new UText to access the + * string in its new position. + * + * Note that the break iterator implementation never copies the underlying text + * of a string being processed, but always operates directly on the original text + * provided by the user. Refreshing simply drops the references to the old text + * and replaces them with references to the new. + * + * Caution: this function is normally used only by very specialized, + * system-level code. One example use case is with garbage collection that moves + * the text in memory. + * + * @param input The new (moved) text string. + * @param status Receives errors detected by this function. + * @return *this + * + * @stable ICU 49 + */ + virtual RuleBasedBreakIterator &refreshInputText(UText *input, UErrorCode &status); + + +private: + //======================================================================= + // implementation + //======================================================================= + /** + * Dumps caches and performs other actions associated with a complete change + * in text or iteration position. + * @internal (private) + */ + void reset(void); + + /** + * Common initialization function, used by constructors and bufferClone. + * @internal (private) + */ + void init(UErrorCode &status); + + /** + * Iterate backwards from an arbitrary position in the input text using the + * synthesized Safe Reverse rules. + * This locates a "Safe Position" from which the forward break rules + * will operate correctly. A Safe Position is not necessarily a boundary itself. + * + * @param fromPosition the position in the input text to begin the iteration. + * @internal (private) + */ + int32_t handleSafePrevious(int32_t fromPosition); + + /** + * Find a rule-based boundary by running the state machine. + * Input + * fPosition, the position in the text to begin from. + * Output + * fPosition: the boundary following the starting position. + * fDictionaryCharCount the number of dictionary characters encountered. + * If > 0, the segment will be further subdivided + * fRuleStatusIndex Info from the state table indicating which rules caused the boundary. + * + * @internal (private) + */ + int32_t handleNext(); + + /* + * Templatized version of handleNext() and handleSafePrevious(). + * + * There will be exactly four instantiations, two each for 8 and 16 bit tables, + * two each for 8 and 16 bit trie. + * Having separate instantiations for the table types keeps conditional tests of + * the table type out of the inner loops, at the expense of replicated code. + * + * The template parameter for the Trie access function is a value, not a type. + * Doing it this way, the compiler will inline the Trie function in the + * expanded functions. (Both the 8 and 16 bit access functions have the same type + * signature) + */ + + typedef uint16_t (*PTrieFunc)(const UCPTrie *, UChar32); + + template<typename RowType, PTrieFunc trieFunc> + int32_t handleSafePrevious(int32_t fromPosition); + + template<typename RowType, PTrieFunc trieFunc> + int32_t handleNext(); + + + /** + * This function returns the appropriate LanguageBreakEngine for a + * given character c. + * @param c A character in the dictionary set + * @internal (private) + */ + const LanguageBreakEngine *getLanguageBreakEngine(UChar32 c); + + public: +#ifndef U_HIDE_INTERNAL_API + /** + * Debugging function only. + * @internal + */ + void dumpCache(); + + /** + * Debugging function only. + * @internal + */ + void dumpTables(); +#endif /* U_HIDE_INTERNAL_API */ +}; + +//------------------------------------------------------------------------------ +// +// Inline Functions Definitions ... +// +//------------------------------------------------------------------------------ + +inline UBool RuleBasedBreakIterator::operator!=(const BreakIterator& that) const { + return !operator==(that); +} + +U_NAMESPACE_END + +#endif /* #if !UCONFIG_NO_BREAK_ITERATION */ + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/rep.h b/thirdparty/icu4c/common/unicode/rep.h new file mode 100644 index 0000000000..6dd4530647 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/rep.h @@ -0,0 +1,266 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +************************************************************************** +* Copyright (C) 1999-2012, International Business Machines Corporation and +* others. All Rights Reserved. +************************************************************************** +* Date Name Description +* 11/17/99 aliu Creation. Ported from java. Modified to +* match current UnicodeString API. Forced +* to use name "handleReplaceBetween" because +* of existing methods in UnicodeString. +************************************************************************** +*/ + +#ifndef REP_H +#define REP_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: Replaceable String + */ + +U_NAMESPACE_BEGIN + +class UnicodeString; + +/** + * <code>Replaceable</code> is an abstract base class representing a + * string of characters that supports the replacement of a range of + * itself with a new string of characters. It is used by APIs that + * change a piece of text while retaining metadata. Metadata is data + * other than the Unicode characters returned by char32At(). One + * example of metadata is style attributes; another is an edit + * history, marking each character with an author and revision number. + * + * <p>An implicit aspect of the <code>Replaceable</code> API is that + * during a replace operation, new characters take on the metadata of + * the old characters. For example, if the string "the <b>bold</b> + * font" has range (4, 8) replaced with "strong", then it becomes "the + * <b>strong</b> font". + * + * <p><code>Replaceable</code> specifies ranges using a start + * offset and a limit offset. The range of characters thus specified + * includes the characters at offset start..limit-1. That is, the + * start offset is inclusive, and the limit offset is exclusive. + * + * <p><code>Replaceable</code> also includes API to access characters + * in the string: <code>length()</code>, <code>charAt()</code>, + * <code>char32At()</code>, and <code>extractBetween()</code>. + * + * <p>For a subclass to support metadata, typical behavior of + * <code>replace()</code> is the following: + * <ul> + * <li>Set the metadata of the new text to the metadata of the first + * character replaced</li> + * <li>If no characters are replaced, use the metadata of the + * previous character</li> + * <li>If there is no previous character (i.e. start == 0), use the + * following character</li> + * <li>If there is no following character (i.e. the replaceable was + * empty), use default metadata.<br> + * <li>If the code point U+FFFF is seen, it should be interpreted as + * a special marker having no metadata<li> + * </li> + * </ul> + * If this is not the behavior, the subclass should document any differences. + * @author Alan Liu + * @stable ICU 2.0 + */ +class U_COMMON_API Replaceable : public UObject { + +public: + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~Replaceable(); + + /** + * Returns the number of 16-bit code units in the text. + * @return number of 16-bit code units in text + * @stable ICU 1.8 + */ + inline int32_t length() const; + + /** + * Returns the 16-bit code unit at the given offset into the text. + * @param offset an integer between 0 and <code>length()</code>-1 + * inclusive + * @return 16-bit code unit of text at given offset + * @stable ICU 1.8 + */ + inline char16_t charAt(int32_t offset) const; + + /** + * Returns the 32-bit code point at the given 16-bit offset into + * the text. This assumes the text is stored as 16-bit code units + * with surrogate pairs intermixed. If the offset of a leading or + * trailing code unit of a surrogate pair is given, return the + * code point of the surrogate pair. + * + * @param offset an integer between 0 and <code>length()</code>-1 + * inclusive + * @return 32-bit code point of text at given offset + * @stable ICU 1.8 + */ + inline UChar32 char32At(int32_t offset) const; + + /** + * Copies characters in the range [<tt>start</tt>, <tt>limit</tt>) + * into the UnicodeString <tt>target</tt>. + * @param start offset of first character which will be copied + * @param limit offset immediately following the last character to + * be copied + * @param target UnicodeString into which to copy characters. + * @return A reference to <TT>target</TT> + * @stable ICU 2.1 + */ + virtual void extractBetween(int32_t start, + int32_t limit, + UnicodeString& target) const = 0; + + /** + * Replaces a substring of this object with the given text. If the + * characters being replaced have metadata, the new characters + * that replace them should be given the same metadata. + * + * <p>Subclasses must ensure that if the text between start and + * limit is equal to the replacement text, that replace has no + * effect. That is, any metadata + * should be unaffected. In addition, subclasses are encouraged to + * check for initial and trailing identical characters, and make a + * smaller replacement if possible. This will preserve as much + * metadata as possible. + * @param start the beginning index, inclusive; <code>0 <= start + * <= limit</code>. + * @param limit the ending index, exclusive; <code>start <= limit + * <= length()</code>. + * @param text the text to replace characters <code>start</code> + * to <code>limit - 1</code> + * @stable ICU 2.0 + */ + virtual void handleReplaceBetween(int32_t start, + int32_t limit, + const UnicodeString& text) = 0; + // Note: All other methods in this class take the names of + // existing UnicodeString methods. This method is the exception. + // It is named differently because all replace methods of + // UnicodeString return a UnicodeString&. The 'between' is + // required in order to conform to the UnicodeString naming + // convention; API taking start/length are named <operation>, and + // those taking start/limit are named <operationBetween>. The + // 'handle' is added because 'replaceBetween' and + // 'doReplaceBetween' are already taken. + + /** + * Copies a substring of this object, retaining metadata. + * This method is used to duplicate or reorder substrings. + * The destination index must not overlap the source range. + * + * @param start the beginning index, inclusive; <code>0 <= start <= + * limit</code>. + * @param limit the ending index, exclusive; <code>start <= limit <= + * length()</code>. + * @param dest the destination index. The characters from + * <code>start..limit-1</code> will be copied to <code>dest</code>. + * Implementations of this method may assume that <code>dest <= start || + * dest >= limit</code>. + * @stable ICU 2.0 + */ + virtual void copy(int32_t start, int32_t limit, int32_t dest) = 0; + + /** + * Returns true if this object contains metadata. If a + * Replaceable object has metadata, calls to the Replaceable API + * must be made so as to preserve metadata. If it does not, calls + * to the Replaceable API may be optimized to improve performance. + * The default implementation returns true. + * @return true if this object contains metadata + * @stable ICU 2.2 + */ + virtual UBool hasMetaData() const; + + /** + * Clone this object, an instance of a subclass of Replaceable. + * Clones can be used concurrently in multiple threads. + * If a subclass does not implement clone(), or if an error occurs, + * then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see getDynamicClassID + * @stable ICU 2.6 + */ + virtual Replaceable *clone() const; + +protected: + + /** + * Default constructor. + * @stable ICU 2.4 + */ + inline Replaceable(); + + /* + * Assignment operator not declared. The compiler will provide one + * which does nothing since this class does not contain any data members. + * API/code coverage may show the assignment operator as present and + * untested - ignore. + * Subclasses need this assignment operator if they use compiler-provided + * assignment operators of their own. An alternative to not declaring one + * here would be to declare and empty-implement a protected or public one. + Replaceable &Replaceable::operator=(const Replaceable &); + */ + + /** + * Virtual version of length(). + * @stable ICU 2.4 + */ + virtual int32_t getLength() const = 0; + + /** + * Virtual version of charAt(). + * @stable ICU 2.4 + */ + virtual char16_t getCharAt(int32_t offset) const = 0; + + /** + * Virtual version of char32At(). + * @stable ICU 2.4 + */ + virtual UChar32 getChar32At(int32_t offset) const = 0; +}; + +inline Replaceable::Replaceable() {} + +inline int32_t +Replaceable::length() const { + return getLength(); +} + +inline char16_t +Replaceable::charAt(int32_t offset) const { + return getCharAt(offset); +} + +inline UChar32 +Replaceable::char32At(int32_t offset) const { + return getChar32At(offset); +} + +// There is no rep.cpp, see unistr.cpp for Replaceable function implementations. + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/resbund.h b/thirdparty/icu4c/common/unicode/resbund.h new file mode 100644 index 0000000000..37738e277b --- /dev/null +++ b/thirdparty/icu4c/common/unicode/resbund.h @@ -0,0 +1,498 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1996-2013, International Business Machines Corporation +* and others. All Rights Reserved. +* +****************************************************************************** +* +* File resbund.h +* +* CREATED BY +* Richard Gillam +* +* Modification History: +* +* Date Name Description +* 2/5/97 aliu Added scanForLocaleInFile. Added +* constructor which attempts to read resource bundle +* from a specific file, without searching other files. +* 2/11/97 aliu Added UErrorCode return values to constructors. Fixed +* infinite loops in scanForFile and scanForLocale. +* Modified getRawResourceData to not delete storage +* in localeData and resourceData which it doesn't own. +* Added Mac compatibility #ifdefs for tellp() and +* ios::nocreate. +* 2/18/97 helena Updated with 100% documentation coverage. +* 3/13/97 aliu Rewrote to load in entire resource bundle and store +* it as a Hashtable of ResourceBundleData objects. +* Added state table to govern parsing of files. +* Modified to load locale index out of new file +* distinct from default.txt. +* 3/25/97 aliu Modified to support 2-d arrays, needed for timezone +* data. Added support for custom file suffixes. Again, +* needed to support timezone data. +* 4/7/97 aliu Cleaned up. +* 03/02/99 stephen Removed dependency on FILE*. +* 03/29/99 helena Merged Bertrand and Stephen's changes. +* 06/11/99 stephen Removed parsing of .txt files. +* Reworked to use new binary format. +* Cleaned up. +* 06/14/99 stephen Removed methods taking a filename suffix. +* 11/09/99 weiv Added getLocale(), fRealLocale, removed fRealLocaleID +****************************************************************************** +*/ + +#ifndef RESBUND_H +#define RESBUND_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" +#include "unicode/ures.h" +#include "unicode/unistr.h" +#include "unicode/locid.h" + +/** + * \file + * \brief C++ API: Resource Bundle + */ + +U_NAMESPACE_BEGIN + +/** + * A class representing a collection of resource information pertaining to a given + * locale. A resource bundle provides a way of accessing locale- specfic information in + * a data file. You create a resource bundle that manages the resources for a given + * locale and then ask it for individual resources. + * <P> + * Resource bundles in ICU4C are currently defined using text files which conform to the following + * <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/bnf_rb.txt">BNF definition</a>. + * More on resource bundle concepts and syntax can be found in the + * <a href="http://icu-project.org/userguide/ResourceManagement.html">Users Guide</a>. + * <P> + * + * The ResourceBundle class is not suitable for subclassing. + * + * @stable ICU 2.0 + */ +class U_COMMON_API ResourceBundle : public UObject { +public: + /** + * Constructor + * + * @param packageName The packageName and locale together point to an ICU udata object, + * as defined by <code> udata_open( packageName, "res", locale, err) </code> + * or equivalent. Typically, packageName will refer to a (.dat) file, or to + * a package registered with udata_setAppData(). Using a full file or directory + * pathname for packageName is deprecated. + * @param locale This is the locale this resource bundle is for. To get resources + * for the French locale, for example, you would create a + * ResourceBundle passing Locale::FRENCH for the "locale" parameter, + * and all subsequent calls to that resource bundle will return + * resources that pertain to the French locale. If the caller doesn't + * pass a locale parameter, the default locale for the system (as + * returned by Locale::getDefault()) will be used. + * @param err The Error Code. + * The UErrorCode& err parameter is used to return status information to the user. To + * check whether the construction succeeded or not, you should check the value of + * U_SUCCESS(err). If you wish more detailed information, you can check for + * informational error results which still indicate success. U_USING_FALLBACK_WARNING + * indicates that a fall back locale was used. For example, 'de_CH' was requested, + * but nothing was found there, so 'de' was used. U_USING_DEFAULT_WARNING indicates that + * the default locale data was used; neither the requested locale nor any of its + * fall back locales could be found. + * @stable ICU 2.0 + */ + ResourceBundle(const UnicodeString& packageName, + const Locale& locale, + UErrorCode& err); + + /** + * Construct a resource bundle for the default bundle in the specified package. + * + * @param packageName The packageName and locale together point to an ICU udata object, + * as defined by <code> udata_open( packageName, "res", locale, err) </code> + * or equivalent. Typically, packageName will refer to a (.dat) file, or to + * a package registered with udata_setAppData(). Using a full file or directory + * pathname for packageName is deprecated. + * @param err A UErrorCode value + * @stable ICU 2.0 + */ + ResourceBundle(const UnicodeString& packageName, + UErrorCode& err); + + /** + * Construct a resource bundle for the ICU default bundle. + * + * @param err A UErrorCode value + * @stable ICU 2.0 + */ + ResourceBundle(UErrorCode &err); + + /** + * Standard constructor, constructs a resource bundle for the locale-specific + * bundle in the specified package. + * + * @param packageName The packageName and locale together point to an ICU udata object, + * as defined by <code> udata_open( packageName, "res", locale, err) </code> + * or equivalent. Typically, packageName will refer to a (.dat) file, or to + * a package registered with udata_setAppData(). Using a full file or directory + * pathname for packageName is deprecated. + * NULL is used to refer to ICU data. + * @param locale The locale for which to open a resource bundle. + * @param err A UErrorCode value + * @stable ICU 2.0 + */ + ResourceBundle(const char* packageName, + const Locale& locale, + UErrorCode& err); + + /** + * Copy constructor. + * + * @param original The resource bundle to copy. + * @stable ICU 2.0 + */ + ResourceBundle(const ResourceBundle &original); + + /** + * Constructor from a C UResourceBundle. The resource bundle is + * copied and not adopted. ures_close will still need to be used on the + * original resource bundle. + * + * @param res A pointer to the C resource bundle. + * @param status A UErrorCode value. + * @stable ICU 2.0 + */ + ResourceBundle(UResourceBundle *res, + UErrorCode &status); + + /** + * Assignment operator. + * + * @param other The resource bundle to copy. + * @stable ICU 2.0 + */ + ResourceBundle& + operator=(const ResourceBundle& other); + + /** Destructor. + * @stable ICU 2.0 + */ + virtual ~ResourceBundle(); + + /** + * Clone this object. + * Clones can be used concurrently in multiple threads. + * If an error occurs, then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see getDynamicClassID + * @stable ICU 2.8 + */ + ResourceBundle *clone() const; + + /** + * Returns the size of a resource. Size for scalar types is always 1, and for vector/table types is + * the number of child resources. + * @warning Integer array is treated as a scalar type. There are no + * APIs to access individual members of an integer array. It + * is always returned as a whole. + * + * @return number of resources in a given resource. + * @stable ICU 2.0 + */ + int32_t + getSize(void) const; + + /** + * returns a string from a string resource type + * + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a warning + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return a pointer to a zero-terminated char16_t array which lives in a memory mapped/DLL file. + * @stable ICU 2.0 + */ + UnicodeString + getString(UErrorCode& status) const; + + /** + * returns a binary data from a resource. Can be used at most primitive resource types (binaries, + * strings, ints) + * + * @param len fills in the length of resulting byte chunk + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a warning + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return a pointer to a chunk of unsigned bytes which live in a memory mapped/DLL file. + * @stable ICU 2.0 + */ + const uint8_t* + getBinary(int32_t& len, UErrorCode& status) const; + + + /** + * returns an integer vector from a resource. + * + * @param len fills in the length of resulting integer vector + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a warning + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return a pointer to a vector of integers that lives in a memory mapped/DLL file. + * @stable ICU 2.0 + */ + const int32_t* + getIntVector(int32_t& len, UErrorCode& status) const; + + /** + * returns an unsigned integer from a resource. + * This integer is originally 28 bits. + * + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a warning + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return an unsigned integer value + * @stable ICU 2.0 + */ + uint32_t + getUInt(UErrorCode& status) const; + + /** + * returns a signed integer from a resource. + * This integer is originally 28 bit and the sign gets propagated. + * + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a warning + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return a signed integer value + * @stable ICU 2.0 + */ + int32_t + getInt(UErrorCode& status) const; + + /** + * Checks whether the resource has another element to iterate over. + * + * @return true if there are more elements, false if there is no more elements + * @stable ICU 2.0 + */ + UBool + hasNext(void) const; + + /** + * Resets the internal context of a resource so that iteration starts from the first element. + * + * @stable ICU 2.0 + */ + void + resetIterator(void); + + /** + * Returns the key associated with this resource. Not all the resources have a key - only + * those that are members of a table. + * + * @return a key associated to this resource, or NULL if it doesn't have a key + * @stable ICU 2.0 + */ + const char* + getKey(void) const; + + /** + * Gets the locale ID of the resource bundle as a string. + * Same as getLocale().getName() . + * + * @return the locale ID of the resource bundle as a string + * @stable ICU 2.0 + */ + const char* + getName(void) const; + + + /** + * Returns the type of a resource. Available types are defined in enum UResType + * + * @return type of the given resource. + * @stable ICU 2.0 + */ + UResType + getType(void) const; + + /** + * Returns the next resource in a given resource or NULL if there are no more resources + * + * @param status fills in the outgoing error code + * @return ResourceBundle object. + * @stable ICU 2.0 + */ + ResourceBundle + getNext(UErrorCode& status); + + /** + * Returns the next string in a resource or NULL if there are no more resources + * to iterate over. + * + * @param status fills in the outgoing error code + * @return an UnicodeString object. + * @stable ICU 2.0 + */ + UnicodeString + getNextString(UErrorCode& status); + + /** + * Returns the next string in a resource or NULL if there are no more resources + * to iterate over. + * + * @param key fill in for key associated with this string + * @param status fills in the outgoing error code + * @return an UnicodeString object. + * @stable ICU 2.0 + */ + UnicodeString + getNextString(const char ** key, + UErrorCode& status); + + /** + * Returns the resource in a resource at the specified index. + * + * @param index an index to the wanted resource. + * @param status fills in the outgoing error code + * @return ResourceBundle object. If there is an error, resource is invalid. + * @stable ICU 2.0 + */ + ResourceBundle + get(int32_t index, + UErrorCode& status) const; + + /** + * Returns the string in a given resource at the specified index. + * + * @param index an index to the wanted string. + * @param status fills in the outgoing error code + * @return an UnicodeString object. If there is an error, string is bogus + * @stable ICU 2.0 + */ + UnicodeString + getStringEx(int32_t index, + UErrorCode& status) const; + + /** + * Returns a resource in a resource that has a given key. This procedure works only with table + * resources. + * + * @param key a key associated with the wanted resource + * @param status fills in the outgoing error code. + * @return ResourceBundle object. If there is an error, resource is invalid. + * @stable ICU 2.0 + */ + ResourceBundle + get(const char* key, + UErrorCode& status) const; + + /** + * Returns a string in a resource that has a given key. This procedure works only with table + * resources. + * + * @param key a key associated with the wanted string + * @param status fills in the outgoing error code + * @return an UnicodeString object. If there is an error, string is bogus + * @stable ICU 2.0 + */ + UnicodeString + getStringEx(const char* key, + UErrorCode& status) const; + +#ifndef U_HIDE_DEPRECATED_API + /** + * Return the version number associated with this ResourceBundle as a string. Please + * use getVersion, as this method is going to be deprecated. + * + * @return A version number string as specified in the resource bundle or its parent. + * The caller does not own this string. + * @see getVersion + * @deprecated ICU 2.8 Use getVersion instead. + */ + const char* + getVersionNumber(void) const; +#endif /* U_HIDE_DEPRECATED_API */ + + /** + * Return the version number associated with this ResourceBundle as a UVersionInfo array. + * + * @param versionInfo A UVersionInfo array that is filled with the version number + * as specified in the resource bundle or its parent. + * @stable ICU 2.0 + */ + void + getVersion(UVersionInfo versionInfo) const; + +#ifndef U_HIDE_DEPRECATED_API + /** + * Return the Locale associated with this ResourceBundle. + * + * @return a Locale object + * @deprecated ICU 2.8 Use getLocale(ULocDataLocaleType type, UErrorCode &status) overload instead. + */ + const Locale& + getLocale(void) const; +#endif /* U_HIDE_DEPRECATED_API */ + + /** + * Return the Locale associated with this ResourceBundle. + * @param type You can choose between requested, valid and actual + * locale. For description see the definition of + * ULocDataLocaleType in uloc.h + * @param status just for catching illegal arguments + * + * @return a Locale object + * @stable ICU 2.8 + */ + const Locale + getLocale(ULocDataLocaleType type, UErrorCode &status) const; +#ifndef U_HIDE_INTERNAL_API + /** + * This API implements multilevel fallback + * @internal + */ + ResourceBundle + getWithFallback(const char* key, UErrorCode& status); +#endif /* U_HIDE_INTERNAL_API */ + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + +private: + ResourceBundle(); // default constructor not implemented + + UResourceBundle *fResource; + void constructForLocale(const UnicodeString& path, const Locale& locale, UErrorCode& error); + Locale *fLocale; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/schriter.h b/thirdparty/icu4c/common/unicode/schriter.h new file mode 100644 index 0000000000..1ca5b70fca --- /dev/null +++ b/thirdparty/icu4c/common/unicode/schriter.h @@ -0,0 +1,195 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1998-2005, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* +* File schriter.h +* +* Modification History: +* +* Date Name Description +* 05/05/99 stephen Cleaned up. +****************************************************************************** +*/ + +#ifndef SCHRITER_H +#define SCHRITER_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/chariter.h" +#include "unicode/uchriter.h" + +/** + * \file + * \brief C++ API: String Character Iterator + */ + +U_NAMESPACE_BEGIN +/** + * A concrete subclass of CharacterIterator that iterates over the + * characters (code units or code points) in a UnicodeString. + * It's possible not only to create an + * iterator that iterates over an entire UnicodeString, but also to + * create one that iterates over only a subrange of a UnicodeString + * (iterators over different subranges of the same UnicodeString don't + * compare equal). + * @see CharacterIterator + * @see ForwardCharacterIterator + * @stable ICU 2.0 + */ +class U_COMMON_API StringCharacterIterator : public UCharCharacterIterator { +public: + /** + * Create an iterator over the UnicodeString referred to by "textStr". + * The UnicodeString object is copied. + * The iteration range is the whole string, and the starting position is 0. + * @param textStr The unicode string used to create an iterator + * @stable ICU 2.0 + */ + StringCharacterIterator(const UnicodeString& textStr); + + /** + * Create an iterator over the UnicodeString referred to by "textStr". + * The iteration range is the whole string, and the starting + * position is specified by "textPos". If "textPos" is outside the valid + * iteration range, the behavior of this object is undefined. + * @param textStr The unicode string used to create an iterator + * @param textPos The starting position of the iteration + * @stable ICU 2.0 + */ + StringCharacterIterator(const UnicodeString& textStr, + int32_t textPos); + + /** + * Create an iterator over the UnicodeString referred to by "textStr". + * The UnicodeString object is copied. + * The iteration range begins with the code unit specified by + * "textBegin" and ends with the code unit BEFORE the code unit specified + * by "textEnd". The starting position is specified by "textPos". If + * "textBegin" and "textEnd" don't form a valid range on "text" (i.e., + * textBegin >= textEnd or either is negative or greater than text.size()), + * or "textPos" is outside the range defined by "textBegin" and "textEnd", + * the behavior of this iterator is undefined. + * @param textStr The unicode string used to create the StringCharacterIterator + * @param textBegin The begin position of the iteration range + * @param textEnd The end position of the iteration range + * @param textPos The starting position of the iteration + * @stable ICU 2.0 + */ + StringCharacterIterator(const UnicodeString& textStr, + int32_t textBegin, + int32_t textEnd, + int32_t textPos); + + /** + * Copy constructor. The new iterator iterates over the same range + * of the same string as "that", and its initial position is the + * same as "that"'s current position. + * The UnicodeString object in "that" is copied. + * @param that The StringCharacterIterator to be copied + * @stable ICU 2.0 + */ + StringCharacterIterator(const StringCharacterIterator& that); + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~StringCharacterIterator(); + + /** + * Assignment operator. *this is altered to iterate over the same + * range of the same string as "that", and refers to the same + * character within that string as "that" does. + * @param that The object to be copied. + * @return the newly created object. + * @stable ICU 2.0 + */ + StringCharacterIterator& + operator=(const StringCharacterIterator& that); + + /** + * Returns true if the iterators iterate over the same range of the + * same string and are pointing at the same character. + * @param that The ForwardCharacterIterator to be compared for equality + * @return true if the iterators iterate over the same range of the + * same string and are pointing at the same character. + * @stable ICU 2.0 + */ + virtual UBool operator==(const ForwardCharacterIterator& that) const; + + /** + * Returns a new StringCharacterIterator referring to the same + * character in the same range of the same string as this one. The + * caller must delete the new iterator. + * @return the newly cloned object. + * @stable ICU 2.0 + */ + virtual StringCharacterIterator* clone() const; + + /** + * Sets the iterator to iterate over the provided string. + * @param newText The string to be iterated over + * @stable ICU 2.0 + */ + void setText(const UnicodeString& newText); + + /** + * Copies the UnicodeString under iteration into the UnicodeString + * referred to by "result". Even if this iterator iterates across + * only a part of this string, the whole string is copied. + * @param result Receives a copy of the text under iteration. + * @stable ICU 2.0 + */ + virtual void getText(UnicodeString& result); + + /** + * Return a class ID for this object (not really public) + * @return a class ID for this object. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + + /** + * Return a class ID for this class (not really public) + * @return a class ID for this class + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + +protected: + /** + * Default constructor, iteration over empty string. + * @stable ICU 2.0 + */ + StringCharacterIterator(); + + /** + * Sets the iterator to iterate over the provided string. + * @param newText The string to be iterated over + * @param newTextLength The length of the String + * @stable ICU 2.0 + */ + void setText(const char16_t* newText, int32_t newTextLength); + + /** + * Copy of the iterated string object. + * @stable ICU 2.0 + */ + UnicodeString text; + +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/simpleformatter.h b/thirdparty/icu4c/common/unicode/simpleformatter.h new file mode 100644 index 0000000000..6d9c04ace2 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/simpleformatter.h @@ -0,0 +1,341 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* Copyright (C) 2014-2016, International Business Machines +* Corporation and others. All Rights Reserved. +****************************************************************************** +* simpleformatter.h +*/ + +#ifndef __SIMPLEFORMATTER_H__ +#define __SIMPLEFORMATTER_H__ + +/** + * \file + * \brief C++ API: Simple formatter, minimal subset of MessageFormat. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/unistr.h" + +U_NAMESPACE_BEGIN + +// Forward declaration: +namespace number { +namespace impl { +class SimpleModifier; +} +} + +/** + * Formats simple patterns like "{1} was born in {0}". + * Minimal subset of MessageFormat; fast, simple, minimal dependencies. + * Supports only numbered arguments with no type nor style parameters, + * and formats only string values. + * Quoting via ASCII apostrophe compatible with ICU MessageFormat default behavior. + * + * Factory methods set error codes for syntax errors + * and for too few or too many arguments/placeholders. + * + * SimpleFormatter objects are thread-safe except for assignment and applying new patterns. + * + * Example: + * <pre> + * UErrorCode errorCode = U_ZERO_ERROR; + * SimpleFormatter fmt("{1} '{born}' in {0}", errorCode); + * UnicodeString result; + * + * // Output: "paul {born} in england" + * fmt.format("england", "paul", result, errorCode); + * </pre> + * + * This class is not intended for public subclassing. + * + * @see MessageFormat + * @see UMessagePatternApostropheMode + * @stable ICU 57 + */ +class U_COMMON_API SimpleFormatter U_FINAL : public UMemory { +public: + /** + * Default constructor. + * @stable ICU 57 + */ + SimpleFormatter() : compiledPattern((char16_t)0) {} + + /** + * Constructs a formatter from the pattern string. + * + * @param pattern The pattern string. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * Set to U_ILLEGAL_ARGUMENT_ERROR for bad argument syntax. + * @stable ICU 57 + */ + SimpleFormatter(const UnicodeString& pattern, UErrorCode &errorCode) { + applyPattern(pattern, errorCode); + } + + /** + * Constructs a formatter from the pattern string. + * The number of arguments checked against the given limits is the + * highest argument number plus one, not the number of occurrences of arguments. + * + * @param pattern The pattern string. + * @param min The pattern must have at least this many arguments. + * @param max The pattern must have at most this many arguments. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * Set to U_ILLEGAL_ARGUMENT_ERROR for bad argument syntax and + * too few or too many arguments. + * @stable ICU 57 + */ + SimpleFormatter(const UnicodeString& pattern, int32_t min, int32_t max, + UErrorCode &errorCode) { + applyPatternMinMaxArguments(pattern, min, max, errorCode); + } + + /** + * Copy constructor. + * @stable ICU 57 + */ + SimpleFormatter(const SimpleFormatter& other) + : compiledPattern(other.compiledPattern) {} + + /** + * Assignment operator. + * @stable ICU 57 + */ + SimpleFormatter &operator=(const SimpleFormatter& other); + + /** + * Destructor. + * @stable ICU 57 + */ + ~SimpleFormatter(); + + /** + * Changes this object according to the new pattern. + * + * @param pattern The pattern string. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * Set to U_ILLEGAL_ARGUMENT_ERROR for bad argument syntax. + * @return true if U_SUCCESS(errorCode). + * @stable ICU 57 + */ + UBool applyPattern(const UnicodeString &pattern, UErrorCode &errorCode) { + return applyPatternMinMaxArguments(pattern, 0, INT32_MAX, errorCode); + } + + /** + * Changes this object according to the new pattern. + * The number of arguments checked against the given limits is the + * highest argument number plus one, not the number of occurrences of arguments. + * + * @param pattern The pattern string. + * @param min The pattern must have at least this many arguments. + * @param max The pattern must have at most this many arguments. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * Set to U_ILLEGAL_ARGUMENT_ERROR for bad argument syntax and + * too few or too many arguments. + * @return true if U_SUCCESS(errorCode). + * @stable ICU 57 + */ + UBool applyPatternMinMaxArguments(const UnicodeString &pattern, + int32_t min, int32_t max, UErrorCode &errorCode); + + /** + * @return The max argument number + 1. + * @stable ICU 57 + */ + int32_t getArgumentLimit() const { + return getArgumentLimit(compiledPattern.getBuffer(), compiledPattern.length()); + } + + /** + * Formats the given value, appending to the appendTo builder. + * The argument value must not be the same object as appendTo. + * getArgumentLimit() must be at most 1. + * + * @param value0 Value for argument {0}. + * @param appendTo Gets the formatted pattern and value appended. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return appendTo + * @stable ICU 57 + */ + UnicodeString &format( + const UnicodeString &value0, + UnicodeString &appendTo, UErrorCode &errorCode) const; + + /** + * Formats the given values, appending to the appendTo builder. + * An argument value must not be the same object as appendTo. + * getArgumentLimit() must be at most 2. + * + * @param value0 Value for argument {0}. + * @param value1 Value for argument {1}. + * @param appendTo Gets the formatted pattern and values appended. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return appendTo + * @stable ICU 57 + */ + UnicodeString &format( + const UnicodeString &value0, + const UnicodeString &value1, + UnicodeString &appendTo, UErrorCode &errorCode) const; + + /** + * Formats the given values, appending to the appendTo builder. + * An argument value must not be the same object as appendTo. + * getArgumentLimit() must be at most 3. + * + * @param value0 Value for argument {0}. + * @param value1 Value for argument {1}. + * @param value2 Value for argument {2}. + * @param appendTo Gets the formatted pattern and values appended. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return appendTo + * @stable ICU 57 + */ + UnicodeString &format( + const UnicodeString &value0, + const UnicodeString &value1, + const UnicodeString &value2, + UnicodeString &appendTo, UErrorCode &errorCode) const; + + /** + * Formats the given values, appending to the appendTo string. + * + * @param values The argument values. + * An argument value must not be the same object as appendTo. + * Can be NULL if valuesLength==getArgumentLimit()==0. + * @param valuesLength The length of the values array. + * Must be at least getArgumentLimit(). + * @param appendTo Gets the formatted pattern and values appended. + * @param offsets offsets[i] receives the offset of where + * values[i] replaced pattern argument {i}. + * Can be shorter or longer than values. Can be NULL if offsetsLength==0. + * If there is no {i} in the pattern, then offsets[i] is set to -1. + * @param offsetsLength The length of the offsets array. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return appendTo + * @stable ICU 57 + */ + UnicodeString &formatAndAppend( + const UnicodeString *const *values, int32_t valuesLength, + UnicodeString &appendTo, + int32_t *offsets, int32_t offsetsLength, UErrorCode &errorCode) const; + + /** + * Formats the given values, replacing the contents of the result string. + * May optimize by actually appending to the result if it is the same object + * as the value corresponding to the initial argument in the pattern. + * + * @param values The argument values. + * An argument value may be the same object as result. + * Can be NULL if valuesLength==getArgumentLimit()==0. + * @param valuesLength The length of the values array. + * Must be at least getArgumentLimit(). + * @param result Gets its contents replaced by the formatted pattern and values. + * @param offsets offsets[i] receives the offset of where + * values[i] replaced pattern argument {i}. + * Can be shorter or longer than values. Can be NULL if offsetsLength==0. + * If there is no {i} in the pattern, then offsets[i] is set to -1. + * @param offsetsLength The length of the offsets array. + * @param errorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return result + * @stable ICU 57 + */ + UnicodeString &formatAndReplace( + const UnicodeString *const *values, int32_t valuesLength, + UnicodeString &result, + int32_t *offsets, int32_t offsetsLength, UErrorCode &errorCode) const; + + /** + * Returns the pattern text with none of the arguments. + * Like formatting with all-empty string values. + * @stable ICU 57 + */ + UnicodeString getTextWithNoArguments() const { + return getTextWithNoArguments( + compiledPattern.getBuffer(), + compiledPattern.length(), + nullptr, + 0); + } + +#ifndef U_HIDE_INTERNAL_API + /** + * Returns the pattern text with none of the arguments. + * Like formatting with all-empty string values. + * + * TODO(ICU-20406): Replace this with an Iterator interface. + * + * @param offsets offsets[i] receives the offset of where {i} was located + * before it was replaced by an empty string. + * For example, "a{0}b{1}" produces offset 1 for i=0 and 2 for i=1. + * Can be nullptr if offsetsLength==0. + * If there is no {i} in the pattern, then offsets[i] is set to -1. + * @param offsetsLength The length of the offsets array. + * + * @internal + */ + UnicodeString getTextWithNoArguments(int32_t *offsets, int32_t offsetsLength) const { + return getTextWithNoArguments( + compiledPattern.getBuffer(), + compiledPattern.length(), + offsets, + offsetsLength); + } +#endif // U_HIDE_INTERNAL_API + +private: + /** + * Binary representation of the compiled pattern. + * Index 0: One more than the highest argument number. + * Followed by zero or more arguments or literal-text segments. + * + * An argument is stored as its number, less than ARG_NUM_LIMIT. + * A literal-text segment is stored as its length (at least 1) offset by ARG_NUM_LIMIT, + * followed by that many chars. + */ + UnicodeString compiledPattern; + + static inline int32_t getArgumentLimit(const char16_t *compiledPattern, + int32_t compiledPatternLength) { + return compiledPatternLength == 0 ? 0 : compiledPattern[0]; + } + + static UnicodeString getTextWithNoArguments( + const char16_t *compiledPattern, + int32_t compiledPatternLength, + int32_t *offsets, + int32_t offsetsLength); + + static UnicodeString &format( + const char16_t *compiledPattern, int32_t compiledPatternLength, + const UnicodeString *const *values, + UnicodeString &result, const UnicodeString *resultCopy, UBool forbidResultAsValue, + int32_t *offsets, int32_t offsetsLength, + UErrorCode &errorCode); + + // Give access to internals to SimpleModifier for number formatting + friend class number::impl::SimpleModifier; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __SIMPLEFORMATTER_H__ diff --git a/thirdparty/icu4c/common/unicode/std_string.h b/thirdparty/icu4c/common/unicode/std_string.h new file mode 100644 index 0000000000..bf87230167 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/std_string.h @@ -0,0 +1,41 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2009-2014, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: std_string.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2009feb19 +* created by: Markus W. Scherer +*/ + +#ifndef __STD_STRING_H__ +#define __STD_STRING_H__ + +/** + * \file + * \brief C++ API: Central ICU header for including the C++ standard <string> + * header and for related definitions. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +// Workaround for a libstdc++ bug before libstdc++4.6 (2011). +// https://bugs.llvm.org/show_bug.cgi?id=13364 +#if defined(__GLIBCXX__) +namespace std { class type_info; } +#endif +#include <string> + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __STD_STRING_H__ diff --git a/thirdparty/icu4c/common/unicode/strenum.h b/thirdparty/icu4c/common/unicode/strenum.h new file mode 100644 index 0000000000..df72b4b7e8 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/strenum.h @@ -0,0 +1,281 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2002-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +*/ + +#ifndef STRENUM_H +#define STRENUM_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" +#include "unicode/unistr.h" + +/** + * \file + * \brief C++ API: String Enumeration + */ + +U_NAMESPACE_BEGIN + +/** + * Base class for 'pure' C++ implementations of uenum api. Adds a + * method that returns the next UnicodeString since in C++ this can + * be a common storage format for strings. + * + * <p>The model is that the enumeration is over strings maintained by + * a 'service.' At any point, the service might change, invalidating + * the enumerator (though this is expected to be rare). The iterator + * returns an error if this has occurred. Lack of the error is no + * guarantee that the service didn't change immediately after the + * call, so the returned string still might not be 'valid' on + * subsequent use.</p> + * + * <p>Strings may take the form of const char*, const char16_t*, or const + * UnicodeString*. The type you get is determine by the variant of + * 'next' that you call. In general the StringEnumeration is + * optimized for one of these types, but all StringEnumerations can + * return all types. Returned strings are each terminated with a NUL. + * Depending on the service data, they might also include embedded NUL + * characters, so API is provided to optionally return the true + * length, counting the embedded NULs but not counting the terminating + * NUL.</p> + * + * <p>The pointers returned by next, unext, and snext become invalid + * upon any subsequent call to the enumeration's destructor, next, + * unext, snext, or reset.</p> + * + * ICU 2.8 adds some default implementations and helper functions + * for subclasses. + * + * @stable ICU 2.4 + */ +class U_COMMON_API StringEnumeration : public UObject { +public: + /** + * Destructor. + * @stable ICU 2.4 + */ + virtual ~StringEnumeration(); + + /** + * Clone this object, an instance of a subclass of StringEnumeration. + * Clones can be used concurrently in multiple threads. + * If a subclass does not implement clone(), or if an error occurs, + * then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see getDynamicClassID + * @stable ICU 2.8 + */ + virtual StringEnumeration *clone() const; + + /** + * <p>Return the number of elements that the iterator traverses. If + * the iterator is out of sync with its service, status is set to + * U_ENUM_OUT_OF_SYNC_ERROR, and the return value is zero.</p> + * + * <p>The return value will not change except possibly as a result of + * a subsequent call to reset, or if the iterator becomes out of sync.</p> + * + * <p>This is a convenience function. It can end up being very + * expensive as all the items might have to be pre-fetched + * (depending on the storage format of the data being + * traversed).</p> + * + * @param status the error code. + * @return number of elements in the iterator. + * + * @stable ICU 2.4 */ + virtual int32_t count(UErrorCode& status) const = 0; + + /** + * <p>Returns the next element as a NUL-terminated char*. If there + * are no more elements, returns NULL. If the resultLength pointer + * is not NULL, the length of the string (not counting the + * terminating NUL) is returned at that address. If an error + * status is returned, the value at resultLength is undefined.</p> + * + * <p>The returned pointer is owned by this iterator and must not be + * deleted by the caller. The pointer is valid until the next call + * to next, unext, snext, reset, or the enumerator's destructor.</p> + * + * <p>If the iterator is out of sync with its service, status is set + * to U_ENUM_OUT_OF_SYNC_ERROR and NULL is returned.</p> + * + * <p>If the native service string is a char16_t* string, it is + * converted to char* with the invariant converter. If the + * conversion fails (because a character cannot be converted) then + * status is set to U_INVARIANT_CONVERSION_ERROR and the return + * value is undefined (though not NULL).</p> + * + * Starting with ICU 2.8, the default implementation calls snext() + * and handles the conversion. + * Either next() or snext() must be implemented differently by a subclass. + * + * @param status the error code. + * @param resultLength a pointer to receive the length, can be NULL. + * @return a pointer to the string, or NULL. + * + * @stable ICU 2.4 + */ + virtual const char* next(int32_t *resultLength, UErrorCode& status); + + /** + * <p>Returns the next element as a NUL-terminated char16_t*. If there + * are no more elements, returns NULL. If the resultLength pointer + * is not NULL, the length of the string (not counting the + * terminating NUL) is returned at that address. If an error + * status is returned, the value at resultLength is undefined.</p> + * + * <p>The returned pointer is owned by this iterator and must not be + * deleted by the caller. The pointer is valid until the next call + * to next, unext, snext, reset, or the enumerator's destructor.</p> + * + * <p>If the iterator is out of sync with its service, status is set + * to U_ENUM_OUT_OF_SYNC_ERROR and NULL is returned.</p> + * + * Starting with ICU 2.8, the default implementation calls snext() + * and handles the conversion. + * + * @param status the error code. + * @param resultLength a ponter to receive the length, can be NULL. + * @return a pointer to the string, or NULL. + * + * @stable ICU 2.4 + */ + virtual const char16_t* unext(int32_t *resultLength, UErrorCode& status); + + /** + * <p>Returns the next element a UnicodeString*. If there are no + * more elements, returns NULL.</p> + * + * <p>The returned pointer is owned by this iterator and must not be + * deleted by the caller. The pointer is valid until the next call + * to next, unext, snext, reset, or the enumerator's destructor.</p> + * + * <p>If the iterator is out of sync with its service, status is set + * to U_ENUM_OUT_OF_SYNC_ERROR and NULL is returned.</p> + * + * Starting with ICU 2.8, the default implementation calls next() + * and handles the conversion. + * Either next() or snext() must be implemented differently by a subclass. + * + * @param status the error code. + * @return a pointer to the string, or NULL. + * + * @stable ICU 2.4 + */ + virtual const UnicodeString* snext(UErrorCode& status); + + /** + * <p>Resets the iterator. This re-establishes sync with the + * service and rewinds the iterator to start at the first + * element.</p> + * + * <p>Previous pointers returned by next, unext, or snext become + * invalid, and the value returned by count might change.</p> + * + * @param status the error code. + * + * @stable ICU 2.4 + */ + virtual void reset(UErrorCode& status) = 0; + + /** + * Compares this enumeration to other to check if both are equal + * + * @param that The other string enumeration to compare this object to + * @return true if the enumerations are equal. false if not. + * @stable ICU 3.6 + */ + virtual UBool operator==(const StringEnumeration& that)const; + /** + * Compares this enumeration to other to check if both are not equal + * + * @param that The other string enumeration to compare this object to + * @return true if the enumerations are equal. false if not. + * @stable ICU 3.6 + */ + virtual UBool operator!=(const StringEnumeration& that)const; + +protected: + /** + * UnicodeString field for use with default implementations and subclasses. + * @stable ICU 2.8 + */ + UnicodeString unistr; + /** + * char * default buffer for use with default implementations and subclasses. + * @stable ICU 2.8 + */ + char charsBuffer[32]; + /** + * char * buffer for use with default implementations and subclasses. + * Allocated in constructor and in ensureCharsCapacity(). + * @stable ICU 2.8 + */ + char *chars; + /** + * Capacity of chars, for use with default implementations and subclasses. + * @stable ICU 2.8 + */ + int32_t charsCapacity; + + /** + * Default constructor for use with default implementations and subclasses. + * @stable ICU 2.8 + */ + StringEnumeration(); + + /** + * Ensures that chars is at least as large as the requested capacity. + * For use with default implementations and subclasses. + * + * @param capacity Requested capacity. + * @param status ICU in/out error code. + * @stable ICU 2.8 + */ + void ensureCharsCapacity(int32_t capacity, UErrorCode &status); + + /** + * Converts s to Unicode and sets unistr to the result. + * For use with default implementations and subclasses, + * especially for implementations of snext() in terms of next(). + * This is provided with a helper function instead of a default implementation + * of snext() to avoid potential infinite loops between next() and snext(). + * + * For example: + * \code + * const UnicodeString* snext(UErrorCode& status) { + * int32_t resultLength=0; + * const char *s=next(&resultLength, status); + * return setChars(s, resultLength, status); + * } + * \endcode + * + * @param s String to be converted to Unicode. + * @param length Length of the string. + * @param status ICU in/out error code. + * @return A pointer to unistr. + * @stable ICU 2.8 + */ + UnicodeString *setChars(const char *s, int32_t length, UErrorCode &status); +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +/* STRENUM_H */ +#endif diff --git a/thirdparty/icu4c/common/unicode/stringoptions.h b/thirdparty/icu4c/common/unicode/stringoptions.h new file mode 100644 index 0000000000..7b9f70944f --- /dev/null +++ b/thirdparty/icu4c/common/unicode/stringoptions.h @@ -0,0 +1,190 @@ +// © 2017 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// stringoptions.h +// created: 2017jun08 Markus W. Scherer + +#ifndef __STRINGOPTIONS_H__ +#define __STRINGOPTIONS_H__ + +#include "unicode/utypes.h" + +/** + * \file + * \brief C API: Bit set option bit constants for various string and character processing functions. + */ + +/** + * Option value for case folding: Use default mappings defined in CaseFolding.txt. + * + * @stable ICU 2.0 + */ +#define U_FOLD_CASE_DEFAULT 0 + +/** + * Option value for case folding: + * + * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I + * and dotless i appropriately for Turkic languages (tr, az). + * + * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that + * are to be included for default mappings and + * excluded for the Turkic-specific mappings. + * + * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that + * are to be excluded for default mappings and + * included for the Turkic-specific mappings. + * + * @stable ICU 2.0 + */ +#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 + +/** + * Titlecase the string as a whole rather than each word. + * (Titlecase only the character at index 0, possibly adjusted.) + * Option bits value for titlecasing APIs that take an options bit set. + * + * It is an error to specify multiple titlecasing iterator options together, + * including both an options bit and an explicit BreakIterator. + * + * @see U_TITLECASE_ADJUST_TO_CASED + * @stable ICU 60 + */ +#define U_TITLECASE_WHOLE_STRING 0x20 + +/** + * Titlecase sentences rather than words. + * (Titlecase only the first character of each sentence, possibly adjusted.) + * Option bits value for titlecasing APIs that take an options bit set. + * + * It is an error to specify multiple titlecasing iterator options together, + * including both an options bit and an explicit BreakIterator. + * + * @see U_TITLECASE_ADJUST_TO_CASED + * @stable ICU 60 + */ +#define U_TITLECASE_SENTENCES 0x40 + +/** + * Do not lowercase non-initial parts of words when titlecasing. + * Option bit for titlecasing APIs that take an options bit set. + * + * By default, titlecasing will titlecase the character at each + * (possibly adjusted) BreakIterator index and + * lowercase all other characters up to the next iterator index. + * With this option, the other characters will not be modified. + * + * @see U_TITLECASE_ADJUST_TO_CASED + * @see UnicodeString::toTitle + * @see CaseMap::toTitle + * @see ucasemap_setOptions + * @see ucasemap_toTitle + * @see ucasemap_utf8ToTitle + * @stable ICU 3.8 + */ +#define U_TITLECASE_NO_LOWERCASE 0x100 + +/** + * Do not adjust the titlecasing BreakIterator indexes; + * titlecase exactly the characters at breaks from the iterator. + * Option bit for titlecasing APIs that take an options bit set. + * + * By default, titlecasing will take each break iterator index, + * adjust it to the next relevant character (see U_TITLECASE_ADJUST_TO_CASED), + * and titlecase that one. + * + * Other characters are lowercased. + * + * It is an error to specify multiple titlecasing adjustment options together. + * + * @see U_TITLECASE_ADJUST_TO_CASED + * @see U_TITLECASE_NO_LOWERCASE + * @see UnicodeString::toTitle + * @see CaseMap::toTitle + * @see ucasemap_setOptions + * @see ucasemap_toTitle + * @see ucasemap_utf8ToTitle + * @stable ICU 3.8 + */ +#define U_TITLECASE_NO_BREAK_ADJUSTMENT 0x200 + +/** + * Adjust each titlecasing BreakIterator index to the next cased character. + * (See the Unicode Standard, chapter 3, Default Case Conversion, R3 toTitlecase(X).) + * Option bit for titlecasing APIs that take an options bit set. + * + * This used to be the default index adjustment in ICU. + * Since ICU 60, the default index adjustment is to the next character that is + * a letter, number, symbol, or private use code point. + * (Uncased modifier letters are skipped.) + * The difference in behavior is small for word titlecasing, + * but the new adjustment is much better for whole-string and sentence titlecasing: + * It yields "49ers" and "«丰(abc)»" instead of "49Ers" and "«丰(Abc)»". + * + * It is an error to specify multiple titlecasing adjustment options together. + * + * @see U_TITLECASE_NO_BREAK_ADJUSTMENT + * @stable ICU 60 + */ +#define U_TITLECASE_ADJUST_TO_CASED 0x400 + +/** + * Option for string transformation functions to not first reset the Edits object. + * Used for example in some case-mapping and normalization functions. + * + * @see CaseMap + * @see Edits + * @see Normalizer2 + * @stable ICU 60 + */ +#define U_EDITS_NO_RESET 0x2000 + +/** + * Omit unchanged text when recording how source substrings + * relate to changed and unchanged result substrings. + * Used for example in some case-mapping and normalization functions. + * + * @see CaseMap + * @see Edits + * @see Normalizer2 + * @stable ICU 60 + */ +#define U_OMIT_UNCHANGED_TEXT 0x4000 + +/** + * Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc: + * Compare strings in code point order instead of code unit order. + * @stable ICU 2.2 + */ +#define U_COMPARE_CODE_POINT_ORDER 0x8000 + +/** + * Option bit for unorm_compare: + * Perform case-insensitive comparison. + * @stable ICU 2.2 + */ +#define U_COMPARE_IGNORE_CASE 0x10000 + +/** + * Option bit for unorm_compare: + * Both input strings are assumed to fulfill FCD conditions. + * @stable ICU 2.2 + */ +#define UNORM_INPUT_IS_FCD 0x20000 + +// Related definitions elsewhere. +// Options that are not meaningful in the same functions +// can share the same bits. +// +// Public: +// unicode/unorm.h #define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20 +// +// Internal: (may change or be removed) +// ucase.h #define _STRCASECMP_OPTIONS_MASK 0xffff +// ucase.h #define _FOLD_CASE_OPTIONS_MASK 7 +// ucasemap_imp.h #define U_TITLECASE_ITERATOR_MASK 0xe0 +// ucasemap_imp.h #define U_TITLECASE_ADJUSTMENT_MASK 0x600 +// ustr_imp.h #define _STRNCMP_STYLE 0x1000 +// unormcmp.cpp #define _COMPARE_EQUIV 0x80000 + +#endif // __STRINGOPTIONS_H__ diff --git a/thirdparty/icu4c/common/unicode/stringpiece.h b/thirdparty/icu4c/common/unicode/stringpiece.h new file mode 100644 index 0000000000..7d7d871e1f --- /dev/null +++ b/thirdparty/icu4c/common/unicode/stringpiece.h @@ -0,0 +1,353 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +// Copyright (C) 2009-2013, International Business Machines +// Corporation and others. All Rights Reserved. +// +// Copyright 2001 and onwards Google Inc. +// Author: Sanjay Ghemawat + +// This code is a contribution of Google code, and the style used here is +// a compromise between the original Google code and the ICU coding guidelines. +// For example, data types are ICU-ified (size_t,int->int32_t), +// and API comments doxygen-ified, but function names and behavior are +// as in the original, if possible. +// Assertion-style error handling, not available in ICU, was changed to +// parameter "pinning" similar to UnicodeString. +// +// In addition, this is only a partial port of the original Google code, +// limited to what was needed so far. The (nearly) complete original code +// is in the ICU svn repository at icuhtml/trunk/design/strings/contrib +// (see ICU ticket 6765, r25517). + +#ifndef __STRINGPIECE_H__ +#define __STRINGPIECE_H__ + +/** + * \file + * \brief C++ API: StringPiece: Read-only byte string wrapper class. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include <cstddef> +#include <type_traits> + +#include "unicode/uobject.h" +#include "unicode/std_string.h" + +// Arghh! I wish C++ literals were "string". + +U_NAMESPACE_BEGIN + +/** + * A string-like object that points to a sized piece of memory. + * + * We provide non-explicit singleton constructors so users can pass + * in a "const char*" or a "string" wherever a "StringPiece" is + * expected. + * + * Functions or methods may use StringPiece parameters to accept either a + * "const char*" or a "string" value that will be implicitly converted to a + * StringPiece. + * + * Systematic usage of StringPiece is encouraged as it will reduce unnecessary + * conversions from "const char*" to "string" and back again. + * + * @stable ICU 4.2 + */ +class U_COMMON_API StringPiece : public UMemory { + private: + const char* ptr_; + int32_t length_; + + public: + /** + * Default constructor, creates an empty StringPiece. + * @stable ICU 4.2 + */ + StringPiece() : ptr_(nullptr), length_(0) { } + + /** + * Constructs from a NUL-terminated const char * pointer. + * @param str a NUL-terminated const char * pointer + * @stable ICU 4.2 + */ + StringPiece(const char* str); +#ifndef U_HIDE_DRAFT_API +#if defined(__cpp_char8_t) || defined(U_IN_DOXYGEN) + /** + * Constructs from a NUL-terminated const char8_t * pointer. + * @param str a NUL-terminated const char8_t * pointer + * @draft ICU 67 + */ + StringPiece(const char8_t* str) : StringPiece(reinterpret_cast<const char*>(str)) {} +#endif + /** + * Constructs an empty StringPiece. + * Needed for type disambiguation from multiple other overloads. + * @param p nullptr + * @draft ICU 67 + */ + StringPiece(std::nullptr_t p) : ptr_(p), length_(0) {} +#endif // U_HIDE_DRAFT_API + + /** + * Constructs from a std::string. + * @stable ICU 4.2 + */ + StringPiece(const std::string& str) + : ptr_(str.data()), length_(static_cast<int32_t>(str.size())) { } +#ifndef U_HIDE_DRAFT_API +#if defined(__cpp_lib_char8_t) || defined(U_IN_DOXYGEN) + /** + * Constructs from a std::u8string. + * @draft ICU 67 + */ + StringPiece(const std::u8string& str) + : ptr_(reinterpret_cast<const char*>(str.data())), + length_(static_cast<int32_t>(str.size())) { } +#endif +#endif // U_HIDE_DRAFT_API + + /** + * Constructs from some other implementation of a string piece class, from any + * C++ record type that has these two methods: + * + * \code{.cpp} + * + * struct OtherStringPieceClass { + * const char* data(); // or const char8_t* + * size_t size(); + * }; + * + * \endcode + * + * The other string piece class will typically be std::string_view from C++17 + * or absl::string_view from Abseil. + * + * Starting with C++20, data() may also return a const char8_t* pointer, + * as from std::u8string_view. + * + * @param str the other string piece + * @stable ICU 65 + */ + template <typename T, + typename = typename std::enable_if< + (std::is_same<decltype(T().data()), const char*>::value +#if defined(__cpp_char8_t) + || std::is_same<decltype(T().data()), const char8_t*>::value +#endif + ) && + std::is_same<decltype(T().size()), size_t>::value>::type> + StringPiece(T str) + : ptr_(reinterpret_cast<const char*>(str.data())), + length_(static_cast<int32_t>(str.size())) {} + + /** + * Constructs from a const char * pointer and a specified length. + * @param offset a const char * pointer (need not be terminated) + * @param len the length of the string; must be non-negative + * @stable ICU 4.2 + */ + StringPiece(const char* offset, int32_t len) : ptr_(offset), length_(len) { } +#ifndef U_HIDE_DRAFT_API +#if defined(__cpp_char8_t) || defined(U_IN_DOXYGEN) + /** + * Constructs from a const char8_t * pointer and a specified length. + * @param str a const char8_t * pointer (need not be terminated) + * @param len the length of the string; must be non-negative + * @draft ICU 67 + */ + StringPiece(const char8_t* str, int32_t len) : + StringPiece(reinterpret_cast<const char*>(str), len) {} +#endif +#endif // U_HIDE_DRAFT_API + + /** + * Substring of another StringPiece. + * @param x the other StringPiece + * @param pos start position in x; must be non-negative and <= x.length(). + * @stable ICU 4.2 + */ + StringPiece(const StringPiece& x, int32_t pos); + /** + * Substring of another StringPiece. + * @param x the other StringPiece + * @param pos start position in x; must be non-negative and <= x.length(). + * @param len length of the substring; + * must be non-negative and will be pinned to at most x.length() - pos. + * @stable ICU 4.2 + */ + StringPiece(const StringPiece& x, int32_t pos, int32_t len); + + /** + * Returns the string pointer. May be nullptr if it is empty. + * + * data() may return a pointer to a buffer with embedded NULs, and the + * returned buffer may or may not be null terminated. Therefore it is + * typically a mistake to pass data() to a routine that expects a NUL + * terminated string. + * @return the string pointer + * @stable ICU 4.2 + */ + const char* data() const { return ptr_; } + /** + * Returns the string length. Same as length(). + * @return the string length + * @stable ICU 4.2 + */ + int32_t size() const { return length_; } + /** + * Returns the string length. Same as size(). + * @return the string length + * @stable ICU 4.2 + */ + int32_t length() const { return length_; } + /** + * Returns whether the string is empty. + * @return true if the string is empty + * @stable ICU 4.2 + */ + UBool empty() const { return length_ == 0; } + + /** + * Sets to an empty string. + * @stable ICU 4.2 + */ + void clear() { ptr_ = nullptr; length_ = 0; } + + /** + * Reset the stringpiece to refer to new data. + * @param xdata pointer the new string data. Need not be nul terminated. + * @param len the length of the new data + * @stable ICU 4.8 + */ + void set(const char* xdata, int32_t len) { ptr_ = xdata; length_ = len; } + + /** + * Reset the stringpiece to refer to new data. + * @param str a pointer to a NUL-terminated string. + * @stable ICU 4.8 + */ + void set(const char* str); + +#ifndef U_HIDE_DRAFT_API +#if defined(__cpp_char8_t) || defined(U_IN_DOXYGEN) + /** + * Resets the stringpiece to refer to new data. + * @param xdata pointer the new string data. Need not be NUL-terminated. + * @param len the length of the new data + * @draft ICU 67 + */ + inline void set(const char8_t* xdata, int32_t len) { + set(reinterpret_cast<const char*>(xdata), len); + } + + /** + * Resets the stringpiece to refer to new data. + * @param str a pointer to a NUL-terminated string. + * @draft ICU 67 + */ + inline void set(const char8_t* str) { + set(reinterpret_cast<const char*>(str)); + } +#endif +#endif // U_HIDE_DRAFT_API + + /** + * Removes the first n string units. + * @param n prefix length, must be non-negative and <=length() + * @stable ICU 4.2 + */ + void remove_prefix(int32_t n) { + if (n >= 0) { + if (n > length_) { + n = length_; + } + ptr_ += n; + length_ -= n; + } + } + + /** + * Removes the last n string units. + * @param n suffix length, must be non-negative and <=length() + * @stable ICU 4.2 + */ + void remove_suffix(int32_t n) { + if (n >= 0) { + if (n <= length_) { + length_ -= n; + } else { + length_ = 0; + } + } + } + +#ifndef U_HIDE_DRAFT_API + /** + * Searches the StringPiece for the given search string (needle); + * @param needle The string for which to search. + * @param offset Where to start searching within this string (haystack). + * @return The offset of needle in haystack, or -1 if not found. + * @draft ICU 67 + */ + int32_t find(StringPiece needle, int32_t offset); + + /** + * Compares this StringPiece with the other StringPiece, with semantics + * similar to std::string::compare(). + * @param other The string to compare to. + * @return below zero if this < other; above zero if this > other; 0 if this == other. + * @draft ICU 67 + */ + int32_t compare(StringPiece other); +#endif // U_HIDE_DRAFT_API + + /** + * Maximum integer, used as a default value for substring methods. + * @stable ICU 4.2 + */ + static const int32_t npos; // = 0x7fffffff; + + /** + * Returns a substring of this StringPiece. + * @param pos start position; must be non-negative and <= length(). + * @param len length of the substring; + * must be non-negative and will be pinned to at most length() - pos. + * @return the substring StringPiece + * @stable ICU 4.2 + */ + StringPiece substr(int32_t pos, int32_t len = npos) const { + return StringPiece(*this, pos, len); + } +}; + +/** + * Global operator == for StringPiece + * @param x The first StringPiece to compare. + * @param y The second StringPiece to compare. + * @return true if the string data is equal + * @stable ICU 4.8 + */ +U_EXPORT UBool U_EXPORT2 +operator==(const StringPiece& x, const StringPiece& y); + +/** + * Global operator != for StringPiece + * @param x The first StringPiece to compare. + * @param y The second StringPiece to compare. + * @return true if the string data is not equal + * @stable ICU 4.8 + */ +inline UBool operator!=(const StringPiece& x, const StringPiece& y) { + return !(x == y); +} + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __STRINGPIECE_H__ diff --git a/thirdparty/icu4c/common/unicode/stringtriebuilder.h b/thirdparty/icu4c/common/unicode/stringtriebuilder.h new file mode 100644 index 0000000000..fe471bbbf9 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/stringtriebuilder.h @@ -0,0 +1,426 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2010-2012,2014, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: stringtriebuilder.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2010dec24 +* created by: Markus W. Scherer +*/ + +#ifndef __STRINGTRIEBUILDER_H__ +#define __STRINGTRIEBUILDER_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: Builder API for trie builders + */ + +// Forward declaration. +/// \cond +struct UHashtable; +typedef struct UHashtable UHashtable; +/// \endcond + +/** + * Build options for BytesTrieBuilder and CharsTrieBuilder. + * @stable ICU 4.8 + */ +enum UStringTrieBuildOption { + /** + * Builds a trie quickly. + * @stable ICU 4.8 + */ + USTRINGTRIE_BUILD_FAST, + /** + * Builds a trie more slowly, attempting to generate + * a shorter but equivalent serialization. + * This build option also uses more memory. + * + * This option can be effective when many integer values are the same + * and string/byte sequence suffixes can be shared. + * Runtime speed is not expected to improve. + * @stable ICU 4.8 + */ + USTRINGTRIE_BUILD_SMALL +}; + +U_NAMESPACE_BEGIN + +/** + * Base class for string trie builder classes. + * + * This class is not intended for public subclassing. + * @stable ICU 4.8 + */ +class U_COMMON_API StringTrieBuilder : public UObject { +public: +#ifndef U_HIDE_INTERNAL_API + /** @internal */ + static int32_t hashNode(const void *node); + /** @internal */ + static UBool equalNodes(const void *left, const void *right); +#endif /* U_HIDE_INTERNAL_API */ + +protected: + // Do not enclose the protected default constructor with #ifndef U_HIDE_INTERNAL_API + // or else the compiler will create a public default constructor. + /** @internal */ + StringTrieBuilder(); + /** @internal */ + virtual ~StringTrieBuilder(); + +#ifndef U_HIDE_INTERNAL_API + /** @internal */ + void createCompactBuilder(int32_t sizeGuess, UErrorCode &errorCode); + /** @internal */ + void deleteCompactBuilder(); + + /** @internal */ + void build(UStringTrieBuildOption buildOption, int32_t elementsLength, UErrorCode &errorCode); + + /** @internal */ + int32_t writeNode(int32_t start, int32_t limit, int32_t unitIndex); + /** @internal */ + int32_t writeBranchSubNode(int32_t start, int32_t limit, int32_t unitIndex, int32_t length); +#endif /* U_HIDE_INTERNAL_API */ + + class Node; + +#ifndef U_HIDE_INTERNAL_API + /** @internal */ + Node *makeNode(int32_t start, int32_t limit, int32_t unitIndex, UErrorCode &errorCode); + /** @internal */ + Node *makeBranchSubNode(int32_t start, int32_t limit, int32_t unitIndex, + int32_t length, UErrorCode &errorCode); +#endif /* U_HIDE_INTERNAL_API */ + + /** @internal */ + virtual int32_t getElementStringLength(int32_t i) const = 0; + /** @internal */ + virtual char16_t getElementUnit(int32_t i, int32_t unitIndex) const = 0; + /** @internal */ + virtual int32_t getElementValue(int32_t i) const = 0; + + // Finds the first unit index after this one where + // the first and last element have different units again. + /** @internal */ + virtual int32_t getLimitOfLinearMatch(int32_t first, int32_t last, int32_t unitIndex) const = 0; + + // Number of different units at unitIndex. + /** @internal */ + virtual int32_t countElementUnits(int32_t start, int32_t limit, int32_t unitIndex) const = 0; + /** @internal */ + virtual int32_t skipElementsBySomeUnits(int32_t i, int32_t unitIndex, int32_t count) const = 0; + /** @internal */ + virtual int32_t indexOfElementWithNextUnit(int32_t i, int32_t unitIndex, char16_t unit) const = 0; + + /** @internal */ + virtual UBool matchNodesCanHaveValues() const = 0; + + /** @internal */ + virtual int32_t getMaxBranchLinearSubNodeLength() const = 0; + /** @internal */ + virtual int32_t getMinLinearMatch() const = 0; + /** @internal */ + virtual int32_t getMaxLinearMatchLength() const = 0; + +#ifndef U_HIDE_INTERNAL_API + // max(BytesTrie::kMaxBranchLinearSubNodeLength, UCharsTrie::kMaxBranchLinearSubNodeLength). + /** @internal */ + static const int32_t kMaxBranchLinearSubNodeLength=5; + + // Maximum number of nested split-branch levels for a branch on all 2^16 possible char16_t units. + // log2(2^16/kMaxBranchLinearSubNodeLength) rounded up. + /** @internal */ + static const int32_t kMaxSplitBranchLevels=14; + + /** + * Makes sure that there is only one unique node registered that is + * equivalent to newNode. + * @param newNode Input node. The builder takes ownership. + * @param errorCode ICU in/out UErrorCode. + Set to U_MEMORY_ALLOCATION_ERROR if it was success but newNode==NULL. + * @return newNode if it is the first of its kind, or + * an equivalent node if newNode is a duplicate. + * @internal + */ + Node *registerNode(Node *newNode, UErrorCode &errorCode); + /** + * Makes sure that there is only one unique FinalValueNode registered + * with this value. + * Avoids creating a node if the value is a duplicate. + * @param value A final value. + * @param errorCode ICU in/out UErrorCode. + Set to U_MEMORY_ALLOCATION_ERROR if it was success but newNode==NULL. + * @return A FinalValueNode with the given value. + * @internal + */ + Node *registerFinalValue(int32_t value, UErrorCode &errorCode); +#endif /* U_HIDE_INTERNAL_API */ + + /* + * C++ note: + * registerNode() and registerFinalValue() take ownership of their input nodes, + * and only return owned nodes. + * If they see a failure UErrorCode, they will delete the input node. + * If they get a NULL pointer, they will record a U_MEMORY_ALLOCATION_ERROR. + * If there is a failure, they return NULL. + * + * NULL Node pointers can be safely passed into other Nodes because + * they call the static Node::hashCode() which checks for a NULL pointer first. + * + * Therefore, as long as builder functions register a new node, + * they need to check for failures only before explicitly dereferencing + * a Node pointer, or before setting a new UErrorCode. + */ + + // Hash set of nodes, maps from nodes to integer 1. + /** @internal */ + UHashtable *nodes; + + // Do not conditionalize the following with #ifndef U_HIDE_INTERNAL_API, + // it is needed for layout of other objects. + /** + * @internal + * \cond + */ + class Node : public UObject { + public: + Node(int32_t initialHash) : hash(initialHash), offset(0) {} + inline int32_t hashCode() const { return hash; } + // Handles node==NULL. + static inline int32_t hashCode(const Node *node) { return node==NULL ? 0 : node->hashCode(); } + // Base class operator==() compares the actual class types. + virtual UBool operator==(const Node &other) const; + inline UBool operator!=(const Node &other) const { return !operator==(other); } + /** + * Traverses the Node graph and numbers branch edges, with rightmost edges first. + * This is to avoid writing a duplicate node twice. + * + * Branch nodes in this trie data structure are not symmetric. + * Most branch edges "jump" to other nodes but the rightmost branch edges + * just continue without a jump. + * Therefore, write() must write the rightmost branch edge last + * (trie units are written backwards), and must write it at that point even if + * it is a duplicate of a node previously written elsewhere. + * + * This function visits and marks right branch edges first. + * Edges are numbered with increasingly negative values because we share the + * offset field which gets positive values when nodes are written. + * A branch edge also remembers the first number for any of its edges. + * + * When a further-left branch edge has a number in the range of the rightmost + * edge's numbers, then it will be written as part of the required right edge + * and we can avoid writing it first. + * + * After root.markRightEdgesFirst(-1) the offsets of all nodes are negative + * edge numbers. + * + * @param edgeNumber The first edge number for this node and its sub-nodes. + * @return An edge number that is at least the maximum-negative + * of the input edge number and the numbers of this node and all of its sub-nodes. + */ + virtual int32_t markRightEdgesFirst(int32_t edgeNumber); + // write() must set the offset to a positive value. + virtual void write(StringTrieBuilder &builder) = 0; + // See markRightEdgesFirst. + inline void writeUnlessInsideRightEdge(int32_t firstRight, int32_t lastRight, + StringTrieBuilder &builder) { + // Note: Edge numbers are negative, lastRight<=firstRight. + // If offset>0 then this node and its sub-nodes have been written already + // and we need not write them again. + // If this node is part of the unwritten right branch edge, + // then we wait until that is written. + if(offset<0 && (offset<lastRight || firstRight<offset)) { + write(builder); + } + } + inline int32_t getOffset() const { return offset; } + protected: + int32_t hash; + int32_t offset; + }; + +#ifndef U_HIDE_INTERNAL_API + // This class should not be overridden because + // registerFinalValue() compares a stack-allocated FinalValueNode + // (stack-allocated so that we don't unnecessarily create lots of duplicate nodes) + // with the input node, and the + // !Node::operator==(other) used inside FinalValueNode::operator==(other) + // will be false if the typeid's are different. + /** @internal */ + class FinalValueNode : public Node { + public: + FinalValueNode(int32_t v) : Node(0x111111u*37u+v), value(v) {} + virtual UBool operator==(const Node &other) const; + virtual void write(StringTrieBuilder &builder); + protected: + int32_t value; + }; +#endif /* U_HIDE_INTERNAL_API */ + + // Do not conditionalize the following with #ifndef U_HIDE_INTERNAL_API, + // it is needed for layout of other objects. + /** + * @internal + */ + class ValueNode : public Node { + public: + ValueNode(int32_t initialHash) : Node(initialHash), hasValue(false), value(0) {} + virtual UBool operator==(const Node &other) const; + void setValue(int32_t v) { + hasValue=true; + value=v; + hash=hash*37u+v; + } + protected: + UBool hasValue; + int32_t value; + }; + +#ifndef U_HIDE_INTERNAL_API + /** + * @internal + */ + class IntermediateValueNode : public ValueNode { + public: + IntermediateValueNode(int32_t v, Node *nextNode) + : ValueNode(0x222222u*37u+hashCode(nextNode)), next(nextNode) { setValue(v); } + virtual UBool operator==(const Node &other) const; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber); + virtual void write(StringTrieBuilder &builder); + protected: + Node *next; + }; +#endif /* U_HIDE_INTERNAL_API */ + + // Do not conditionalize the following with #ifndef U_HIDE_INTERNAL_API, + // it is needed for layout of other objects. + /** + * @internal + */ + class LinearMatchNode : public ValueNode { + public: + LinearMatchNode(int32_t len, Node *nextNode) + : ValueNode((0x333333u*37u+len)*37u+hashCode(nextNode)), + length(len), next(nextNode) {} + virtual UBool operator==(const Node &other) const; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber); + protected: + int32_t length; + Node *next; + }; + +#ifndef U_HIDE_INTERNAL_API + /** + * @internal + */ + class BranchNode : public Node { + public: + BranchNode(int32_t initialHash) : Node(initialHash) {} + protected: + int32_t firstEdgeNumber; + }; + + /** + * @internal + */ + class ListBranchNode : public BranchNode { + public: + ListBranchNode() : BranchNode(0x444444), length(0) {} + virtual UBool operator==(const Node &other) const; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber); + virtual void write(StringTrieBuilder &builder); + // Adds a unit with a final value. + void add(int32_t c, int32_t value) { + units[length]=(char16_t)c; + equal[length]=NULL; + values[length]=value; + ++length; + hash=(hash*37u+c)*37u+value; + } + // Adds a unit which leads to another match node. + void add(int32_t c, Node *node) { + units[length]=(char16_t)c; + equal[length]=node; + values[length]=0; + ++length; + hash=(hash*37u+c)*37u+hashCode(node); + } + protected: + Node *equal[kMaxBranchLinearSubNodeLength]; // NULL means "has final value". + int32_t length; + int32_t values[kMaxBranchLinearSubNodeLength]; + char16_t units[kMaxBranchLinearSubNodeLength]; + }; + + /** + * @internal + */ + class SplitBranchNode : public BranchNode { + public: + SplitBranchNode(char16_t middleUnit, Node *lessThanNode, Node *greaterOrEqualNode) + : BranchNode(((0x555555u*37u+middleUnit)*37u+ + hashCode(lessThanNode))*37u+hashCode(greaterOrEqualNode)), + unit(middleUnit), lessThan(lessThanNode), greaterOrEqual(greaterOrEqualNode) {} + virtual UBool operator==(const Node &other) const; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber); + virtual void write(StringTrieBuilder &builder); + protected: + char16_t unit; + Node *lessThan; + Node *greaterOrEqual; + }; + + // Branch head node, for writing the actual node lead unit. + /** @internal */ + class BranchHeadNode : public ValueNode { + public: + BranchHeadNode(int32_t len, Node *subNode) + : ValueNode((0x666666u*37u+len)*37u+hashCode(subNode)), + length(len), next(subNode) {} + virtual UBool operator==(const Node &other) const; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber); + virtual void write(StringTrieBuilder &builder); + protected: + int32_t length; + Node *next; // A branch sub-node. + }; + +#endif /* U_HIDE_INTERNAL_API */ + /// \endcond + + /** @internal */ + virtual Node *createLinearMatchNode(int32_t i, int32_t unitIndex, int32_t length, + Node *nextNode) const = 0; + + /** @internal */ + virtual int32_t write(int32_t unit) = 0; + /** @internal */ + virtual int32_t writeElementUnits(int32_t i, int32_t unitIndex, int32_t length) = 0; + /** @internal */ + virtual int32_t writeValueAndFinal(int32_t i, UBool isFinal) = 0; + /** @internal */ + virtual int32_t writeValueAndType(UBool hasValue, int32_t value, int32_t node) = 0; + /** @internal */ + virtual int32_t writeDeltaTo(int32_t jumpTarget) = 0; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __STRINGTRIEBUILDER_H__ diff --git a/thirdparty/icu4c/common/unicode/symtable.h b/thirdparty/icu4c/common/unicode/symtable.h new file mode 100644 index 0000000000..b64d877f97 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/symtable.h @@ -0,0 +1,119 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (c) 2000-2005, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Date Name Description +* 02/04/00 aliu Creation. +********************************************************************** +*/ +#ifndef SYMTABLE_H +#define SYMTABLE_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: An interface that defines both lookup protocol and parsing of + * symbolic names. + */ + +U_NAMESPACE_BEGIN + +class ParsePosition; +class UnicodeFunctor; +class UnicodeSet; +class UnicodeString; + +/** + * An interface that defines both lookup protocol and parsing of + * symbolic names. + * + * <p>A symbol table maintains two kinds of mappings. The first is + * between symbolic names and their values. For example, if the + * variable with the name "start" is set to the value "alpha" + * (perhaps, though not necessarily, through an expression such as + * "$start=alpha"), then the call lookup("start") will return the + * char[] array ['a', 'l', 'p', 'h', 'a']. + * + * <p>The second kind of mapping is between character values and + * UnicodeMatcher objects. This is used by RuleBasedTransliterator, + * which uses characters in the private use area to represent objects + * such as UnicodeSets. If U+E015 is mapped to the UnicodeSet [a-z], + * then lookupMatcher(0xE015) will return the UnicodeSet [a-z]. + * + * <p>Finally, a symbol table defines parsing behavior for symbolic + * names. All symbolic names start with the SYMBOL_REF character. + * When a parser encounters this character, it calls parseReference() + * with the position immediately following the SYMBOL_REF. The symbol + * table parses the name, if there is one, and returns it. + * + * @stable ICU 2.8 + */ +class U_COMMON_API SymbolTable /* not : public UObject because this is an interface/mixin class */ { +public: + + /** + * The character preceding a symbol reference name. + * @stable ICU 2.8 + */ + enum { SYMBOL_REF = 0x0024 /*$*/ }; + + /** + * Destructor. + * @stable ICU 2.8 + */ + virtual ~SymbolTable(); + + /** + * Lookup the characters associated with this string and return it. + * Return <tt>NULL</tt> if no such name exists. The resultant + * string may have length zero. + * @param s the symbolic name to lookup + * @return a string containing the name's value, or <tt>NULL</tt> if + * there is no mapping for s. + * @stable ICU 2.8 + */ + virtual const UnicodeString* lookup(const UnicodeString& s) const = 0; + + /** + * Lookup the UnicodeMatcher associated with the given character, and + * return it. Return <tt>NULL</tt> if not found. + * @param ch a 32-bit code point from 0 to 0x10FFFF inclusive. + * @return the UnicodeMatcher object represented by the given + * character, or NULL if there is no mapping for ch. + * @stable ICU 2.8 + */ + virtual const UnicodeFunctor* lookupMatcher(UChar32 ch) const = 0; + + /** + * Parse a symbol reference name from the given string, starting + * at the given position. If no valid symbol reference name is + * found, return the empty string and leave pos unchanged. That is, if the + * character at pos cannot start a name, or if pos is at or after + * text.length(), then return an empty string. This indicates an + * isolated SYMBOL_REF character. + * @param text the text to parse for the name + * @param pos on entry, the index of the first character to parse. + * This is the character following the SYMBOL_REF character. On + * exit, the index after the last parsed character. If the parse + * failed, pos is unchanged on exit. + * @param limit the index after the last character to be parsed. + * @return the parsed name, or an empty string if there is no + * valid symbolic name at the given position. + * @stable ICU 2.8 + */ + virtual UnicodeString parseReference(const UnicodeString& text, + ParsePosition& pos, int32_t limit) const = 0; +}; +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/ubidi.h b/thirdparty/icu4c/common/unicode/ubidi.h new file mode 100644 index 0000000000..63d0e45cb7 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ubidi.h @@ -0,0 +1,2210 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1999-2013, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* file name: ubidi.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999jul27 +* created by: Markus W. Scherer, updated by Matitiahu Allouche +*/ + +#ifndef UBIDI_H +#define UBIDI_H + +#include "unicode/utypes.h" +#include "unicode/uchar.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + *\file + * \brief C API: Bidi algorithm + * + * <h2>Bidi algorithm for ICU</h2> + * + * This is an implementation of the Unicode Bidirectional Algorithm. + * The algorithm is defined in the + * <a href="http://www.unicode.org/unicode/reports/tr9/">Unicode Standard Annex #9</a>.<p> + * + * Note: Libraries that perform a bidirectional algorithm and + * reorder strings accordingly are sometimes called "Storage Layout Engines". + * ICU's Bidi and shaping (u_shapeArabic()) APIs can be used at the core of such + * "Storage Layout Engines". + * + * <h3>General remarks about the API:</h3> + * + * In functions with an error code parameter, + * the <code>pErrorCode</code> pointer must be valid + * and the value that it points to must not indicate a failure before + * the function call. Otherwise, the function returns immediately. + * After the function call, the value indicates success or failure.<p> + * + * The "limit" of a sequence of characters is the position just after their + * last character, i.e., one more than that position.<p> + * + * Some of the API functions provide access to "runs". + * Such a "run" is defined as a sequence of characters + * that are at the same embedding level + * after performing the Bidi algorithm.<p> + * + * @author Markus W. Scherer + * @version 1.0 + * + * + * <h4> Sample code for the ICU Bidi API </h4> + * + * <h5>Rendering a paragraph with the ICU Bidi API</h5> + * + * This is (hypothetical) sample code that illustrates + * how the ICU Bidi API could be used to render a paragraph of text. + * Rendering code depends highly on the graphics system, + * therefore this sample code must make a lot of assumptions, + * which may or may not match any existing graphics system's properties. + * + * <p>The basic assumptions are:</p> + * <ul> + * <li>Rendering is done from left to right on a horizontal line.</li> + * <li>A run of single-style, unidirectional text can be rendered at once.</li> + * <li>Such a run of text is passed to the graphics system with + * characters (code units) in logical order.</li> + * <li>The line-breaking algorithm is very complicated + * and Locale-dependent - + * and therefore its implementation omitted from this sample code.</li> + * </ul> + * + * <pre> + * \code + *#include "unicode/ubidi.h" + * + *typedef enum { + * styleNormal=0, styleSelected=1, + * styleBold=2, styleItalics=4, + * styleSuper=8, styleSub=16 + *} Style; + * + *typedef struct { int32_t limit; Style style; } StyleRun; + * + *int getTextWidth(const UChar *text, int32_t start, int32_t limit, + * const StyleRun *styleRuns, int styleRunCount); + * + * // set *pLimit and *pStyleRunLimit for a line + * // from text[start] and from styleRuns[styleRunStart] + * // using ubidi_getLogicalRun(para, ...) + *void getLineBreak(const UChar *text, int32_t start, int32_t *pLimit, + * UBiDi *para, + * const StyleRun *styleRuns, int styleRunStart, int *pStyleRunLimit, + * int *pLineWidth); + * + * // render runs on a line sequentially, always from left to right + * + * // prepare rendering a new line + * void startLine(UBiDiDirection textDirection, int lineWidth); + * + * // render a run of text and advance to the right by the run width + * // the text[start..limit-1] is always in logical order + * void renderRun(const UChar *text, int32_t start, int32_t limit, + * UBiDiDirection textDirection, Style style); + * + * // We could compute a cross-product + * // from the style runs with the directional runs + * // and then reorder it. + * // Instead, here we iterate over each run type + * // and render the intersections - + * // with shortcuts in simple (and common) cases. + * // renderParagraph() is the main function. + * + * // render a directional run with + * // (possibly) multiple style runs intersecting with it + * void renderDirectionalRun(const UChar *text, + * int32_t start, int32_t limit, + * UBiDiDirection direction, + * const StyleRun *styleRuns, int styleRunCount) { + * int i; + * + * // iterate over style runs + * if(direction==UBIDI_LTR) { + * int styleLimit; + * + * for(i=0; i<styleRunCount; ++i) { + * styleLimit=styleRun[i].limit; + * if(start<styleLimit) { + * if(styleLimit>limit) { styleLimit=limit; } + * renderRun(text, start, styleLimit, + * direction, styleRun[i].style); + * if(styleLimit==limit) { break; } + * start=styleLimit; + * } + * } + * } else { + * int styleStart; + * + * for(i=styleRunCount-1; i>=0; --i) { + * if(i>0) { + * styleStart=styleRun[i-1].limit; + * } else { + * styleStart=0; + * } + * if(limit>=styleStart) { + * if(styleStart<start) { styleStart=start; } + * renderRun(text, styleStart, limit, + * direction, styleRun[i].style); + * if(styleStart==start) { break; } + * limit=styleStart; + * } + * } + * } + * } + * + * // the line object represents text[start..limit-1] + * void renderLine(UBiDi *line, const UChar *text, + * int32_t start, int32_t limit, + * const StyleRun *styleRuns, int styleRunCount) { + * UBiDiDirection direction=ubidi_getDirection(line); + * if(direction!=UBIDI_MIXED) { + * // unidirectional + * if(styleRunCount<=1) { + * renderRun(text, start, limit, direction, styleRuns[0].style); + * } else { + * renderDirectionalRun(text, start, limit, + * direction, styleRuns, styleRunCount); + * } + * } else { + * // mixed-directional + * int32_t count, i, length; + * UBiDiLevel level; + * + * count=ubidi_countRuns(para, pErrorCode); + * if(U_SUCCESS(*pErrorCode)) { + * if(styleRunCount<=1) { + * Style style=styleRuns[0].style; + * + * // iterate over directional runs + * for(i=0; i<count; ++i) { + * direction=ubidi_getVisualRun(para, i, &start, &length); + * renderRun(text, start, start+length, direction, style); + * } + * } else { + * int32_t j; + * + * // iterate over both directional and style runs + * for(i=0; i<count; ++i) { + * direction=ubidi_getVisualRun(line, i, &start, &length); + * renderDirectionalRun(text, start, start+length, + * direction, styleRuns, styleRunCount); + * } + * } + * } + * } + * } + * + *void renderParagraph(const UChar *text, int32_t length, + * UBiDiDirection textDirection, + * const StyleRun *styleRuns, int styleRunCount, + * int lineWidth, + * UErrorCode *pErrorCode) { + * UBiDi *para; + * + * if(pErrorCode==NULL || U_FAILURE(*pErrorCode) || length<=0) { + * return; + * } + * + * para=ubidi_openSized(length, 0, pErrorCode); + * if(para==NULL) { return; } + * + * ubidi_setPara(para, text, length, + * textDirection ? UBIDI_DEFAULT_RTL : UBIDI_DEFAULT_LTR, + * NULL, pErrorCode); + * if(U_SUCCESS(*pErrorCode)) { + * UBiDiLevel paraLevel=1&ubidi_getParaLevel(para); + * StyleRun styleRun={ length, styleNormal }; + * int width; + * + * if(styleRuns==NULL || styleRunCount<=0) { + * styleRunCount=1; + * styleRuns=&styleRun; + * } + * + * // assume styleRuns[styleRunCount-1].limit>=length + * + * width=getTextWidth(text, 0, length, styleRuns, styleRunCount); + * if(width<=lineWidth) { + * // everything fits onto one line + * + * // prepare rendering a new line from either left or right + * startLine(paraLevel, width); + * + * renderLine(para, text, 0, length, + * styleRuns, styleRunCount); + * } else { + * UBiDi *line; + * + * // we need to render several lines + * line=ubidi_openSized(length, 0, pErrorCode); + * if(line!=NULL) { + * int32_t start=0, limit; + * int styleRunStart=0, styleRunLimit; + * + * for(;;) { + * limit=length; + * styleRunLimit=styleRunCount; + * getLineBreak(text, start, &limit, para, + * styleRuns, styleRunStart, &styleRunLimit, + * &width); + * ubidi_setLine(para, start, limit, line, pErrorCode); + * if(U_SUCCESS(*pErrorCode)) { + * // prepare rendering a new line + * // from either left or right + * startLine(paraLevel, width); + * + * renderLine(line, text, start, limit, + * styleRuns+styleRunStart, + * styleRunLimit-styleRunStart); + * } + * if(limit==length) { break; } + * start=limit; + * styleRunStart=styleRunLimit-1; + * if(start>=styleRuns[styleRunStart].limit) { + * ++styleRunStart; + * } + * } + * + * ubidi_close(line); + * } + * } + * } + * + * ubidi_close(para); + *} + *\endcode + * </pre> + */ + +/*DOCXX_TAG*/ +/*@{*/ + +/** + * UBiDiLevel is the type of the level values in this + * Bidi implementation. + * It holds an embedding level and indicates the visual direction + * by its bit 0 (even/odd value).<p> + * + * It can also hold non-level values for the + * <code>paraLevel</code> and <code>embeddingLevels</code> + * arguments of <code>ubidi_setPara()</code>; there: + * <ul> + * <li>bit 7 of an <code>embeddingLevels[]</code> + * value indicates whether the using application is + * specifying the level of a character to <i>override</i> whatever the + * Bidi implementation would resolve it to.</li> + * <li><code>paraLevel</code> can be set to the + * pseudo-level values <code>UBIDI_DEFAULT_LTR</code> + * and <code>UBIDI_DEFAULT_RTL</code>.</li> + * </ul> + * + * @see ubidi_setPara + * + * <p>The related constants are not real, valid level values. + * <code>UBIDI_DEFAULT_XXX</code> can be used to specify + * a default for the paragraph level for + * when the <code>ubidi_setPara()</code> function + * shall determine it but there is no + * strongly typed character in the input.<p> + * + * Note that the value for <code>UBIDI_DEFAULT_LTR</code> is even + * and the one for <code>UBIDI_DEFAULT_RTL</code> is odd, + * just like with normal LTR and RTL level values - + * these special values are designed that way. Also, the implementation + * assumes that UBIDI_MAX_EXPLICIT_LEVEL is odd. + * + * Note: The numeric values of the related constants will not change: + * They are tied to the use of 7-bit byte values (plus the override bit) + * and of the UBiDiLevel=uint8_t data type in this API. + * + * @see UBIDI_DEFAULT_LTR + * @see UBIDI_DEFAULT_RTL + * @see UBIDI_LEVEL_OVERRIDE + * @see UBIDI_MAX_EXPLICIT_LEVEL + * @stable ICU 2.0 + */ +typedef uint8_t UBiDiLevel; + +/** Paragraph level setting.<p> + * + * Constant indicating that the base direction depends on the first strong + * directional character in the text according to the Unicode Bidirectional + * Algorithm. If no strong directional character is present, + * then set the paragraph level to 0 (left-to-right).<p> + * + * If this value is used in conjunction with reordering modes + * <code>UBIDI_REORDER_INVERSE_LIKE_DIRECT</code> or + * <code>UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL</code>, the text to reorder + * is assumed to be visual LTR, and the text after reordering is required + * to be the corresponding logical string with appropriate contextual + * direction. The direction of the result string will be RTL if either + * the righmost or leftmost strong character of the source text is RTL + * or Arabic Letter, the direction will be LTR otherwise.<p> + * + * If reordering option <code>UBIDI_OPTION_INSERT_MARKS</code> is set, an RLM may + * be added at the beginning of the result string to ensure round trip + * (that the result string, when reordered back to visual, will produce + * the original source text). + * @see UBIDI_REORDER_INVERSE_LIKE_DIRECT + * @see UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL + * @stable ICU 2.0 + */ +#define UBIDI_DEFAULT_LTR 0xfe + +/** Paragraph level setting.<p> + * + * Constant indicating that the base direction depends on the first strong + * directional character in the text according to the Unicode Bidirectional + * Algorithm. If no strong directional character is present, + * then set the paragraph level to 1 (right-to-left).<p> + * + * If this value is used in conjunction with reordering modes + * <code>UBIDI_REORDER_INVERSE_LIKE_DIRECT</code> or + * <code>UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL</code>, the text to reorder + * is assumed to be visual LTR, and the text after reordering is required + * to be the corresponding logical string with appropriate contextual + * direction. The direction of the result string will be RTL if either + * the righmost or leftmost strong character of the source text is RTL + * or Arabic Letter, or if the text contains no strong character; + * the direction will be LTR otherwise.<p> + * + * If reordering option <code>UBIDI_OPTION_INSERT_MARKS</code> is set, an RLM may + * be added at the beginning of the result string to ensure round trip + * (that the result string, when reordered back to visual, will produce + * the original source text). + * @see UBIDI_REORDER_INVERSE_LIKE_DIRECT + * @see UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL + * @stable ICU 2.0 + */ +#define UBIDI_DEFAULT_RTL 0xff + +/** + * Maximum explicit embedding level. + * Same as the max_depth value in the + * <a href="http://www.unicode.org/reports/tr9/#BD2">Unicode Bidirectional Algorithm</a>. + * (The maximum resolved level can be up to <code>UBIDI_MAX_EXPLICIT_LEVEL+1</code>). + * @stable ICU 2.0 + */ +#define UBIDI_MAX_EXPLICIT_LEVEL 125 + +/** Bit flag for level input. + * Overrides directional properties. + * @stable ICU 2.0 + */ +#define UBIDI_LEVEL_OVERRIDE 0x80 + +/** + * Special value which can be returned by the mapping functions when a logical + * index has no corresponding visual index or vice-versa. This may happen + * for the logical-to-visual mapping of a Bidi control when option + * <code>#UBIDI_OPTION_REMOVE_CONTROLS</code> is specified. This can also happen + * for the visual-to-logical mapping of a Bidi mark (LRM or RLM) inserted + * by option <code>#UBIDI_OPTION_INSERT_MARKS</code>. + * @see ubidi_getVisualIndex + * @see ubidi_getVisualMap + * @see ubidi_getLogicalIndex + * @see ubidi_getLogicalMap + * @stable ICU 3.6 + */ +#define UBIDI_MAP_NOWHERE (-1) + +/** + * <code>UBiDiDirection</code> values indicate the text direction. + * @stable ICU 2.0 + */ +enum UBiDiDirection { + /** Left-to-right text. This is a 0 value. + * <ul> + * <li>As return value for <code>ubidi_getDirection()</code>, it means + * that the source string contains no right-to-left characters, or + * that the source string is empty and the paragraph level is even. + * <li> As return value for <code>ubidi_getBaseDirection()</code>, it + * means that the first strong character of the source string has + * a left-to-right direction. + * </ul> + * @stable ICU 2.0 + */ + UBIDI_LTR, + /** Right-to-left text. This is a 1 value. + * <ul> + * <li>As return value for <code>ubidi_getDirection()</code>, it means + * that the source string contains no left-to-right characters, or + * that the source string is empty and the paragraph level is odd. + * <li> As return value for <code>ubidi_getBaseDirection()</code>, it + * means that the first strong character of the source string has + * a right-to-left direction. + * </ul> + * @stable ICU 2.0 + */ + UBIDI_RTL, + /** Mixed-directional text. + * <p>As return value for <code>ubidi_getDirection()</code>, it means + * that the source string contains both left-to-right and + * right-to-left characters. + * @stable ICU 2.0 + */ + UBIDI_MIXED, + /** No strongly directional text. + * <p>As return value for <code>ubidi_getBaseDirection()</code>, it means + * that the source string is missing or empty, or contains neither left-to-right + * nor right-to-left characters. + * @stable ICU 4.6 + */ + UBIDI_NEUTRAL +}; + +/** @stable ICU 2.0 */ +typedef enum UBiDiDirection UBiDiDirection; + +/** + * Forward declaration of the <code>UBiDi</code> structure for the declaration of + * the API functions. Its fields are implementation-specific.<p> + * This structure holds information about a paragraph (or multiple paragraphs) + * of text with Bidi-algorithm-related details, or about one line of + * such a paragraph.<p> + * Reordering can be done on a line, or on one or more paragraphs which are + * then interpreted each as one single line. + * @stable ICU 2.0 + */ +struct UBiDi; + +/** @stable ICU 2.0 */ +typedef struct UBiDi UBiDi; + +/** + * Allocate a <code>UBiDi</code> structure. + * Such an object is initially empty. It is assigned + * the Bidi properties of a piece of text containing one or more paragraphs + * by <code>ubidi_setPara()</code> + * or the Bidi properties of a line within a paragraph by + * <code>ubidi_setLine()</code>.<p> + * This object can be reused for as long as it is not deallocated + * by calling <code>ubidi_close()</code>.<p> + * <code>ubidi_setPara()</code> and <code>ubidi_setLine()</code> will allocate + * additional memory for internal structures as necessary. + * + * @return An empty <code>UBiDi</code> object. + * @stable ICU 2.0 + */ +U_CAPI UBiDi * U_EXPORT2 +ubidi_open(void); + +/** + * Allocate a <code>UBiDi</code> structure with preallocated memory + * for internal structures. + * This function provides a <code>UBiDi</code> object like <code>ubidi_open()</code> + * with no arguments, but it also preallocates memory for internal structures + * according to the sizings supplied by the caller.<p> + * Subsequent functions will not allocate any more memory, and are thus + * guaranteed not to fail because of lack of memory.<p> + * The preallocation can be limited to some of the internal memory + * by setting some values to 0 here. That means that if, e.g., + * <code>maxRunCount</code> cannot be reasonably predetermined and should not + * be set to <code>maxLength</code> (the only failproof value) to avoid + * wasting memory, then <code>maxRunCount</code> could be set to 0 here + * and the internal structures that are associated with it will be allocated + * on demand, just like with <code>ubidi_open()</code>. + * + * @param maxLength is the maximum text or line length that internal memory + * will be preallocated for. An attempt to associate this object with a + * longer text will fail, unless this value is 0, which leaves the allocation + * up to the implementation. + * + * @param maxRunCount is the maximum anticipated number of same-level runs + * that internal memory will be preallocated for. An attempt to access + * visual runs on an object that was not preallocated for as many runs + * as the text was actually resolved to will fail, + * unless this value is 0, which leaves the allocation up to the implementation.<br><br> + * The number of runs depends on the actual text and maybe anywhere between + * 1 and <code>maxLength</code>. It is typically small. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @return An empty <code>UBiDi</code> object with preallocated memory. + * @stable ICU 2.0 + */ +U_CAPI UBiDi * U_EXPORT2 +ubidi_openSized(int32_t maxLength, int32_t maxRunCount, UErrorCode *pErrorCode); + +/** + * <code>ubidi_close()</code> must be called to free the memory + * associated with a UBiDi object.<p> + * + * <strong>Important: </strong> + * A parent <code>UBiDi</code> object must not be destroyed or reused if + * it still has children. + * If a <code>UBiDi</code> object has become the <i>child</i> + * of another one (its <i>parent</i>) by calling + * <code>ubidi_setLine()</code>, then the child object must + * be destroyed (closed) or reused (by calling + * <code>ubidi_setPara()</code> or <code>ubidi_setLine()</code>) + * before the parent object. + * + * @param pBiDi is a <code>UBiDi</code> object. + * + * @see ubidi_setPara + * @see ubidi_setLine + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_close(UBiDi *pBiDi); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUBiDiPointer + * "Smart pointer" class, closes a UBiDi via ubidi_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUBiDiPointer, UBiDi, ubidi_close); + +U_NAMESPACE_END + +#endif + +/** + * Modify the operation of the Bidi algorithm such that it + * approximates an "inverse Bidi" algorithm. This function + * must be called before <code>ubidi_setPara()</code>. + * + * <p>The normal operation of the Bidi algorithm as described + * in the Unicode Technical Report is to take text stored in logical + * (keyboard, typing) order and to determine the reordering of it for visual + * rendering. + * Some legacy systems store text in visual order, and for operations + * with standard, Unicode-based algorithms, the text needs to be transformed + * to logical order. This is effectively the inverse algorithm of the + * described Bidi algorithm. Note that there is no standard algorithm for + * this "inverse Bidi" and that the current implementation provides only an + * approximation of "inverse Bidi".</p> + * + * <p>With <code>isInverse</code> set to <code>true</code>, + * this function changes the behavior of some of the subsequent functions + * in a way that they can be used for the inverse Bidi algorithm. + * Specifically, runs of text with numeric characters will be treated in a + * special way and may need to be surrounded with LRM characters when they are + * written in reordered sequence.</p> + * + * <p>Output runs should be retrieved using <code>ubidi_getVisualRun()</code>. + * Since the actual input for "inverse Bidi" is visually ordered text and + * <code>ubidi_getVisualRun()</code> gets the reordered runs, these are actually + * the runs of the logically ordered output.</p> + * + * <p>Calling this function with argument <code>isInverse</code> set to + * <code>true</code> is equivalent to calling + * <code>ubidi_setReorderingMode</code> with argument + * <code>reorderingMode</code> + * set to <code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code>.<br> + * Calling this function with argument <code>isInverse</code> set to + * <code>false</code> is equivalent to calling + * <code>ubidi_setReorderingMode</code> with argument + * <code>reorderingMode</code> + * set to <code>#UBIDI_REORDER_DEFAULT</code>. + * + * @param pBiDi is a <code>UBiDi</code> object. + * + * @param isInverse specifies "forward" or "inverse" Bidi operation. + * + * @see ubidi_setPara + * @see ubidi_writeReordered + * @see ubidi_setReorderingMode + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_setInverse(UBiDi *pBiDi, UBool isInverse); + +/** + * Is this Bidi object set to perform the inverse Bidi algorithm? + * <p>Note: calling this function after setting the reordering mode with + * <code>ubidi_setReorderingMode</code> will return <code>true</code> if the + * reordering mode was set to <code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code>, + * <code>false</code> for all other values.</p> + * + * @param pBiDi is a <code>UBiDi</code> object. + * @return true if the Bidi object is set to perform the inverse Bidi algorithm + * by handling numbers as L. + * + * @see ubidi_setInverse + * @see ubidi_setReorderingMode + * @stable ICU 2.0 + */ + +U_CAPI UBool U_EXPORT2 +ubidi_isInverse(UBiDi *pBiDi); + +/** + * Specify whether block separators must be allocated level zero, + * so that successive paragraphs will progress from left to right. + * This function must be called before <code>ubidi_setPara()</code>. + * Paragraph separators (B) may appear in the text. Setting them to level zero + * means that all paragraph separators (including one possibly appearing + * in the last text position) are kept in the reordered text after the text + * that they follow in the source text. + * When this feature is not enabled, a paragraph separator at the last + * position of the text before reordering will go to the first position + * of the reordered text when the paragraph level is odd. + * + * @param pBiDi is a <code>UBiDi</code> object. + * + * @param orderParagraphsLTR specifies whether paragraph separators (B) must + * receive level 0, so that successive paragraphs progress from left to right. + * + * @see ubidi_setPara + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +ubidi_orderParagraphsLTR(UBiDi *pBiDi, UBool orderParagraphsLTR); + +/** + * Is this Bidi object set to allocate level 0 to block separators so that + * successive paragraphs progress from left to right? + * + * @param pBiDi is a <code>UBiDi</code> object. + * @return true if the Bidi object is set to allocate level 0 to block + * separators. + * + * @see ubidi_orderParagraphsLTR + * @stable ICU 3.4 + */ +U_CAPI UBool U_EXPORT2 +ubidi_isOrderParagraphsLTR(UBiDi *pBiDi); + +/** + * <code>UBiDiReorderingMode</code> values indicate which variant of the Bidi + * algorithm to use. + * + * @see ubidi_setReorderingMode + * @stable ICU 3.6 + */ +typedef enum UBiDiReorderingMode { + /** Regular Logical to Visual Bidi algorithm according to Unicode. + * This is a 0 value. + * @stable ICU 3.6 */ + UBIDI_REORDER_DEFAULT = 0, + /** Logical to Visual algorithm which handles numbers in a way which + * mimics the behavior of Windows XP. + * @stable ICU 3.6 */ + UBIDI_REORDER_NUMBERS_SPECIAL, + /** Logical to Visual algorithm grouping numbers with adjacent R characters + * (reversible algorithm). + * @stable ICU 3.6 */ + UBIDI_REORDER_GROUP_NUMBERS_WITH_R, + /** Reorder runs only to transform a Logical LTR string to the Logical RTL + * string with the same display, or vice-versa.<br> + * If this mode is set together with option + * <code>#UBIDI_OPTION_INSERT_MARKS</code>, some Bidi controls in the source + * text may be removed and other controls may be added to produce the + * minimum combination which has the required display. + * @stable ICU 3.6 */ + UBIDI_REORDER_RUNS_ONLY, + /** Visual to Logical algorithm which handles numbers like L + * (same algorithm as selected by <code>ubidi_setInverse(true)</code>. + * @see ubidi_setInverse + * @stable ICU 3.6 */ + UBIDI_REORDER_INVERSE_NUMBERS_AS_L, + /** Visual to Logical algorithm equivalent to the regular Logical to Visual + * algorithm. + * @stable ICU 3.6 */ + UBIDI_REORDER_INVERSE_LIKE_DIRECT, + /** Inverse Bidi (Visual to Logical) algorithm for the + * <code>UBIDI_REORDER_NUMBERS_SPECIAL</code> Bidi algorithm. + * @stable ICU 3.6 */ + UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL, +#ifndef U_HIDE_DEPRECATED_API + /** + * Number of values for reordering mode. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UBIDI_REORDER_COUNT +#endif // U_HIDE_DEPRECATED_API +} UBiDiReorderingMode; + +/** + * Modify the operation of the Bidi algorithm such that it implements some + * variant to the basic Bidi algorithm or approximates an "inverse Bidi" + * algorithm, depending on different values of the "reordering mode". + * This function must be called before <code>ubidi_setPara()</code>, and stays + * in effect until called again with a different argument. + * + * <p>The normal operation of the Bidi algorithm as described + * in the Unicode Standard Annex #9 is to take text stored in logical + * (keyboard, typing) order and to determine how to reorder it for visual + * rendering.</p> + * + * <p>With the reordering mode set to a value other than + * <code>#UBIDI_REORDER_DEFAULT</code>, this function changes the behavior of + * some of the subsequent functions in a way such that they implement an + * inverse Bidi algorithm or some other algorithm variants.</p> + * + * <p>Some legacy systems store text in visual order, and for operations + * with standard, Unicode-based algorithms, the text needs to be transformed + * into logical order. This is effectively the inverse algorithm of the + * described Bidi algorithm. Note that there is no standard algorithm for + * this "inverse Bidi", so a number of variants are implemented here.</p> + * + * <p>In other cases, it may be desirable to emulate some variant of the + * Logical to Visual algorithm (e.g. one used in MS Windows), or perform a + * Logical to Logical transformation.</p> + * + * <ul> + * <li>When the reordering mode is set to <code>#UBIDI_REORDER_DEFAULT</code>, + * the standard Bidi Logical to Visual algorithm is applied.</li> + * + * <li>When the reordering mode is set to + * <code>#UBIDI_REORDER_NUMBERS_SPECIAL</code>, + * the algorithm used to perform Bidi transformations when calling + * <code>ubidi_setPara</code> should approximate the algorithm used in + * Microsoft Windows XP rather than strictly conform to the Unicode Bidi + * algorithm. + * <br> + * The differences between the basic algorithm and the algorithm addressed + * by this option are as follows: + * <ul> + * <li>Within text at an even embedding level, the sequence "123AB" + * (where AB represent R or AL letters) is transformed to "123BA" by the + * Unicode algorithm and to "BA123" by the Windows algorithm.</li> + * <li>Arabic-Indic numbers (AN) are handled by the Windows algorithm just + * like regular numbers (EN).</li> + * </ul></li> + * + * <li>When the reordering mode is set to + * <code>#UBIDI_REORDER_GROUP_NUMBERS_WITH_R</code>, + * numbers located between LTR text and RTL text are associated with the RTL + * text. For instance, an LTR paragraph with content "abc 123 DEF" (where + * upper case letters represent RTL characters) will be transformed to + * "abc FED 123" (and not "abc 123 FED"), "DEF 123 abc" will be transformed + * to "123 FED abc" and "123 FED abc" will be transformed to "DEF 123 abc". + * This makes the algorithm reversible and makes it useful when round trip + * (from visual to logical and back to visual) must be achieved without + * adding LRM characters. However, this is a variation from the standard + * Unicode Bidi algorithm.<br> + * The source text should not contain Bidi control characters other than LRM + * or RLM.</li> + * + * <li>When the reordering mode is set to + * <code>#UBIDI_REORDER_RUNS_ONLY</code>, + * a "Logical to Logical" transformation must be performed: + * <ul> + * <li>If the default text level of the source text (argument <code>paraLevel</code> + * in <code>ubidi_setPara</code>) is even, the source text will be handled as + * LTR logical text and will be transformed to the RTL logical text which has + * the same LTR visual display.</li> + * <li>If the default level of the source text is odd, the source text + * will be handled as RTL logical text and will be transformed to the + * LTR logical text which has the same LTR visual display.</li> + * </ul> + * This mode may be needed when logical text which is basically Arabic or + * Hebrew, with possible included numbers or phrases in English, has to be + * displayed as if it had an even embedding level (this can happen if the + * displaying application treats all text as if it was basically LTR). + * <br> + * This mode may also be needed in the reverse case, when logical text which is + * basically English, with possible included phrases in Arabic or Hebrew, has to + * be displayed as if it had an odd embedding level. + * <br> + * Both cases could be handled by adding LRE or RLE at the head of the text, + * if the display subsystem supports these formatting controls. If it does not, + * the problem may be handled by transforming the source text in this mode + * before displaying it, so that it will be displayed properly.<br> + * The source text should not contain Bidi control characters other than LRM + * or RLM.</li> + * + * <li>When the reordering mode is set to + * <code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code>, an "inverse Bidi" algorithm + * is applied. + * Runs of text with numeric characters will be treated like LTR letters and + * may need to be surrounded with LRM characters when they are written in + * reordered sequence (the option <code>#UBIDI_INSERT_LRM_FOR_NUMERIC</code> can + * be used with function <code>ubidi_writeReordered</code> to this end. This + * mode is equivalent to calling <code>ubidi_setInverse()</code> with + * argument <code>isInverse</code> set to <code>true</code>.</li> + * + * <li>When the reordering mode is set to + * <code>#UBIDI_REORDER_INVERSE_LIKE_DIRECT</code>, the "direct" Logical to Visual + * Bidi algorithm is used as an approximation of an "inverse Bidi" algorithm. + * This mode is similar to mode <code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code> + * but is closer to the regular Bidi algorithm. + * <br> + * For example, an LTR paragraph with the content "FED 123 456 CBA" (where + * upper case represents RTL characters) will be transformed to + * "ABC 456 123 DEF", as opposed to "DEF 123 456 ABC" + * with mode <code>UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code>.<br> + * When used in conjunction with option + * <code>#UBIDI_OPTION_INSERT_MARKS</code>, this mode generally + * adds Bidi marks to the output significantly more sparingly than mode + * <code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code> with option + * <code>#UBIDI_INSERT_LRM_FOR_NUMERIC</code> in calls to + * <code>ubidi_writeReordered</code>.</li> + * + * <li>When the reordering mode is set to + * <code>#UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL</code>, the Logical to Visual + * Bidi algorithm used in Windows XP is used as an approximation of an "inverse Bidi" algorithm. + * <br> + * For example, an LTR paragraph with the content "abc FED123" (where + * upper case represents RTL characters) will be transformed to "abc 123DEF."</li> + * </ul> + * + * <p>In all the reordering modes specifying an "inverse Bidi" algorithm + * (i.e. those with a name starting with <code>UBIDI_REORDER_INVERSE</code>), + * output runs should be retrieved using + * <code>ubidi_getVisualRun()</code>, and the output text with + * <code>ubidi_writeReordered()</code>. The caller should keep in mind that in + * "inverse Bidi" modes the input is actually visually ordered text and + * reordered output returned by <code>ubidi_getVisualRun()</code> or + * <code>ubidi_writeReordered()</code> are actually runs or character string + * of logically ordered output.<br> + * For all the "inverse Bidi" modes, the source text should not contain + * Bidi control characters other than LRM or RLM.</p> + * + * <p>Note that option <code>#UBIDI_OUTPUT_REVERSE</code> of + * <code>ubidi_writeReordered</code> has no useful meaning and should not be + * used in conjunction with any value of the reordering mode specifying + * "inverse Bidi" or with value <code>UBIDI_REORDER_RUNS_ONLY</code>. + * + * @param pBiDi is a <code>UBiDi</code> object. + * @param reorderingMode specifies the required variant of the Bidi algorithm. + * + * @see UBiDiReorderingMode + * @see ubidi_setInverse + * @see ubidi_setPara + * @see ubidi_writeReordered + * @stable ICU 3.6 + */ +U_CAPI void U_EXPORT2 +ubidi_setReorderingMode(UBiDi *pBiDi, UBiDiReorderingMode reorderingMode); + +/** + * What is the requested reordering mode for a given Bidi object? + * + * @param pBiDi is a <code>UBiDi</code> object. + * @return the current reordering mode of the Bidi object + * @see ubidi_setReorderingMode + * @stable ICU 3.6 + */ +U_CAPI UBiDiReorderingMode U_EXPORT2 +ubidi_getReorderingMode(UBiDi *pBiDi); + +/** + * <code>UBiDiReorderingOption</code> values indicate which options are + * specified to affect the Bidi algorithm. + * + * @see ubidi_setReorderingOptions + * @stable ICU 3.6 + */ +typedef enum UBiDiReorderingOption { + /** + * option value for <code>ubidi_setReorderingOptions</code>: + * disable all the options which can be set with this function + * @see ubidi_setReorderingOptions + * @stable ICU 3.6 + */ + UBIDI_OPTION_DEFAULT = 0, + + /** + * option bit for <code>ubidi_setReorderingOptions</code>: + * insert Bidi marks (LRM or RLM) when needed to ensure correct result of + * a reordering to a Logical order + * + * <p>This option must be set or reset before calling + * <code>ubidi_setPara</code>.</p> + * + * <p>This option is significant only with reordering modes which generate + * a result with Logical order, specifically:</p> + * <ul> + * <li><code>#UBIDI_REORDER_RUNS_ONLY</code></li> + * <li><code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code></li> + * <li><code>#UBIDI_REORDER_INVERSE_LIKE_DIRECT</code></li> + * <li><code>#UBIDI_REORDER_INVERSE_FOR_NUMBERS_SPECIAL</code></li> + * </ul> + * + * <p>If this option is set in conjunction with reordering mode + * <code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code> or with calling + * <code>ubidi_setInverse(true)</code>, it implies + * option <code>#UBIDI_INSERT_LRM_FOR_NUMERIC</code> + * in calls to function <code>ubidi_writeReordered()</code>.</p> + * + * <p>For other reordering modes, a minimum number of LRM or RLM characters + * will be added to the source text after reordering it so as to ensure + * round trip, i.e. when applying the inverse reordering mode on the + * resulting logical text with removal of Bidi marks + * (option <code>#UBIDI_OPTION_REMOVE_CONTROLS</code> set before calling + * <code>ubidi_setPara()</code> or option <code>#UBIDI_REMOVE_BIDI_CONTROLS</code> + * in <code>ubidi_writeReordered</code>), the result will be identical to the + * source text in the first transformation. + * + * <p>This option will be ignored if specified together with option + * <code>#UBIDI_OPTION_REMOVE_CONTROLS</code>. It inhibits option + * <code>UBIDI_REMOVE_BIDI_CONTROLS</code> in calls to function + * <code>ubidi_writeReordered()</code> and it implies option + * <code>#UBIDI_INSERT_LRM_FOR_NUMERIC</code> in calls to function + * <code>ubidi_writeReordered()</code> if the reordering mode is + * <code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code>.</p> + * + * @see ubidi_setReorderingMode + * @see ubidi_setReorderingOptions + * @stable ICU 3.6 + */ + UBIDI_OPTION_INSERT_MARKS = 1, + + /** + * option bit for <code>ubidi_setReorderingOptions</code>: + * remove Bidi control characters + * + * <p>This option must be set or reset before calling + * <code>ubidi_setPara</code>.</p> + * + * <p>This option nullifies option <code>#UBIDI_OPTION_INSERT_MARKS</code>. + * It inhibits option <code>#UBIDI_INSERT_LRM_FOR_NUMERIC</code> in calls + * to function <code>ubidi_writeReordered()</code> and it implies option + * <code>#UBIDI_REMOVE_BIDI_CONTROLS</code> in calls to that function.</p> + * + * @see ubidi_setReorderingMode + * @see ubidi_setReorderingOptions + * @stable ICU 3.6 + */ + UBIDI_OPTION_REMOVE_CONTROLS = 2, + + /** + * option bit for <code>ubidi_setReorderingOptions</code>: + * process the output as part of a stream to be continued + * + * <p>This option must be set or reset before calling + * <code>ubidi_setPara</code>.</p> + * + * <p>This option specifies that the caller is interested in processing large + * text object in parts. + * The results of the successive calls are expected to be concatenated by the + * caller. Only the call for the last part will have this option bit off.</p> + * + * <p>When this option bit is on, <code>ubidi_setPara()</code> may process + * less than the full source text in order to truncate the text at a meaningful + * boundary. The caller should call <code>ubidi_getProcessedLength()</code> + * immediately after calling <code>ubidi_setPara()</code> in order to + * determine how much of the source text has been processed. + * Source text beyond that length should be resubmitted in following calls to + * <code>ubidi_setPara</code>. The processed length may be less than + * the length of the source text if a character preceding the last character of + * the source text constitutes a reasonable boundary (like a block separator) + * for text to be continued.<br> + * If the last character of the source text constitutes a reasonable + * boundary, the whole text will be processed at once.<br> + * If nowhere in the source text there exists + * such a reasonable boundary, the processed length will be zero.<br> + * The caller should check for such an occurrence and do one of the following: + * <ul><li>submit a larger amount of text with a better chance to include + * a reasonable boundary.</li> + * <li>resubmit the same text after turning off option + * <code>UBIDI_OPTION_STREAMING</code>.</li></ul> + * In all cases, this option should be turned off before processing the last + * part of the text.</p> + * + * <p>When the <code>UBIDI_OPTION_STREAMING</code> option is used, + * it is recommended to call <code>ubidi_orderParagraphsLTR()</code> with + * argument <code>orderParagraphsLTR</code> set to <code>true</code> before + * calling <code>ubidi_setPara</code> so that later paragraphs may be + * concatenated to previous paragraphs on the right.</p> + * + * @see ubidi_setReorderingMode + * @see ubidi_setReorderingOptions + * @see ubidi_getProcessedLength + * @see ubidi_orderParagraphsLTR + * @stable ICU 3.6 + */ + UBIDI_OPTION_STREAMING = 4 +} UBiDiReorderingOption; + +/** + * Specify which of the reordering options + * should be applied during Bidi transformations. + * + * @param pBiDi is a <code>UBiDi</code> object. + * @param reorderingOptions is a combination of zero or more of the following + * options: + * <code>#UBIDI_OPTION_DEFAULT</code>, <code>#UBIDI_OPTION_INSERT_MARKS</code>, + * <code>#UBIDI_OPTION_REMOVE_CONTROLS</code>, <code>#UBIDI_OPTION_STREAMING</code>. + * + * @see ubidi_getReorderingOptions + * @stable ICU 3.6 + */ +U_CAPI void U_EXPORT2 +ubidi_setReorderingOptions(UBiDi *pBiDi, uint32_t reorderingOptions); + +/** + * What are the reordering options applied to a given Bidi object? + * + * @param pBiDi is a <code>UBiDi</code> object. + * @return the current reordering options of the Bidi object + * @see ubidi_setReorderingOptions + * @stable ICU 3.6 + */ +U_CAPI uint32_t U_EXPORT2 +ubidi_getReorderingOptions(UBiDi *pBiDi); + +/** + * Set the context before a call to ubidi_setPara().<p> + * + * ubidi_setPara() computes the left-right directionality for a given piece + * of text which is supplied as one of its arguments. Sometimes this piece + * of text (the "main text") should be considered in context, because text + * appearing before ("prologue") and/or after ("epilogue") the main text + * may affect the result of this computation.<p> + * + * This function specifies the prologue and/or the epilogue for the next + * call to ubidi_setPara(). The characters specified as prologue and + * epilogue should not be modified by the calling program until the call + * to ubidi_setPara() has returned. If successive calls to ubidi_setPara() + * all need specification of a context, ubidi_setContext() must be called + * before each call to ubidi_setPara(). In other words, a context is not + * "remembered" after the following successful call to ubidi_setPara().<p> + * + * If a call to ubidi_setPara() specifies UBIDI_DEFAULT_LTR or + * UBIDI_DEFAULT_RTL as paraLevel and is preceded by a call to + * ubidi_setContext() which specifies a prologue, the paragraph level will + * be computed taking in consideration the text in the prologue.<p> + * + * When ubidi_setPara() is called without a previous call to + * ubidi_setContext, the main text is handled as if preceded and followed + * by strong directional characters at the current paragraph level. + * Calling ubidi_setContext() with specification of a prologue will change + * this behavior by handling the main text as if preceded by the last + * strong character appearing in the prologue, if any. + * Calling ubidi_setContext() with specification of an epilogue will change + * the behavior of ubidi_setPara() by handling the main text as if followed + * by the first strong character or digit appearing in the epilogue, if any.<p> + * + * Note 1: if <code>ubidi_setContext</code> is called repeatedly without + * calling <code>ubidi_setPara</code>, the earlier calls have no effect, + * only the last call will be remembered for the next call to + * <code>ubidi_setPara</code>.<p> + * + * Note 2: calling <code>ubidi_setContext(pBiDi, NULL, 0, NULL, 0, &errorCode)</code> + * cancels any previous setting of non-empty prologue or epilogue. + * The next call to <code>ubidi_setPara()</code> will process no + * prologue or epilogue.<p> + * + * Note 3: users must be aware that even after setting the context + * before a call to ubidi_setPara() to perform e.g. a logical to visual + * transformation, the resulting string may not be identical to what it + * would have been if all the text, including prologue and epilogue, had + * been processed together.<br> + * Example (upper case letters represent RTL characters):<br> + * prologue = "<code>abc DE</code>"<br> + * epilogue = none<br> + * main text = "<code>FGH xyz</code>"<br> + * paraLevel = UBIDI_LTR<br> + * display without prologue = "<code>HGF xyz</code>" + * ("HGF" is adjacent to "xyz")<br> + * display with prologue = "<code>abc HGFED xyz</code>" + * ("HGF" is not adjacent to "xyz")<br> + * + * @param pBiDi is a paragraph <code>UBiDi</code> object. + * + * @param prologue is a pointer to the text which precedes the text that + * will be specified in a coming call to ubidi_setPara(). + * If there is no prologue to consider, then <code>proLength</code> + * must be zero and this pointer can be NULL. + * + * @param proLength is the length of the prologue; if <code>proLength==-1</code> + * then the prologue must be zero-terminated. + * Otherwise proLength must be >= 0. If <code>proLength==0</code>, it means + * that there is no prologue to consider. + * + * @param epilogue is a pointer to the text which follows the text that + * will be specified in a coming call to ubidi_setPara(). + * If there is no epilogue to consider, then <code>epiLength</code> + * must be zero and this pointer can be NULL. + * + * @param epiLength is the length of the epilogue; if <code>epiLength==-1</code> + * then the epilogue must be zero-terminated. + * Otherwise epiLength must be >= 0. If <code>epiLength==0</code>, it means + * that there is no epilogue to consider. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @see ubidi_setPara + * @stable ICU 4.8 + */ +U_CAPI void U_EXPORT2 +ubidi_setContext(UBiDi *pBiDi, + const UChar *prologue, int32_t proLength, + const UChar *epilogue, int32_t epiLength, + UErrorCode *pErrorCode); + +/** + * Perform the Unicode Bidi algorithm. It is defined in the + * <a href="http://www.unicode.org/unicode/reports/tr9/">Unicode Standard Annex #9</a>, + * version 13, + * also described in The Unicode Standard, Version 4.0 .<p> + * + * This function takes a piece of plain text containing one or more paragraphs, + * with or without externally specified embedding levels from <i>styled</i> + * text and computes the left-right-directionality of each character.<p> + * + * If the entire text is all of the same directionality, then + * the function may not perform all the steps described by the algorithm, + * i.e., some levels may not be the same as if all steps were performed. + * This is not relevant for unidirectional text.<br> + * For example, in pure LTR text with numbers the numbers would get + * a resolved level of 2 higher than the surrounding text according to + * the algorithm. This implementation may set all resolved levels to + * the same value in such a case.<p> + * + * The text can be composed of multiple paragraphs. Occurrence of a block + * separator in the text terminates a paragraph, and whatever comes next starts + * a new paragraph. The exception to this rule is when a Carriage Return (CR) + * is followed by a Line Feed (LF). Both CR and LF are block separators, but + * in that case, the pair of characters is considered as terminating the + * preceding paragraph, and a new paragraph will be started by a character + * coming after the LF. + * + * @param pBiDi A <code>UBiDi</code> object allocated with <code>ubidi_open()</code> + * which will be set to contain the reordering information, + * especially the resolved levels for all the characters in <code>text</code>. + * + * @param text is a pointer to the text that the Bidi algorithm will be performed on. + * This pointer is stored in the UBiDi object and can be retrieved + * with <code>ubidi_getText()</code>.<br> + * <strong>Note:</strong> the text must be (at least) <code>length</code> long. + * + * @param length is the length of the text; if <code>length==-1</code> then + * the text must be zero-terminated. + * + * @param paraLevel specifies the default level for the text; + * it is typically 0 (LTR) or 1 (RTL). + * If the function shall determine the paragraph level from the text, + * then <code>paraLevel</code> can be set to + * either <code>#UBIDI_DEFAULT_LTR</code> + * or <code>#UBIDI_DEFAULT_RTL</code>; if the text contains multiple + * paragraphs, the paragraph level shall be determined separately for + * each paragraph; if a paragraph does not include any strongly typed + * character, then the desired default is used (0 for LTR or 1 for RTL). + * Any other value between 0 and <code>#UBIDI_MAX_EXPLICIT_LEVEL</code> + * is also valid, with odd levels indicating RTL. + * + * @param embeddingLevels (in) may be used to preset the embedding and override levels, + * ignoring characters like LRE and PDF in the text. + * A level overrides the directional property of its corresponding + * (same index) character if the level has the + * <code>#UBIDI_LEVEL_OVERRIDE</code> bit set.<br><br> + * Aside from that bit, it must be + * <code>paraLevel<=embeddingLevels[]<=UBIDI_MAX_EXPLICIT_LEVEL</code>, + * except that level 0 is always allowed. + * Level 0 for a paragraph separator prevents reordering of paragraphs; + * this only works reliably if <code>#UBIDI_LEVEL_OVERRIDE</code> + * is also set for paragraph separators. + * Level 0 for other characters is treated as a wildcard + * and is lifted up to the resolved level of the surrounding paragraph.<br><br> + * <strong>Caution: </strong>A copy of this pointer, not of the levels, + * will be stored in the <code>UBiDi</code> object; + * the <code>embeddingLevels</code> array must not be + * deallocated before the <code>UBiDi</code> structure is destroyed or reused, + * and the <code>embeddingLevels</code> + * should not be modified to avoid unexpected results on subsequent Bidi operations. + * However, the <code>ubidi_setPara()</code> and + * <code>ubidi_setLine()</code> functions may modify some or all of the levels.<br><br> + * After the <code>UBiDi</code> object is reused or destroyed, the caller + * must take care of the deallocation of the <code>embeddingLevels</code> array.<br><br> + * <strong>Note:</strong> the <code>embeddingLevels</code> array must be + * at least <code>length</code> long. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @param pErrorCode must be a valid pointer to an error code value. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_setPara(UBiDi *pBiDi, const UChar *text, int32_t length, + UBiDiLevel paraLevel, UBiDiLevel *embeddingLevels, + UErrorCode *pErrorCode); + +/** + * <code>ubidi_setLine()</code> sets a <code>UBiDi</code> to + * contain the reordering information, especially the resolved levels, + * for all the characters in a line of text. This line of text is + * specified by referring to a <code>UBiDi</code> object representing + * this information for a piece of text containing one or more paragraphs, + * and by specifying a range of indexes in this text.<p> + * In the new line object, the indexes will range from 0 to <code>limit-start-1</code>.<p> + * + * This is used after calling <code>ubidi_setPara()</code> + * for a piece of text, and after line-breaking on that text. + * It is not necessary if each paragraph is treated as a single line.<p> + * + * After line-breaking, rules (L1) and (L2) for the treatment of + * trailing WS and for reordering are performed on + * a <code>UBiDi</code> object that represents a line.<p> + * + * <strong>Important: </strong><code>pLineBiDi</code> shares data with + * <code>pParaBiDi</code>. + * You must destroy or reuse <code>pLineBiDi</code> before <code>pParaBiDi</code>. + * In other words, you must destroy or reuse the <code>UBiDi</code> object for a line + * before the object for its parent paragraph.<p> + * + * The text pointer that was stored in <code>pParaBiDi</code> is also copied, + * and <code>start</code> is added to it so that it points to the beginning of the + * line for this object. + * + * @param pParaBiDi is the parent paragraph object. It must have been set + * by a successful call to ubidi_setPara. + * + * @param start is the line's first index into the text. + * + * @param limit is just behind the line's last index into the text + * (its last index +1).<br> + * It must be <code>0<=start<limit<=</code>containing paragraph limit. + * If the specified line crosses a paragraph boundary, the function + * will terminate with error code U_ILLEGAL_ARGUMENT_ERROR. + * + * @param pLineBiDi is the object that will now represent a line of the text. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @see ubidi_setPara + * @see ubidi_getProcessedLength + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_setLine(const UBiDi *pParaBiDi, + int32_t start, int32_t limit, + UBiDi *pLineBiDi, + UErrorCode *pErrorCode); + +/** + * Get the directionality of the text. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @return a value of <code>UBIDI_LTR</code>, <code>UBIDI_RTL</code> + * or <code>UBIDI_MIXED</code> + * that indicates if the entire text + * represented by this object is unidirectional, + * and which direction, or if it is mixed-directional. + * Note - The value <code>UBIDI_NEUTRAL</code> is never returned from this method. + * + * @see UBiDiDirection + * @stable ICU 2.0 + */ +U_CAPI UBiDiDirection U_EXPORT2 +ubidi_getDirection(const UBiDi *pBiDi); + +/** + * Gets the base direction of the text provided according + * to the Unicode Bidirectional Algorithm. The base direction + * is derived from the first character in the string with bidirectional + * character type L, R, or AL. If the first such character has type L, + * <code>UBIDI_LTR</code> is returned. If the first such character has + * type R or AL, <code>UBIDI_RTL</code> is returned. If the string does + * not contain any character of these types, then + * <code>UBIDI_NEUTRAL</code> is returned. + * + * This is a lightweight function for use when only the base direction + * is needed and no further bidi processing of the text is needed. + * + * @param text is a pointer to the text whose base + * direction is needed. + * Note: the text must be (at least) @c length long. + * + * @param length is the length of the text; + * if <code>length==-1</code> then the text + * must be zero-terminated. + * + * @return <code>UBIDI_LTR</code>, <code>UBIDI_RTL</code>, + * <code>UBIDI_NEUTRAL</code> + * + * @see UBiDiDirection + * @stable ICU 4.6 + */ +U_CAPI UBiDiDirection U_EXPORT2 +ubidi_getBaseDirection(const UChar *text, int32_t length ); + +/** + * Get the pointer to the text. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @return The pointer to the text that the UBiDi object was created for. + * + * @see ubidi_setPara + * @see ubidi_setLine + * @stable ICU 2.0 + */ +U_CAPI const UChar * U_EXPORT2 +ubidi_getText(const UBiDi *pBiDi); + +/** + * Get the length of the text. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @return The length of the text that the UBiDi object was created for. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_getLength(const UBiDi *pBiDi); + +/** + * Get the paragraph level of the text. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @return The paragraph level. If there are multiple paragraphs, their + * level may vary if the required paraLevel is UBIDI_DEFAULT_LTR or + * UBIDI_DEFAULT_RTL. In that case, the level of the first paragraph + * is returned. + * + * @see UBiDiLevel + * @see ubidi_getParagraph + * @see ubidi_getParagraphByIndex + * @stable ICU 2.0 + */ +U_CAPI UBiDiLevel U_EXPORT2 +ubidi_getParaLevel(const UBiDi *pBiDi); + +/** + * Get the number of paragraphs. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @return The number of paragraphs. + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_countParagraphs(UBiDi *pBiDi); + +/** + * Get a paragraph, given a position within the text. + * This function returns information about a paragraph.<br> + * Note: if the paragraph index is known, it is more efficient to + * retrieve the paragraph information using ubidi_getParagraphByIndex().<p> + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param charIndex is the index of a character within the text, in the + * range <code>[0..ubidi_getProcessedLength(pBiDi)-1]</code>. + * + * @param pParaStart will receive the index of the first character of the + * paragraph in the text. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @param pParaLimit will receive the limit of the paragraph. + * The l-value that you point to here may be the + * same expression (variable) as the one for + * <code>charIndex</code>. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @param pParaLevel will receive the level of the paragraph. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @return The index of the paragraph containing the specified position. + * + * @see ubidi_getProcessedLength + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_getParagraph(const UBiDi *pBiDi, int32_t charIndex, int32_t *pParaStart, + int32_t *pParaLimit, UBiDiLevel *pParaLevel, + UErrorCode *pErrorCode); + +/** + * Get a paragraph, given the index of this paragraph. + * + * This function returns information about a paragraph.<p> + * + * @param pBiDi is the paragraph <code>UBiDi</code> object. + * + * @param paraIndex is the number of the paragraph, in the + * range <code>[0..ubidi_countParagraphs(pBiDi)-1]</code>. + * + * @param pParaStart will receive the index of the first character of the + * paragraph in the text. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @param pParaLimit will receive the limit of the paragraph. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @param pParaLevel will receive the level of the paragraph. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +ubidi_getParagraphByIndex(const UBiDi *pBiDi, int32_t paraIndex, + int32_t *pParaStart, int32_t *pParaLimit, + UBiDiLevel *pParaLevel, UErrorCode *pErrorCode); + +/** + * Get the level for one character. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param charIndex the index of a character. It must be in the range + * [0..ubidi_getProcessedLength(pBiDi)]. + * + * @return The level for the character at charIndex (0 if charIndex is not + * in the valid range). + * + * @see UBiDiLevel + * @see ubidi_getProcessedLength + * @stable ICU 2.0 + */ +U_CAPI UBiDiLevel U_EXPORT2 +ubidi_getLevelAt(const UBiDi *pBiDi, int32_t charIndex); + +/** + * Get an array of levels for each character.<p> + * + * Note that this function may allocate memory under some + * circumstances, unlike <code>ubidi_getLevelAt()</code>. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object, whose + * text length must be strictly positive. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @return The levels array for the text, + * or <code>NULL</code> if an error occurs. + * + * @see UBiDiLevel + * @see ubidi_getProcessedLength + * @stable ICU 2.0 + */ +U_CAPI const UBiDiLevel * U_EXPORT2 +ubidi_getLevels(UBiDi *pBiDi, UErrorCode *pErrorCode); + +/** + * Get a logical run. + * This function returns information about a run and is used + * to retrieve runs in logical order.<p> + * This is especially useful for line-breaking on a paragraph. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param logicalPosition is a logical position within the source text. + * + * @param pLogicalLimit will receive the limit of the corresponding run. + * The l-value that you point to here may be the + * same expression (variable) as the one for + * <code>logicalPosition</code>. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @param pLevel will receive the level of the corresponding run. + * This pointer can be <code>NULL</code> if this + * value is not necessary. + * + * @see ubidi_getProcessedLength + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_getLogicalRun(const UBiDi *pBiDi, int32_t logicalPosition, + int32_t *pLogicalLimit, UBiDiLevel *pLevel); + +/** + * Get the number of runs. + * This function may invoke the actual reordering on the + * <code>UBiDi</code> object, after <code>ubidi_setPara()</code> + * may have resolved only the levels of the text. Therefore, + * <code>ubidi_countRuns()</code> may have to allocate memory, + * and may fail doing so. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @return The number of runs. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_countRuns(UBiDi *pBiDi, UErrorCode *pErrorCode); + +/** + * Get one run's logical start, length, and directionality, + * which can be 0 for LTR or 1 for RTL. + * In an RTL run, the character at the logical start is + * visually on the right of the displayed run. + * The length is the number of characters in the run.<p> + * <code>ubidi_countRuns()</code> should be called + * before the runs are retrieved. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param runIndex is the number of the run in visual order, in the + * range <code>[0..ubidi_countRuns(pBiDi)-1]</code>. + * + * @param pLogicalStart is the first logical character index in the text. + * The pointer may be <code>NULL</code> if this index is not needed. + * + * @param pLength is the number of characters (at least one) in the run. + * The pointer may be <code>NULL</code> if this is not needed. + * + * @return the directionality of the run, + * <code>UBIDI_LTR==0</code> or <code>UBIDI_RTL==1</code>, + * never <code>UBIDI_MIXED</code>, + * never <code>UBIDI_NEUTRAL</code>. + * + * @see ubidi_countRuns + * + * Example: + * <pre> + * \code + * int32_t i, count=ubidi_countRuns(pBiDi), + * logicalStart, visualIndex=0, length; + * for(i=0; i<count; ++i) { + * if(UBIDI_LTR==ubidi_getVisualRun(pBiDi, i, &logicalStart, &length)) { + * do { // LTR + * show_char(text[logicalStart++], visualIndex++); + * } while(--length>0); + * } else { + * logicalStart+=length; // logicalLimit + * do { // RTL + * show_char(text[--logicalStart], visualIndex++); + * } while(--length>0); + * } + * } + *\endcode + * </pre> + * + * Note that in right-to-left runs, code like this places + * second surrogates before first ones (which is generally a bad idea) + * and combining characters before base characters. + * <p> + * Use of <code>ubidi_writeReordered()</code>, optionally with the + * <code>#UBIDI_KEEP_BASE_COMBINING</code> option, can be considered in order + * to avoid these issues. + * @stable ICU 2.0 + */ +U_CAPI UBiDiDirection U_EXPORT2 +ubidi_getVisualRun(UBiDi *pBiDi, int32_t runIndex, + int32_t *pLogicalStart, int32_t *pLength); + +/** + * Get the visual position from a logical text position. + * If such a mapping is used many times on the same + * <code>UBiDi</code> object, then calling + * <code>ubidi_getLogicalMap()</code> is more efficient.<p> + * + * The value returned may be <code>#UBIDI_MAP_NOWHERE</code> if there is no + * visual position because the corresponding text character is a Bidi control + * removed from output by the option <code>#UBIDI_OPTION_REMOVE_CONTROLS</code>. + * <p> + * When the visual output is altered by using options of + * <code>ubidi_writeReordered()</code> such as <code>UBIDI_INSERT_LRM_FOR_NUMERIC</code>, + * <code>UBIDI_KEEP_BASE_COMBINING</code>, <code>UBIDI_OUTPUT_REVERSE</code>, + * <code>UBIDI_REMOVE_BIDI_CONTROLS</code>, the visual position returned may not + * be correct. It is advised to use, when possible, reordering options + * such as <code>UBIDI_OPTION_INSERT_MARKS</code> and <code>UBIDI_OPTION_REMOVE_CONTROLS</code>. + * <p> + * Note that in right-to-left runs, this mapping places + * second surrogates before first ones (which is generally a bad idea) + * and combining characters before base characters. + * Use of <code>ubidi_writeReordered()</code>, optionally with the + * <code>#UBIDI_KEEP_BASE_COMBINING</code> option can be considered instead + * of using the mapping, in order to avoid these issues. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param logicalIndex is the index of a character in the text. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @return The visual position of this character. + * + * @see ubidi_getLogicalMap + * @see ubidi_getLogicalIndex + * @see ubidi_getProcessedLength + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_getVisualIndex(UBiDi *pBiDi, int32_t logicalIndex, UErrorCode *pErrorCode); + +/** + * Get the logical text position from a visual position. + * If such a mapping is used many times on the same + * <code>UBiDi</code> object, then calling + * <code>ubidi_getVisualMap()</code> is more efficient.<p> + * + * The value returned may be <code>#UBIDI_MAP_NOWHERE</code> if there is no + * logical position because the corresponding text character is a Bidi mark + * inserted in the output by option <code>#UBIDI_OPTION_INSERT_MARKS</code>. + * <p> + * This is the inverse function to <code>ubidi_getVisualIndex()</code>. + * <p> + * When the visual output is altered by using options of + * <code>ubidi_writeReordered()</code> such as <code>UBIDI_INSERT_LRM_FOR_NUMERIC</code>, + * <code>UBIDI_KEEP_BASE_COMBINING</code>, <code>UBIDI_OUTPUT_REVERSE</code>, + * <code>UBIDI_REMOVE_BIDI_CONTROLS</code>, the logical position returned may not + * be correct. It is advised to use, when possible, reordering options + * such as <code>UBIDI_OPTION_INSERT_MARKS</code> and <code>UBIDI_OPTION_REMOVE_CONTROLS</code>. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param visualIndex is the visual position of a character. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @return The index of this character in the text. + * + * @see ubidi_getVisualMap + * @see ubidi_getVisualIndex + * @see ubidi_getResultLength + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_getLogicalIndex(UBiDi *pBiDi, int32_t visualIndex, UErrorCode *pErrorCode); + +/** + * Get a logical-to-visual index map (array) for the characters in the UBiDi + * (paragraph or line) object. + * <p> + * Some values in the map may be <code>#UBIDI_MAP_NOWHERE</code> if the + * corresponding text characters are Bidi controls removed from the visual + * output by the option <code>#UBIDI_OPTION_REMOVE_CONTROLS</code>. + * <p> + * When the visual output is altered by using options of + * <code>ubidi_writeReordered()</code> such as <code>UBIDI_INSERT_LRM_FOR_NUMERIC</code>, + * <code>UBIDI_KEEP_BASE_COMBINING</code>, <code>UBIDI_OUTPUT_REVERSE</code>, + * <code>UBIDI_REMOVE_BIDI_CONTROLS</code>, the visual positions returned may not + * be correct. It is advised to use, when possible, reordering options + * such as <code>UBIDI_OPTION_INSERT_MARKS</code> and <code>UBIDI_OPTION_REMOVE_CONTROLS</code>. + * <p> + * Note that in right-to-left runs, this mapping places + * second surrogates before first ones (which is generally a bad idea) + * and combining characters before base characters. + * Use of <code>ubidi_writeReordered()</code>, optionally with the + * <code>#UBIDI_KEEP_BASE_COMBINING</code> option can be considered instead + * of using the mapping, in order to avoid these issues. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param indexMap is a pointer to an array of <code>ubidi_getProcessedLength()</code> + * indexes which will reflect the reordering of the characters. + * If option <code>#UBIDI_OPTION_INSERT_MARKS</code> is set, the number + * of elements allocated in <code>indexMap</code> must be no less than + * <code>ubidi_getResultLength()</code>. + * The array does not need to be initialized.<br><br> + * The index map will result in <code>indexMap[logicalIndex]==visualIndex</code>. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @see ubidi_getVisualMap + * @see ubidi_getVisualIndex + * @see ubidi_getProcessedLength + * @see ubidi_getResultLength + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_getLogicalMap(UBiDi *pBiDi, int32_t *indexMap, UErrorCode *pErrorCode); + +/** + * Get a visual-to-logical index map (array) for the characters in the UBiDi + * (paragraph or line) object. + * <p> + * Some values in the map may be <code>#UBIDI_MAP_NOWHERE</code> if the + * corresponding text characters are Bidi marks inserted in the visual output + * by the option <code>#UBIDI_OPTION_INSERT_MARKS</code>. + * <p> + * When the visual output is altered by using options of + * <code>ubidi_writeReordered()</code> such as <code>UBIDI_INSERT_LRM_FOR_NUMERIC</code>, + * <code>UBIDI_KEEP_BASE_COMBINING</code>, <code>UBIDI_OUTPUT_REVERSE</code>, + * <code>UBIDI_REMOVE_BIDI_CONTROLS</code>, the logical positions returned may not + * be correct. It is advised to use, when possible, reordering options + * such as <code>UBIDI_OPTION_INSERT_MARKS</code> and <code>UBIDI_OPTION_REMOVE_CONTROLS</code>. + * + * @param pBiDi is the paragraph or line <code>UBiDi</code> object. + * + * @param indexMap is a pointer to an array of <code>ubidi_getResultLength()</code> + * indexes which will reflect the reordering of the characters. + * If option <code>#UBIDI_OPTION_REMOVE_CONTROLS</code> is set, the number + * of elements allocated in <code>indexMap</code> must be no less than + * <code>ubidi_getProcessedLength()</code>. + * The array does not need to be initialized.<br><br> + * The index map will result in <code>indexMap[visualIndex]==logicalIndex</code>. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @see ubidi_getLogicalMap + * @see ubidi_getLogicalIndex + * @see ubidi_getProcessedLength + * @see ubidi_getResultLength + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_getVisualMap(UBiDi *pBiDi, int32_t *indexMap, UErrorCode *pErrorCode); + +/** + * This is a convenience function that does not use a UBiDi object. + * It is intended to be used for when an application has determined the levels + * of objects (character sequences) and just needs to have them reordered (L2). + * This is equivalent to using <code>ubidi_getLogicalMap()</code> on a + * <code>UBiDi</code> object. + * + * @param levels is an array with <code>length</code> levels that have been determined by + * the application. + * + * @param length is the number of levels in the array, or, semantically, + * the number of objects to be reordered. + * It must be <code>length>0</code>. + * + * @param indexMap is a pointer to an array of <code>length</code> + * indexes which will reflect the reordering of the characters. + * The array does not need to be initialized.<p> + * The index map will result in <code>indexMap[logicalIndex]==visualIndex</code>. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_reorderLogical(const UBiDiLevel *levels, int32_t length, int32_t *indexMap); + +/** + * This is a convenience function that does not use a UBiDi object. + * It is intended to be used for when an application has determined the levels + * of objects (character sequences) and just needs to have them reordered (L2). + * This is equivalent to using <code>ubidi_getVisualMap()</code> on a + * <code>UBiDi</code> object. + * + * @param levels is an array with <code>length</code> levels that have been determined by + * the application. + * + * @param length is the number of levels in the array, or, semantically, + * the number of objects to be reordered. + * It must be <code>length>0</code>. + * + * @param indexMap is a pointer to an array of <code>length</code> + * indexes which will reflect the reordering of the characters. + * The array does not need to be initialized.<p> + * The index map will result in <code>indexMap[visualIndex]==logicalIndex</code>. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_reorderVisual(const UBiDiLevel *levels, int32_t length, int32_t *indexMap); + +/** + * Invert an index map. + * The index mapping of the first map is inverted and written to + * the second one. + * + * @param srcMap is an array with <code>length</code> elements + * which defines the original mapping from a source array containing + * <code>length</code> elements to a destination array. + * Some elements of the source array may have no mapping in the + * destination array. In that case, their value will be + * the special value <code>UBIDI_MAP_NOWHERE</code>. + * All elements must be >=0 or equal to <code>UBIDI_MAP_NOWHERE</code>. + * Some elements may have a value >= <code>length</code>, if the + * destination array has more elements than the source array. + * There must be no duplicate indexes (two or more elements with the + * same value except <code>UBIDI_MAP_NOWHERE</code>). + * + * @param destMap is an array with a number of elements equal to 1 + the highest + * value in <code>srcMap</code>. + * <code>destMap</code> will be filled with the inverse mapping. + * If element with index i in <code>srcMap</code> has a value k different + * from <code>UBIDI_MAP_NOWHERE</code>, this means that element i of + * the source array maps to element k in the destination array. + * The inverse map will have value i in its k-th element. + * For all elements of the destination array which do not map to + * an element in the source array, the corresponding element in the + * inverse map will have a value equal to <code>UBIDI_MAP_NOWHERE</code>. + * + * @param length is the length of each array. + * @see UBIDI_MAP_NOWHERE + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubidi_invertMap(const int32_t *srcMap, int32_t *destMap, int32_t length); + +/** option flags for ubidi_writeReordered() */ + +/** + * option bit for ubidi_writeReordered(): + * keep combining characters after their base characters in RTL runs + * + * @see ubidi_writeReordered + * @stable ICU 2.0 + */ +#define UBIDI_KEEP_BASE_COMBINING 1 + +/** + * option bit for ubidi_writeReordered(): + * replace characters with the "mirrored" property in RTL runs + * by their mirror-image mappings + * + * @see ubidi_writeReordered + * @stable ICU 2.0 + */ +#define UBIDI_DO_MIRRORING 2 + +/** + * option bit for ubidi_writeReordered(): + * surround the run with LRMs if necessary; + * this is part of the approximate "inverse Bidi" algorithm + * + * <p>This option does not imply corresponding adjustment of the index + * mappings.</p> + * + * @see ubidi_setInverse + * @see ubidi_writeReordered + * @stable ICU 2.0 + */ +#define UBIDI_INSERT_LRM_FOR_NUMERIC 4 + +/** + * option bit for ubidi_writeReordered(): + * remove Bidi control characters + * (this does not affect #UBIDI_INSERT_LRM_FOR_NUMERIC) + * + * <p>This option does not imply corresponding adjustment of the index + * mappings.</p> + * + * @see ubidi_writeReordered + * @stable ICU 2.0 + */ +#define UBIDI_REMOVE_BIDI_CONTROLS 8 + +/** + * option bit for ubidi_writeReordered(): + * write the output in reverse order + * + * <p>This has the same effect as calling <code>ubidi_writeReordered()</code> + * first without this option, and then calling + * <code>ubidi_writeReverse()</code> without mirroring. + * Doing this in the same step is faster and avoids a temporary buffer. + * An example for using this option is output to a character terminal that + * is designed for RTL scripts and stores text in reverse order.</p> + * + * @see ubidi_writeReordered + * @stable ICU 2.0 + */ +#define UBIDI_OUTPUT_REVERSE 16 + +/** + * Get the length of the source text processed by the last call to + * <code>ubidi_setPara()</code>. This length may be different from the length + * of the source text if option <code>#UBIDI_OPTION_STREAMING</code> + * has been set. + * <br> + * Note that whenever the length of the text affects the execution or the + * result of a function, it is the processed length which must be considered, + * except for <code>ubidi_setPara</code> (which receives unprocessed source + * text) and <code>ubidi_getLength</code> (which returns the original length + * of the source text).<br> + * In particular, the processed length is the one to consider in the following + * cases: + * <ul> + * <li>maximum value of the <code>limit</code> argument of + * <code>ubidi_setLine</code></li> + * <li>maximum value of the <code>charIndex</code> argument of + * <code>ubidi_getParagraph</code></li> + * <li>maximum value of the <code>charIndex</code> argument of + * <code>ubidi_getLevelAt</code></li> + * <li>number of elements in the array returned by <code>ubidi_getLevels</code></li> + * <li>maximum value of the <code>logicalStart</code> argument of + * <code>ubidi_getLogicalRun</code></li> + * <li>maximum value of the <code>logicalIndex</code> argument of + * <code>ubidi_getVisualIndex</code></li> + * <li>number of elements filled in the <code>*indexMap</code> argument of + * <code>ubidi_getLogicalMap</code></li> + * <li>length of text processed by <code>ubidi_writeReordered</code></li> + * </ul> + * + * @param pBiDi is the paragraph <code>UBiDi</code> object. + * + * @return The length of the part of the source text processed by + * the last call to <code>ubidi_setPara</code>. + * @see ubidi_setPara + * @see UBIDI_OPTION_STREAMING + * @stable ICU 3.6 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_getProcessedLength(const UBiDi *pBiDi); + +/** + * Get the length of the reordered text resulting from the last call to + * <code>ubidi_setPara()</code>. This length may be different from the length + * of the source text if option <code>#UBIDI_OPTION_INSERT_MARKS</code> + * or option <code>#UBIDI_OPTION_REMOVE_CONTROLS</code> has been set. + * <br> + * This resulting length is the one to consider in the following cases: + * <ul> + * <li>maximum value of the <code>visualIndex</code> argument of + * <code>ubidi_getLogicalIndex</code></li> + * <li>number of elements of the <code>*indexMap</code> argument of + * <code>ubidi_getVisualMap</code></li> + * </ul> + * Note that this length stays identical to the source text length if + * Bidi marks are inserted or removed using option bits of + * <code>ubidi_writeReordered</code>, or if option + * <code>#UBIDI_REORDER_INVERSE_NUMBERS_AS_L</code> has been set. + * + * @param pBiDi is the paragraph <code>UBiDi</code> object. + * + * @return The length of the reordered text resulting from + * the last call to <code>ubidi_setPara</code>. + * @see ubidi_setPara + * @see UBIDI_OPTION_INSERT_MARKS + * @see UBIDI_OPTION_REMOVE_CONTROLS + * @stable ICU 3.6 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_getResultLength(const UBiDi *pBiDi); + +U_CDECL_BEGIN + +#ifndef U_HIDE_DEPRECATED_API +/** + * Value returned by <code>UBiDiClassCallback</code> callbacks when + * there is no need to override the standard Bidi class for a given code point. + * + * This constant is deprecated; use u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS)+1 instead. + * + * @see UBiDiClassCallback + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ +#define U_BIDI_CLASS_DEFAULT U_CHAR_DIRECTION_COUNT +#endif // U_HIDE_DEPRECATED_API + +/** + * Callback type declaration for overriding default Bidi class values with + * custom ones. + * <p>Usually, the function pointer will be propagated to a <code>UBiDi</code> + * object by calling the <code>ubidi_setClassCallback()</code> function; + * then the callback will be invoked by the UBA implementation any time the + * class of a character is to be determined.</p> + * + * @param context is a pointer to the callback private data. + * + * @param c is the code point to get a Bidi class for. + * + * @return The directional property / Bidi class for the given code point + * <code>c</code> if the default class has been overridden, or + * <code>u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS)+1</code> + * if the standard Bidi class value for <code>c</code> is to be used. + * @see ubidi_setClassCallback + * @see ubidi_getClassCallback + * @stable ICU 3.6 + */ +typedef UCharDirection U_CALLCONV +UBiDiClassCallback(const void *context, UChar32 c); + +U_CDECL_END + +/** + * Retrieve the Bidi class for a given code point. + * <p>If a <code>#UBiDiClassCallback</code> callback is defined and returns a + * value other than <code>u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS)+1</code>, + * that value is used; otherwise the default class determination mechanism is invoked.</p> + * + * @param pBiDi is the paragraph <code>UBiDi</code> object. + * + * @param c is the code point whose Bidi class must be retrieved. + * + * @return The Bidi class for character <code>c</code> based + * on the given <code>pBiDi</code> instance. + * @see UBiDiClassCallback + * @stable ICU 3.6 + */ +U_CAPI UCharDirection U_EXPORT2 +ubidi_getCustomizedClass(UBiDi *pBiDi, UChar32 c); + +/** + * Set the callback function and callback data used by the UBA + * implementation for Bidi class determination. + * <p>This may be useful for assigning Bidi classes to PUA characters, or + * for special application needs. For instance, an application may want to + * handle all spaces like L or R characters (according to the base direction) + * when creating the visual ordering of logical lines which are part of a report + * organized in columns: there should not be interaction between adjacent + * cells.<p> + * + * @param pBiDi is the paragraph <code>UBiDi</code> object. + * + * @param newFn is the new callback function pointer. + * + * @param newContext is the new callback context pointer. This can be NULL. + * + * @param oldFn fillin: Returns the old callback function pointer. This can be + * NULL. + * + * @param oldContext fillin: Returns the old callback's context. This can be + * NULL. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @see ubidi_getClassCallback + * @stable ICU 3.6 + */ +U_CAPI void U_EXPORT2 +ubidi_setClassCallback(UBiDi *pBiDi, UBiDiClassCallback *newFn, + const void *newContext, UBiDiClassCallback **oldFn, + const void **oldContext, UErrorCode *pErrorCode); + +/** + * Get the current callback function used for Bidi class determination. + * + * @param pBiDi is the paragraph <code>UBiDi</code> object. + * + * @param fn fillin: Returns the callback function pointer. + * + * @param context fillin: Returns the callback's private context. + * + * @see ubidi_setClassCallback + * @stable ICU 3.6 + */ +U_CAPI void U_EXPORT2 +ubidi_getClassCallback(UBiDi *pBiDi, UBiDiClassCallback **fn, const void **context); + +/** + * Take a <code>UBiDi</code> object containing the reordering + * information for a piece of text (one or more paragraphs) set by + * <code>ubidi_setPara()</code> or for a line of text set by + * <code>ubidi_setLine()</code> and write a reordered string to the + * destination buffer. + * + * This function preserves the integrity of characters with multiple + * code units and (optionally) combining characters. + * Characters in RTL runs can be replaced by mirror-image characters + * in the destination buffer. Note that "real" mirroring has + * to be done in a rendering engine by glyph selection + * and that for many "mirrored" characters there are no + * Unicode characters as mirror-image equivalents. + * There are also options to insert or remove Bidi control + * characters; see the description of the <code>destSize</code> + * and <code>options</code> parameters and of the option bit flags. + * + * @param pBiDi A pointer to a <code>UBiDi</code> object that + * is set by <code>ubidi_setPara()</code> or + * <code>ubidi_setLine()</code> and contains the reordering + * information for the text that it was defined for, + * as well as a pointer to that text.<br><br> + * The text was aliased (only the pointer was stored + * without copying the contents) and must not have been modified + * since the <code>ubidi_setPara()</code> call. + * + * @param dest A pointer to where the reordered text is to be copied. + * The source text and <code>dest[destSize]</code> + * must not overlap. + * + * @param destSize The size of the <code>dest</code> buffer, + * in number of UChars. + * If the <code>UBIDI_INSERT_LRM_FOR_NUMERIC</code> + * option is set, then the destination length could be + * as large as + * <code>ubidi_getLength(pBiDi)+2*ubidi_countRuns(pBiDi)</code>. + * If the <code>UBIDI_REMOVE_BIDI_CONTROLS</code> option + * is set, then the destination length may be less than + * <code>ubidi_getLength(pBiDi)</code>. + * If none of these options is set, then the destination length + * will be exactly <code>ubidi_getProcessedLength(pBiDi)</code>. + * + * @param options A bit set of options for the reordering that control + * how the reordered text is written. + * The options include mirroring the characters on a code + * point basis and inserting LRM characters, which is used + * especially for transforming visually stored text + * to logically stored text (although this is still an + * imperfect implementation of an "inverse Bidi" algorithm + * because it uses the "forward Bidi" algorithm at its core). + * The available options are: + * <code>#UBIDI_DO_MIRRORING</code>, + * <code>#UBIDI_INSERT_LRM_FOR_NUMERIC</code>, + * <code>#UBIDI_KEEP_BASE_COMBINING</code>, + * <code>#UBIDI_OUTPUT_REVERSE</code>, + * <code>#UBIDI_REMOVE_BIDI_CONTROLS</code> + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @return The length of the output string. + * + * @see ubidi_getProcessedLength + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_writeReordered(UBiDi *pBiDi, + UChar *dest, int32_t destSize, + uint16_t options, + UErrorCode *pErrorCode); + +/** + * Reverse a Right-To-Left run of Unicode text. + * + * This function preserves the integrity of characters with multiple + * code units and (optionally) combining characters. + * Characters can be replaced by mirror-image characters + * in the destination buffer. Note that "real" mirroring has + * to be done in a rendering engine by glyph selection + * and that for many "mirrored" characters there are no + * Unicode characters as mirror-image equivalents. + * There are also options to insert or remove Bidi control + * characters. + * + * This function is the implementation for reversing RTL runs as part + * of <code>ubidi_writeReordered()</code>. For detailed descriptions + * of the parameters, see there. + * Since no Bidi controls are inserted here, the output string length + * will never exceed <code>srcLength</code>. + * + * @see ubidi_writeReordered + * + * @param src A pointer to the RTL run text. + * + * @param srcLength The length of the RTL run. + * + * @param dest A pointer to where the reordered text is to be copied. + * <code>src[srcLength]</code> and <code>dest[destSize]</code> + * must not overlap. + * + * @param destSize The size of the <code>dest</code> buffer, + * in number of UChars. + * If the <code>UBIDI_REMOVE_BIDI_CONTROLS</code> option + * is set, then the destination length may be less than + * <code>srcLength</code>. + * If this option is not set, then the destination length + * will be exactly <code>srcLength</code>. + * + * @param options A bit set of options for the reordering that control + * how the reordered text is written. + * See the <code>options</code> parameter in <code>ubidi_writeReordered()</code>. + * + * @param pErrorCode must be a valid pointer to an error code value. + * + * @return The length of the output string. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubidi_writeReverse(const UChar *src, int32_t srcLength, + UChar *dest, int32_t destSize, + uint16_t options, + UErrorCode *pErrorCode); + +/*#define BIDI_SAMPLE_CODE*/ +/*@}*/ + +#endif diff --git a/thirdparty/icu4c/common/unicode/ubiditransform.h b/thirdparty/icu4c/common/unicode/ubiditransform.h new file mode 100644 index 0000000000..2dd7564010 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ubiditransform.h @@ -0,0 +1,326 @@ +/* +****************************************************************************** +* +* © 2016 and later: Unicode, Inc. and others. +* License & terms of use: http://www.unicode.org/copyright.html +* +****************************************************************************** +* file name: ubiditransform.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2016jul24 +* created by: Lina Kemmel +* +*/ + +#ifndef UBIDITRANSFORM_H +#define UBIDITRANSFORM_H + +#include "unicode/utypes.h" +#include "unicode/ubidi.h" +#include "unicode/uchar.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * \file + * \brief Bidi Transformations + */ + +/** + * `UBiDiOrder` indicates the order of text. + * + * This bidi transformation engine supports all possible combinations (4 in + * total) of input and output text order: + * + * - <logical input, visual output>: unless the output direction is RTL, this + * corresponds to a normal operation of the Bidi algorithm as described in the + * Unicode Technical Report and implemented by `UBiDi` when the + * reordering mode is set to `UBIDI_REORDER_DEFAULT`. Visual RTL + * mode is not supported by `UBiDi` and is accomplished through + * reversing a visual LTR string, + * + * - <visual input, logical output>: unless the input direction is RTL, this + * corresponds to an "inverse bidi algorithm" in `UBiDi` with the + * reordering mode set to `UBIDI_REORDER_INVERSE_LIKE_DIRECT`. + * Visual RTL mode is not not supported by `UBiDi` and is + * accomplished through reversing a visual LTR string, + * + * - <logical input, logical output>: if the input and output base directions + * mismatch, this corresponds to the `UBiDi` implementation with the + * reordering mode set to `UBIDI_REORDER_RUNS_ONLY`; and if the + * input and output base directions are identical, the transformation engine + * will only handle character mirroring and Arabic shaping operations without + * reordering, + * + * - <visual input, visual output>: this reordering mode is not supported by + * the `UBiDi` engine; it implies character mirroring, Arabic + * shaping, and - if the input/output base directions mismatch - string + * reverse operations. + * @see ubidi_setInverse + * @see ubidi_setReorderingMode + * @see UBIDI_REORDER_DEFAULT + * @see UBIDI_REORDER_INVERSE_LIKE_DIRECT + * @see UBIDI_REORDER_RUNS_ONLY + * @stable ICU 58 + */ +typedef enum { + /** 0: Constant indicating a logical order. + * This is the default for input text. + * @stable ICU 58 + */ + UBIDI_LOGICAL = 0, + /** 1: Constant indicating a visual order. + * This is a default for output text. + * @stable ICU 58 + */ + UBIDI_VISUAL +} UBiDiOrder; + +/** + * <code>UBiDiMirroring</code> indicates whether or not characters with the + * "mirrored" property in RTL runs should be replaced with their mirror-image + * counterparts. + * @see UBIDI_DO_MIRRORING + * @see ubidi_setReorderingOptions + * @see ubidi_writeReordered + * @see ubidi_writeReverse + * @stable ICU 58 + */ +typedef enum { + /** 0: Constant indicating that character mirroring should not be + * performed. + * This is the default. + * @stable ICU 58 + */ + UBIDI_MIRRORING_OFF = 0, + /** 1: Constant indicating that character mirroring should be performed. + * This corresponds to calling <code>ubidi_writeReordered</code> or + * <code>ubidi_writeReverse</code> with the + * <code>UBIDI_DO_MIRRORING</code> option bit set. + * @stable ICU 58 + */ + UBIDI_MIRRORING_ON +} UBiDiMirroring; + +/** + * Forward declaration of the <code>UBiDiTransform</code> structure that stores + * information used by the layout transformation engine. + * @stable ICU 58 + */ +typedef struct UBiDiTransform UBiDiTransform; + +/** + * Performs transformation of text from the bidi layout defined by the input + * ordering scheme to the bidi layout defined by the output ordering scheme, + * and applies character mirroring and Arabic shaping operations.<p> + * In terms of <code>UBiDi</code>, such a transformation implies: + * <ul> + * <li>calling <code>ubidi_setReorderingMode</code> as needed (when the + * reordering mode is other than normal),</li> + * <li>calling <code>ubidi_setInverse</code> as needed (when text should be + * transformed from a visual to a logical form),</li> + * <li>resolving embedding levels of each character in the input text by + * calling <code>ubidi_setPara</code>,</li> + * <li>reordering the characters based on the computed embedding levels, also + * performing character mirroring as needed, and streaming the result to the + * output, by calling <code>ubidi_writeReordered</code>,</li> + * <li>performing Arabic digit and letter shaping on the output text by calling + * <code>u_shapeArabic</code>.</li> + * </ul> + * An "ordering scheme" encompasses the base direction and the order of text, + * and these characteristics must be defined by the caller for both input and + * output explicitly .<p> + * There are 36 possible combinations of <input, output> ordering schemes, + * which are partially supported by <code>UBiDi</code> already. Examples of the + * currently supported combinations: + * <ul> + * <li><Logical LTR, Visual LTR>: this is equivalent to calling + * <code>ubidi_setPara</code> with <code>paraLevel == UBIDI_LTR</code>,</li> + * <li><Logical RTL, Visual LTR>: this is equivalent to calling + * <code>ubidi_setPara</code> with <code>paraLevel == UBIDI_RTL</code>,</li> + * <li><Logical Default ("Auto") LTR, Visual LTR>: this is equivalent to + * calling <code>ubidi_setPara</code> with + * <code>paraLevel == UBIDI_DEFAULT_LTR</code>,</li> + * <li><Logical Default ("Auto") RTL, Visual LTR>: this is equivalent to + * calling <code>ubidi_setPara</code> with + * <code>paraLevel == UBIDI_DEFAULT_RTL</code>,</li> + * <li><Visual LTR, Logical LTR>: this is equivalent to + * calling <code>ubidi_setInverse(UBiDi*, true)</code> and then + * <code>ubidi_setPara</code> with <code>paraLevel == UBIDI_LTR</code>,</li> + * <li><Visual LTR, Logical RTL>: this is equivalent to + * calling <code>ubidi_setInverse(UBiDi*, true)</code> and then + * <code>ubidi_setPara</code> with <code>paraLevel == UBIDI_RTL</code>.</li> + * </ul> + * All combinations that involve the Visual RTL scheme are unsupported by + * <code>UBiDi</code>, for instance: + * <ul> + * <li><Logical LTR, Visual RTL>,</li> + * <li><Visual RTL, Logical RTL>.</li> + * </ul> + * <p>Example of usage of the transformation engine:<br> + * <pre> + * \code + * UChar text1[] = {'a', 'b', 'c', 0x0625, '1', 0}; + * UChar text2[] = {'a', 'b', 'c', 0x0625, '1', 0}; + * UErrorCode errorCode = U_ZERO_ERROR; + * // Run a transformation. + * ubiditransform_transform(pBidiTransform, + * text1, -1, text2, -1, + * UBIDI_LTR, UBIDI_VISUAL, + * UBIDI_RTL, UBIDI_LOGICAL, + * UBIDI_MIRRORING_OFF, + * U_SHAPE_DIGITS_AN2EN | U_SHAPE_DIGIT_TYPE_AN_EXTENDED, + * &errorCode); + * // Do something with text2. + * text2[4] = '2'; + * // Run a reverse transformation. + * ubiditransform_transform(pBidiTransform, + * text2, -1, text1, -1, + * UBIDI_RTL, UBIDI_LOGICAL, + * UBIDI_LTR, UBIDI_VISUAL, + * UBIDI_MIRRORING_OFF, + * U_SHAPE_DIGITS_EN2AN | U_SHAPE_DIGIT_TYPE_AN_EXTENDED, + * &errorCode); + *\endcode + * </pre> + * </p> + * + * @param pBiDiTransform A pointer to a <code>UBiDiTransform</code> object + * allocated with <code>ubiditransform_open()</code> or + * <code>NULL</code>.<p> + * This object serves for one-time setup to amortize initialization + * overheads. Use of this object is not thread-safe. All other threads + * should allocate a new <code>UBiDiTransform</code> object by calling + * <code>ubiditransform_open()</code> before using it. Alternatively, + * a caller can set this parameter to <code>NULL</code>, in which case + * the object will be allocated by the engine on the fly.</p> + * @param src A pointer to the text that the Bidi layout transformations will + * be performed on. + * <p><strong>Note:</strong> the text must be (at least) + * <code>srcLength</code> long.</p> + * @param srcLength The length of the text, in number of UChars. If + * <code>length == -1</code> then the text must be zero-terminated. + * @param dest A pointer to where the processed text is to be copied. + * @param destSize The size of the <code>dest</code> buffer, in number of + * UChars. If the <code>U_SHAPE_LETTERS_UNSHAPE</code> option is set, + * then the destination length could be as large as + * <code>srcLength * 2</code>. Otherwise, the destination length will + * not exceed <code>srcLength</code>. If the caller reserves the last + * position for zero-termination, it should be excluded from + * <code>destSize</code>. + * <p><code>destSize == -1</code> is allowed and makes sense when + * <code>dest</code> was holds some meaningful value, e.g. that of + * <code>src</code>. In this case <code>dest</code> must be + * zero-terminated.</p> + * @param inParaLevel A base embedding level of the input as defined in + * <code>ubidi_setPara</code> documentation for the + * <code>paraLevel</code> parameter. + * @param inOrder An order of the input, which can be one of the + * <code>UBiDiOrder</code> values. + * @param outParaLevel A base embedding level of the output as defined in + * <code>ubidi_setPara</code> documentation for the + * <code>paraLevel</code> parameter. + * @param outOrder An order of the output, which can be one of the + * <code>UBiDiOrder</code> values. + * @param doMirroring Indicates whether or not to perform character mirroring, + * and can accept one of the <code>UBiDiMirroring</code> values. + * @param shapingOptions Arabic digit and letter shaping options defined in the + * ushape.h documentation. + * <p><strong>Note:</strong> Direction indicator options are computed by + * the transformation engine based on the effective ordering schemes, so + * user-defined direction indicators will be ignored.</p> + * @param pErrorCode A pointer to an error code value. + * + * @return The destination length, i.e. the number of UChars written to + * <code>dest</code>. If the transformation fails, the return value + * will be 0 (and the error code will be written to + * <code>pErrorCode</code>). + * + * @see UBiDiLevel + * @see UBiDiOrder + * @see UBiDiMirroring + * @see ubidi_setPara + * @see u_shapeArabic + * @stable ICU 58 + */ +U_CAPI uint32_t U_EXPORT2 +ubiditransform_transform(UBiDiTransform *pBiDiTransform, + const UChar *src, int32_t srcLength, + UChar *dest, int32_t destSize, + UBiDiLevel inParaLevel, UBiDiOrder inOrder, + UBiDiLevel outParaLevel, UBiDiOrder outOrder, + UBiDiMirroring doMirroring, uint32_t shapingOptions, + UErrorCode *pErrorCode); + +/** + * Allocates a <code>UBiDiTransform</code> object. This object can be reused, + * e.g. with different ordering schemes, mirroring or shaping options.<p> + * <strong>Note:</strong>The object can only be reused in the same thread. + * All other threads should allocate a new <code>UBiDiTransform</code> object + * before using it.<p> + * Example of usage:<p> + * <pre> + * \code + * UErrorCode errorCode = U_ZERO_ERROR; + * // Open a new UBiDiTransform. + * UBiDiTransform* transform = ubiditransform_open(&errorCode); + * // Run a transformation. + * ubiditransform_transform(transform, + * text1, -1, text2, -1, + * UBIDI_RTL, UBIDI_LOGICAL, + * UBIDI_LTR, UBIDI_VISUAL, + * UBIDI_MIRRORING_ON, + * U_SHAPE_DIGITS_EN2AN, + * &errorCode); + * // Do something with the output text and invoke another transformation using + * // that text as input. + * ubiditransform_transform(transform, + * text2, -1, text3, -1, + * UBIDI_LTR, UBIDI_VISUAL, + * UBIDI_RTL, UBIDI_VISUAL, + * UBIDI_MIRRORING_ON, + * 0, &errorCode); + *\endcode + * </pre> + * <p> + * The <code>UBiDiTransform</code> object must be deallocated by calling + * <code>ubiditransform_close()</code>. + * + * @return An empty <code>UBiDiTransform</code> object. + * @stable ICU 58 + */ +U_CAPI UBiDiTransform* U_EXPORT2 +ubiditransform_open(UErrorCode *pErrorCode); + +/** + * Deallocates the given <code>UBiDiTransform</code> object. + * @stable ICU 58 + */ +U_CAPI void U_EXPORT2 +ubiditransform_close(UBiDiTransform *pBidiTransform); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUBiDiTransformPointer + * "Smart pointer" class, closes a UBiDiTransform via ubiditransform_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 58 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUBiDiTransformPointer, UBiDiTransform, ubiditransform_close); + +U_NAMESPACE_END + +#endif + +#endif diff --git a/thirdparty/icu4c/common/unicode/ubrk.h b/thirdparty/icu4c/common/unicode/ubrk.h new file mode 100644 index 0000000000..37189a8598 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ubrk.h @@ -0,0 +1,631 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* Copyright (C) 1996-2015, International Business Machines Corporation and others. +* All Rights Reserved. +****************************************************************************** +*/ + +#ifndef UBRK_H +#define UBRK_H + +#include "unicode/utypes.h" +#include "unicode/uloc.h" +#include "unicode/utext.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * A text-break iterator. + * For usage in C programs. + */ +#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR +# define UBRK_TYPEDEF_UBREAK_ITERATOR + /** + * Opaque type representing an ICU Break iterator object. + * @stable ICU 2.0 + */ + typedef struct UBreakIterator UBreakIterator; +#endif + +#if !UCONFIG_NO_BREAK_ITERATION + +#include "unicode/parseerr.h" + +/** + * \file + * \brief C API: BreakIterator + * + * <h2> BreakIterator C API </h2> + * + * The BreakIterator C API defines methods for finding the location + * of boundaries in text. Pointer to a UBreakIterator maintain a + * current position and scan over text returning the index of characters + * where boundaries occur. + * <p> + * Line boundary analysis determines where a text string can be broken + * when line-wrapping. The mechanism correctly handles punctuation and + * hyphenated words. + * <p> + * Note: The locale keyword "lb" can be used to modify line break + * behavior according to the CSS level 3 line-break options, see + * <http://dev.w3.org/csswg/css-text/#line-breaking>. For example: + * "ja@lb=strict", "zh@lb=loose". + * <p> + * Sentence boundary analysis allows selection with correct + * interpretation of periods within numbers and abbreviations, and + * trailing punctuation marks such as quotation marks and parentheses. + * <p> + * Note: The locale keyword "ss" can be used to enable use of + * segmentation suppression data (preventing breaks in English after + * abbreviations such as "Mr." or "Est.", for example), as follows: + * "en@ss=standard". + * <p> + * Word boundary analysis is used by search and replace functions, as + * well as within text editing applications that allow the user to + * select words with a double click. Word selection provides correct + * interpretation of punctuation marks within and following + * words. Characters that are not part of a word, such as symbols or + * punctuation marks, have word-breaks on both sides. + * <p> + * Character boundary analysis identifies the boundaries of + * "Extended Grapheme Clusters", which are groupings of codepoints + * that should be treated as character-like units for many text operations. + * Please see Unicode Standard Annex #29, Unicode Text Segmentation, + * http://www.unicode.org/reports/tr29/ for additional information + * on grapheme clusters and guidelines on their use. + * <p> + * Title boundary analysis locates all positions, + * typically starts of words, that should be set to Title Case + * when title casing the text. + * <p> + * The text boundary positions are found according to the rules + * described in Unicode Standard Annex #29, Text Boundaries, and + * Unicode Standard Annex #14, Line Breaking Properties. These + * are available at http://www.unicode.org/reports/tr14/ and + * http://www.unicode.org/reports/tr29/. + * <p> + * In addition to the plain C API defined in this header file, an + * object oriented C++ API with equivalent functionality is defined in the + * file brkiter.h. + * <p> + * Code snippets illustrating the use of the Break Iterator APIs + * are available in the ICU User Guide, + * http://icu-project.org/userguide/boundaryAnalysis.html + * and in the sample program icu/source/samples/break/break.cpp + */ + +/** The possible types of text boundaries. @stable ICU 2.0 */ +typedef enum UBreakIteratorType { + /** Character breaks @stable ICU 2.0 */ + UBRK_CHARACTER = 0, + /** Word breaks @stable ICU 2.0 */ + UBRK_WORD = 1, + /** Line breaks @stable ICU 2.0 */ + UBRK_LINE = 2, + /** Sentence breaks @stable ICU 2.0 */ + UBRK_SENTENCE = 3, + +#ifndef U_HIDE_DEPRECATED_API + /** + * Title Case breaks + * The iterator created using this type locates title boundaries as described for + * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration, + * please use Word Boundary iterator. + * + * @deprecated ICU 2.8 Use the word break iterator for titlecasing for Unicode 4 and later. + */ + UBRK_TITLE = 4, + /** + * One more than the highest normal UBreakIteratorType value. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UBRK_COUNT = 5 +#endif // U_HIDE_DEPRECATED_API +} UBreakIteratorType; + +/** Value indicating all text boundaries have been returned. + * @stable ICU 2.0 + */ +#define UBRK_DONE ((int32_t) -1) + + +/** + * Enum constants for the word break tags returned by + * getRuleStatus(). A range of values is defined for each category of + * word, to allow for further subdivisions of a category in future releases. + * Applications should check for tag values falling within the range, rather + * than for single individual values. + * + * The numeric values of all of these constants are stable (will not change). + * + * @stable ICU 2.2 +*/ +typedef enum UWordBreak { + /** Tag value for "words" that do not fit into any of other categories. + * Includes spaces and most punctuation. */ + UBRK_WORD_NONE = 0, + /** Upper bound for tags for uncategorized words. */ + UBRK_WORD_NONE_LIMIT = 100, + /** Tag value for words that appear to be numbers, lower limit. */ + UBRK_WORD_NUMBER = 100, + /** Tag value for words that appear to be numbers, upper limit. */ + UBRK_WORD_NUMBER_LIMIT = 200, + /** Tag value for words that contain letters, excluding + * hiragana, katakana or ideographic characters, lower limit. */ + UBRK_WORD_LETTER = 200, + /** Tag value for words containing letters, upper limit */ + UBRK_WORD_LETTER_LIMIT = 300, + /** Tag value for words containing kana characters, lower limit */ + UBRK_WORD_KANA = 300, + /** Tag value for words containing kana characters, upper limit */ + UBRK_WORD_KANA_LIMIT = 400, + /** Tag value for words containing ideographic characters, lower limit */ + UBRK_WORD_IDEO = 400, + /** Tag value for words containing ideographic characters, upper limit */ + UBRK_WORD_IDEO_LIMIT = 500 +} UWordBreak; + +/** + * Enum constants for the line break tags returned by getRuleStatus(). + * A range of values is defined for each category of + * word, to allow for further subdivisions of a category in future releases. + * Applications should check for tag values falling within the range, rather + * than for single individual values. + * + * The numeric values of all of these constants are stable (will not change). + * + * @stable ICU 2.8 +*/ +typedef enum ULineBreakTag { + /** Tag value for soft line breaks, positions at which a line break + * is acceptable but not required */ + UBRK_LINE_SOFT = 0, + /** Upper bound for soft line breaks. */ + UBRK_LINE_SOFT_LIMIT = 100, + /** Tag value for a hard, or mandatory line break */ + UBRK_LINE_HARD = 100, + /** Upper bound for hard line breaks. */ + UBRK_LINE_HARD_LIMIT = 200 +} ULineBreakTag; + + + +/** + * Enum constants for the sentence break tags returned by getRuleStatus(). + * A range of values is defined for each category of + * sentence, to allow for further subdivisions of a category in future releases. + * Applications should check for tag values falling within the range, rather + * than for single individual values. + * + * The numeric values of all of these constants are stable (will not change). + * + * @stable ICU 2.8 +*/ +typedef enum USentenceBreakTag { + /** Tag value for for sentences ending with a sentence terminator + * ('.', '?', '!', etc.) character, possibly followed by a + * hard separator (CR, LF, PS, etc.) + */ + UBRK_SENTENCE_TERM = 0, + /** Upper bound for tags for sentences ended by sentence terminators. */ + UBRK_SENTENCE_TERM_LIMIT = 100, + /** Tag value for for sentences that do not contain an ending + * sentence terminator ('.', '?', '!', etc.) character, but + * are ended only by a hard separator (CR, LF, PS, etc.) or end of input. + */ + UBRK_SENTENCE_SEP = 100, + /** Upper bound for tags for sentences ended by a separator. */ + UBRK_SENTENCE_SEP_LIMIT = 200 + /** Tag value for a hard, or mandatory line break */ +} USentenceBreakTag; + + +/** + * Open a new UBreakIterator for locating text boundaries for a specified locale. + * A UBreakIterator may be used for detecting character, line, word, + * and sentence breaks in text. + * @param type The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD, + * UBRK_LINE, UBRK_SENTENCE + * @param locale The locale specifying the text-breaking conventions. Note that + * locale keys such as "lb" and "ss" may be used to modify text break behavior, + * see general discussion of BreakIterator C API. + * @param text The text to be iterated over. May be null, in which case ubrk_setText() is + * used to specify the text to be iterated. + * @param textLength The number of characters in text, or -1 if null-terminated. + * @param status A UErrorCode to receive any errors. + * @return A UBreakIterator for the specified locale. + * @see ubrk_openRules + * @stable ICU 2.0 + */ +U_CAPI UBreakIterator* U_EXPORT2 +ubrk_open(UBreakIteratorType type, + const char *locale, + const UChar *text, + int32_t textLength, + UErrorCode *status); + +/** + * Open a new UBreakIterator for locating text boundaries using specified breaking rules. + * The rule syntax is ... (TBD) + * @param rules A set of rules specifying the text breaking conventions. + * @param rulesLength The number of characters in rules, or -1 if null-terminated. + * @param text The text to be iterated over. May be null, in which case ubrk_setText() is + * used to specify the text to be iterated. + * @param textLength The number of characters in text, or -1 if null-terminated. + * @param parseErr Receives position and context information for any syntax errors + * detected while parsing the rules. + * @param status A UErrorCode to receive any errors. + * @return A UBreakIterator for the specified rules. + * @see ubrk_open + * @stable ICU 2.2 + */ +U_CAPI UBreakIterator* U_EXPORT2 +ubrk_openRules(const UChar *rules, + int32_t rulesLength, + const UChar *text, + int32_t textLength, + UParseError *parseErr, + UErrorCode *status); + +/** + * Open a new UBreakIterator for locating text boundaries using precompiled binary rules. + * Opening a UBreakIterator this way is substantially faster than using ubrk_openRules. + * Binary rules may be obtained using ubrk_getBinaryRules. The compiled rules are not + * compatible across different major versions of ICU, nor across platforms of different + * endianness or different base character set family (ASCII vs EBCDIC). + * @param binaryRules A set of compiled binary rules specifying the text breaking + * conventions. Ownership of the storage containing the compiled + * rules remains with the caller of this function. The compiled + * rules must not be modified or deleted during the life of the + * break iterator. + * @param rulesLength The length of binaryRules in bytes; must be >= 0. + * @param text The text to be iterated over. May be null, in which case + * ubrk_setText() is used to specify the text to be iterated. + * @param textLength The number of characters in text, or -1 if null-terminated. + * @param status Pointer to UErrorCode to receive any errors. + * @return UBreakIterator for the specified rules. + * @see ubrk_getBinaryRules + * @stable ICU 59 + */ +U_CAPI UBreakIterator* U_EXPORT2 +ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength, + const UChar * text, int32_t textLength, + UErrorCode * status); + +/** + * Thread safe cloning operation + * @param bi iterator to be cloned + * @param stackBuffer <em>Deprecated functionality as of ICU 52, use NULL.</em><br> + * user allocated space for the new clone. If NULL new memory will be allocated. + * If buffer is not large enough, new memory will be allocated. + * Clients can use the U_BRK_SAFECLONE_BUFFERSIZE. + * @param pBufferSize <em>Deprecated functionality as of ICU 52, use NULL or 1.</em><br> + * pointer to size of allocated space. + * If *pBufferSize == 0, a sufficient size for use in cloning will + * be returned ('pre-flighting') + * If *pBufferSize is not enough for a stack-based safe clone, + * new memory will be allocated. + * @param status to indicate whether the operation went on smoothly or there were errors + * An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were necessary. + * @return pointer to the new clone + * @stable ICU 2.0 + */ +U_CAPI UBreakIterator * U_EXPORT2 +ubrk_safeClone( + const UBreakIterator *bi, + void *stackBuffer, + int32_t *pBufferSize, + UErrorCode *status); + +#ifndef U_HIDE_DEPRECATED_API + +/** + * A recommended size (in bytes) for the memory buffer to be passed to ubrk_saveClone(). + * @deprecated ICU 52. Do not rely on ubrk_safeClone() cloning into any provided buffer. + */ +#define U_BRK_SAFECLONE_BUFFERSIZE 1 + +#endif /* U_HIDE_DEPRECATED_API */ + +/** +* Close a UBreakIterator. +* Once closed, a UBreakIterator may no longer be used. +* @param bi The break iterator to close. + * @stable ICU 2.0 +*/ +U_CAPI void U_EXPORT2 +ubrk_close(UBreakIterator *bi); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUBreakIteratorPointer + * "Smart pointer" class, closes a UBreakIterator via ubrk_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUBreakIteratorPointer, UBreakIterator, ubrk_close); + +U_NAMESPACE_END + +#endif + +/** + * Sets an existing iterator to point to a new piece of text. + * The break iterator retains a pointer to the supplied text. + * The caller must not modify or delete the text while the BreakIterator + * retains the reference. + * + * @param bi The iterator to use + * @param text The text to be set + * @param textLength The length of the text + * @param status The error code + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ubrk_setText(UBreakIterator* bi, + const UChar* text, + int32_t textLength, + UErrorCode* status); + + +/** + * Sets an existing iterator to point to a new piece of text. + * + * All index positions returned by break iterator functions are + * native indices from the UText. For example, when breaking UTF-8 + * encoded text, the break positions returned by \ref ubrk_next, \ref ubrk_previous, etc. + * will be UTF-8 string indices, not UTF-16 positions. + * + * @param bi The iterator to use + * @param text The text to be set. + * This function makes a shallow clone of the supplied UText. This means + * that the caller is free to immediately close or otherwise reuse the + * UText that was passed as a parameter, but that the underlying text itself + * must not be altered while being referenced by the break iterator. + * @param status The error code + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +ubrk_setUText(UBreakIterator* bi, + UText* text, + UErrorCode* status); + + + +/** + * Determine the most recently-returned text boundary. + * + * @param bi The break iterator to use. + * @return The character index most recently returned by \ref ubrk_next, \ref ubrk_previous, + * \ref ubrk_first, or \ref ubrk_last. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_current(const UBreakIterator *bi); + +/** + * Advance the iterator to the boundary following the current boundary. + * + * @param bi The break iterator to use. + * @return The character index of the next text boundary, or UBRK_DONE + * if all text boundaries have been returned. + * @see ubrk_previous + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_next(UBreakIterator *bi); + +/** + * Set the iterator position to the boundary preceding the current boundary. + * + * @param bi The break iterator to use. + * @return The character index of the preceding text boundary, or UBRK_DONE + * if all text boundaries have been returned. + * @see ubrk_next + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_previous(UBreakIterator *bi); + +/** + * Set the iterator position to zero, the start of the text being scanned. + * @param bi The break iterator to use. + * @return The new iterator position (zero). + * @see ubrk_last + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_first(UBreakIterator *bi); + +/** + * Set the iterator position to the index immediately <EM>beyond</EM> the last character in the text being scanned. + * This is not the same as the last character. + * @param bi The break iterator to use. + * @return The character offset immediately <EM>beyond</EM> the last character in the + * text being scanned. + * @see ubrk_first + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_last(UBreakIterator *bi); + +/** + * Set the iterator position to the first boundary preceding the specified offset. + * The new position is always smaller than offset, or UBRK_DONE. + * @param bi The break iterator to use. + * @param offset The offset to begin scanning. + * @return The text boundary preceding offset, or UBRK_DONE. + * @see ubrk_following + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_preceding(UBreakIterator *bi, + int32_t offset); + +/** + * Advance the iterator to the first boundary following the specified offset. + * The value returned is always greater than offset, or UBRK_DONE. + * @param bi The break iterator to use. + * @param offset The offset to begin scanning. + * @return The text boundary following offset, or UBRK_DONE. + * @see ubrk_preceding + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_following(UBreakIterator *bi, + int32_t offset); + +/** +* Get a locale for which text breaking information is available. +* A UBreakIterator in a locale returned by this function will perform the correct +* text breaking for the locale. +* @param index The index of the desired locale. +* @return A locale for which number text breaking information is available, or 0 if none. +* @see ubrk_countAvailable +* @stable ICU 2.0 +*/ +U_CAPI const char* U_EXPORT2 +ubrk_getAvailable(int32_t index); + +/** +* Determine how many locales have text breaking information available. +* This function is most useful as determining the loop ending condition for +* calls to \ref ubrk_getAvailable. +* @return The number of locales for which text breaking information is available. +* @see ubrk_getAvailable +* @stable ICU 2.0 +*/ +U_CAPI int32_t U_EXPORT2 +ubrk_countAvailable(void); + + +/** +* Returns true if the specified position is a boundary position. As a side +* effect, leaves the iterator pointing to the first boundary position at +* or after "offset". +* @param bi The break iterator to use. +* @param offset the offset to check. +* @return True if "offset" is a boundary position. +* @stable ICU 2.0 +*/ +U_CAPI UBool U_EXPORT2 +ubrk_isBoundary(UBreakIterator *bi, int32_t offset); + +/** + * Return the status from the break rule that determined the most recently + * returned break position. The values appear in the rule source + * within brackets, {123}, for example. For rules that do not specify a + * status, a default value of 0 is returned. + * <p> + * For word break iterators, the possible values are defined in enum UWordBreak. + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_getRuleStatus(UBreakIterator *bi); + +/** + * Get the statuses from the break rules that determined the most recently + * returned break position. The values appear in the rule source + * within brackets, {123}, for example. The default status value for rules + * that do not explicitly provide one is zero. + * <p> + * For word break iterators, the possible values are defined in enum UWordBreak. + * @param bi The break iterator to use + * @param fillInVec an array to be filled in with the status values. + * @param capacity the length of the supplied vector. A length of zero causes + * the function to return the number of status values, in the + * normal way, without attempting to store any values. + * @param status receives error codes. + * @return The number of rule status values from rules that determined + * the most recent boundary returned by the break iterator. + * @stable ICU 3.0 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status); + +/** + * Return the locale of the break iterator. You can choose between the valid and + * the actual locale. + * @param bi break iterator + * @param type locale type (valid or actual) + * @param status error code + * @return locale string + * @stable ICU 2.8 + */ +U_CAPI const char* U_EXPORT2 +ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode* status); + +/** + * Set the subject text string upon which the break iterator is operating + * without changing any other aspect of the state. + * The new and previous text strings must have the same content. + * + * This function is intended for use in environments where ICU is operating on + * strings that may move around in memory. It provides a mechanism for notifying + * ICU that the string has been relocated, and providing a new UText to access the + * string in its new position. + * + * Note that the break iterator never copies the underlying text + * of a string being processed, but always operates directly on the original text + * provided by the user. Refreshing simply drops the references to the old text + * and replaces them with references to the new. + * + * Caution: this function is normally used only by very specialized + * system-level code. One example use case is with garbage collection + * that moves the text in memory. + * + * @param bi The break iterator. + * @param text The new (moved) text string. + * @param status Receives errors detected by this function. + * + * @stable ICU 49 + */ +U_CAPI void U_EXPORT2 +ubrk_refreshUText(UBreakIterator *bi, + UText *text, + UErrorCode *status); + + +/** + * Get a compiled binary version of the rules specifying the behavior of a UBreakIterator. + * The binary rules may be used with ubrk_openBinaryRules to open a new UBreakIterator + * more quickly than using ubrk_openRules. The compiled rules are not compatible across + * different major versions of ICU, nor across platforms of different endianness or + * different base character set family (ASCII vs EBCDIC). Supports preflighting (with + * binaryRules=NULL and rulesCapacity=0) to get the rules length without copying them to + * the binaryRules buffer. However, whether preflighting or not, if the actual length + * is greater than INT32_MAX, then the function returns 0 and sets *status to + * U_INDEX_OUTOFBOUNDS_ERROR. + + * @param bi The break iterator to use. + * @param binaryRules Buffer to receive the compiled binary rules; set to NULL for + * preflighting. + * @param rulesCapacity Capacity (in bytes) of the binaryRules buffer; set to 0 for + * preflighting. Must be >= 0. + * @param status Pointer to UErrorCode to receive any errors, such as + * U_BUFFER_OVERFLOW_ERROR, U_INDEX_OUTOFBOUNDS_ERROR, or + * U_ILLEGAL_ARGUMENT_ERROR. + * @return The actual byte length of the binary rules, if <= INT32_MAX; + * otherwise 0. If not preflighting and this is larger than + * rulesCapacity, *status will be set to an error. + * @see ubrk_openBinaryRules + * @stable ICU 59 + */ +U_CAPI int32_t U_EXPORT2 +ubrk_getBinaryRules(UBreakIterator *bi, + uint8_t * binaryRules, int32_t rulesCapacity, + UErrorCode * status); + +#endif /* #if !UCONFIG_NO_BREAK_ITERATION */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/ucasemap.h b/thirdparty/icu4c/common/unicode/ucasemap.h new file mode 100644 index 0000000000..d1c1b483ab --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucasemap.h @@ -0,0 +1,388 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2005-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: ucasemap.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2005may06 +* created by: Markus W. Scherer +* +* Case mapping service object and functions using it. +*/ + +#ifndef __UCASEMAP_H__ +#define __UCASEMAP_H__ + +#include "unicode/utypes.h" +#include "unicode/stringoptions.h" +#include "unicode/ustring.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * \file + * \brief C API: Unicode case mapping functions using a UCaseMap service object. + * + * The service object takes care of memory allocations, data loading, and setup + * for the attributes, as usual. + * + * Currently, the functionality provided here does not overlap with uchar.h + * and ustring.h, except for ucasemap_toTitle(). + * + * ucasemap_utf8XYZ() functions operate directly on UTF-8 strings. + */ + +/** + * UCaseMap is an opaque service object for newer ICU case mapping functions. + * Older functions did not use a service object. + * @stable ICU 3.4 + */ +struct UCaseMap; +typedef struct UCaseMap UCaseMap; /**< C typedef for struct UCaseMap. @stable ICU 3.4 */ + +/** + * Open a UCaseMap service object for a locale and a set of options. + * The locale ID and options are preprocessed so that functions using the + * service object need not process them in each call. + * + * @param locale ICU locale ID, used for language-dependent + * upper-/lower-/title-casing according to the Unicode standard. + * Usual semantics: ""=root, NULL=default locale, etc. + * @param options Options bit set, used for case folding and string comparisons. + * Same flags as for u_foldCase(), u_strFoldCase(), + * u_strCaseCompare(), etc. + * Use 0 or U_FOLD_CASE_DEFAULT for default behavior. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return Pointer to a UCaseMap service object, if successful. + * + * @see U_FOLD_CASE_DEFAULT + * @see U_FOLD_CASE_EXCLUDE_SPECIAL_I + * @see U_TITLECASE_NO_LOWERCASE + * @see U_TITLECASE_NO_BREAK_ADJUSTMENT + * @stable ICU 3.4 + */ +U_CAPI UCaseMap * U_EXPORT2 +ucasemap_open(const char *locale, uint32_t options, UErrorCode *pErrorCode); + +/** + * Close a UCaseMap service object. + * @param csm Object to be closed. + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +ucasemap_close(UCaseMap *csm); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUCaseMapPointer + * "Smart pointer" class, closes a UCaseMap via ucasemap_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUCaseMapPointer, UCaseMap, ucasemap_close); + +U_NAMESPACE_END + +#endif + +/** + * Get the locale ID that is used for language-dependent case mappings. + * @param csm UCaseMap service object. + * @return locale ID + * @stable ICU 3.4 + */ +U_CAPI const char * U_EXPORT2 +ucasemap_getLocale(const UCaseMap *csm); + +/** + * Get the options bit set that is used for case folding and string comparisons. + * @param csm UCaseMap service object. + * @return options bit set + * @stable ICU 3.4 + */ +U_CAPI uint32_t U_EXPORT2 +ucasemap_getOptions(const UCaseMap *csm); + +/** + * Set the locale ID that is used for language-dependent case mappings. + * + * @param csm UCaseMap service object. + * @param locale Locale ID, see ucasemap_open(). + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @see ucasemap_open + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +ucasemap_setLocale(UCaseMap *csm, const char *locale, UErrorCode *pErrorCode); + +/** + * Set the options bit set that is used for case folding and string comparisons. + * + * @param csm UCaseMap service object. + * @param options Options bit set, see ucasemap_open(). + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @see ucasemap_open + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +ucasemap_setOptions(UCaseMap *csm, uint32_t options, UErrorCode *pErrorCode); + +#if !UCONFIG_NO_BREAK_ITERATION + +/** + * Get the break iterator that is used for titlecasing. + * Do not modify the returned break iterator. + * @param csm UCaseMap service object. + * @return titlecasing break iterator + * @stable ICU 3.8 + */ +U_CAPI const UBreakIterator * U_EXPORT2 +ucasemap_getBreakIterator(const UCaseMap *csm); + +/** + * Set the break iterator that is used for titlecasing. + * The UCaseMap service object releases a previously set break iterator + * and "adopts" this new one, taking ownership of it. + * It will be released in a subsequent call to ucasemap_setBreakIterator() + * or ucasemap_close(). + * + * Break iterator operations are not thread-safe. Therefore, titlecasing + * functions use non-const UCaseMap objects. It is not possible to titlecase + * strings concurrently using the same UCaseMap. + * + * @param csm UCaseMap service object. + * @param iterToAdopt Break iterator to be adopted for titlecasing. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @see ucasemap_toTitle + * @see ucasemap_utf8ToTitle + * @stable ICU 3.8 + */ +U_CAPI void U_EXPORT2 +ucasemap_setBreakIterator(UCaseMap *csm, UBreakIterator *iterToAdopt, UErrorCode *pErrorCode); + +/** + * Titlecase a UTF-16 string. This function is almost a duplicate of u_strToTitle(), + * except that it takes ucasemap_setOptions() into account and has performance + * advantages from being able to use a UCaseMap object for multiple case mapping + * operations, saving setup time. + * + * Casing is locale-dependent and context-sensitive. + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. (This can be modified with ucasemap_setOptions().) + * + * Note: This function takes a non-const UCaseMap pointer because it will + * open a default break iterator if no break iterator was set yet, + * and effectively call ucasemap_setBreakIterator(); + * also because the break iterator is stateful and will be modified during + * the iteration. + * + * The titlecase break iterator can be provided to customize for arbitrary + * styles, using rules and dictionaries beyond the standard iterators. + * The standard titlecase iterator for the root locale implements the + * algorithm of Unicode TR 21. + * + * This function uses only the setText(), first() and next() methods of the + * provided break iterator. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param csm UCaseMap service object. This pointer is non-const! + * See the note above for details. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * + * @see u_strToTitle + * @stable ICU 3.8 + */ +U_CAPI int32_t U_EXPORT2 +ucasemap_toTitle(UCaseMap *csm, + UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + UErrorCode *pErrorCode); + +#endif // UCONFIG_NO_BREAK_ITERATION + +/** + * Lowercase the characters in a UTF-8 string. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param csm UCaseMap service object. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of bytes). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * + * @see u_strToLower + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +ucasemap_utf8ToLower(const UCaseMap *csm, + char *dest, int32_t destCapacity, + const char *src, int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Uppercase the characters in a UTF-8 string. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param csm UCaseMap service object. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of bytes). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * + * @see u_strToUpper + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +ucasemap_utf8ToUpper(const UCaseMap *csm, + char *dest, int32_t destCapacity, + const char *src, int32_t srcLength, + UErrorCode *pErrorCode); + +#if !UCONFIG_NO_BREAK_ITERATION + +/** + * Titlecase a UTF-8 string. + * Casing is locale-dependent and context-sensitive. + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. (This can be modified with ucasemap_setOptions().) + * + * Note: This function takes a non-const UCaseMap pointer because it will + * open a default break iterator if no break iterator was set yet, + * and effectively call ucasemap_setBreakIterator(); + * also because the break iterator is stateful and will be modified during + * the iteration. + * + * The titlecase break iterator can be provided to customize for arbitrary + * styles, using rules and dictionaries beyond the standard iterators. + * The standard titlecase iterator for the root locale implements the + * algorithm of Unicode TR 21. + * + * This function uses only the setUText(), first(), next() and close() methods of the + * provided break iterator. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param csm UCaseMap service object. This pointer is non-const! + * See the note above for details. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of bytes). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * + * @see u_strToTitle + * @see U_TITLECASE_NO_LOWERCASE + * @see U_TITLECASE_NO_BREAK_ADJUSTMENT + * @stable ICU 3.8 + */ +U_CAPI int32_t U_EXPORT2 +ucasemap_utf8ToTitle(UCaseMap *csm, + char *dest, int32_t destCapacity, + const char *src, int32_t srcLength, + UErrorCode *pErrorCode); + +#endif + +/** + * Case-folds the characters in a UTF-8 string. + * + * Case-folding is locale-independent and not context-sensitive, + * but there is an option for whether to include or exclude mappings for dotted I + * and dotless i that are marked with 'T' in CaseFolding.txt. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer must not overlap. + * + * @param csm UCaseMap service object. + * @param dest A buffer for the result string. The result will be NUL-terminated if + * the buffer is large enough. + * The contents is undefined in case of failure. + * @param destCapacity The size of the buffer (number of bytes). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string. + * @param srcLength The length of the original string. If -1, then src must be NUL-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * + * @see u_strFoldCase + * @see ucasemap_setOptions + * @see U_FOLD_CASE_DEFAULT + * @see U_FOLD_CASE_EXCLUDE_SPECIAL_I + * @stable ICU 3.8 + */ +U_CAPI int32_t U_EXPORT2 +ucasemap_utf8FoldCase(const UCaseMap *csm, + char *dest, int32_t destCapacity, + const char *src, int32_t srcLength, + UErrorCode *pErrorCode); + +#endif diff --git a/thirdparty/icu4c/common/unicode/ucat.h b/thirdparty/icu4c/common/unicode/ucat.h new file mode 100644 index 0000000000..93850348ff --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucat.h @@ -0,0 +1,160 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (c) 2003-2004, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* Author: Alan Liu +* Created: March 19 2003 +* Since: ICU 2.6 +********************************************************************** +*/ +#ifndef UCAT_H +#define UCAT_H + +#include "unicode/utypes.h" +#include "unicode/ures.h" + +/** + * \file + * \brief C API: Message Catalog Wrappers + * + * This C API provides look-alike functions that deliberately resemble + * the POSIX catopen, catclose, and catgets functions. The underlying + * implementation is in terms of ICU resource bundles, rather than + * POSIX message catalogs. + * + * The ICU resource bundles obey standard ICU inheritance policies. + * To facilitate this, sets and messages are flattened into one tier. + * This is done by creating resource bundle keys of the form + * <set_num>%<msg_num> where set_num is the set number and msg_num is + * the message number, formatted as decimal strings. + * + * Example: Consider a message catalog containing two sets: + * + * Set 1: Message 4 = "Good morning." + * Message 5 = "Good afternoon." + * Message 7 = "Good evening." + * Message 8 = "Good night." + * Set 4: Message 14 = "Please " + * Message 19 = "Thank you." + * Message 20 = "Sincerely," + * + * The ICU resource bundle source file would, assuming it is named + * "greet.txt", would look like this: + * + * greet + * { + * 1%4 { "Good morning." } + * 1%5 { "Good afternoon." } + * 1%7 { "Good evening." } + * 1%8 { "Good night." } + * + * 4%14 { "Please " } + * 4%19 { "Thank you." } + * 4%20 { "Sincerely," } + * } + * + * The catgets function is commonly used in combination with functions + * like printf and strftime. ICU components like message format can + * be used instead, although they use a different format syntax. + * There is an ICU package, icuio, that provides some of + * the POSIX-style formatting API. + */ + +U_CDECL_BEGIN + +/** + * An ICU message catalog descriptor, analogous to nl_catd. + * + * @stable ICU 2.6 + */ +typedef UResourceBundle* u_nl_catd; + +/** + * Open and return an ICU message catalog descriptor. The descriptor + * may be passed to u_catgets() to retrieve localized strings. + * + * @param name string containing the full path pointing to the + * directory where the resources reside followed by the package name + * e.g. "/usr/resource/my_app/resources/guimessages" on a Unix system. + * If NULL, ICU default data files will be used. + * + * Unlike POSIX, environment variables are not interpolated within the + * name. + * + * @param locale the locale for which we want to open the resource. If + * NULL, the default ICU locale will be used (see uloc_getDefault). If + * strlen(locale) == 0, the root locale will be used. + * + * @param ec input/output error code. Upon output, + * U_USING_FALLBACK_WARNING indicates that a fallback locale was + * used. For example, 'de_CH' was requested, but nothing was found + * there, so 'de' was used. U_USING_DEFAULT_WARNING indicates that the + * default locale data or root locale data was used; neither the + * requested locale nor any of its fallback locales were found. + * + * @return a message catalog descriptor that may be passed to + * u_catgets(). If the ec parameter indicates success, then the caller + * is responsible for calling u_catclose() to close the message + * catalog. If the ec parameter indicates failure, then NULL will be + * returned. + * + * @stable ICU 2.6 + */ +U_CAPI u_nl_catd U_EXPORT2 +u_catopen(const char* name, const char* locale, UErrorCode* ec); + +/** + * Close an ICU message catalog, given its descriptor. + * + * @param catd a message catalog descriptor to be closed. May be NULL, + * in which case no action is taken. + * + * @stable ICU 2.6 + */ +U_CAPI void U_EXPORT2 +u_catclose(u_nl_catd catd); + +/** + * Retrieve a localized string from an ICU message catalog. + * + * @param catd a message catalog descriptor returned by u_catopen. + * + * @param set_num the message catalog set number. Sets need not be + * numbered consecutively. + * + * @param msg_num the message catalog message number within the + * set. Messages need not be numbered consecutively. + * + * @param s the default string. This is returned if the string + * specified by the set_num and msg_num is not found. It must be + * zero-terminated. + * + * @param len fill-in parameter to receive the length of the result. + * May be NULL, in which case it is ignored. + * + * @param ec input/output error code. May be U_USING_FALLBACK_WARNING + * or U_USING_DEFAULT_WARNING. U_MISSING_RESOURCE_ERROR indicates that + * the set_num/msg_num tuple does not specify a valid message string + * in this catalog. + * + * @return a pointer to a zero-terminated UChar array which lives in + * an internal buffer area, typically a memory mapped/DLL file. The + * caller must NOT delete this pointer. If the call is unsuccessful + * for any reason, then s is returned. This includes the situation in + * which ec indicates a failing error code upon entry to this + * function. + * + * @stable ICU 2.6 + */ +U_CAPI const UChar* U_EXPORT2 +u_catgets(u_nl_catd catd, int32_t set_num, int32_t msg_num, + const UChar* s, + int32_t* len, UErrorCode* ec); + +U_CDECL_END + +#endif /*UCAT_H*/ +/*eof*/ diff --git a/thirdparty/icu4c/common/unicode/uchar.h b/thirdparty/icu4c/common/unicode/uchar.h new file mode 100644 index 0000000000..1e0f82e706 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uchar.h @@ -0,0 +1,4056 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1997-2016, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* +* File UCHAR.H +* +* Modification History: +* +* Date Name Description +* 04/02/97 aliu Creation. +* 03/29/99 helena Updated for C APIs. +* 4/15/99 Madhu Updated for C Implementation and Javadoc +* 5/20/99 Madhu Added the function u_getVersion() +* 8/19/1999 srl Upgraded scripts to Unicode 3.0 +* 8/27/1999 schererm UCharDirection constants: U_... +* 11/11/1999 weiv added u_isalnum(), cleaned comments +* 01/11/2000 helena Renamed u_getVersion to u_getUnicodeVersion(). +****************************************************************************** +*/ + +#ifndef UCHAR_H +#define UCHAR_H + +#include "unicode/utypes.h" +#include "unicode/stringoptions.h" +#include "unicode/ucpmap.h" + +#if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN) + +#define USET_DEFINED + +/** + * USet is the C API type corresponding to C++ class UnicodeSet. + * It is forward-declared here to avoid including unicode/uset.h file if related + * APIs are not used. + * + * @see ucnv_getUnicodeSet + * @stable ICU 2.4 + */ +typedef struct USet USet; + +#endif + + +U_CDECL_BEGIN + +/*==========================================================================*/ +/* Unicode version number */ +/*==========================================================================*/ +/** + * Unicode version number, default for the current ICU version. + * The actual Unicode Character Database (UCD) data is stored in uprops.dat + * and may be generated from UCD files from a different Unicode version. + * Call u_getUnicodeVersion to get the actual Unicode version of the data. + * + * @see u_getUnicodeVersion + * @stable ICU 2.0 + */ +#define U_UNICODE_VERSION "13.0" + +/** + * \file + * \brief C API: Unicode Properties + * + * This C API provides low-level access to the Unicode Character Database. + * In addition to raw property values, some convenience functions calculate + * derived properties, for example for Java-style programming. + * + * Unicode assigns each code point (not just assigned character) values for + * many properties. + * Most of them are simple boolean flags, or constants from a small enumerated list. + * For some properties, values are strings or other relatively more complex types. + * + * For more information see + * "About the Unicode Character Database" (http://www.unicode.org/ucd/) + * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html). + * + * Many properties are accessible via generic functions that take a UProperty selector. + * - u_hasBinaryProperty() returns a binary value (true/false) per property and code point. + * - u_getIntPropertyValue() returns an integer value per property and code point. + * For each supported enumerated or catalog property, there is + * an enum type for all of the property's values, and + * u_getIntPropertyValue() returns the numeric values of those constants. + * - u_getBinaryPropertySet() returns a set for each ICU-supported binary property with + * all code points for which the property is true. + * - u_getIntPropertyMap() returns a map for each + * ICU-supported enumerated/catalog/int-valued property which + * maps all Unicode code points to their values for that property. + * + * Many functions are designed to match java.lang.Character functions. + * See the individual function documentation, + * and see the JDK 1.4 java.lang.Character documentation + * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html + * + * There are also functions that provide easy migration from C/POSIX functions + * like isblank(). Their use is generally discouraged because the C/POSIX + * standards do not define their semantics beyond the ASCII range, which means + * that different implementations exhibit very different behavior. + * Instead, Unicode properties should be used directly. + * + * There are also only a few, broad C/POSIX character classes, and they tend + * to be used for conflicting purposes. For example, the "isalpha()" class + * is sometimes used to determine word boundaries, while a more sophisticated + * approach would at least distinguish initial letters from continuation + * characters (the latter including combining marks). + * (In ICU, BreakIterator is the most sophisticated API for word boundaries.) + * Another example: There is no "istitle()" class for titlecase characters. + * + * ICU 3.4 and later provides API access for all twelve C/POSIX character classes. + * ICU implements them according to the Standard Recommendations in + * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions + * (http://www.unicode.org/reports/tr18/#Compatibility_Properties). + * + * API access for C/POSIX character classes is as follows: + * - alpha: u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC) + * - lower: u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE) + * - upper: u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE) + * - punct: u_ispunct(c) + * - digit: u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER + * - xdigit: u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT) + * - alnum: u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM) + * - space: u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE) + * - blank: u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK) + * - cntrl: u_charType(c)==U_CONTROL_CHAR + * - graph: u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH) + * - print: u_hasBinaryProperty(c, UCHAR_POSIX_PRINT) + * + * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, + * the Standard Recommendations in UTS #18. Instead, they match Java + * functions according to their API documentation. + * + * \htmlonly + * The C/POSIX character classes are also available in UnicodeSet patterns, + * using patterns like [:graph:] or \p{graph}. + * \endhtmlonly + * + * Note: There are several ICU whitespace functions. + * Comparison: + * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; + * most of general categories "Z" (separators) + most whitespace ISO controls + * (including no-break spaces, but excluding IS1..IS4) + * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces + * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces) + * - u_isspace: Z + whitespace ISO controls (including no-break spaces) + * - u_isblank: "horizontal spaces" = TAB + Zs + */ + +/** + * Constants. + */ + +/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */ +#define UCHAR_MIN_VALUE 0 + +/** + * The highest Unicode code point value (scalar value) according to + * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). + * For a single character, UChar32 is a simple type that can hold any code point value. + * + * @see UChar32 + * @stable ICU 2.0 + */ +#define UCHAR_MAX_VALUE 0x10ffff + +/** + * Get a single-bit bit set (a flag) from a bit number 0..31. + * @stable ICU 2.1 + */ +#define U_MASK(x) ((uint32_t)1<<(x)) + +/** + * Selection constants for Unicode properties. + * These constants are used in functions like u_hasBinaryProperty to select + * one of the Unicode properties. + * + * The properties APIs are intended to reflect Unicode properties as defined + * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). + * + * For details about the properties see + * UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/). + * + * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, + * then properties marked with "new in Unicode 3.2" are not or not fully available. + * Check u_getUnicodeVersion to be sure. + * + * @see u_hasBinaryProperty + * @see u_getIntPropertyValue + * @see u_getUnicodeVersion + * @stable ICU 2.1 + */ +typedef enum UProperty { + /* + * Note: UProperty constants are parsed by preparseucd.py. + * It matches lines like + * UCHAR_<Unicode property name>=<integer>, + */ + + /* Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that + debuggers display UCHAR_ALPHABETIC as the symbolic name for 0, + rather than UCHAR_BINARY_START. Likewise for other *_START + identifiers. */ + + /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. + Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */ + UCHAR_ALPHABETIC=0, + /** First constant for binary Unicode properties. @stable ICU 2.1 */ + UCHAR_BINARY_START=UCHAR_ALPHABETIC, + /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */ + UCHAR_ASCII_HEX_DIGIT=1, + /** Binary property Bidi_Control. + Format controls which have specific functions + in the Bidi Algorithm. @stable ICU 2.1 */ + UCHAR_BIDI_CONTROL=2, + /** Binary property Bidi_Mirrored. + Characters that may change display in RTL text. + Same as u_isMirrored. + See Bidi Algorithm, UTR 9. @stable ICU 2.1 */ + UCHAR_BIDI_MIRRORED=3, + /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */ + UCHAR_DASH=4, + /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). + Ignorable in most processing. + <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */ + UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5, + /** Binary property Deprecated (new in Unicode 3.2). + The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */ + UCHAR_DEPRECATED=6, + /** Binary property Diacritic. Characters that linguistically modify + the meaning of another character to which they apply. @stable ICU 2.1 */ + UCHAR_DIACRITIC=7, + /** Binary property Extender. + Extend the value or shape of a preceding alphabetic character, + e.g., length and iteration marks. @stable ICU 2.1 */ + UCHAR_EXTENDER=8, + /** Binary property Full_Composition_Exclusion. + CompositionExclusions.txt+Singleton Decompositions+ + Non-Starter Decompositions. @stable ICU 2.1 */ + UCHAR_FULL_COMPOSITION_EXCLUSION=9, + /** Binary property Grapheme_Base (new in Unicode 3.2). + For programmatic determination of grapheme cluster boundaries. + [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */ + UCHAR_GRAPHEME_BASE=10, + /** Binary property Grapheme_Extend (new in Unicode 3.2). + For programmatic determination of grapheme cluster boundaries. + Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */ + UCHAR_GRAPHEME_EXTEND=11, + /** Binary property Grapheme_Link (new in Unicode 3.2). + For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */ + UCHAR_GRAPHEME_LINK=12, + /** Binary property Hex_Digit. + Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */ + UCHAR_HEX_DIGIT=13, + /** Binary property Hyphen. Dashes used to mark connections + between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */ + UCHAR_HYPHEN=14, + /** Binary property ID_Continue. + Characters that can continue an identifier. + DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." + ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */ + UCHAR_ID_CONTINUE=15, + /** Binary property ID_Start. + Characters that can start an identifier. + Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */ + UCHAR_ID_START=16, + /** Binary property Ideographic. + CJKV ideographs. @stable ICU 2.1 */ + UCHAR_IDEOGRAPHIC=17, + /** Binary property IDS_Binary_Operator (new in Unicode 3.2). + For programmatic determination of + Ideographic Description Sequences. @stable ICU 2.1 */ + UCHAR_IDS_BINARY_OPERATOR=18, + /** Binary property IDS_Trinary_Operator (new in Unicode 3.2). + For programmatic determination of + Ideographic Description Sequences. @stable ICU 2.1 */ + UCHAR_IDS_TRINARY_OPERATOR=19, + /** Binary property Join_Control. + Format controls for cursive joining and ligation. @stable ICU 2.1 */ + UCHAR_JOIN_CONTROL=20, + /** Binary property Logical_Order_Exception (new in Unicode 3.2). + Characters that do not use logical order and + require special handling in most processing. @stable ICU 2.1 */ + UCHAR_LOGICAL_ORDER_EXCEPTION=21, + /** Binary property Lowercase. Same as u_isULowercase, different from u_islower. + Ll+Other_Lowercase @stable ICU 2.1 */ + UCHAR_LOWERCASE=22, + /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */ + UCHAR_MATH=23, + /** Binary property Noncharacter_Code_Point. + Code points that are explicitly defined as illegal + for the encoding of characters. @stable ICU 2.1 */ + UCHAR_NONCHARACTER_CODE_POINT=24, + /** Binary property Quotation_Mark. @stable ICU 2.1 */ + UCHAR_QUOTATION_MARK=25, + /** Binary property Radical (new in Unicode 3.2). + For programmatic determination of + Ideographic Description Sequences. @stable ICU 2.1 */ + UCHAR_RADICAL=26, + /** Binary property Soft_Dotted (new in Unicode 3.2). + Characters with a "soft dot", like i or j. + An accent placed on these characters causes + the dot to disappear. @stable ICU 2.1 */ + UCHAR_SOFT_DOTTED=27, + /** Binary property Terminal_Punctuation. + Punctuation characters that generally mark + the end of textual units. @stable ICU 2.1 */ + UCHAR_TERMINAL_PUNCTUATION=28, + /** Binary property Unified_Ideograph (new in Unicode 3.2). + For programmatic determination of + Ideographic Description Sequences. @stable ICU 2.1 */ + UCHAR_UNIFIED_IDEOGRAPH=29, + /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. + Lu+Other_Uppercase @stable ICU 2.1 */ + UCHAR_UPPERCASE=30, + /** Binary property White_Space. + Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. + Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */ + UCHAR_WHITE_SPACE=31, + /** Binary property XID_Continue. + ID_Continue modified to allow closure under + normalization forms NFKC and NFKD. @stable ICU 2.1 */ + UCHAR_XID_CONTINUE=32, + /** Binary property XID_Start. ID_Start modified to allow + closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */ + UCHAR_XID_START=33, + /** Binary property Case_Sensitive. Either the source of a case + mapping or _in_ the target of a case mapping. Not the same as + the general category Cased_Letter. @stable ICU 2.6 */ + UCHAR_CASE_SENSITIVE=34, + /** Binary property STerm (new in Unicode 4.0.1). + Sentence Terminal. Used in UAX #29: Text Boundaries + (http://www.unicode.org/reports/tr29/) + @stable ICU 3.0 */ + UCHAR_S_TERM=35, + /** Binary property Variation_Selector (new in Unicode 4.0.1). + Indicates all those characters that qualify as Variation Selectors. + For details on the behavior of these characters, + see StandardizedVariants.html and 15.6 Variation Selectors. + @stable ICU 3.0 */ + UCHAR_VARIATION_SELECTOR=36, + /** Binary property NFD_Inert. + ICU-specific property for characters that are inert under NFD, + i.e., they do not interact with adjacent characters. + See the documentation for the Normalizer2 class and the + Normalizer2::isInert() method. + @stable ICU 3.0 */ + UCHAR_NFD_INERT=37, + /** Binary property NFKD_Inert. + ICU-specific property for characters that are inert under NFKD, + i.e., they do not interact with adjacent characters. + See the documentation for the Normalizer2 class and the + Normalizer2::isInert() method. + @stable ICU 3.0 */ + UCHAR_NFKD_INERT=38, + /** Binary property NFC_Inert. + ICU-specific property for characters that are inert under NFC, + i.e., they do not interact with adjacent characters. + See the documentation for the Normalizer2 class and the + Normalizer2::isInert() method. + @stable ICU 3.0 */ + UCHAR_NFC_INERT=39, + /** Binary property NFKC_Inert. + ICU-specific property for characters that are inert under NFKC, + i.e., they do not interact with adjacent characters. + See the documentation for the Normalizer2 class and the + Normalizer2::isInert() method. + @stable ICU 3.0 */ + UCHAR_NFKC_INERT=40, + /** Binary Property Segment_Starter. + ICU-specific property for characters that are starters in terms of + Unicode normalization and combining character sequences. + They have ccc=0 and do not occur in non-initial position of the + canonical decomposition of any character + (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). + ICU uses this property for segmenting a string for generating a set of + canonically equivalent strings, e.g. for canonical closure while + processing collation tailoring rules. + @stable ICU 3.0 */ + UCHAR_SEGMENT_STARTER=41, + /** Binary property Pattern_Syntax (new in Unicode 4.1). + See UAX #31 Identifier and Pattern Syntax + (http://www.unicode.org/reports/tr31/) + @stable ICU 3.4 */ + UCHAR_PATTERN_SYNTAX=42, + /** Binary property Pattern_White_Space (new in Unicode 4.1). + See UAX #31 Identifier and Pattern Syntax + (http://www.unicode.org/reports/tr31/) + @stable ICU 3.4 */ + UCHAR_PATTERN_WHITE_SPACE=43, + /** Binary property alnum (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_ALNUM=44, + /** Binary property blank (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_BLANK=45, + /** Binary property graph (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_GRAPH=46, + /** Binary property print (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_PRINT=47, + /** Binary property xdigit (a C/POSIX character class). + Implemented according to the UTS #18 Annex C Standard Recommendation. + See the uchar.h file documentation. + @stable ICU 3.4 */ + UCHAR_POSIX_XDIGIT=48, + /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */ + UCHAR_CASED=49, + /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */ + UCHAR_CASE_IGNORABLE=50, + /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_LOWERCASED=51, + /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_UPPERCASED=52, + /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_TITLECASED=53, + /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_CASEFOLDED=54, + /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_CASEMAPPED=55, + /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */ + UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56, + /** + * Binary property Emoji. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 57 + */ + UCHAR_EMOJI=57, + /** + * Binary property Emoji_Presentation. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 57 + */ + UCHAR_EMOJI_PRESENTATION=58, + /** + * Binary property Emoji_Modifier. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 57 + */ + UCHAR_EMOJI_MODIFIER=59, + /** + * Binary property Emoji_Modifier_Base. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 57 + */ + UCHAR_EMOJI_MODIFIER_BASE=60, + /** + * Binary property Emoji_Component. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 60 + */ + UCHAR_EMOJI_COMPONENT=61, + /** + * Binary property Regional_Indicator. + * @stable ICU 60 + */ + UCHAR_REGIONAL_INDICATOR=62, + /** + * Binary property Prepended_Concatenation_Mark. + * @stable ICU 60 + */ + UCHAR_PREPENDED_CONCATENATION_MARK=63, + /** + * Binary property Extended_Pictographic. + * See http://www.unicode.org/reports/tr51/#Emoji_Properties + * + * @stable ICU 62 + */ + UCHAR_EXTENDED_PICTOGRAPHIC=64, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for binary Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_BINARY_LIMIT, +#endif // U_HIDE_DEPRECATED_API + + /** Enumerated property Bidi_Class. + Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */ + UCHAR_BIDI_CLASS=0x1000, + /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */ + UCHAR_INT_START=UCHAR_BIDI_CLASS, + /** Enumerated property Block. + Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */ + UCHAR_BLOCK=0x1001, + /** Enumerated property Canonical_Combining_Class. + Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */ + UCHAR_CANONICAL_COMBINING_CLASS=0x1002, + /** Enumerated property Decomposition_Type. + Returns UDecompositionType values. @stable ICU 2.2 */ + UCHAR_DECOMPOSITION_TYPE=0x1003, + /** Enumerated property East_Asian_Width. + See http://www.unicode.org/reports/tr11/ + Returns UEastAsianWidth values. @stable ICU 2.2 */ + UCHAR_EAST_ASIAN_WIDTH=0x1004, + /** Enumerated property General_Category. + Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */ + UCHAR_GENERAL_CATEGORY=0x1005, + /** Enumerated property Joining_Group. + Returns UJoiningGroup values. @stable ICU 2.2 */ + UCHAR_JOINING_GROUP=0x1006, + /** Enumerated property Joining_Type. + Returns UJoiningType values. @stable ICU 2.2 */ + UCHAR_JOINING_TYPE=0x1007, + /** Enumerated property Line_Break. + Returns ULineBreak values. @stable ICU 2.2 */ + UCHAR_LINE_BREAK=0x1008, + /** Enumerated property Numeric_Type. + Returns UNumericType values. @stable ICU 2.2 */ + UCHAR_NUMERIC_TYPE=0x1009, + /** Enumerated property Script. + Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */ + UCHAR_SCRIPT=0x100A, + /** Enumerated property Hangul_Syllable_Type, new in Unicode 4. + Returns UHangulSyllableType values. @stable ICU 2.6 */ + UCHAR_HANGUL_SYLLABLE_TYPE=0x100B, + /** Enumerated property NFD_Quick_Check. + Returns UNormalizationCheckResult values. @stable ICU 3.0 */ + UCHAR_NFD_QUICK_CHECK=0x100C, + /** Enumerated property NFKD_Quick_Check. + Returns UNormalizationCheckResult values. @stable ICU 3.0 */ + UCHAR_NFKD_QUICK_CHECK=0x100D, + /** Enumerated property NFC_Quick_Check. + Returns UNormalizationCheckResult values. @stable ICU 3.0 */ + UCHAR_NFC_QUICK_CHECK=0x100E, + /** Enumerated property NFKC_Quick_Check. + Returns UNormalizationCheckResult values. @stable ICU 3.0 */ + UCHAR_NFKC_QUICK_CHECK=0x100F, + /** Enumerated property Lead_Canonical_Combining_Class. + ICU-specific property for the ccc of the first code point + of the decomposition, or lccc(c)=ccc(NFD(c)[0]). + Useful for checking for canonically ordered text; + see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . + Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ + UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010, + /** Enumerated property Trail_Canonical_Combining_Class. + ICU-specific property for the ccc of the last code point + of the decomposition, or tccc(c)=ccc(NFD(c)[last]). + Useful for checking for canonically ordered text; + see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . + Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */ + UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011, + /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). + Used in UAX #29: Text Boundaries + (http://www.unicode.org/reports/tr29/) + Returns UGraphemeClusterBreak values. @stable ICU 3.4 */ + UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012, + /** Enumerated property Sentence_Break (new in Unicode 4.1). + Used in UAX #29: Text Boundaries + (http://www.unicode.org/reports/tr29/) + Returns USentenceBreak values. @stable ICU 3.4 */ + UCHAR_SENTENCE_BREAK=0x1013, + /** Enumerated property Word_Break (new in Unicode 4.1). + Used in UAX #29: Text Boundaries + (http://www.unicode.org/reports/tr29/) + Returns UWordBreakValues values. @stable ICU 3.4 */ + UCHAR_WORD_BREAK=0x1014, + /** Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). + Used in UAX #9: Unicode Bidirectional Algorithm + (http://www.unicode.org/reports/tr9/) + Returns UBidiPairedBracketType values. @stable ICU 52 */ + UCHAR_BIDI_PAIRED_BRACKET_TYPE=0x1015, + /** + * Enumerated property Indic_Positional_Category. + * New in Unicode 6.0 as provisional property Indic_Matra_Category; + * renamed and changed to informative in Unicode 8.0. + * See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt + * @stable ICU 63 + */ + UCHAR_INDIC_POSITIONAL_CATEGORY=0x1016, + /** + * Enumerated property Indic_Syllabic_Category. + * New in Unicode 6.0 as provisional; informative since Unicode 8.0. + * See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt + * @stable ICU 63 + */ + UCHAR_INDIC_SYLLABIC_CATEGORY=0x1017, + /** + * Enumerated property Vertical_Orientation. + * Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/). + * New as a UCD property in Unicode 10.0. + * @stable ICU 63 + */ + UCHAR_VERTICAL_ORIENTATION=0x1018, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for enumerated/integer Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_INT_LIMIT=0x1019, +#endif // U_HIDE_DEPRECATED_API + + /** Bitmask property General_Category_Mask. + This is the General_Category property returned as a bit mask. + When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), + returns bit masks for UCharCategory values where exactly one bit is set. + When used with u_getPropertyValueName() and u_getPropertyValueEnum(), + a multi-bit mask is used for sets of categories like "Letters". + Mask values should be cast to uint32_t. + @stable ICU 2.4 */ + UCHAR_GENERAL_CATEGORY_MASK=0x2000, + /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */ + UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for bit-mask Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_MASK_LIMIT=0x2001, +#endif // U_HIDE_DEPRECATED_API + + /** Double property Numeric_Value. + Corresponds to u_getNumericValue. @stable ICU 2.4 */ + UCHAR_NUMERIC_VALUE=0x3000, + /** First constant for double Unicode properties. @stable ICU 2.4 */ + UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for double Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_DOUBLE_LIMIT=0x3001, +#endif // U_HIDE_DEPRECATED_API + + /** String property Age. + Corresponds to u_charAge. @stable ICU 2.4 */ + UCHAR_AGE=0x4000, + /** First constant for string Unicode properties. @stable ICU 2.4 */ + UCHAR_STRING_START=UCHAR_AGE, + /** String property Bidi_Mirroring_Glyph. + Corresponds to u_charMirror. @stable ICU 2.4 */ + UCHAR_BIDI_MIRRORING_GLYPH=0x4001, + /** String property Case_Folding. + Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */ + UCHAR_CASE_FOLDING=0x4002, +#ifndef U_HIDE_DEPRECATED_API + /** Deprecated string property ISO_Comment. + Corresponds to u_getISOComment. @deprecated ICU 49 */ + UCHAR_ISO_COMMENT=0x4003, +#endif /* U_HIDE_DEPRECATED_API */ + /** String property Lowercase_Mapping. + Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */ + UCHAR_LOWERCASE_MAPPING=0x4004, + /** String property Name. + Corresponds to u_charName. @stable ICU 2.4 */ + UCHAR_NAME=0x4005, + /** String property Simple_Case_Folding. + Corresponds to u_foldCase. @stable ICU 2.4 */ + UCHAR_SIMPLE_CASE_FOLDING=0x4006, + /** String property Simple_Lowercase_Mapping. + Corresponds to u_tolower. @stable ICU 2.4 */ + UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007, + /** String property Simple_Titlecase_Mapping. + Corresponds to u_totitle. @stable ICU 2.4 */ + UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008, + /** String property Simple_Uppercase_Mapping. + Corresponds to u_toupper. @stable ICU 2.4 */ + UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009, + /** String property Titlecase_Mapping. + Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */ + UCHAR_TITLECASE_MAPPING=0x400A, +#ifndef U_HIDE_DEPRECATED_API + /** String property Unicode_1_Name. + This property is of little practical value. + Beginning with ICU 49, ICU APIs return an empty string for this property. + Corresponds to u_charName(U_UNICODE_10_CHAR_NAME). @deprecated ICU 49 */ + UCHAR_UNICODE_1_NAME=0x400B, +#endif /* U_HIDE_DEPRECATED_API */ + /** String property Uppercase_Mapping. + Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */ + UCHAR_UPPERCASE_MAPPING=0x400C, + /** String property Bidi_Paired_Bracket (new in Unicode 6.3). + Corresponds to u_getBidiPairedBracket. @stable ICU 52 */ + UCHAR_BIDI_PAIRED_BRACKET=0x400D, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for string Unicode properties. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_STRING_LIMIT=0x400E, +#endif // U_HIDE_DEPRECATED_API + + /** Miscellaneous property Script_Extensions (new in Unicode 6.0). + Some characters are commonly used in multiple scripts. + For more information, see UAX #24: http://www.unicode.org/reports/tr24/. + Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. + @stable ICU 4.6 */ + UCHAR_SCRIPT_EXTENSIONS=0x7000, + /** First constant for Unicode properties with unusual value types. @stable ICU 4.6 */ + UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last constant for Unicode properties with unusual value types. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCHAR_OTHER_PROPERTY_LIMIT=0x7001, +#endif // U_HIDE_DEPRECATED_API + + /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */ + UCHAR_INVALID_CODE = -1 +} UProperty; + +/** + * Data for enumerated Unicode general category types. + * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . + * @stable ICU 2.0 + */ +typedef enum UCharCategory +{ + /* + * Note: UCharCategory constants and their API comments are parsed by preparseucd.py. + * It matches pairs of lines like + * / ** <Unicode 2-letter General_Category value> comment... * / + * U_<[A-Z_]+> = <integer>, + */ + + /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */ + U_UNASSIGNED = 0, + /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */ + U_GENERAL_OTHER_TYPES = 0, + /** Lu @stable ICU 2.0 */ + U_UPPERCASE_LETTER = 1, + /** Ll @stable ICU 2.0 */ + U_LOWERCASE_LETTER = 2, + /** Lt @stable ICU 2.0 */ + U_TITLECASE_LETTER = 3, + /** Lm @stable ICU 2.0 */ + U_MODIFIER_LETTER = 4, + /** Lo @stable ICU 2.0 */ + U_OTHER_LETTER = 5, + /** Mn @stable ICU 2.0 */ + U_NON_SPACING_MARK = 6, + /** Me @stable ICU 2.0 */ + U_ENCLOSING_MARK = 7, + /** Mc @stable ICU 2.0 */ + U_COMBINING_SPACING_MARK = 8, + /** Nd @stable ICU 2.0 */ + U_DECIMAL_DIGIT_NUMBER = 9, + /** Nl @stable ICU 2.0 */ + U_LETTER_NUMBER = 10, + /** No @stable ICU 2.0 */ + U_OTHER_NUMBER = 11, + /** Zs @stable ICU 2.0 */ + U_SPACE_SEPARATOR = 12, + /** Zl @stable ICU 2.0 */ + U_LINE_SEPARATOR = 13, + /** Zp @stable ICU 2.0 */ + U_PARAGRAPH_SEPARATOR = 14, + /** Cc @stable ICU 2.0 */ + U_CONTROL_CHAR = 15, + /** Cf @stable ICU 2.0 */ + U_FORMAT_CHAR = 16, + /** Co @stable ICU 2.0 */ + U_PRIVATE_USE_CHAR = 17, + /** Cs @stable ICU 2.0 */ + U_SURROGATE = 18, + /** Pd @stable ICU 2.0 */ + U_DASH_PUNCTUATION = 19, + /** Ps @stable ICU 2.0 */ + U_START_PUNCTUATION = 20, + /** Pe @stable ICU 2.0 */ + U_END_PUNCTUATION = 21, + /** Pc @stable ICU 2.0 */ + U_CONNECTOR_PUNCTUATION = 22, + /** Po @stable ICU 2.0 */ + U_OTHER_PUNCTUATION = 23, + /** Sm @stable ICU 2.0 */ + U_MATH_SYMBOL = 24, + /** Sc @stable ICU 2.0 */ + U_CURRENCY_SYMBOL = 25, + /** Sk @stable ICU 2.0 */ + U_MODIFIER_SYMBOL = 26, + /** So @stable ICU 2.0 */ + U_OTHER_SYMBOL = 27, + /** Pi @stable ICU 2.0 */ + U_INITIAL_PUNCTUATION = 28, + /** Pf @stable ICU 2.0 */ + U_FINAL_PUNCTUATION = 29, + /** + * One higher than the last enum UCharCategory constant. + * This numeric value is stable (will not change), see + * http://www.unicode.org/policies/stability_policy.html#Property_Value + * + * @stable ICU 2.0 + */ + U_CHAR_CATEGORY_COUNT +} UCharCategory; + +/** + * U_GC_XX_MASK constants are bit flags corresponding to Unicode + * general category values. + * For each category, the nth bit is set if the numeric value of the + * corresponding UCharCategory constant is n. + * + * There are also some U_GC_Y_MASK constants for groups of general categories + * like L for all letter categories. + * + * @see u_charType + * @see U_GET_GC_MASK + * @see UCharCategory + * @stable ICU 2.1 + */ +#define U_GC_CN_MASK U_MASK(U_GENERAL_OTHER_TYPES) + +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_LO_MASK U_MASK(U_OTHER_LETTER) + +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) + +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) + +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) + +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_CS_MASK U_MASK(U_SURROGATE) + +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) + +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) + +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) +/** Mask constant for a UCharCategory. @stable ICU 2.1 */ +#define U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) + + +/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */ +#define U_GC_L_MASK \ + (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) + +/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */ +#define U_GC_LC_MASK \ + (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK) + +/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */ +#define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) + +/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */ +#define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) + +/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */ +#define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) + +/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */ +#define U_GC_C_MASK \ + (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) + +/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */ +#define U_GC_P_MASK \ + (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ + U_GC_PI_MASK|U_GC_PF_MASK) + +/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */ +#define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) + +/** + * This specifies the language directional property of a character set. + * @stable ICU 2.0 + */ +typedef enum UCharDirection { + /* + * Note: UCharDirection constants and their API comments are parsed by preparseucd.py. + * It matches pairs of lines like + * / ** <Unicode 1..3-letter Bidi_Class value> comment... * / + * U_<[A-Z_]+> = <integer>, + */ + + /** L @stable ICU 2.0 */ + U_LEFT_TO_RIGHT = 0, + /** R @stable ICU 2.0 */ + U_RIGHT_TO_LEFT = 1, + /** EN @stable ICU 2.0 */ + U_EUROPEAN_NUMBER = 2, + /** ES @stable ICU 2.0 */ + U_EUROPEAN_NUMBER_SEPARATOR = 3, + /** ET @stable ICU 2.0 */ + U_EUROPEAN_NUMBER_TERMINATOR = 4, + /** AN @stable ICU 2.0 */ + U_ARABIC_NUMBER = 5, + /** CS @stable ICU 2.0 */ + U_COMMON_NUMBER_SEPARATOR = 6, + /** B @stable ICU 2.0 */ + U_BLOCK_SEPARATOR = 7, + /** S @stable ICU 2.0 */ + U_SEGMENT_SEPARATOR = 8, + /** WS @stable ICU 2.0 */ + U_WHITE_SPACE_NEUTRAL = 9, + /** ON @stable ICU 2.0 */ + U_OTHER_NEUTRAL = 10, + /** LRE @stable ICU 2.0 */ + U_LEFT_TO_RIGHT_EMBEDDING = 11, + /** LRO @stable ICU 2.0 */ + U_LEFT_TO_RIGHT_OVERRIDE = 12, + /** AL @stable ICU 2.0 */ + U_RIGHT_TO_LEFT_ARABIC = 13, + /** RLE @stable ICU 2.0 */ + U_RIGHT_TO_LEFT_EMBEDDING = 14, + /** RLO @stable ICU 2.0 */ + U_RIGHT_TO_LEFT_OVERRIDE = 15, + /** PDF @stable ICU 2.0 */ + U_POP_DIRECTIONAL_FORMAT = 16, + /** NSM @stable ICU 2.0 */ + U_DIR_NON_SPACING_MARK = 17, + /** BN @stable ICU 2.0 */ + U_BOUNDARY_NEUTRAL = 18, + /** FSI @stable ICU 52 */ + U_FIRST_STRONG_ISOLATE = 19, + /** LRI @stable ICU 52 */ + U_LEFT_TO_RIGHT_ISOLATE = 20, + /** RLI @stable ICU 52 */ + U_RIGHT_TO_LEFT_ISOLATE = 21, + /** PDI @stable ICU 52 */ + U_POP_DIRECTIONAL_ISOLATE = 22, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest UCharDirection value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_CHAR_DIRECTION_COUNT +#endif // U_HIDE_DEPRECATED_API +} UCharDirection; + +/** + * Bidi Paired Bracket Type constants. + * + * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE + * @stable ICU 52 + */ +typedef enum UBidiPairedBracketType { + /* + * Note: UBidiPairedBracketType constants are parsed by preparseucd.py. + * It matches lines like + * U_BPT_<Unicode Bidi_Paired_Bracket_Type value name> + */ + + /** Not a paired bracket. @stable ICU 52 */ + U_BPT_NONE, + /** Open paired bracket. @stable ICU 52 */ + U_BPT_OPEN, + /** Close paired bracket. @stable ICU 52 */ + U_BPT_CLOSE, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UBidiPairedBracketType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_BPT_COUNT /* 3 */ +#endif // U_HIDE_DEPRECATED_API +} UBidiPairedBracketType; + +/** + * Constants for Unicode blocks, see the Unicode Data file Blocks.txt + * @stable ICU 2.0 + */ +enum UBlockCode { + /* + * Note: UBlockCode constants are parsed by preparseucd.py. + * It matches lines like + * UBLOCK_<Unicode Block value name> = <integer>, + */ + + /** New No_Block value in Unicode 4. @stable ICU 2.6 */ + UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */ + + /** @stable ICU 2.0 */ + UBLOCK_BASIC_LATIN = 1, /*[0000]*/ + + /** @stable ICU 2.0 */ + UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/ + + /** @stable ICU 2.0 */ + UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/ + + /** @stable ICU 2.0 */ + UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/ + + /** @stable ICU 2.0 */ + UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/ + + /** @stable ICU 2.0 */ + UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/ + + /** + * Unicode 3.2 renames this block to "Greek and Coptic". + * @stable ICU 2.0 + */ + UBLOCK_GREEK =8, /*[0370]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CYRILLIC =9, /*[0400]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ARMENIAN =10, /*[0530]*/ + + /** @stable ICU 2.0 */ + UBLOCK_HEBREW =11, /*[0590]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ARABIC =12, /*[0600]*/ + + /** @stable ICU 2.0 */ + UBLOCK_SYRIAC =13, /*[0700]*/ + + /** @stable ICU 2.0 */ + UBLOCK_THAANA =14, /*[0780]*/ + + /** @stable ICU 2.0 */ + UBLOCK_DEVANAGARI =15, /*[0900]*/ + + /** @stable ICU 2.0 */ + UBLOCK_BENGALI =16, /*[0980]*/ + + /** @stable ICU 2.0 */ + UBLOCK_GURMUKHI =17, /*[0A00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_GUJARATI =18, /*[0A80]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ORIYA =19, /*[0B00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_TAMIL =20, /*[0B80]*/ + + /** @stable ICU 2.0 */ + UBLOCK_TELUGU =21, /*[0C00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_KANNADA =22, /*[0C80]*/ + + /** @stable ICU 2.0 */ + UBLOCK_MALAYALAM =23, /*[0D00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_SINHALA =24, /*[0D80]*/ + + /** @stable ICU 2.0 */ + UBLOCK_THAI =25, /*[0E00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_LAO =26, /*[0E80]*/ + + /** @stable ICU 2.0 */ + UBLOCK_TIBETAN =27, /*[0F00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_MYANMAR =28, /*[1000]*/ + + /** @stable ICU 2.0 */ + UBLOCK_GEORGIAN =29, /*[10A0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_HANGUL_JAMO =30, /*[1100]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ETHIOPIC =31, /*[1200]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CHEROKEE =32, /*[13A0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/ + + /** @stable ICU 2.0 */ + UBLOCK_OGHAM =34, /*[1680]*/ + + /** @stable ICU 2.0 */ + UBLOCK_RUNIC =35, /*[16A0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_KHMER =36, /*[1780]*/ + + /** @stable ICU 2.0 */ + UBLOCK_MONGOLIAN =37, /*[1800]*/ + + /** @stable ICU 2.0 */ + UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/ + + /** @stable ICU 2.0 */ + UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/ + + /** + * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". + * @stable ICU 2.0 + */ + UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/ + + /** @stable ICU 2.0 */ + UBLOCK_NUMBER_FORMS =45, /*[2150]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ARROWS =46, /*[2190]*/ + + /** @stable ICU 2.0 */ + UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/ + + /** @stable ICU 2.0 */ + UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CONTROL_PICTURES =49, /*[2400]*/ + + /** @stable ICU 2.0 */ + UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/ + + /** @stable ICU 2.0 */ + UBLOCK_BOX_DRAWING =52, /*[2500]*/ + + /** @stable ICU 2.0 */ + UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/ + + /** @stable ICU 2.0 */ + UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/ + + /** @stable ICU 2.0 */ + UBLOCK_DINGBATS =56, /*[2700]*/ + + /** @stable ICU 2.0 */ + UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/ + + /** @stable ICU 2.0 */ + UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/ + + /** @stable ICU 2.0 */ + UBLOCK_HIRAGANA =62, /*[3040]*/ + + /** @stable ICU 2.0 */ + UBLOCK_KATAKANA =63, /*[30A0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_BOPOMOFO =64, /*[3100]*/ + + /** @stable ICU 2.0 */ + UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/ + + /** @stable ICU 2.0 */ + UBLOCK_KANBUN =66, /*[3190]*/ + + /** @stable ICU 2.0 */ + UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_YI_SYLLABLES =72, /*[A000]*/ + + /** @stable ICU 2.0 */ + UBLOCK_YI_RADICALS =73, /*[A490]*/ + + /** @stable ICU 2.0 */ + UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_HIGH_SURROGATES =75, /*[D800]*/ + + /** @stable ICU 2.0 */ + UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/ + + /** @stable ICU 2.0 */ + UBLOCK_LOW_SURROGATES =77, /*[DC00]*/ + + /** + * Same as UBLOCK_PRIVATE_USE. + * Until Unicode 3.1.1, the corresponding block name was "Private Use", + * and multiple code point ranges had this block. + * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and + * adds separate blocks for the supplementary PUAs. + * + * @stable ICU 2.0 + */ + UBLOCK_PRIVATE_USE_AREA =78, /*[E000]*/ + /** + * Same as UBLOCK_PRIVATE_USE_AREA. + * Until Unicode 3.1.1, the corresponding block name was "Private Use", + * and multiple code point ranges had this block. + * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and + * adds separate blocks for the supplementary PUAs. + * + * @stable ICU 2.0 + */ + UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA, + + /** @stable ICU 2.0 */ + UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/ + + /** @stable ICU 2.0 */ + UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/ + + /** @stable ICU 2.0 */ + UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/ + + /** @stable ICU 2.0 */ + UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/ + + /** @stable ICU 2.0 */ + UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/ + + /** @stable ICU 2.0 */ + UBLOCK_SPECIALS =86, /*[FFF0]*/ + + /** @stable ICU 2.0 */ + UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/ + + /* New blocks in Unicode 3.1 */ + + /** @stable ICU 2.0 */ + UBLOCK_OLD_ITALIC = 88, /*[10300]*/ + /** @stable ICU 2.0 */ + UBLOCK_GOTHIC = 89, /*[10330]*/ + /** @stable ICU 2.0 */ + UBLOCK_DESERET = 90, /*[10400]*/ + /** @stable ICU 2.0 */ + UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91, /*[1D000]*/ + /** @stable ICU 2.0 */ + UBLOCK_MUSICAL_SYMBOLS = 92, /*[1D100]*/ + /** @stable ICU 2.0 */ + UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93, /*[1D400]*/ + /** @stable ICU 2.0 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94, /*[20000]*/ + /** @stable ICU 2.0 */ + UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95, /*[2F800]*/ + /** @stable ICU 2.0 */ + UBLOCK_TAGS = 96, /*[E0000]*/ + + /* New blocks in Unicode 3.2 */ + + /** @stable ICU 3.0 */ + UBLOCK_CYRILLIC_SUPPLEMENT = 97, /*[0500]*/ + /** + * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". + * @stable ICU 2.2 + */ + UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT, + /** @stable ICU 2.2 */ + UBLOCK_TAGALOG = 98, /*[1700]*/ + /** @stable ICU 2.2 */ + UBLOCK_HANUNOO = 99, /*[1720]*/ + /** @stable ICU 2.2 */ + UBLOCK_BUHID = 100, /*[1740]*/ + /** @stable ICU 2.2 */ + UBLOCK_TAGBANWA = 101, /*[1760]*/ + /** @stable ICU 2.2 */ + UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/ + /** @stable ICU 2.2 */ + UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/ + /** @stable ICU 2.2 */ + UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/ + /** @stable ICU 2.2 */ + UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/ + /** @stable ICU 2.2 */ + UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/ + /** @stable ICU 2.2 */ + UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/ + /** @stable ICU 2.2 */ + UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/ + /** @stable ICU 2.2 */ + UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/ + /** @stable ICU 2.2 */ + UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/ + + /* New blocks in Unicode 4 */ + + /** @stable ICU 2.6 */ + UBLOCK_LIMBU = 111, /*[1900]*/ + /** @stable ICU 2.6 */ + UBLOCK_TAI_LE = 112, /*[1950]*/ + /** @stable ICU 2.6 */ + UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/ + /** @stable ICU 2.6 */ + UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/ + /** @stable ICU 2.6 */ + UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/ + /** @stable ICU 2.6 */ + UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/ + /** @stable ICU 2.6 */ + UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/ + /** @stable ICU 2.6 */ + UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/ + /** @stable ICU 2.6 */ + UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/ + /** @stable ICU 2.6 */ + UBLOCK_UGARITIC = 120, /*[10380]*/ + /** @stable ICU 2.6 */ + UBLOCK_SHAVIAN = 121, /*[10450]*/ + /** @stable ICU 2.6 */ + UBLOCK_OSMANYA = 122, /*[10480]*/ + /** @stable ICU 2.6 */ + UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/ + /** @stable ICU 2.6 */ + UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/ + /** @stable ICU 2.6 */ + UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/ + + /* New blocks in Unicode 4.1 */ + + /** @stable ICU 3.4 */ + UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/ + /** @stable ICU 3.4 */ + UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/ + /** @stable ICU 3.4 */ + UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/ + /** @stable ICU 3.4 */ + UBLOCK_BUGINESE = 129, /*[1A00]*/ + /** @stable ICU 3.4 */ + UBLOCK_CJK_STROKES = 130, /*[31C0]*/ + /** @stable ICU 3.4 */ + UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/ + /** @stable ICU 3.4 */ + UBLOCK_COPTIC = 132, /*[2C80]*/ + /** @stable ICU 3.4 */ + UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/ + /** @stable ICU 3.4 */ + UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/ + /** @stable ICU 3.4 */ + UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/ + /** @stable ICU 3.4 */ + UBLOCK_GLAGOLITIC = 136, /*[2C00]*/ + /** @stable ICU 3.4 */ + UBLOCK_KHAROSHTHI = 137, /*[10A00]*/ + /** @stable ICU 3.4 */ + UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/ + /** @stable ICU 3.4 */ + UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/ + /** @stable ICU 3.4 */ + UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/ + /** @stable ICU 3.4 */ + UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/ + /** @stable ICU 3.4 */ + UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/ + /** @stable ICU 3.4 */ + UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/ + /** @stable ICU 3.4 */ + UBLOCK_TIFINAGH = 144, /*[2D30]*/ + /** @stable ICU 3.4 */ + UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/ + + /* New blocks in Unicode 5.0 */ + + /** @stable ICU 3.6 */ + UBLOCK_NKO = 146, /*[07C0]*/ + /** @stable ICU 3.6 */ + UBLOCK_BALINESE = 147, /*[1B00]*/ + /** @stable ICU 3.6 */ + UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/ + /** @stable ICU 3.6 */ + UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/ + /** @stable ICU 3.6 */ + UBLOCK_PHAGS_PA = 150, /*[A840]*/ + /** @stable ICU 3.6 */ + UBLOCK_PHOENICIAN = 151, /*[10900]*/ + /** @stable ICU 3.6 */ + UBLOCK_CUNEIFORM = 152, /*[12000]*/ + /** @stable ICU 3.6 */ + UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/ + /** @stable ICU 3.6 */ + UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/ + + /* New blocks in Unicode 5.1 */ + + /** @stable ICU 4.0 */ + UBLOCK_SUNDANESE = 155, /*[1B80]*/ + /** @stable ICU 4.0 */ + UBLOCK_LEPCHA = 156, /*[1C00]*/ + /** @stable ICU 4.0 */ + UBLOCK_OL_CHIKI = 157, /*[1C50]*/ + /** @stable ICU 4.0 */ + UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/ + /** @stable ICU 4.0 */ + UBLOCK_VAI = 159, /*[A500]*/ + /** @stable ICU 4.0 */ + UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/ + /** @stable ICU 4.0 */ + UBLOCK_SAURASHTRA = 161, /*[A880]*/ + /** @stable ICU 4.0 */ + UBLOCK_KAYAH_LI = 162, /*[A900]*/ + /** @stable ICU 4.0 */ + UBLOCK_REJANG = 163, /*[A930]*/ + /** @stable ICU 4.0 */ + UBLOCK_CHAM = 164, /*[AA00]*/ + /** @stable ICU 4.0 */ + UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/ + /** @stable ICU 4.0 */ + UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/ + /** @stable ICU 4.0 */ + UBLOCK_LYCIAN = 167, /*[10280]*/ + /** @stable ICU 4.0 */ + UBLOCK_CARIAN = 168, /*[102A0]*/ + /** @stable ICU 4.0 */ + UBLOCK_LYDIAN = 169, /*[10920]*/ + /** @stable ICU 4.0 */ + UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/ + /** @stable ICU 4.0 */ + UBLOCK_DOMINO_TILES = 171, /*[1F030]*/ + + /* New blocks in Unicode 5.2 */ + + /** @stable ICU 4.4 */ + UBLOCK_SAMARITAN = 172, /*[0800]*/ + /** @stable ICU 4.4 */ + UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/ + /** @stable ICU 4.4 */ + UBLOCK_TAI_THAM = 174, /*[1A20]*/ + /** @stable ICU 4.4 */ + UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/ + /** @stable ICU 4.4 */ + UBLOCK_LISU = 176, /*[A4D0]*/ + /** @stable ICU 4.4 */ + UBLOCK_BAMUM = 177, /*[A6A0]*/ + /** @stable ICU 4.4 */ + UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/ + /** @stable ICU 4.4 */ + UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/ + /** @stable ICU 4.4 */ + UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/ + /** @stable ICU 4.4 */ + UBLOCK_JAVANESE = 181, /*[A980]*/ + /** @stable ICU 4.4 */ + UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/ + /** @stable ICU 4.4 */ + UBLOCK_TAI_VIET = 183, /*[AA80]*/ + /** @stable ICU 4.4 */ + UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/ + /** @stable ICU 4.4 */ + UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/ + /** @stable ICU 4.4 */ + UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/ + /** @stable ICU 4.4 */ + UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/ + /** @stable ICU 4.4 */ + UBLOCK_AVESTAN = 188, /*[10B00]*/ + /** @stable ICU 4.4 */ + UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/ + /** @stable ICU 4.4 */ + UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/ + /** @stable ICU 4.4 */ + UBLOCK_OLD_TURKIC = 191, /*[10C00]*/ + /** @stable ICU 4.4 */ + UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/ + /** @stable ICU 4.4 */ + UBLOCK_KAITHI = 193, /*[11080]*/ + /** @stable ICU 4.4 */ + UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/ + /** @stable ICU 4.4 */ + UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/ + /** @stable ICU 4.4 */ + UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/ + /** @stable ICU 4.4 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/ + + /* New blocks in Unicode 6.0 */ + + /** @stable ICU 4.6 */ + UBLOCK_MANDAIC = 198, /*[0840]*/ + /** @stable ICU 4.6 */ + UBLOCK_BATAK = 199, /*[1BC0]*/ + /** @stable ICU 4.6 */ + UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/ + /** @stable ICU 4.6 */ + UBLOCK_BRAHMI = 201, /*[11000]*/ + /** @stable ICU 4.6 */ + UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/ + /** @stable ICU 4.6 */ + UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/ + /** @stable ICU 4.6 */ + UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/ + /** @stable ICU 4.6 */ + UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/ + /** @stable ICU 4.6 */ + UBLOCK_EMOTICONS = 206, /*[1F600]*/ + /** @stable ICU 4.6 */ + UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/ + /** @stable ICU 4.6 */ + UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/ + /** @stable ICU 4.6 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/ + + /* New blocks in Unicode 6.1 */ + + /** @stable ICU 49 */ + UBLOCK_ARABIC_EXTENDED_A = 210, /*[08A0]*/ + /** @stable ICU 49 */ + UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211, /*[1EE00]*/ + /** @stable ICU 49 */ + UBLOCK_CHAKMA = 212, /*[11100]*/ + /** @stable ICU 49 */ + UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213, /*[AAE0]*/ + /** @stable ICU 49 */ + UBLOCK_MEROITIC_CURSIVE = 214, /*[109A0]*/ + /** @stable ICU 49 */ + UBLOCK_MEROITIC_HIEROGLYPHS = 215, /*[10980]*/ + /** @stable ICU 49 */ + UBLOCK_MIAO = 216, /*[16F00]*/ + /** @stable ICU 49 */ + UBLOCK_SHARADA = 217, /*[11180]*/ + /** @stable ICU 49 */ + UBLOCK_SORA_SOMPENG = 218, /*[110D0]*/ + /** @stable ICU 49 */ + UBLOCK_SUNDANESE_SUPPLEMENT = 219, /*[1CC0]*/ + /** @stable ICU 49 */ + UBLOCK_TAKRI = 220, /*[11680]*/ + + /* New blocks in Unicode 7.0 */ + + /** @stable ICU 54 */ + UBLOCK_BASSA_VAH = 221, /*[16AD0]*/ + /** @stable ICU 54 */ + UBLOCK_CAUCASIAN_ALBANIAN = 222, /*[10530]*/ + /** @stable ICU 54 */ + UBLOCK_COPTIC_EPACT_NUMBERS = 223, /*[102E0]*/ + /** @stable ICU 54 */ + UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224, /*[1AB0]*/ + /** @stable ICU 54 */ + UBLOCK_DUPLOYAN = 225, /*[1BC00]*/ + /** @stable ICU 54 */ + UBLOCK_ELBASAN = 226, /*[10500]*/ + /** @stable ICU 54 */ + UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227, /*[1F780]*/ + /** @stable ICU 54 */ + UBLOCK_GRANTHA = 228, /*[11300]*/ + /** @stable ICU 54 */ + UBLOCK_KHOJKI = 229, /*[11200]*/ + /** @stable ICU 54 */ + UBLOCK_KHUDAWADI = 230, /*[112B0]*/ + /** @stable ICU 54 */ + UBLOCK_LATIN_EXTENDED_E = 231, /*[AB30]*/ + /** @stable ICU 54 */ + UBLOCK_LINEAR_A = 232, /*[10600]*/ + /** @stable ICU 54 */ + UBLOCK_MAHAJANI = 233, /*[11150]*/ + /** @stable ICU 54 */ + UBLOCK_MANICHAEAN = 234, /*[10AC0]*/ + /** @stable ICU 54 */ + UBLOCK_MENDE_KIKAKUI = 235, /*[1E800]*/ + /** @stable ICU 54 */ + UBLOCK_MODI = 236, /*[11600]*/ + /** @stable ICU 54 */ + UBLOCK_MRO = 237, /*[16A40]*/ + /** @stable ICU 54 */ + UBLOCK_MYANMAR_EXTENDED_B = 238, /*[A9E0]*/ + /** @stable ICU 54 */ + UBLOCK_NABATAEAN = 239, /*[10880]*/ + /** @stable ICU 54 */ + UBLOCK_OLD_NORTH_ARABIAN = 240, /*[10A80]*/ + /** @stable ICU 54 */ + UBLOCK_OLD_PERMIC = 241, /*[10350]*/ + /** @stable ICU 54 */ + UBLOCK_ORNAMENTAL_DINGBATS = 242, /*[1F650]*/ + /** @stable ICU 54 */ + UBLOCK_PAHAWH_HMONG = 243, /*[16B00]*/ + /** @stable ICU 54 */ + UBLOCK_PALMYRENE = 244, /*[10860]*/ + /** @stable ICU 54 */ + UBLOCK_PAU_CIN_HAU = 245, /*[11AC0]*/ + /** @stable ICU 54 */ + UBLOCK_PSALTER_PAHLAVI = 246, /*[10B80]*/ + /** @stable ICU 54 */ + UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247, /*[1BCA0]*/ + /** @stable ICU 54 */ + UBLOCK_SIDDHAM = 248, /*[11580]*/ + /** @stable ICU 54 */ + UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249, /*[111E0]*/ + /** @stable ICU 54 */ + UBLOCK_SUPPLEMENTAL_ARROWS_C = 250, /*[1F800]*/ + /** @stable ICU 54 */ + UBLOCK_TIRHUTA = 251, /*[11480]*/ + /** @stable ICU 54 */ + UBLOCK_WARANG_CITI = 252, /*[118A0]*/ + + /* New blocks in Unicode 8.0 */ + + /** @stable ICU 56 */ + UBLOCK_AHOM = 253, /*[11700]*/ + /** @stable ICU 56 */ + UBLOCK_ANATOLIAN_HIEROGLYPHS = 254, /*[14400]*/ + /** @stable ICU 56 */ + UBLOCK_CHEROKEE_SUPPLEMENT = 255, /*[AB70]*/ + /** @stable ICU 56 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256, /*[2B820]*/ + /** @stable ICU 56 */ + UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257, /*[12480]*/ + /** @stable ICU 56 */ + UBLOCK_HATRAN = 258, /*[108E0]*/ + /** @stable ICU 56 */ + UBLOCK_MULTANI = 259, /*[11280]*/ + /** @stable ICU 56 */ + UBLOCK_OLD_HUNGARIAN = 260, /*[10C80]*/ + /** @stable ICU 56 */ + UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261, /*[1F900]*/ + /** @stable ICU 56 */ + UBLOCK_SUTTON_SIGNWRITING = 262, /*[1D800]*/ + + /* New blocks in Unicode 9.0 */ + + /** @stable ICU 58 */ + UBLOCK_ADLAM = 263, /*[1E900]*/ + /** @stable ICU 58 */ + UBLOCK_BHAIKSUKI = 264, /*[11C00]*/ + /** @stable ICU 58 */ + UBLOCK_CYRILLIC_EXTENDED_C = 265, /*[1C80]*/ + /** @stable ICU 58 */ + UBLOCK_GLAGOLITIC_SUPPLEMENT = 266, /*[1E000]*/ + /** @stable ICU 58 */ + UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267, /*[16FE0]*/ + /** @stable ICU 58 */ + UBLOCK_MARCHEN = 268, /*[11C70]*/ + /** @stable ICU 58 */ + UBLOCK_MONGOLIAN_SUPPLEMENT = 269, /*[11660]*/ + /** @stable ICU 58 */ + UBLOCK_NEWA = 270, /*[11400]*/ + /** @stable ICU 58 */ + UBLOCK_OSAGE = 271, /*[104B0]*/ + /** @stable ICU 58 */ + UBLOCK_TANGUT = 272, /*[17000]*/ + /** @stable ICU 58 */ + UBLOCK_TANGUT_COMPONENTS = 273, /*[18800]*/ + + // New blocks in Unicode 10.0 + + /** @stable ICU 60 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274, /*[2CEB0]*/ + /** @stable ICU 60 */ + UBLOCK_KANA_EXTENDED_A = 275, /*[1B100]*/ + /** @stable ICU 60 */ + UBLOCK_MASARAM_GONDI = 276, /*[11D00]*/ + /** @stable ICU 60 */ + UBLOCK_NUSHU = 277, /*[1B170]*/ + /** @stable ICU 60 */ + UBLOCK_SOYOMBO = 278, /*[11A50]*/ + /** @stable ICU 60 */ + UBLOCK_SYRIAC_SUPPLEMENT = 279, /*[0860]*/ + /** @stable ICU 60 */ + UBLOCK_ZANABAZAR_SQUARE = 280, /*[11A00]*/ + + // New blocks in Unicode 11.0 + + /** @stable ICU 62 */ + UBLOCK_CHESS_SYMBOLS = 281, /*[1FA00]*/ + /** @stable ICU 62 */ + UBLOCK_DOGRA = 282, /*[11800]*/ + /** @stable ICU 62 */ + UBLOCK_GEORGIAN_EXTENDED = 283, /*[1C90]*/ + /** @stable ICU 62 */ + UBLOCK_GUNJALA_GONDI = 284, /*[11D60]*/ + /** @stable ICU 62 */ + UBLOCK_HANIFI_ROHINGYA = 285, /*[10D00]*/ + /** @stable ICU 62 */ + UBLOCK_INDIC_SIYAQ_NUMBERS = 286, /*[1EC70]*/ + /** @stable ICU 62 */ + UBLOCK_MAKASAR = 287, /*[11EE0]*/ + /** @stable ICU 62 */ + UBLOCK_MAYAN_NUMERALS = 288, /*[1D2E0]*/ + /** @stable ICU 62 */ + UBLOCK_MEDEFAIDRIN = 289, /*[16E40]*/ + /** @stable ICU 62 */ + UBLOCK_OLD_SOGDIAN = 290, /*[10F00]*/ + /** @stable ICU 62 */ + UBLOCK_SOGDIAN = 291, /*[10F30]*/ + + // New blocks in Unicode 12.0 + + /** @stable ICU 64 */ + UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS = 292, /*[13430]*/ + /** @stable ICU 64 */ + UBLOCK_ELYMAIC = 293, /*[10FE0]*/ + /** @stable ICU 64 */ + UBLOCK_NANDINAGARI = 294, /*[119A0]*/ + /** @stable ICU 64 */ + UBLOCK_NYIAKENG_PUACHUE_HMONG = 295, /*[1E100]*/ + /** @stable ICU 64 */ + UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296, /*[1ED00]*/ + /** @stable ICU 64 */ + UBLOCK_SMALL_KANA_EXTENSION = 297, /*[1B130]*/ + /** @stable ICU 64 */ + UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A = 298, /*[1FA70]*/ + /** @stable ICU 64 */ + UBLOCK_TAMIL_SUPPLEMENT = 299, /*[11FC0]*/ + /** @stable ICU 64 */ + UBLOCK_WANCHO = 300, /*[1E2C0]*/ + + // New blocks in Unicode 13.0 + + /** @stable ICU 66 */ + UBLOCK_CHORASMIAN = 301, /*[10FB0]*/ + /** @stable ICU 66 */ + UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G = 302, /*[30000]*/ + /** @stable ICU 66 */ + UBLOCK_DIVES_AKURU = 303, /*[11900]*/ + /** @stable ICU 66 */ + UBLOCK_KHITAN_SMALL_SCRIPT = 304, /*[18B00]*/ + /** @stable ICU 66 */ + UBLOCK_LISU_SUPPLEMENT = 305, /*[11FB0]*/ + /** @stable ICU 66 */ + UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING = 306, /*[1FB00]*/ + /** @stable ICU 66 */ + UBLOCK_TANGUT_SUPPLEMENT = 307, /*[18D00]*/ + /** @stable ICU 66 */ + UBLOCK_YEZIDI = 308, /*[10E80]*/ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UBlockCode value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UBLOCK_COUNT = 309, +#endif // U_HIDE_DEPRECATED_API + + /** @stable ICU 2.0 */ + UBLOCK_INVALID_CODE=-1 +}; + +/** @stable ICU 2.0 */ +typedef enum UBlockCode UBlockCode; + +/** + * East Asian Width constants. + * + * @see UCHAR_EAST_ASIAN_WIDTH + * @see u_getIntPropertyValue + * @stable ICU 2.2 + */ +typedef enum UEastAsianWidth { + /* + * Note: UEastAsianWidth constants are parsed by preparseucd.py. + * It matches lines like + * U_EA_<Unicode East_Asian_Width value name> + */ + + U_EA_NEUTRAL, /*[N]*/ + U_EA_AMBIGUOUS, /*[A]*/ + U_EA_HALFWIDTH, /*[H]*/ + U_EA_FULLWIDTH, /*[F]*/ + U_EA_NARROW, /*[Na]*/ + U_EA_WIDE, /*[W]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UEastAsianWidth value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_EA_COUNT +#endif // U_HIDE_DEPRECATED_API +} UEastAsianWidth; + +/** + * Selector constants for u_charName(). + * u_charName() returns the "modern" name of a + * Unicode character; or the name that was defined in + * Unicode version 1.0, before the Unicode standard merged + * with ISO-10646; or an "extended" name that gives each + * Unicode code point a unique name. + * + * @see u_charName + * @stable ICU 2.0 + */ +typedef enum UCharNameChoice { + /** Unicode character name (Name property). @stable ICU 2.0 */ + U_UNICODE_CHAR_NAME, +#ifndef U_HIDE_DEPRECATED_API + /** + * The Unicode_1_Name property value which is of little practical value. + * Beginning with ICU 49, ICU APIs return an empty string for this name choice. + * @deprecated ICU 49 + */ + U_UNICODE_10_CHAR_NAME, +#endif /* U_HIDE_DEPRECATED_API */ + /** Standard or synthetic character name. @stable ICU 2.0 */ + U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2, + /** Corrected name from NameAliases.txt. @stable ICU 4.4 */ + U_CHAR_NAME_ALIAS, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UCharNameChoice value. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_CHAR_NAME_CHOICE_COUNT +#endif // U_HIDE_DEPRECATED_API +} UCharNameChoice; + +/** + * Selector constants for u_getPropertyName() and + * u_getPropertyValueName(). These selectors are used to choose which + * name is returned for a given property or value. All properties and + * values have a long name. Most have a short name, but some do not. + * Unicode allows for additional names, beyond the long and short + * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where + * i=1, 2,... + * + * @see u_getPropertyName() + * @see u_getPropertyValueName() + * @stable ICU 2.4 + */ +typedef enum UPropertyNameChoice { + U_SHORT_PROPERTY_NAME, + U_LONG_PROPERTY_NAME, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UPropertyNameChoice value. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_PROPERTY_NAME_CHOICE_COUNT +#endif // U_HIDE_DEPRECATED_API +} UPropertyNameChoice; + +/** + * Decomposition Type constants. + * + * @see UCHAR_DECOMPOSITION_TYPE + * @stable ICU 2.2 + */ +typedef enum UDecompositionType { + /* + * Note: UDecompositionType constants are parsed by preparseucd.py. + * It matches lines like + * U_DT_<Unicode Decomposition_Type value name> + */ + + U_DT_NONE, /*[none]*/ + U_DT_CANONICAL, /*[can]*/ + U_DT_COMPAT, /*[com]*/ + U_DT_CIRCLE, /*[enc]*/ + U_DT_FINAL, /*[fin]*/ + U_DT_FONT, /*[font]*/ + U_DT_FRACTION, /*[fra]*/ + U_DT_INITIAL, /*[init]*/ + U_DT_ISOLATED, /*[iso]*/ + U_DT_MEDIAL, /*[med]*/ + U_DT_NARROW, /*[nar]*/ + U_DT_NOBREAK, /*[nb]*/ + U_DT_SMALL, /*[sml]*/ + U_DT_SQUARE, /*[sqr]*/ + U_DT_SUB, /*[sub]*/ + U_DT_SUPER, /*[sup]*/ + U_DT_VERTICAL, /*[vert]*/ + U_DT_WIDE, /*[wide]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UDecompositionType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_DT_COUNT /* 18 */ +#endif // U_HIDE_DEPRECATED_API +} UDecompositionType; + +/** + * Joining Type constants. + * + * @see UCHAR_JOINING_TYPE + * @stable ICU 2.2 + */ +typedef enum UJoiningType { + /* + * Note: UJoiningType constants are parsed by preparseucd.py. + * It matches lines like + * U_JT_<Unicode Joining_Type value name> + */ + + U_JT_NON_JOINING, /*[U]*/ + U_JT_JOIN_CAUSING, /*[C]*/ + U_JT_DUAL_JOINING, /*[D]*/ + U_JT_LEFT_JOINING, /*[L]*/ + U_JT_RIGHT_JOINING, /*[R]*/ + U_JT_TRANSPARENT, /*[T]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UJoiningType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_JT_COUNT /* 6 */ +#endif // U_HIDE_DEPRECATED_API +} UJoiningType; + +/** + * Joining Group constants. + * + * @see UCHAR_JOINING_GROUP + * @stable ICU 2.2 + */ +typedef enum UJoiningGroup { + /* + * Note: UJoiningGroup constants are parsed by preparseucd.py. + * It matches lines like + * U_JG_<Unicode Joining_Group value name> + */ + + U_JG_NO_JOINING_GROUP, + U_JG_AIN, + U_JG_ALAPH, + U_JG_ALEF, + U_JG_BEH, + U_JG_BETH, + U_JG_DAL, + U_JG_DALATH_RISH, + U_JG_E, + U_JG_FEH, + U_JG_FINAL_SEMKATH, + U_JG_GAF, + U_JG_GAMAL, + U_JG_HAH, + U_JG_TEH_MARBUTA_GOAL, /**< @stable ICU 4.6 */ + U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL, + U_JG_HE, + U_JG_HEH, + U_JG_HEH_GOAL, + U_JG_HETH, + U_JG_KAF, + U_JG_KAPH, + U_JG_KNOTTED_HEH, + U_JG_LAM, + U_JG_LAMADH, + U_JG_MEEM, + U_JG_MIM, + U_JG_NOON, + U_JG_NUN, + U_JG_PE, + U_JG_QAF, + U_JG_QAPH, + U_JG_REH, + U_JG_REVERSED_PE, + U_JG_SAD, + U_JG_SADHE, + U_JG_SEEN, + U_JG_SEMKATH, + U_JG_SHIN, + U_JG_SWASH_KAF, + U_JG_SYRIAC_WAW, + U_JG_TAH, + U_JG_TAW, + U_JG_TEH_MARBUTA, + U_JG_TETH, + U_JG_WAW, + U_JG_YEH, + U_JG_YEH_BARREE, + U_JG_YEH_WITH_TAIL, + U_JG_YUDH, + U_JG_YUDH_HE, + U_JG_ZAIN, + U_JG_FE, /**< @stable ICU 2.6 */ + U_JG_KHAPH, /**< @stable ICU 2.6 */ + U_JG_ZHAIN, /**< @stable ICU 2.6 */ + U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */ + U_JG_FARSI_YEH, /**< @stable ICU 4.4 */ + U_JG_NYA, /**< @stable ICU 4.4 */ + U_JG_ROHINGYA_YEH, /**< @stable ICU 49 */ + U_JG_MANICHAEAN_ALEPH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_AYIN, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_BETH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_DALETH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_DHAMEDH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_FIVE, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_GIMEL, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_HETH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_HUNDRED, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_KAPH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_LAMEDH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_MEM, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_NUN, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_ONE, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_PE, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_QOPH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_RESH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_SADHE, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_SAMEKH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_TAW, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_TEN, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_TETH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_THAMEDH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_TWENTY, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_WAW, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_YODH, /**< @stable ICU 54 */ + U_JG_MANICHAEAN_ZAYIN, /**< @stable ICU 54 */ + U_JG_STRAIGHT_WAW, /**< @stable ICU 54 */ + U_JG_AFRICAN_FEH, /**< @stable ICU 58 */ + U_JG_AFRICAN_NOON, /**< @stable ICU 58 */ + U_JG_AFRICAN_QAF, /**< @stable ICU 58 */ + + U_JG_MALAYALAM_BHA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_JA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_LLA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_LLLA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_NGA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_NNA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_NNNA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_NYA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_RA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_SSA, /**< @stable ICU 60 */ + U_JG_MALAYALAM_TTA, /**< @stable ICU 60 */ + + U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */ + U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UJoiningGroup value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_JG_COUNT +#endif // U_HIDE_DEPRECATED_API +} UJoiningGroup; + +/** + * Grapheme Cluster Break constants. + * + * @see UCHAR_GRAPHEME_CLUSTER_BREAK + * @stable ICU 3.4 + */ +typedef enum UGraphemeClusterBreak { + /* + * Note: UGraphemeClusterBreak constants are parsed by preparseucd.py. + * It matches lines like + * U_GCB_<Unicode Grapheme_Cluster_Break value name> + */ + + U_GCB_OTHER = 0, /*[XX]*/ + U_GCB_CONTROL = 1, /*[CN]*/ + U_GCB_CR = 2, /*[CR]*/ + U_GCB_EXTEND = 3, /*[EX]*/ + U_GCB_L = 4, /*[L]*/ + U_GCB_LF = 5, /*[LF]*/ + U_GCB_LV = 6, /*[LV]*/ + U_GCB_LVT = 7, /*[LVT]*/ + U_GCB_T = 8, /*[T]*/ + U_GCB_V = 9, /*[V]*/ + /** @stable ICU 4.0 */ + U_GCB_SPACING_MARK = 10, /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ + /** @stable ICU 4.0 */ + U_GCB_PREPEND = 11, /*[PP]*/ + /** @stable ICU 50 */ + U_GCB_REGIONAL_INDICATOR = 12, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ + /** @stable ICU 58 */ + U_GCB_E_BASE = 13, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ + /** @stable ICU 58 */ + U_GCB_E_BASE_GAZ = 14, /*[EBG]*/ + /** @stable ICU 58 */ + U_GCB_E_MODIFIER = 15, /*[EM]*/ + /** @stable ICU 58 */ + U_GCB_GLUE_AFTER_ZWJ = 16, /*[GAZ]*/ + /** @stable ICU 58 */ + U_GCB_ZWJ = 17, /*[ZWJ]*/ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UGraphemeClusterBreak value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_GCB_COUNT = 18 +#endif // U_HIDE_DEPRECATED_API +} UGraphemeClusterBreak; + +/** + * Word Break constants. + * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.) + * + * @see UCHAR_WORD_BREAK + * @stable ICU 3.4 + */ +typedef enum UWordBreakValues { + /* + * Note: UWordBreakValues constants are parsed by preparseucd.py. + * It matches lines like + * U_WB_<Unicode Word_Break value name> + */ + + U_WB_OTHER = 0, /*[XX]*/ + U_WB_ALETTER = 1, /*[LE]*/ + U_WB_FORMAT = 2, /*[FO]*/ + U_WB_KATAKANA = 3, /*[KA]*/ + U_WB_MIDLETTER = 4, /*[ML]*/ + U_WB_MIDNUM = 5, /*[MN]*/ + U_WB_NUMERIC = 6, /*[NU]*/ + U_WB_EXTENDNUMLET = 7, /*[EX]*/ + /** @stable ICU 4.0 */ + U_WB_CR = 8, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ + /** @stable ICU 4.0 */ + U_WB_EXTEND = 9, /*[Extend]*/ + /** @stable ICU 4.0 */ + U_WB_LF = 10, /*[LF]*/ + /** @stable ICU 4.0 */ + U_WB_MIDNUMLET =11, /*[MB]*/ + /** @stable ICU 4.0 */ + U_WB_NEWLINE =12, /*[NL]*/ + /** @stable ICU 50 */ + U_WB_REGIONAL_INDICATOR = 13, /*[RI]*/ /* new in Unicode 6.2/ICU 50 */ + /** @stable ICU 52 */ + U_WB_HEBREW_LETTER = 14, /*[HL]*/ /* from here on: new in Unicode 6.3/ICU 52 */ + /** @stable ICU 52 */ + U_WB_SINGLE_QUOTE = 15, /*[SQ]*/ + /** @stable ICU 52 */ + U_WB_DOUBLE_QUOTE = 16, /*[DQ]*/ + /** @stable ICU 58 */ + U_WB_E_BASE = 17, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ + /** @stable ICU 58 */ + U_WB_E_BASE_GAZ = 18, /*[EBG]*/ + /** @stable ICU 58 */ + U_WB_E_MODIFIER = 19, /*[EM]*/ + /** @stable ICU 58 */ + U_WB_GLUE_AFTER_ZWJ = 20, /*[GAZ]*/ + /** @stable ICU 58 */ + U_WB_ZWJ = 21, /*[ZWJ]*/ + /** @stable ICU 62 */ + U_WB_WSEGSPACE = 22, /*[WSEGSPACE]*/ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UWordBreakValues value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_WB_COUNT = 23 +#endif // U_HIDE_DEPRECATED_API +} UWordBreakValues; + +/** + * Sentence Break constants. + * + * @see UCHAR_SENTENCE_BREAK + * @stable ICU 3.4 + */ +typedef enum USentenceBreak { + /* + * Note: USentenceBreak constants are parsed by preparseucd.py. + * It matches lines like + * U_SB_<Unicode Sentence_Break value name> + */ + + U_SB_OTHER = 0, /*[XX]*/ + U_SB_ATERM = 1, /*[AT]*/ + U_SB_CLOSE = 2, /*[CL]*/ + U_SB_FORMAT = 3, /*[FO]*/ + U_SB_LOWER = 4, /*[LO]*/ + U_SB_NUMERIC = 5, /*[NU]*/ + U_SB_OLETTER = 6, /*[LE]*/ + U_SB_SEP = 7, /*[SE]*/ + U_SB_SP = 8, /*[SP]*/ + U_SB_STERM = 9, /*[ST]*/ + U_SB_UPPER = 10, /*[UP]*/ + U_SB_CR = 11, /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */ + U_SB_EXTEND = 12, /*[EX]*/ + U_SB_LF = 13, /*[LF]*/ + U_SB_SCONTINUE = 14, /*[SC]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal USentenceBreak value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_SB_COUNT = 15 +#endif // U_HIDE_DEPRECATED_API +} USentenceBreak; + +/** + * Line Break constants. + * + * @see UCHAR_LINE_BREAK + * @stable ICU 2.2 + */ +typedef enum ULineBreak { + /* + * Note: ULineBreak constants are parsed by preparseucd.py. + * It matches lines like + * U_LB_<Unicode Line_Break value name> + */ + + U_LB_UNKNOWN = 0, /*[XX]*/ + U_LB_AMBIGUOUS = 1, /*[AI]*/ + U_LB_ALPHABETIC = 2, /*[AL]*/ + U_LB_BREAK_BOTH = 3, /*[B2]*/ + U_LB_BREAK_AFTER = 4, /*[BA]*/ + U_LB_BREAK_BEFORE = 5, /*[BB]*/ + U_LB_MANDATORY_BREAK = 6, /*[BK]*/ + U_LB_CONTINGENT_BREAK = 7, /*[CB]*/ + U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/ + U_LB_COMBINING_MARK = 9, /*[CM]*/ + U_LB_CARRIAGE_RETURN = 10, /*[CR]*/ + U_LB_EXCLAMATION = 11, /*[EX]*/ + U_LB_GLUE = 12, /*[GL]*/ + U_LB_HYPHEN = 13, /*[HY]*/ + U_LB_IDEOGRAPHIC = 14, /*[ID]*/ + /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */ + U_LB_INSEPARABLE = 15, /*[IN]*/ + U_LB_INSEPERABLE = U_LB_INSEPARABLE, + U_LB_INFIX_NUMERIC = 16, /*[IS]*/ + U_LB_LINE_FEED = 17, /*[LF]*/ + U_LB_NONSTARTER = 18, /*[NS]*/ + U_LB_NUMERIC = 19, /*[NU]*/ + U_LB_OPEN_PUNCTUATION = 20, /*[OP]*/ + U_LB_POSTFIX_NUMERIC = 21, /*[PO]*/ + U_LB_PREFIX_NUMERIC = 22, /*[PR]*/ + U_LB_QUOTATION = 23, /*[QU]*/ + U_LB_COMPLEX_CONTEXT = 24, /*[SA]*/ + U_LB_SURROGATE = 25, /*[SG]*/ + U_LB_SPACE = 26, /*[SP]*/ + U_LB_BREAK_SYMBOLS = 27, /*[SY]*/ + U_LB_ZWSPACE = 28, /*[ZW]*/ + /** @stable ICU 2.6 */ + U_LB_NEXT_LINE = 29, /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */ + /** @stable ICU 2.6 */ + U_LB_WORD_JOINER = 30, /*[WJ]*/ + /** @stable ICU 3.4 */ + U_LB_H2 = 31, /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */ + /** @stable ICU 3.4 */ + U_LB_H3 = 32, /*[H3]*/ + /** @stable ICU 3.4 */ + U_LB_JL = 33, /*[JL]*/ + /** @stable ICU 3.4 */ + U_LB_JT = 34, /*[JT]*/ + /** @stable ICU 3.4 */ + U_LB_JV = 35, /*[JV]*/ + /** @stable ICU 4.4 */ + U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */ + /** @stable ICU 49 */ + U_LB_CONDITIONAL_JAPANESE_STARTER = 37,/*[CJ]*/ /* new in Unicode 6.1/ICU 49 */ + /** @stable ICU 49 */ + U_LB_HEBREW_LETTER = 38, /*[HL]*/ /* new in Unicode 6.1/ICU 49 */ + /** @stable ICU 50 */ + U_LB_REGIONAL_INDICATOR = 39,/*[RI]*/ /* new in Unicode 6.2/ICU 50 */ + /** @stable ICU 58 */ + U_LB_E_BASE = 40, /*[EB]*/ /* from here on: new in Unicode 9.0/ICU 58 */ + /** @stable ICU 58 */ + U_LB_E_MODIFIER = 41, /*[EM]*/ + /** @stable ICU 58 */ + U_LB_ZWJ = 42, /*[ZWJ]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal ULineBreak value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_LB_COUNT = 43 +#endif // U_HIDE_DEPRECATED_API +} ULineBreak; + +/** + * Numeric Type constants. + * + * @see UCHAR_NUMERIC_TYPE + * @stable ICU 2.2 + */ +typedef enum UNumericType { + /* + * Note: UNumericType constants are parsed by preparseucd.py. + * It matches lines like + * U_NT_<Unicode Numeric_Type value name> + */ + + U_NT_NONE, /*[None]*/ + U_NT_DECIMAL, /*[de]*/ + U_NT_DIGIT, /*[di]*/ + U_NT_NUMERIC, /*[nu]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UNumericType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_NT_COUNT +#endif // U_HIDE_DEPRECATED_API +} UNumericType; + +/** + * Hangul Syllable Type constants. + * + * @see UCHAR_HANGUL_SYLLABLE_TYPE + * @stable ICU 2.6 + */ +typedef enum UHangulSyllableType { + /* + * Note: UHangulSyllableType constants are parsed by preparseucd.py. + * It matches lines like + * U_HST_<Unicode Hangul_Syllable_Type value name> + */ + + U_HST_NOT_APPLICABLE, /*[NA]*/ + U_HST_LEADING_JAMO, /*[L]*/ + U_HST_VOWEL_JAMO, /*[V]*/ + U_HST_TRAILING_JAMO, /*[T]*/ + U_HST_LV_SYLLABLE, /*[LV]*/ + U_HST_LVT_SYLLABLE, /*[LVT]*/ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UHangulSyllableType value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_HST_COUNT +#endif // U_HIDE_DEPRECATED_API +} UHangulSyllableType; + +/** + * Indic Positional Category constants. + * + * @see UCHAR_INDIC_POSITIONAL_CATEGORY + * @stable ICU 63 + */ +typedef enum UIndicPositionalCategory { + /* + * Note: UIndicPositionalCategory constants are parsed by preparseucd.py. + * It matches lines like + * U_INPC_<Unicode Indic_Positional_Category value name> + */ + + /** @stable ICU 63 */ + U_INPC_NA, + /** @stable ICU 63 */ + U_INPC_BOTTOM, + /** @stable ICU 63 */ + U_INPC_BOTTOM_AND_LEFT, + /** @stable ICU 63 */ + U_INPC_BOTTOM_AND_RIGHT, + /** @stable ICU 63 */ + U_INPC_LEFT, + /** @stable ICU 63 */ + U_INPC_LEFT_AND_RIGHT, + /** @stable ICU 63 */ + U_INPC_OVERSTRUCK, + /** @stable ICU 63 */ + U_INPC_RIGHT, + /** @stable ICU 63 */ + U_INPC_TOP, + /** @stable ICU 63 */ + U_INPC_TOP_AND_BOTTOM, + /** @stable ICU 63 */ + U_INPC_TOP_AND_BOTTOM_AND_RIGHT, + /** @stable ICU 63 */ + U_INPC_TOP_AND_LEFT, + /** @stable ICU 63 */ + U_INPC_TOP_AND_LEFT_AND_RIGHT, + /** @stable ICU 63 */ + U_INPC_TOP_AND_RIGHT, + /** @stable ICU 63 */ + U_INPC_VISUAL_ORDER_LEFT, + /** @stable ICU 66 */ + U_INPC_TOP_AND_BOTTOM_AND_LEFT, +} UIndicPositionalCategory; + +/** + * Indic Syllabic Category constants. + * + * @see UCHAR_INDIC_SYLLABIC_CATEGORY + * @stable ICU 63 + */ +typedef enum UIndicSyllabicCategory { + /* + * Note: UIndicSyllabicCategory constants are parsed by preparseucd.py. + * It matches lines like + * U_INSC_<Unicode Indic_Syllabic_Category value name> + */ + + /** @stable ICU 63 */ + U_INSC_OTHER, + /** @stable ICU 63 */ + U_INSC_AVAGRAHA, + /** @stable ICU 63 */ + U_INSC_BINDU, + /** @stable ICU 63 */ + U_INSC_BRAHMI_JOINING_NUMBER, + /** @stable ICU 63 */ + U_INSC_CANTILLATION_MARK, + /** @stable ICU 63 */ + U_INSC_CONSONANT, + /** @stable ICU 63 */ + U_INSC_CONSONANT_DEAD, + /** @stable ICU 63 */ + U_INSC_CONSONANT_FINAL, + /** @stable ICU 63 */ + U_INSC_CONSONANT_HEAD_LETTER, + /** @stable ICU 63 */ + U_INSC_CONSONANT_INITIAL_POSTFIXED, + /** @stable ICU 63 */ + U_INSC_CONSONANT_KILLER, + /** @stable ICU 63 */ + U_INSC_CONSONANT_MEDIAL, + /** @stable ICU 63 */ + U_INSC_CONSONANT_PLACEHOLDER, + /** @stable ICU 63 */ + U_INSC_CONSONANT_PRECEDING_REPHA, + /** @stable ICU 63 */ + U_INSC_CONSONANT_PREFIXED, + /** @stable ICU 63 */ + U_INSC_CONSONANT_SUBJOINED, + /** @stable ICU 63 */ + U_INSC_CONSONANT_SUCCEEDING_REPHA, + /** @stable ICU 63 */ + U_INSC_CONSONANT_WITH_STACKER, + /** @stable ICU 63 */ + U_INSC_GEMINATION_MARK, + /** @stable ICU 63 */ + U_INSC_INVISIBLE_STACKER, + /** @stable ICU 63 */ + U_INSC_JOINER, + /** @stable ICU 63 */ + U_INSC_MODIFYING_LETTER, + /** @stable ICU 63 */ + U_INSC_NON_JOINER, + /** @stable ICU 63 */ + U_INSC_NUKTA, + /** @stable ICU 63 */ + U_INSC_NUMBER, + /** @stable ICU 63 */ + U_INSC_NUMBER_JOINER, + /** @stable ICU 63 */ + U_INSC_PURE_KILLER, + /** @stable ICU 63 */ + U_INSC_REGISTER_SHIFTER, + /** @stable ICU 63 */ + U_INSC_SYLLABLE_MODIFIER, + /** @stable ICU 63 */ + U_INSC_TONE_LETTER, + /** @stable ICU 63 */ + U_INSC_TONE_MARK, + /** @stable ICU 63 */ + U_INSC_VIRAMA, + /** @stable ICU 63 */ + U_INSC_VISARGA, + /** @stable ICU 63 */ + U_INSC_VOWEL, + /** @stable ICU 63 */ + U_INSC_VOWEL_DEPENDENT, + /** @stable ICU 63 */ + U_INSC_VOWEL_INDEPENDENT, +} UIndicSyllabicCategory; + +/** + * Vertical Orientation constants. + * + * @see UCHAR_VERTICAL_ORIENTATION + * @stable ICU 63 + */ +typedef enum UVerticalOrientation { + /* + * Note: UVerticalOrientation constants are parsed by preparseucd.py. + * It matches lines like + * U_VO_<Unicode Vertical_Orientation value name> + */ + + /** @stable ICU 63 */ + U_VO_ROTATED, + /** @stable ICU 63 */ + U_VO_TRANSFORMED_ROTATED, + /** @stable ICU 63 */ + U_VO_TRANSFORMED_UPRIGHT, + /** @stable ICU 63 */ + U_VO_UPRIGHT, +} UVerticalOrientation; + +/** + * Check a binary Unicode property for a code point. + * + * Unicode, especially in version 3.2, defines many more properties than the + * original set in UnicodeData.txt. + * + * The properties APIs are intended to reflect Unicode properties as defined + * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). + * For details about the properties see http://www.unicode.org/ucd/ . + * For names of Unicode properties see the UCD file PropertyAliases.txt. + * + * Important: If ICU is built with UCD files from Unicode versions below 3.2, + * then properties marked with "new in Unicode 3.2" are not or not fully available. + * + * @param c Code point to test. + * @param which UProperty selector constant, identifies which binary property to check. + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. + * @return true or false according to the binary Unicode property value for c. + * Also false if 'which' is out of bounds or if the Unicode version + * does not have data for the property at all, or not for this code point. + * + * @see UProperty + * @see u_getBinaryPropertySet + * @see u_getIntPropertyValue + * @see u_getUnicodeVersion + * @stable ICU 2.1 + */ +U_CAPI UBool U_EXPORT2 +u_hasBinaryProperty(UChar32 c, UProperty which); + +/** + * Returns a frozen USet for a binary property. + * The library retains ownership over the returned object. + * Sets an error code if the property number is not one for a binary property. + * + * The returned set contains all code points for which the property is true. + * + * @param property UCHAR_BINARY_START..UCHAR_BINARY_LIMIT-1 + * @param pErrorCode an in/out ICU UErrorCode + * @return the property as a set + * @see UProperty + * @see u_hasBinaryProperty + * @see Unicode::fromUSet + * @stable ICU 63 + */ +U_CAPI const USet * U_EXPORT2 +u_getBinaryPropertySet(UProperty property, UErrorCode *pErrorCode); + +/** + * Check if a code point has the Alphabetic Unicode property. + * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). + * This is different from u_isalpha! + * @param c Code point to test + * @return true if the code point has the Alphabetic Unicode property, false otherwise + * + * @see UCHAR_ALPHABETIC + * @see u_isalpha + * @see u_hasBinaryProperty + * @stable ICU 2.1 + */ +U_CAPI UBool U_EXPORT2 +u_isUAlphabetic(UChar32 c); + +/** + * Check if a code point has the Lowercase Unicode property. + * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). + * This is different from u_islower! + * @param c Code point to test + * @return true if the code point has the Lowercase Unicode property, false otherwise + * + * @see UCHAR_LOWERCASE + * @see u_islower + * @see u_hasBinaryProperty + * @stable ICU 2.1 + */ +U_CAPI UBool U_EXPORT2 +u_isULowercase(UChar32 c); + +/** + * Check if a code point has the Uppercase Unicode property. + * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). + * This is different from u_isupper! + * @param c Code point to test + * @return true if the code point has the Uppercase Unicode property, false otherwise + * + * @see UCHAR_UPPERCASE + * @see u_isupper + * @see u_hasBinaryProperty + * @stable ICU 2.1 + */ +U_CAPI UBool U_EXPORT2 +u_isUUppercase(UChar32 c); + +/** + * Check if a code point has the White_Space Unicode property. + * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). + * This is different from both u_isspace and u_isWhitespace! + * + * Note: There are several ICU whitespace functions; please see the uchar.h + * file documentation for a detailed comparison. + * + * @param c Code point to test + * @return true if the code point has the White_Space Unicode property, false otherwise. + * + * @see UCHAR_WHITE_SPACE + * @see u_isWhitespace + * @see u_isspace + * @see u_isJavaSpaceChar + * @see u_hasBinaryProperty + * @stable ICU 2.1 + */ +U_CAPI UBool U_EXPORT2 +u_isUWhiteSpace(UChar32 c); + +/** + * Get the property value for an enumerated or integer Unicode property for a code point. + * Also returns binary and mask property values. + * + * Unicode, especially in version 3.2, defines many more properties than the + * original set in UnicodeData.txt. + * + * The properties APIs are intended to reflect Unicode properties as defined + * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). + * For details about the properties see http://www.unicode.org/ . + * For names of Unicode properties see the UCD file PropertyAliases.txt. + * + * Sample usage: + * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); + * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC); + * + * @param c Code point to test. + * @param which UProperty selector constant, identifies which property to check. + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT + * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. + * @return Numeric value that is directly the property value or, + * for enumerated properties, corresponds to the numeric value of the enumerated + * constant of the respective property value enumeration type + * (cast to enum type if necessary). + * Returns 0 or 1 (for false/true) for binary Unicode properties. + * Returns a bit-mask for mask properties. + * Returns 0 if 'which' is out of bounds or if the Unicode version + * does not have data for the property at all, or not for this code point. + * + * @see UProperty + * @see u_hasBinaryProperty + * @see u_getIntPropertyMinValue + * @see u_getIntPropertyMaxValue + * @see u_getIntPropertyMap + * @see u_getUnicodeVersion + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +u_getIntPropertyValue(UChar32 c, UProperty which); + +/** + * Get the minimum value for an enumerated/integer/binary Unicode property. + * Can be used together with u_getIntPropertyMaxValue + * to allocate arrays of UnicodeSet or similar. + * + * @param which UProperty selector constant, identifies which binary property to check. + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. + * @return Minimum value returned by u_getIntPropertyValue for a Unicode property. + * 0 if the property selector is out of range. + * + * @see UProperty + * @see u_hasBinaryProperty + * @see u_getUnicodeVersion + * @see u_getIntPropertyMaxValue + * @see u_getIntPropertyValue + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +u_getIntPropertyMinValue(UProperty which); + +/** + * Get the maximum value for an enumerated/integer/binary Unicode property. + * Can be used together with u_getIntPropertyMinValue + * to allocate arrays of UnicodeSet or similar. + * + * Examples for min/max values (for Unicode 3.2): + * + * - UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL) + * - UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA) + * - UCHAR_IDEOGRAPHIC: 0/1 (false/true) + * + * For undefined UProperty constant values, min/max values will be 0/-1. + * + * @param which UProperty selector constant, identifies which binary property to check. + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT. + * @return Maximum value returned by u_getIntPropertyValue for a Unicode property. + * <=0 if the property selector is out of range. + * + * @see UProperty + * @see u_hasBinaryProperty + * @see u_getUnicodeVersion + * @see u_getIntPropertyMaxValue + * @see u_getIntPropertyValue + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +u_getIntPropertyMaxValue(UProperty which); + +/** + * Returns an immutable UCPMap for an enumerated/catalog/int-valued property. + * The library retains ownership over the returned object. + * Sets an error code if the property number is not one for an "int property". + * + * The returned object maps all Unicode code points to their values for that property. + * For documentation of the integer values see u_getIntPropertyValue(). + * + * @param property UCHAR_INT_START..UCHAR_INT_LIMIT-1 + * @param pErrorCode an in/out ICU UErrorCode + * @return the property as a map + * @see UProperty + * @see u_getIntPropertyValue + * @stable ICU 63 + */ +U_CAPI const UCPMap * U_EXPORT2 +u_getIntPropertyMap(UProperty property, UErrorCode *pErrorCode); + +/** + * Get the numeric value for a Unicode code point as defined in the + * Unicode Character Database. + * + * A "double" return type is necessary because + * some numeric values are fractions, negative, or too large for int32_t. + * + * For characters without any numeric values in the Unicode Character Database, + * this function will return U_NO_NUMERIC_VALUE. + * Note: This is different from the Unicode Standard which specifies NaN as the default value. + * (NaN is not available on all platforms.) + * + * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() + * also supports negative values, large values, and fractions, + * while Java's getNumericValue() returns values 10..35 for ASCII letters. + * + * @param c Code point to get the numeric value for. + * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined. + * + * @see U_NO_NUMERIC_VALUE + * @stable ICU 2.2 + */ +U_CAPI double U_EXPORT2 +u_getNumericValue(UChar32 c); + +/** + * Special value that is returned by u_getNumericValue when + * no numeric value is defined for a code point. + * + * @see u_getNumericValue + * @stable ICU 2.2 + */ +#define U_NO_NUMERIC_VALUE ((double)-123456789.) + +/** + * Determines whether the specified code point has the general category "Ll" + * (lowercase letter). + * + * Same as java.lang.Character.isLowerCase(). + * + * This misses some characters that are also lowercase but + * have a different general category value. + * In order to include those, use UCHAR_LOWERCASE. + * + * In addition to being equivalent to a Java function, this also serves + * as a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is an Ll lowercase letter + * + * @see UCHAR_LOWERCASE + * @see u_isupper + * @see u_istitle + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_islower(UChar32 c); + +/** + * Determines whether the specified code point has the general category "Lu" + * (uppercase letter). + * + * Same as java.lang.Character.isUpperCase(). + * + * This misses some characters that are also uppercase but + * have a different general category value. + * In order to include those, use UCHAR_UPPERCASE. + * + * In addition to being equivalent to a Java function, this also serves + * as a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is an Lu uppercase letter + * + * @see UCHAR_UPPERCASE + * @see u_islower + * @see u_istitle + * @see u_tolower + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isupper(UChar32 c); + +/** + * Determines whether the specified code point is a titlecase letter. + * True for general category "Lt" (titlecase letter). + * + * Same as java.lang.Character.isTitleCase(). + * + * @param c the code point to be tested + * @return true if the code point is an Lt titlecase letter + * + * @see u_isupper + * @see u_islower + * @see u_totitle + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_istitle(UChar32 c); + +/** + * Determines whether the specified code point is a digit character according to Java. + * True for characters with general category "Nd" (decimal digit numbers). + * Beginning with Unicode 4, this is the same as + * testing for the Numeric_Type of Decimal. + * + * Same as java.lang.Character.isDigit(). + * + * In addition to being equivalent to a Java function, this also serves + * as a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is a digit character according to Character.isDigit() + * + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isdigit(UChar32 c); + +/** + * Determines whether the specified code point is a letter character. + * True for general categories "L" (letters). + * + * Same as java.lang.Character.isLetter(). + * + * In addition to being equivalent to a Java function, this also serves + * as a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is a letter character + * + * @see u_isdigit + * @see u_isalnum + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isalpha(UChar32 c); + +/** + * Determines whether the specified code point is an alphanumeric character + * (letter or digit) according to Java. + * True for characters with general categories + * "L" (letters) and "Nd" (decimal digit numbers). + * + * Same as java.lang.Character.isLetterOrDigit(). + * + * In addition to being equivalent to a Java function, this also serves + * as a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is an alphanumeric character according to Character.isLetterOrDigit() + * + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isalnum(UChar32 c); + +/** + * Determines whether the specified code point is a hexadecimal digit. + * This is equivalent to u_digit(c, 16)>=0. + * True for characters with general category "Nd" (decimal digit numbers) + * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. + * (That is, for letters with code points + * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) + * + * In order to narrow the definition of hexadecimal digits to only ASCII + * characters, use (c<=0x7f && u_isxdigit(c)). + * + * This is a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is a hexadecimal digit + * + * @stable ICU 2.6 + */ +U_CAPI UBool U_EXPORT2 +u_isxdigit(UChar32 c); + +/** + * Determines whether the specified code point is a punctuation character. + * True for characters with general categories "P" (punctuation). + * + * This is a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is a punctuation character + * + * @stable ICU 2.6 + */ +U_CAPI UBool U_EXPORT2 +u_ispunct(UChar32 c); + +/** + * Determines whether the specified code point is a "graphic" character + * (printable, excluding spaces). + * true for all characters except those with general categories + * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), + * "Cn" (unassigned), and "Z" (separators). + * + * This is a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is a "graphic" character + * + * @stable ICU 2.6 + */ +U_CAPI UBool U_EXPORT2 +u_isgraph(UChar32 c); + +/** + * Determines whether the specified code point is a "blank" or "horizontal space", + * a character that visibly separates words on a line. + * The following are equivalent definitions: + * + * true for Unicode White_Space characters except for "vertical space controls" + * where "vertical space controls" are the following characters: + * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) + * + * same as + * + * true for U+0009 (TAB) and characters with general category "Zs" (space separators). + * + * Note: There are several ICU whitespace functions; please see the uchar.h + * file documentation for a detailed comparison. + * + * This is a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is a "blank" + * + * @stable ICU 2.6 + */ +U_CAPI UBool U_EXPORT2 +u_isblank(UChar32 c); + +/** + * Determines whether the specified code point is "defined", + * which usually means that it is assigned a character. + * True for general categories other than "Cn" (other, not assigned), + * i.e., true for all code points mentioned in UnicodeData.txt. + * + * Note that non-character code points (e.g., U+FDD0) are not "defined" + * (they are Cn), but surrogate code points are "defined" (Cs). + * + * Same as java.lang.Character.isDefined(). + * + * @param c the code point to be tested + * @return true if the code point is assigned a character + * + * @see u_isdigit + * @see u_isalpha + * @see u_isalnum + * @see u_isupper + * @see u_islower + * @see u_istitle + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isdefined(UChar32 c); + +/** + * Determines if the specified character is a space character or not. + * + * Note: There are several ICU whitespace functions; please see the uchar.h + * file documentation for a detailed comparison. + * + * This is a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the character to be tested + * @return true if the character is a space character; false otherwise. + * + * @see u_isJavaSpaceChar + * @see u_isWhitespace + * @see u_isUWhiteSpace + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isspace(UChar32 c); + +/** + * Determine if the specified code point is a space character according to Java. + * True for characters with general categories "Z" (separators), + * which does not include control codes (e.g., TAB or Line Feed). + * + * Same as java.lang.Character.isSpaceChar(). + * + * Note: There are several ICU whitespace functions; please see the uchar.h + * file documentation for a detailed comparison. + * + * @param c the code point to be tested + * @return true if the code point is a space character according to Character.isSpaceChar() + * + * @see u_isspace + * @see u_isWhitespace + * @see u_isUWhiteSpace + * @stable ICU 2.6 + */ +U_CAPI UBool U_EXPORT2 +u_isJavaSpaceChar(UChar32 c); + +/** + * Determines if the specified code point is a whitespace character according to Java/ICU. + * A character is considered to be a Java whitespace character if and only + * if it satisfies one of the following criteria: + * + * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not + * also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP). + * - It is U+0009 HORIZONTAL TABULATION. + * - It is U+000A LINE FEED. + * - It is U+000B VERTICAL TABULATION. + * - It is U+000C FORM FEED. + * - It is U+000D CARRIAGE RETURN. + * - It is U+001C FILE SEPARATOR. + * - It is U+001D GROUP SEPARATOR. + * - It is U+001E RECORD SEPARATOR. + * - It is U+001F UNIT SEPARATOR. + * + * This API tries to sync with the semantics of Java's + * java.lang.Character.isWhitespace(), but it may not return + * the exact same results because of the Unicode version + * difference. + * + * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) + * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. + * See http://www.unicode.org/versions/Unicode4.0.1/ + * + * Note: There are several ICU whitespace functions; please see the uchar.h + * file documentation for a detailed comparison. + * + * @param c the code point to be tested + * @return true if the code point is a whitespace character according to Java/ICU + * + * @see u_isspace + * @see u_isJavaSpaceChar + * @see u_isUWhiteSpace + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isWhitespace(UChar32 c); + +/** + * Determines whether the specified code point is a control character + * (as defined by this function). + * A control character is one of the following: + * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f) + * - U_CONTROL_CHAR (Cc) + * - U_FORMAT_CHAR (Cf) + * - U_LINE_SEPARATOR (Zl) + * - U_PARAGRAPH_SEPARATOR (Zp) + * + * This is a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is a control character + * + * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT + * @see u_isprint + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_iscntrl(UChar32 c); + +/** + * Determines whether the specified code point is an ISO control code. + * True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). + * + * Same as java.lang.Character.isISOControl(). + * + * @param c the code point to be tested + * @return true if the code point is an ISO control code + * + * @see u_iscntrl + * @stable ICU 2.6 + */ +U_CAPI UBool U_EXPORT2 +u_isISOControl(UChar32 c); + +/** + * Determines whether the specified code point is a printable character. + * True for general categories <em>other</em> than "C" (controls). + * + * This is a C/POSIX migration function. + * See the comments about C/POSIX character classification functions in the + * documentation at the top of this header file. + * + * @param c the code point to be tested + * @return true if the code point is a printable character + * + * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT + * @see u_iscntrl + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isprint(UChar32 c); + +/** + * Non-standard: Determines whether the specified code point is a base character. + * True for general categories "L" (letters), "N" (numbers), + * "Mc" (spacing combining marks), and "Me" (enclosing marks). + * + * Note that this is different from the Unicode Standard definition in + * chapter 3.6, conformance clause D51 “Base character”, + * which defines base characters as the code points with general categories + * Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs). + * + * @param c the code point to be tested + * @return true if the code point is a base character according to this function + * + * @see u_isalpha + * @see u_isdigit + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isbase(UChar32 c); + +/** + * Returns the bidirectional category value for the code point, + * which is used in the Unicode bidirectional algorithm + * (UAX #9 http://www.unicode.org/reports/tr9/). + * Note that some <em>unassigned</em> code points have bidi values + * of R or AL because they are in blocks that are reserved + * for Right-To-Left scripts. + * + * Same as java.lang.Character.getDirectionality() + * + * @param c the code point to be tested + * @return the bidirectional category (UCharDirection) value + * + * @see UCharDirection + * @stable ICU 2.0 + */ +U_CAPI UCharDirection U_EXPORT2 +u_charDirection(UChar32 c); + +/** + * Determines whether the code point has the Bidi_Mirrored property. + * This property is set for characters that are commonly used in + * Right-To-Left contexts and need to be displayed with a "mirrored" + * glyph. + * + * Same as java.lang.Character.isMirrored(). + * Same as UCHAR_BIDI_MIRRORED + * + * @param c the code point to be tested + * @return true if the character has the Bidi_Mirrored property + * + * @see UCHAR_BIDI_MIRRORED + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isMirrored(UChar32 c); + +/** + * Maps the specified character to a "mirror-image" character. + * For characters with the Bidi_Mirrored property, implementations + * sometimes need a "poor man's" mapping to another Unicode + * character (code point) such that the default glyph may serve + * as the mirror-image of the default glyph of the specified + * character. This is useful for text conversion to and from + * codepages with visual order, and for displays without glyph + * selection capabilities. + * + * @param c the code point to be mapped + * @return another Unicode code point that may serve as a mirror-image + * substitute, or c itself if there is no such mapping or c + * does not have the Bidi_Mirrored property + * + * @see UCHAR_BIDI_MIRRORED + * @see u_isMirrored + * @stable ICU 2.0 + */ +U_CAPI UChar32 U_EXPORT2 +u_charMirror(UChar32 c); + +/** + * Maps the specified character to its paired bracket character. + * For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). + * Otherwise c itself is returned. + * See http://www.unicode.org/reports/tr9/ + * + * @param c the code point to be mapped + * @return the paired bracket code point, + * or c itself if there is no such mapping + * (Bidi_Paired_Bracket_Type=None) + * + * @see UCHAR_BIDI_PAIRED_BRACKET + * @see UCHAR_BIDI_PAIRED_BRACKET_TYPE + * @see u_charMirror + * @stable ICU 52 + */ +U_CAPI UChar32 U_EXPORT2 +u_getBidiPairedBracket(UChar32 c); + +/** + * Returns the general category value for the code point. + * + * Same as java.lang.Character.getType(). + * + * @param c the code point to be tested + * @return the general category (UCharCategory) value + * + * @see UCharCategory + * @stable ICU 2.0 + */ +U_CAPI int8_t U_EXPORT2 +u_charType(UChar32 c); + +/** + * Get a single-bit bit set for the general category of a character. + * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. + * Same as U_MASK(u_charType(c)). + * + * @param c the code point to be tested + * @return a single-bit mask corresponding to the general category (UCharCategory) value + * + * @see u_charType + * @see UCharCategory + * @see U_GC_CN_MASK + * @stable ICU 2.1 + */ +#define U_GET_GC_MASK(c) U_MASK(u_charType(c)) + +/** + * Callback from u_enumCharTypes(), is called for each contiguous range + * of code points c (where start<=c<limit) + * with the same Unicode general category ("character type"). + * + * The callback function can stop the enumeration by returning false. + * + * @param context an opaque pointer, as passed into utrie_enum() + * @param start the first code point in a contiguous range with value + * @param limit one past the last code point in a contiguous range with value + * @param type the general category for all code points in [start..limit[ + * @return false to stop the enumeration + * + * @stable ICU 2.1 + * @see UCharCategory + * @see u_enumCharTypes + */ +typedef UBool U_CALLCONV +UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type); + +/** + * Enumerate efficiently all code points with their Unicode general categories. + * + * This is useful for building data structures (e.g., UnicodeSet's), + * for enumerating all assigned code points (type!=U_UNASSIGNED), etc. + * + * For each contiguous range of code points with a given general category ("character type"), + * the UCharEnumTypeRange function is called. + * Adjacent ranges have different types. + * The Unicode Standard guarantees that the numeric value of the type is 0..31. + * + * @param enumRange a pointer to a function that is called for each contiguous range + * of code points with the same general category + * @param context an opaque pointer that is passed on to the callback function + * + * @stable ICU 2.1 + * @see UCharCategory + * @see UCharEnumTypeRange + */ +U_CAPI void U_EXPORT2 +u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context); + +#if !UCONFIG_NO_NORMALIZATION + +/** + * Returns the combining class of the code point as specified in UnicodeData.txt. + * + * @param c the code point of the character + * @return the combining class of the character + * @stable ICU 2.0 + */ +U_CAPI uint8_t U_EXPORT2 +u_getCombiningClass(UChar32 c); + +#endif + +/** + * Returns the decimal digit value of a decimal digit character. + * Such characters have the general category "Nd" (decimal digit numbers) + * and a Numeric_Type of Decimal. + * + * Unlike ICU releases before 2.6, no digit values are returned for any + * Han characters because Han number characters are often used with a special + * Chinese-style number format (with characters for powers of 10 in between) + * instead of in decimal-positional notation. + * Unicode 4 explicitly assigns Han number characters the Numeric_Type + * Numeric instead of Decimal. + * See Jitterbug 1483 for more details. + * + * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() + * for complete numeric Unicode properties. + * + * @param c the code point for which to get the decimal digit value + * @return the decimal digit value of c, + * or -1 if c is not a decimal digit character + * + * @see u_getNumericValue + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_charDigitValue(UChar32 c); + +/** + * Returns the Unicode allocation block that contains the character. + * + * @param c the code point to be tested + * @return the block value (UBlockCode) for c + * + * @see UBlockCode + * @stable ICU 2.0 + */ +U_CAPI UBlockCode U_EXPORT2 +ublock_getCode(UChar32 c); + +/** + * Retrieve the name of a Unicode character. + * Depending on <code>nameChoice</code>, the character name written + * into the buffer is the "modern" name or the name that was defined + * in Unicode version 1.0. + * The name contains only "invariant" characters + * like A-Z, 0-9, space, and '-'. + * Unicode 1.0 names are only retrieved if they are different from the modern + * names and if the data file contains the data for them. gennames may or may + * not be called with a command line option to include 1.0 names in unames.dat. + * + * @param code The character (code point) for which to get the name. + * It must be <code>0<=code<=0x10ffff</code>. + * @param nameChoice Selector for which name to get. + * @param buffer Destination address for copying the name. + * The name will always be zero-terminated. + * If there is no name, then the buffer will be set to the empty string. + * @param bufferLength <code>==sizeof(buffer)</code> + * @param pErrorCode Pointer to a UErrorCode variable; + * check for <code>U_SUCCESS()</code> after <code>u_charName()</code> + * returns. + * @return The length of the name, or 0 if there is no name for this character. + * If the bufferLength is less than or equal to the length, then the buffer + * contains the truncated name and the returned length indicates the full + * length of the name. + * The length does not include the zero-termination. + * + * @see UCharNameChoice + * @see u_charFromName + * @see u_enumCharNames + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_charName(UChar32 code, UCharNameChoice nameChoice, + char *buffer, int32_t bufferLength, + UErrorCode *pErrorCode); + +#ifndef U_HIDE_DEPRECATED_API +/** + * Returns an empty string. + * Used to return the ISO 10646 comment for a character. + * The Unicode ISO_Comment property is deprecated and has no values. + * + * @param c The character (code point) for which to get the ISO comment. + * It must be <code>0<=c<=0x10ffff</code>. + * @param dest Destination address for copying the comment. + * The comment will be zero-terminated if possible. + * If there is no comment, then the buffer will be set to the empty string. + * @param destCapacity <code>==sizeof(dest)</code> + * @param pErrorCode Pointer to a UErrorCode variable; + * check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code> + * returns. + * @return 0 + * + * @deprecated ICU 49 + */ +U_DEPRECATED int32_t U_EXPORT2 +u_getISOComment(UChar32 c, + char *dest, int32_t destCapacity, + UErrorCode *pErrorCode); +#endif /* U_HIDE_DEPRECATED_API */ + +/** + * Find a Unicode character by its name and return its code point value. + * The name is matched exactly and completely. + * If the name does not correspond to a code point, <i>pErrorCode</i> + * is set to <code>U_INVALID_CHAR_FOUND</code>. + * A Unicode 1.0 name is matched only if it differs from the modern name. + * Unicode names are all uppercase. Extended names are lowercase followed + * by an uppercase hexadecimal number, and within angle brackets. + * + * @param nameChoice Selector for which name to match. + * @param name The name to match. + * @param pErrorCode Pointer to a UErrorCode variable + * @return The Unicode value of the code point with the given name, + * or an undefined value if there is no such code point. + * + * @see UCharNameChoice + * @see u_charName + * @see u_enumCharNames + * @stable ICU 1.7 + */ +U_CAPI UChar32 U_EXPORT2 +u_charFromName(UCharNameChoice nameChoice, + const char *name, + UErrorCode *pErrorCode); + +/** + * Type of a callback function for u_enumCharNames() that gets called + * for each Unicode character with the code point value and + * the character name. + * If such a function returns false, then the enumeration is stopped. + * + * @param context The context pointer that was passed to u_enumCharNames(). + * @param code The Unicode code point for the character with this name. + * @param nameChoice Selector for which kind of names is enumerated. + * @param name The character's name, zero-terminated. + * @param length The length of the name. + * @return true if the enumeration should continue, false to stop it. + * + * @see UCharNameChoice + * @see u_enumCharNames + * @stable ICU 1.7 + */ +typedef UBool U_CALLCONV UEnumCharNamesFn(void *context, + UChar32 code, + UCharNameChoice nameChoice, + const char *name, + int32_t length); + +/** + * Enumerate all assigned Unicode characters between the start and limit + * code points (start inclusive, limit exclusive) and call a function + * for each, passing the code point value and the character name. + * For Unicode 1.0 names, only those are enumerated that differ from the + * modern names. + * + * @param start The first code point in the enumeration range. + * @param limit One more than the last code point in the enumeration range + * (the first one after the range). + * @param fn The function that is to be called for each character name. + * @param context An arbitrary pointer that is passed to the function. + * @param nameChoice Selector for which kind of names to enumerate. + * @param pErrorCode Pointer to a UErrorCode variable + * + * @see UCharNameChoice + * @see UEnumCharNamesFn + * @see u_charName + * @see u_charFromName + * @stable ICU 1.7 + */ +U_CAPI void U_EXPORT2 +u_enumCharNames(UChar32 start, UChar32 limit, + UEnumCharNamesFn *fn, + void *context, + UCharNameChoice nameChoice, + UErrorCode *pErrorCode); + +/** + * Return the Unicode name for a given property, as given in the + * Unicode database file PropertyAliases.txt. + * + * In addition, this function maps the property + * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / + * "General_Category_Mask". These names are not in + * PropertyAliases.txt. + * + * @param property UProperty selector other than UCHAR_INVALID_CODE. + * If out of range, NULL is returned. + * + * @param nameChoice selector for which name to get. If out of range, + * NULL is returned. All properties have a long name. Most + * have a short name, but some do not. Unicode allows for + * additional names; if present these will be returned by + * U_LONG_PROPERTY_NAME + i, where i=1, 2,... + * + * @return a pointer to the name, or NULL if either the + * property or the nameChoice is out of range. If a given + * nameChoice returns NULL, then all larger values of + * nameChoice will return NULL, with one exception: if NULL is + * returned for U_SHORT_PROPERTY_NAME, then + * U_LONG_PROPERTY_NAME (and higher) may still return a + * non-NULL value. The returned pointer is valid until + * u_cleanup() is called. + * + * @see UProperty + * @see UPropertyNameChoice + * @stable ICU 2.4 + */ +U_CAPI const char* U_EXPORT2 +u_getPropertyName(UProperty property, + UPropertyNameChoice nameChoice); + +/** + * Return the UProperty enum for a given property name, as specified + * in the Unicode database file PropertyAliases.txt. Short, long, and + * any other variants are recognized. + * + * In addition, this function maps the synthetic names "gcm" / + * "General_Category_Mask" to the property + * UCHAR_GENERAL_CATEGORY_MASK. These names are not in + * PropertyAliases.txt. + * + * @param alias the property name to be matched. The name is compared + * using "loose matching" as described in PropertyAliases.txt. + * + * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name + * does not match any property. + * + * @see UProperty + * @stable ICU 2.4 + */ +U_CAPI UProperty U_EXPORT2 +u_getPropertyEnum(const char* alias); + +/** + * Return the Unicode name for a given property value, as given in the + * Unicode database file PropertyValueAliases.txt. + * + * Note: Some of the names in PropertyValueAliases.txt can only be + * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not + * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / + * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" + * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". + * + * @param property UProperty selector constant. + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT + * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. + * If out of range, NULL is returned. + * + * @param value selector for a value for the given property. If out + * of range, NULL is returned. In general, valid values range + * from 0 up to some maximum. There are a few exceptions: + * (1.) UCHAR_BLOCK values begin at the non-zero value + * UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS + * values are not contiguous and range from 0..240. (3.) + * UCHAR_GENERAL_CATEGORY_MASK values are not values of + * UCharCategory, but rather mask values produced by + * U_GET_GC_MASK(). This allows grouped categories such as + * [:L:] to be represented. Mask values range + * non-contiguously from 1..U_GC_P_MASK. + * + * @param nameChoice selector for which name to get. If out of range, + * NULL is returned. All values have a long name. Most have + * a short name, but some do not. Unicode allows for + * additional names; if present these will be returned by + * U_LONG_PROPERTY_NAME + i, where i=1, 2,... + + * @return a pointer to the name, or NULL if either the + * property or the nameChoice is out of range. If a given + * nameChoice returns NULL, then all larger values of + * nameChoice will return NULL, with one exception: if NULL is + * returned for U_SHORT_PROPERTY_NAME, then + * U_LONG_PROPERTY_NAME (and higher) may still return a + * non-NULL value. The returned pointer is valid until + * u_cleanup() is called. + * + * @see UProperty + * @see UPropertyNameChoice + * @stable ICU 2.4 + */ +U_CAPI const char* U_EXPORT2 +u_getPropertyValueName(UProperty property, + int32_t value, + UPropertyNameChoice nameChoice); + +/** + * Return the property value integer for a given value name, as + * specified in the Unicode database file PropertyValueAliases.txt. + * Short, long, and any other variants are recognized. + * + * Note: Some of the names in PropertyValueAliases.txt will only be + * recognized with UCHAR_GENERAL_CATEGORY_MASK, not + * UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / + * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" + * / "Punctuation", "S" / "Symbol", and "Z" / "Separator". + * + * @param property UProperty selector constant. + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT + * or UCHAR_INT_START<=which<UCHAR_INT_LIMIT + * or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. + * If out of range, UCHAR_INVALID_CODE is returned. + * + * @param alias the value name to be matched. The name is compared + * using "loose matching" as described in + * PropertyValueAliases.txt. + * + * @return a value integer or UCHAR_INVALID_CODE if the given name + * does not match any value of the given property, or if the + * property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values + * are not values of UCharCategory, but rather mask values + * produced by U_GET_GC_MASK(). This allows grouped + * categories such as [:L:] to be represented. + * + * @see UProperty + * @stable ICU 2.4 + */ +U_CAPI int32_t U_EXPORT2 +u_getPropertyValueEnum(UProperty property, + const char* alias); + +/** + * Determines if the specified character is permissible as the + * first character in an identifier according to Unicode + * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). + * True for characters with general categories "L" (letters) and "Nl" (letter numbers). + * + * Same as java.lang.Character.isUnicodeIdentifierStart(). + * Same as UCHAR_ID_START + * + * @param c the code point to be tested + * @return true if the code point may start an identifier + * + * @see UCHAR_ID_START + * @see u_isalpha + * @see u_isIDPart + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isIDStart(UChar32 c); + +/** + * Determines if the specified character is permissible + * in an identifier according to Java. + * True for characters with general categories "L" (letters), + * "Nl" (letter numbers), "Nd" (decimal digits), + * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and + * u_isIDIgnorable(c). + * + * Same as java.lang.Character.isUnicodeIdentifierPart(). + * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) + * except that Unicode recommends to ignore Cf which is less than + * u_isIDIgnorable(c). + * + * @param c the code point to be tested + * @return true if the code point may occur in an identifier according to Java + * + * @see UCHAR_ID_CONTINUE + * @see u_isIDStart + * @see u_isIDIgnorable + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isIDPart(UChar32 c); + +/** + * Determines if the specified character should be regarded + * as an ignorable character in an identifier, + * according to Java. + * True for characters with general category "Cf" (format controls) as well as + * non-whitespace ISO controls + * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F). + * + * Same as java.lang.Character.isIdentifierIgnorable(). + * + * Note that Unicode just recommends to ignore Cf (format controls). + * + * @param c the code point to be tested + * @return true if the code point is ignorable in identifiers according to Java + * + * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT + * @see u_isIDStart + * @see u_isIDPart + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isIDIgnorable(UChar32 c); + +/** + * Determines if the specified character is permissible as the + * first character in a Java identifier. + * In addition to u_isIDStart(c), true for characters with + * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). + * + * Same as java.lang.Character.isJavaIdentifierStart(). + * + * @param c the code point to be tested + * @return true if the code point may start a Java identifier + * + * @see u_isJavaIDPart + * @see u_isalpha + * @see u_isIDStart + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isJavaIDStart(UChar32 c); + +/** + * Determines if the specified character is permissible + * in a Java identifier. + * In addition to u_isIDPart(c), true for characters with + * general category "Sc" (currency symbols). + * + * Same as java.lang.Character.isJavaIdentifierPart(). + * + * @param c the code point to be tested + * @return true if the code point may occur in a Java identifier + * + * @see u_isIDIgnorable + * @see u_isJavaIDStart + * @see u_isalpha + * @see u_isdigit + * @see u_isIDPart + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +u_isJavaIDPart(UChar32 c); + +/** + * The given character is mapped to its lowercase equivalent according to + * UnicodeData.txt; if the character has no lowercase equivalent, the character + * itself is returned. + * + * Same as java.lang.Character.toLowerCase(). + * + * This function only returns the simple, single-code point case mapping. + * Full case mappings should be used whenever possible because they produce + * better results by working on whole strings. + * They take into account the string context and the language and can map + * to a result string with a different length as appropriate. + * Full case mappings are applied by the string case mapping functions, + * see ustring.h and the UnicodeString class. + * See also the User Guide chapter on C/POSIX migration: + * http://icu-project.org/userguide/posix.html#case_mappings + * + * @param c the code point to be mapped + * @return the Simple_Lowercase_Mapping of the code point, if any; + * otherwise the code point itself. + * @stable ICU 2.0 + */ +U_CAPI UChar32 U_EXPORT2 +u_tolower(UChar32 c); + +/** + * The given character is mapped to its uppercase equivalent according to UnicodeData.txt; + * if the character has no uppercase equivalent, the character itself is + * returned. + * + * Same as java.lang.Character.toUpperCase(). + * + * This function only returns the simple, single-code point case mapping. + * Full case mappings should be used whenever possible because they produce + * better results by working on whole strings. + * They take into account the string context and the language and can map + * to a result string with a different length as appropriate. + * Full case mappings are applied by the string case mapping functions, + * see ustring.h and the UnicodeString class. + * See also the User Guide chapter on C/POSIX migration: + * http://icu-project.org/userguide/posix.html#case_mappings + * + * @param c the code point to be mapped + * @return the Simple_Uppercase_Mapping of the code point, if any; + * otherwise the code point itself. + * @stable ICU 2.0 + */ +U_CAPI UChar32 U_EXPORT2 +u_toupper(UChar32 c); + +/** + * The given character is mapped to its titlecase equivalent + * according to UnicodeData.txt; + * if none is defined, the character itself is returned. + * + * Same as java.lang.Character.toTitleCase(). + * + * This function only returns the simple, single-code point case mapping. + * Full case mappings should be used whenever possible because they produce + * better results by working on whole strings. + * They take into account the string context and the language and can map + * to a result string with a different length as appropriate. + * Full case mappings are applied by the string case mapping functions, + * see ustring.h and the UnicodeString class. + * See also the User Guide chapter on C/POSIX migration: + * http://icu-project.org/userguide/posix.html#case_mappings + * + * @param c the code point to be mapped + * @return the Simple_Titlecase_Mapping of the code point, if any; + * otherwise the code point itself. + * @stable ICU 2.0 + */ +U_CAPI UChar32 U_EXPORT2 +u_totitle(UChar32 c); + +/** + * The given character is mapped to its case folding equivalent according to + * UnicodeData.txt and CaseFolding.txt; + * if the character has no case folding equivalent, the character + * itself is returned. + * + * This function only returns the simple, single-code point case mapping. + * Full case mappings should be used whenever possible because they produce + * better results by working on whole strings. + * They take into account the string context and the language and can map + * to a result string with a different length as appropriate. + * Full case mappings are applied by the string case mapping functions, + * see ustring.h and the UnicodeString class. + * See also the User Guide chapter on C/POSIX migration: + * http://icu-project.org/userguide/posix.html#case_mappings + * + * @param c the code point to be mapped + * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I + * @return the Simple_Case_Folding of the code point, if any; + * otherwise the code point itself. + * @stable ICU 2.0 + */ +U_CAPI UChar32 U_EXPORT2 +u_foldCase(UChar32 c, uint32_t options); + +/** + * Returns the decimal digit value of the code point in the + * specified radix. + * + * If the radix is not in the range <code>2<=radix<=36</code> or if the + * value of <code>c</code> is not a valid digit in the specified + * radix, <code>-1</code> is returned. A character is a valid digit + * if at least one of the following is true: + * <ul> + * <li>The character has a decimal digit value. + * Such characters have the general category "Nd" (decimal digit numbers) + * and a Numeric_Type of Decimal. + * In this case the value is the character's decimal digit value.</li> + * <li>The character is one of the uppercase Latin letters + * <code>'A'</code> through <code>'Z'</code>. + * In this case the value is <code>c-'A'+10</code>.</li> + * <li>The character is one of the lowercase Latin letters + * <code>'a'</code> through <code>'z'</code>. + * In this case the value is <code>ch-'a'+10</code>.</li> + * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A) + * as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) + * are recognized.</li> + * </ul> + * + * Same as java.lang.Character.digit(). + * + * @param ch the code point to be tested. + * @param radix the radix. + * @return the numeric value represented by the character in the + * specified radix, + * or -1 if there is no value or if the value exceeds the radix. + * + * @see UCHAR_NUMERIC_TYPE + * @see u_forDigit + * @see u_charDigitValue + * @see u_isdigit + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_digit(UChar32 ch, int8_t radix); + +/** + * Determines the character representation for a specific digit in + * the specified radix. If the value of <code>radix</code> is not a + * valid radix, or the value of <code>digit</code> is not a valid + * digit in the specified radix, the null character + * (<code>U+0000</code>) is returned. + * <p> + * The <code>radix</code> argument is valid if it is greater than or + * equal to 2 and less than or equal to 36. + * The <code>digit</code> argument is valid if + * <code>0 <= digit < radix</code>. + * <p> + * If the digit is less than 10, then + * <code>'0' + digit</code> is returned. Otherwise, the value + * <code>'a' + digit - 10</code> is returned. + * + * Same as java.lang.Character.forDigit(). + * + * @param digit the number to convert to a character. + * @param radix the radix. + * @return the <code>char</code> representation of the specified digit + * in the specified radix. + * + * @see u_digit + * @see u_charDigitValue + * @see u_isdigit + * @stable ICU 2.0 + */ +U_CAPI UChar32 U_EXPORT2 +u_forDigit(int32_t digit, int8_t radix); + +/** + * Get the "age" of the code point. + * The "age" is the Unicode version when the code point was first + * designated (as a non-character or for Private Use) + * or assigned a character. + * This can be useful to avoid emitting code points to receiving + * processes that do not accept newer characters. + * The data is from the UCD file DerivedAge.txt. + * + * @param c The code point. + * @param versionArray The Unicode version number array, to be filled in. + * + * @stable ICU 2.1 + */ +U_CAPI void U_EXPORT2 +u_charAge(UChar32 c, UVersionInfo versionArray); + +/** + * Gets the Unicode version information. + * The version array is filled in with the version information + * for the Unicode standard that is currently used by ICU. + * For example, Unicode version 3.1.1 is represented as an array with + * the values { 3, 1, 1, 0 }. + * + * @param versionArray an output array that will be filled in with + * the Unicode version number + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +u_getUnicodeVersion(UVersionInfo versionArray); + +#if !UCONFIG_NO_NORMALIZATION +/** + * Get the FC_NFKC_Closure property string for a character. + * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" + * or for "FNC": http://www.unicode.org/reports/tr15/ + * + * @param c The character (code point) for which to get the FC_NFKC_Closure string. + * It must be <code>0<=c<=0x10ffff</code>. + * @param dest Destination address for copying the string. + * The string will be zero-terminated if possible. + * If there is no FC_NFKC_Closure string, + * then the buffer will be set to the empty string. + * @param destCapacity <code>==sizeof(dest)</code> + * @param pErrorCode Pointer to a UErrorCode variable. + * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. + * If the destCapacity is less than or equal to the length, then the buffer + * contains the truncated name and the returned length indicates the full + * length of the name. + * The length does not include the zero-termination. + * + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode); + +#endif + + +U_CDECL_END + +#endif /*_UCHAR*/ +/*eof*/ diff --git a/thirdparty/icu4c/common/unicode/ucharstrie.h b/thirdparty/icu4c/common/unicode/ucharstrie.h new file mode 100644 index 0000000000..b6f9e3e075 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucharstrie.h @@ -0,0 +1,623 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2010-2012, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: ucharstrie.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2010nov14 +* created by: Markus W. Scherer +*/ + +#ifndef __UCHARSTRIE_H__ +#define __UCHARSTRIE_H__ + +/** + * \file + * \brief C++ API: Trie for mapping Unicode strings (or 16-bit-unit sequences) + * to integer values. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/unistr.h" +#include "unicode/uobject.h" +#include "unicode/ustringtrie.h" + +U_NAMESPACE_BEGIN + +class Appendable; +class UCharsTrieBuilder; +class UVector32; + +/** + * Light-weight, non-const reader class for a UCharsTrie. + * Traverses a char16_t-serialized data structure with minimal state, + * for mapping strings (16-bit-unit sequences) to non-negative integer values. + * + * This class owns the serialized trie data only if it was constructed by + * the builder's build() method. + * The public constructor and the copy constructor only alias the data (only copy the pointer). + * There is no assignment operator. + * + * This class is not intended for public subclassing. + * @stable ICU 4.8 + */ +class U_COMMON_API UCharsTrie : public UMemory { +public: + /** + * Constructs a UCharsTrie reader instance. + * + * The trieUChars must contain a copy of a char16_t sequence from the UCharsTrieBuilder, + * starting with the first char16_t of that sequence. + * The UCharsTrie object will not read more char16_ts than + * the UCharsTrieBuilder generated in the corresponding build() call. + * + * The array is not copied/cloned and must not be modified while + * the UCharsTrie object is in use. + * + * @param trieUChars The char16_t array that contains the serialized trie. + * @stable ICU 4.8 + */ + UCharsTrie(ConstChar16Ptr trieUChars) + : ownedArray_(NULL), uchars_(trieUChars), + pos_(uchars_), remainingMatchLength_(-1) {} + + /** + * Destructor. + * @stable ICU 4.8 + */ + ~UCharsTrie(); + + /** + * Copy constructor, copies the other trie reader object and its state, + * but not the char16_t array which will be shared. (Shallow copy.) + * @param other Another UCharsTrie object. + * @stable ICU 4.8 + */ + UCharsTrie(const UCharsTrie &other) + : ownedArray_(NULL), uchars_(other.uchars_), + pos_(other.pos_), remainingMatchLength_(other.remainingMatchLength_) {} + + /** + * Resets this trie to its initial state. + * @return *this + * @stable ICU 4.8 + */ + UCharsTrie &reset() { + pos_=uchars_; + remainingMatchLength_=-1; + return *this; + } + + /** + * Returns the state of this trie as a 64-bit integer. + * The state value is never 0. + * + * @return opaque state value + * @see resetToState64 + * @stable ICU 65 + */ + uint64_t getState64() const { + return (static_cast<uint64_t>(remainingMatchLength_ + 2) << kState64RemainingShift) | + (uint64_t)(pos_ - uchars_); + } + + /** + * Resets this trie to the saved state. + * Unlike resetToState(State), the 64-bit state value + * must be from getState64() from the same trie object or + * from one initialized the exact same way. + * Because of no validation, this method is faster. + * + * @param state The opaque trie state value from getState64(). + * @return *this + * @see getState64 + * @see resetToState + * @see reset + * @stable ICU 65 + */ + UCharsTrie &resetToState64(uint64_t state) { + remainingMatchLength_ = static_cast<int32_t>(state >> kState64RemainingShift) - 2; + pos_ = uchars_ + (state & kState64PosMask); + return *this; + } + + /** + * UCharsTrie state object, for saving a trie's current state + * and resetting the trie back to this state later. + * @stable ICU 4.8 + */ + class State : public UMemory { + public: + /** + * Constructs an empty State. + * @stable ICU 4.8 + */ + State() { uchars=NULL; } + private: + friend class UCharsTrie; + + const char16_t *uchars; + const char16_t *pos; + int32_t remainingMatchLength; + }; + + /** + * Saves the state of this trie. + * @param state The State object to hold the trie's state. + * @return *this + * @see resetToState + * @stable ICU 4.8 + */ + const UCharsTrie &saveState(State &state) const { + state.uchars=uchars_; + state.pos=pos_; + state.remainingMatchLength=remainingMatchLength_; + return *this; + } + + /** + * Resets this trie to the saved state. + * If the state object contains no state, or the state of a different trie, + * then this trie remains unchanged. + * @param state The State object which holds a saved trie state. + * @return *this + * @see saveState + * @see reset + * @stable ICU 4.8 + */ + UCharsTrie &resetToState(const State &state) { + if(uchars_==state.uchars && uchars_!=NULL) { + pos_=state.pos; + remainingMatchLength_=state.remainingMatchLength; + } + return *this; + } + + /** + * Determines whether the string so far matches, whether it has a value, + * and whether another input char16_t can continue a matching string. + * @return The match/value Result. + * @stable ICU 4.8 + */ + UStringTrieResult current() const; + + /** + * Traverses the trie from the initial state for this input char16_t. + * Equivalent to reset().next(uchar). + * @param uchar Input char value. Values below 0 and above 0xffff will never match. + * @return The match/value Result. + * @stable ICU 4.8 + */ + inline UStringTrieResult first(int32_t uchar) { + remainingMatchLength_=-1; + return nextImpl(uchars_, uchar); + } + + /** + * Traverses the trie from the initial state for the + * one or two UTF-16 code units for this input code point. + * Equivalent to reset().nextForCodePoint(cp). + * @param cp A Unicode code point 0..0x10ffff. + * @return The match/value Result. + * @stable ICU 4.8 + */ + UStringTrieResult firstForCodePoint(UChar32 cp); + + /** + * Traverses the trie from the current state for this input char16_t. + * @param uchar Input char value. Values below 0 and above 0xffff will never match. + * @return The match/value Result. + * @stable ICU 4.8 + */ + UStringTrieResult next(int32_t uchar); + + /** + * Traverses the trie from the current state for the + * one or two UTF-16 code units for this input code point. + * @param cp A Unicode code point 0..0x10ffff. + * @return The match/value Result. + * @stable ICU 4.8 + */ + UStringTrieResult nextForCodePoint(UChar32 cp); + + /** + * Traverses the trie from the current state for this string. + * Equivalent to + * \code + * Result result=current(); + * for(each c in s) + * if(!USTRINGTRIE_HAS_NEXT(result)) return USTRINGTRIE_NO_MATCH; + * result=next(c); + * return result; + * \endcode + * @param s A string. Can be NULL if length is 0. + * @param length The length of the string. Can be -1 if NUL-terminated. + * @return The match/value Result. + * @stable ICU 4.8 + */ + UStringTrieResult next(ConstChar16Ptr s, int32_t length); + + /** + * Returns a matching string's value if called immediately after + * current()/first()/next() returned USTRINGTRIE_INTERMEDIATE_VALUE or USTRINGTRIE_FINAL_VALUE. + * getValue() can be called multiple times. + * + * Do not call getValue() after USTRINGTRIE_NO_MATCH or USTRINGTRIE_NO_VALUE! + * @return The value for the string so far. + * @stable ICU 4.8 + */ + inline int32_t getValue() const { + const char16_t *pos=pos_; + int32_t leadUnit=*pos++; + // U_ASSERT(leadUnit>=kMinValueLead); + return leadUnit&kValueIsFinal ? + readValue(pos, leadUnit&0x7fff) : readNodeValue(pos, leadUnit); + } + + /** + * Determines whether all strings reachable from the current state + * map to the same value. + * @param uniqueValue Receives the unique value, if this function returns true. + * (output-only) + * @return true if all strings reachable from the current state + * map to the same value. + * @stable ICU 4.8 + */ + inline UBool hasUniqueValue(int32_t &uniqueValue) const { + const char16_t *pos=pos_; + // Skip the rest of a pending linear-match node. + return pos!=NULL && findUniqueValue(pos+remainingMatchLength_+1, false, uniqueValue); + } + + /** + * Finds each char16_t which continues the string from the current state. + * That is, each char16_t c for which it would be next(c)!=USTRINGTRIE_NO_MATCH now. + * @param out Each next char16_t is appended to this object. + * @return the number of char16_ts which continue the string from here + * @stable ICU 4.8 + */ + int32_t getNextUChars(Appendable &out) const; + + /** + * Iterator for all of the (string, value) pairs in a UCharsTrie. + * @stable ICU 4.8 + */ + class U_COMMON_API Iterator : public UMemory { + public: + /** + * Iterates from the root of a char16_t-serialized UCharsTrie. + * @param trieUChars The trie char16_ts. + * @param maxStringLength If 0, the iterator returns full strings. + * Otherwise, the iterator returns strings with this maximum length. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @stable ICU 4.8 + */ + Iterator(ConstChar16Ptr trieUChars, int32_t maxStringLength, UErrorCode &errorCode); + + /** + * Iterates from the current state of the specified UCharsTrie. + * @param trie The trie whose state will be copied for iteration. + * @param maxStringLength If 0, the iterator returns full strings. + * Otherwise, the iterator returns strings with this maximum length. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @stable ICU 4.8 + */ + Iterator(const UCharsTrie &trie, int32_t maxStringLength, UErrorCode &errorCode); + + /** + * Destructor. + * @stable ICU 4.8 + */ + ~Iterator(); + + /** + * Resets this iterator to its initial state. + * @return *this + * @stable ICU 4.8 + */ + Iterator &reset(); + + /** + * @return true if there are more elements. + * @stable ICU 4.8 + */ + UBool hasNext() const; + + /** + * Finds the next (string, value) pair if there is one. + * + * If the string is truncated to the maximum length and does not + * have a real value, then the value is set to -1. + * In this case, this "not a real value" is indistinguishable from + * a real value of -1. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return true if there is another element. + * @stable ICU 4.8 + */ + UBool next(UErrorCode &errorCode); + + /** + * @return The string for the last successful next(). + * @stable ICU 4.8 + */ + const UnicodeString &getString() const { return str_; } + /** + * @return The value for the last successful next(). + * @stable ICU 4.8 + */ + int32_t getValue() const { return value_; } + + private: + UBool truncateAndStop() { + pos_=NULL; + value_=-1; // no real value for str + return true; + } + + const char16_t *branchNext(const char16_t *pos, int32_t length, UErrorCode &errorCode); + + const char16_t *uchars_; + const char16_t *pos_; + const char16_t *initialPos_; + int32_t remainingMatchLength_; + int32_t initialRemainingMatchLength_; + UBool skipValue_; // Skip intermediate value which was already delivered. + + UnicodeString str_; + int32_t maxLength_; + int32_t value_; + + // The stack stores pairs of integers for backtracking to another + // outbound edge of a branch node. + // The first integer is an offset from uchars_. + // The second integer has the str_.length() from before the node in bits 15..0, + // and the remaining branch length in bits 31..16. + // (We could store the remaining branch length minus 1 in bits 30..16 and not use the sign bit, + // but the code looks more confusing that way.) + UVector32 *stack_; + }; + +private: + friend class UCharsTrieBuilder; + + /** + * Constructs a UCharsTrie reader instance. + * Unlike the public constructor which just aliases an array, + * this constructor adopts the builder's array. + * This constructor is only called by the builder. + */ + UCharsTrie(char16_t *adoptUChars, const char16_t *trieUChars) + : ownedArray_(adoptUChars), uchars_(trieUChars), + pos_(uchars_), remainingMatchLength_(-1) {} + + // No assignment operator. + UCharsTrie &operator=(const UCharsTrie &other); + + inline void stop() { + pos_=NULL; + } + + // Reads a compact 32-bit integer. + // pos is already after the leadUnit, and the lead unit has bit 15 reset. + static inline int32_t readValue(const char16_t *pos, int32_t leadUnit) { + int32_t value; + if(leadUnit<kMinTwoUnitValueLead) { + value=leadUnit; + } else if(leadUnit<kThreeUnitValueLead) { + value=((leadUnit-kMinTwoUnitValueLead)<<16)|*pos; + } else { + value=(pos[0]<<16)|pos[1]; + } + return value; + } + static inline const char16_t *skipValue(const char16_t *pos, int32_t leadUnit) { + if(leadUnit>=kMinTwoUnitValueLead) { + if(leadUnit<kThreeUnitValueLead) { + ++pos; + } else { + pos+=2; + } + } + return pos; + } + static inline const char16_t *skipValue(const char16_t *pos) { + int32_t leadUnit=*pos++; + return skipValue(pos, leadUnit&0x7fff); + } + + static inline int32_t readNodeValue(const char16_t *pos, int32_t leadUnit) { + // U_ASSERT(kMinValueLead<=leadUnit && leadUnit<kValueIsFinal); + int32_t value; + if(leadUnit<kMinTwoUnitNodeValueLead) { + value=(leadUnit>>6)-1; + } else if(leadUnit<kThreeUnitNodeValueLead) { + value=(((leadUnit&0x7fc0)-kMinTwoUnitNodeValueLead)<<10)|*pos; + } else { + value=(pos[0]<<16)|pos[1]; + } + return value; + } + static inline const char16_t *skipNodeValue(const char16_t *pos, int32_t leadUnit) { + // U_ASSERT(kMinValueLead<=leadUnit && leadUnit<kValueIsFinal); + if(leadUnit>=kMinTwoUnitNodeValueLead) { + if(leadUnit<kThreeUnitNodeValueLead) { + ++pos; + } else { + pos+=2; + } + } + return pos; + } + + static inline const char16_t *jumpByDelta(const char16_t *pos) { + int32_t delta=*pos++; + if(delta>=kMinTwoUnitDeltaLead) { + if(delta==kThreeUnitDeltaLead) { + delta=(pos[0]<<16)|pos[1]; + pos+=2; + } else { + delta=((delta-kMinTwoUnitDeltaLead)<<16)|*pos++; + } + } + return pos+delta; + } + + static const char16_t *skipDelta(const char16_t *pos) { + int32_t delta=*pos++; + if(delta>=kMinTwoUnitDeltaLead) { + if(delta==kThreeUnitDeltaLead) { + pos+=2; + } else { + ++pos; + } + } + return pos; + } + + static inline UStringTrieResult valueResult(int32_t node) { + return (UStringTrieResult)(USTRINGTRIE_INTERMEDIATE_VALUE-(node>>15)); + } + + // Handles a branch node for both next(uchar) and next(string). + UStringTrieResult branchNext(const char16_t *pos, int32_t length, int32_t uchar); + + // Requires remainingLength_<0. + UStringTrieResult nextImpl(const char16_t *pos, int32_t uchar); + + // Helper functions for hasUniqueValue(). + // Recursively finds a unique value (or whether there is not a unique one) + // from a branch. + static const char16_t *findUniqueValueFromBranch(const char16_t *pos, int32_t length, + UBool haveUniqueValue, int32_t &uniqueValue); + // Recursively finds a unique value (or whether there is not a unique one) + // starting from a position on a node lead unit. + static UBool findUniqueValue(const char16_t *pos, UBool haveUniqueValue, int32_t &uniqueValue); + + // Helper functions for getNextUChars(). + // getNextUChars() when pos is on a branch node. + static void getNextBranchUChars(const char16_t *pos, int32_t length, Appendable &out); + + // UCharsTrie data structure + // + // The trie consists of a series of char16_t-serialized nodes for incremental + // Unicode string/char16_t sequence matching. (char16_t=16-bit unsigned integer) + // The root node is at the beginning of the trie data. + // + // Types of nodes are distinguished by their node lead unit ranges. + // After each node, except a final-value node, another node follows to + // encode match values or continue matching further units. + // + // Node types: + // - Final-value node: Stores a 32-bit integer in a compact, variable-length format. + // The value is for the string/char16_t sequence so far. + // - Match node, optionally with an intermediate value in a different compact format. + // The value, if present, is for the string/char16_t sequence so far. + // + // Aside from the value, which uses the node lead unit's high bits: + // + // - Linear-match node: Matches a number of units. + // - Branch node: Branches to other nodes according to the current input unit. + // The node unit is the length of the branch (number of units to select from) + // minus 1. It is followed by a sub-node: + // - If the length is at most kMaxBranchLinearSubNodeLength, then + // there are length-1 (key, value) pairs and then one more comparison unit. + // If one of the key units matches, then the value is either a final value for + // the string so far, or a "jump" delta to the next node. + // If the last unit matches, then matching continues with the next node. + // (Values have the same encoding as final-value nodes.) + // - If the length is greater than kMaxBranchLinearSubNodeLength, then + // there is one unit and one "jump" delta. + // If the input unit is less than the sub-node unit, then "jump" by delta to + // the next sub-node which will have a length of length/2. + // (The delta has its own compact encoding.) + // Otherwise, skip the "jump" delta to the next sub-node + // which will have a length of length-length/2. + + // Match-node lead unit values, after masking off intermediate-value bits: + + // 0000..002f: Branch node. If node!=0 then the length is node+1, otherwise + // the length is one more than the next unit. + + // For a branch sub-node with at most this many entries, we drop down + // to a linear search. + static const int32_t kMaxBranchLinearSubNodeLength=5; + + // 0030..003f: Linear-match node, match 1..16 units and continue reading the next node. + static const int32_t kMinLinearMatch=0x30; + static const int32_t kMaxLinearMatchLength=0x10; + + // Match-node lead unit bits 14..6 for the optional intermediate value. + // If these bits are 0, then there is no intermediate value. + // Otherwise, see the *NodeValue* constants below. + static const int32_t kMinValueLead=kMinLinearMatch+kMaxLinearMatchLength; // 0x0040 + static const int32_t kNodeTypeMask=kMinValueLead-1; // 0x003f + + // A final-value node has bit 15 set. + static const int32_t kValueIsFinal=0x8000; + + // Compact value: After testing and masking off bit 15, use the following thresholds. + static const int32_t kMaxOneUnitValue=0x3fff; + + static const int32_t kMinTwoUnitValueLead=kMaxOneUnitValue+1; // 0x4000 + static const int32_t kThreeUnitValueLead=0x7fff; + + static const int32_t kMaxTwoUnitValue=((kThreeUnitValueLead-kMinTwoUnitValueLead)<<16)-1; // 0x3ffeffff + + // Compact intermediate-value integer, lead unit shared with a branch or linear-match node. + static const int32_t kMaxOneUnitNodeValue=0xff; + static const int32_t kMinTwoUnitNodeValueLead=kMinValueLead+((kMaxOneUnitNodeValue+1)<<6); // 0x4040 + static const int32_t kThreeUnitNodeValueLead=0x7fc0; + + static const int32_t kMaxTwoUnitNodeValue= + ((kThreeUnitNodeValueLead-kMinTwoUnitNodeValueLead)<<10)-1; // 0xfdffff + + // Compact delta integers. + static const int32_t kMaxOneUnitDelta=0xfbff; + static const int32_t kMinTwoUnitDeltaLead=kMaxOneUnitDelta+1; // 0xfc00 + static const int32_t kThreeUnitDeltaLead=0xffff; + + static const int32_t kMaxTwoUnitDelta=((kThreeUnitDeltaLead-kMinTwoUnitDeltaLead)<<16)-1; // 0x03feffff + + // For getState64(): + // The remainingMatchLength_ is -1..14=(kMaxLinearMatchLength=0x10)-2 + // so we need at least 5 bits for that. + // We add 2 to store it as a positive value 1..16=kMaxLinearMatchLength. + static constexpr int32_t kState64RemainingShift = 59; + static constexpr uint64_t kState64PosMask = (UINT64_C(1) << kState64RemainingShift) - 1; + + char16_t *ownedArray_; + + // Fixed value referencing the UCharsTrie words. + const char16_t *uchars_; + + // Iterator variables. + + // Pointer to next trie unit to read. NULL if no more matches. + const char16_t *pos_; + // Remaining length of a linear-match node, minus 1. Negative if not in such a node. + int32_t remainingMatchLength_; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __UCHARSTRIE_H__ diff --git a/thirdparty/icu4c/common/unicode/ucharstriebuilder.h b/thirdparty/icu4c/common/unicode/ucharstriebuilder.h new file mode 100644 index 0000000000..15657702f9 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucharstriebuilder.h @@ -0,0 +1,193 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2010-2016, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: ucharstriebuilder.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2010nov14 +* created by: Markus W. Scherer +*/ + +#ifndef __UCHARSTRIEBUILDER_H__ +#define __UCHARSTRIEBUILDER_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/stringtriebuilder.h" +#include "unicode/ucharstrie.h" +#include "unicode/unistr.h" + +/** + * \file + * \brief C++ API: Builder for icu::UCharsTrie + */ + +U_NAMESPACE_BEGIN + +class UCharsTrieElement; + +/** + * Builder class for UCharsTrie. + * + * This class is not intended for public subclassing. + * @stable ICU 4.8 + */ +class U_COMMON_API UCharsTrieBuilder : public StringTrieBuilder { +public: + /** + * Constructs an empty builder. + * @param errorCode Standard ICU error code. + * @stable ICU 4.8 + */ + UCharsTrieBuilder(UErrorCode &errorCode); + + /** + * Destructor. + * @stable ICU 4.8 + */ + virtual ~UCharsTrieBuilder(); + + /** + * Adds a (string, value) pair. + * The string must be unique. + * The string contents will be copied; the builder does not keep + * a reference to the input UnicodeString or its buffer. + * @param s The input string. + * @param value The value associated with this string. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return *this + * @stable ICU 4.8 + */ + UCharsTrieBuilder &add(const UnicodeString &s, int32_t value, UErrorCode &errorCode); + + /** + * Builds a UCharsTrie for the add()ed data. + * Once built, no further data can be add()ed until clear() is called. + * + * A UCharsTrie cannot be empty. At least one (string, value) pair + * must have been add()ed. + * + * This method passes ownership of the builder's internal result array to the new trie object. + * Another call to any build() variant will re-serialize the trie. + * After clear() has been called, a new array will be used as well. + * @param buildOption Build option, see UStringTrieBuildOption. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return A new UCharsTrie for the add()ed data. + * @stable ICU 4.8 + */ + UCharsTrie *build(UStringTrieBuildOption buildOption, UErrorCode &errorCode); + + /** + * Builds a UCharsTrie for the add()ed data and char16_t-serializes it. + * Once built, no further data can be add()ed until clear() is called. + * + * A UCharsTrie cannot be empty. At least one (string, value) pair + * must have been add()ed. + * + * Multiple calls to buildUnicodeString() set the UnicodeStrings to the + * builder's same char16_t array, without rebuilding. + * If buildUnicodeString() is called after build(), the trie will be + * re-serialized into a new array (because build() passes on ownership). + * If build() is called after buildUnicodeString(), the trie object returned + * by build() will become the owner of the underlying data for the + * previously returned UnicodeString. + * After clear() has been called, a new array will be used as well. + * @param buildOption Build option, see UStringTrieBuildOption. + * @param result A UnicodeString which will be set to the char16_t-serialized + * UCharsTrie for the add()ed data. + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return result + * @stable ICU 4.8 + */ + UnicodeString &buildUnicodeString(UStringTrieBuildOption buildOption, UnicodeString &result, + UErrorCode &errorCode); + + /** + * Removes all (string, value) pairs. + * New data can then be add()ed and a new trie can be built. + * @return *this + * @stable ICU 4.8 + */ + UCharsTrieBuilder &clear() { + strings.remove(); + elementsLength=0; + ucharsLength=0; + return *this; + } + +private: + UCharsTrieBuilder(const UCharsTrieBuilder &other); // no copy constructor + UCharsTrieBuilder &operator=(const UCharsTrieBuilder &other); // no assignment operator + + void buildUChars(UStringTrieBuildOption buildOption, UErrorCode &errorCode); + + virtual int32_t getElementStringLength(int32_t i) const; + virtual char16_t getElementUnit(int32_t i, int32_t unitIndex) const; + virtual int32_t getElementValue(int32_t i) const; + + virtual int32_t getLimitOfLinearMatch(int32_t first, int32_t last, int32_t unitIndex) const; + + virtual int32_t countElementUnits(int32_t start, int32_t limit, int32_t unitIndex) const; + virtual int32_t skipElementsBySomeUnits(int32_t i, int32_t unitIndex, int32_t count) const; + virtual int32_t indexOfElementWithNextUnit(int32_t i, int32_t unitIndex, char16_t unit) const; + + virtual UBool matchNodesCanHaveValues() const { return true; } + + virtual int32_t getMaxBranchLinearSubNodeLength() const { return UCharsTrie::kMaxBranchLinearSubNodeLength; } + virtual int32_t getMinLinearMatch() const { return UCharsTrie::kMinLinearMatch; } + virtual int32_t getMaxLinearMatchLength() const { return UCharsTrie::kMaxLinearMatchLength; } + + class UCTLinearMatchNode : public LinearMatchNode { + public: + UCTLinearMatchNode(const char16_t *units, int32_t len, Node *nextNode); + virtual UBool operator==(const Node &other) const; + virtual void write(StringTrieBuilder &builder); + private: + const char16_t *s; + }; + + virtual Node *createLinearMatchNode(int32_t i, int32_t unitIndex, int32_t length, + Node *nextNode) const; + + UBool ensureCapacity(int32_t length); + virtual int32_t write(int32_t unit); + int32_t write(const char16_t *s, int32_t length); + virtual int32_t writeElementUnits(int32_t i, int32_t unitIndex, int32_t length); + virtual int32_t writeValueAndFinal(int32_t i, UBool isFinal); + virtual int32_t writeValueAndType(UBool hasValue, int32_t value, int32_t node); + virtual int32_t writeDeltaTo(int32_t jumpTarget); + + UnicodeString strings; + UCharsTrieElement *elements; + int32_t elementsCapacity; + int32_t elementsLength; + + // char16_t serialization of the trie. + // Grows from the back: ucharsLength measures from the end of the buffer! + char16_t *uchars; + int32_t ucharsCapacity; + int32_t ucharsLength; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif // __UCHARSTRIEBUILDER_H__ diff --git a/thirdparty/icu4c/common/unicode/uchriter.h b/thirdparty/icu4c/common/unicode/uchriter.h new file mode 100644 index 0000000000..f5083561a8 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uchriter.h @@ -0,0 +1,393 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1998-2005, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +*/ + +#ifndef UCHRITER_H +#define UCHRITER_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/chariter.h" + +/** + * \file + * \brief C++ API: char16_t Character Iterator + */ + +U_NAMESPACE_BEGIN + +/** + * A concrete subclass of CharacterIterator that iterates over the + * characters (code units or code points) in a char16_t array. + * It's possible not only to create an + * iterator that iterates over an entire char16_t array, but also to + * create one that iterates over only a subrange of a char16_t array + * (iterators over different subranges of the same char16_t array don't + * compare equal). + * @see CharacterIterator + * @see ForwardCharacterIterator + * @stable ICU 2.0 + */ +class U_COMMON_API UCharCharacterIterator : public CharacterIterator { +public: + /** + * Create an iterator over the char16_t array referred to by "textPtr". + * The iteration range is 0 to <code>length-1</code>. + * text is only aliased, not adopted (the + * destructor will not delete it). + * @param textPtr The char16_t array to be iterated over + * @param length The length of the char16_t array + * @stable ICU 2.0 + */ + UCharCharacterIterator(ConstChar16Ptr textPtr, int32_t length); + + /** + * Create an iterator over the char16_t array referred to by "textPtr". + * The iteration range is 0 to <code>length-1</code>. + * text is only aliased, not adopted (the + * destructor will not delete it). + * The starting + * position is specified by "position". If "position" is outside the valid + * iteration range, the behavior of this object is undefined. + * @param textPtr The char16_t array to be iteratd over + * @param length The length of the char16_t array + * @param position The starting position of the iteration + * @stable ICU 2.0 + */ + UCharCharacterIterator(ConstChar16Ptr textPtr, int32_t length, + int32_t position); + + /** + * Create an iterator over the char16_t array referred to by "textPtr". + * The iteration range is 0 to <code>end-1</code>. + * text is only aliased, not adopted (the + * destructor will not delete it). + * The starting + * position is specified by "position". If begin and end do not + * form a valid iteration range or "position" is outside the valid + * iteration range, the behavior of this object is undefined. + * @param textPtr The char16_t array to be iterated over + * @param length The length of the char16_t array + * @param textBegin The begin position of the iteration range + * @param textEnd The end position of the iteration range + * @param position The starting position of the iteration + * @stable ICU 2.0 + */ + UCharCharacterIterator(ConstChar16Ptr textPtr, int32_t length, + int32_t textBegin, + int32_t textEnd, + int32_t position); + + /** + * Copy constructor. The new iterator iterates over the same range + * of the same string as "that", and its initial position is the + * same as "that"'s current position. + * @param that The UCharCharacterIterator to be copied + * @stable ICU 2.0 + */ + UCharCharacterIterator(const UCharCharacterIterator& that); + + /** + * Destructor. + * @stable ICU 2.0 + */ + virtual ~UCharCharacterIterator(); + + /** + * Assignment operator. *this is altered to iterate over the sane + * range of the same string as "that", and refers to the same + * character within that string as "that" does. + * @param that The object to be copied + * @return the newly created object + * @stable ICU 2.0 + */ + UCharCharacterIterator& + operator=(const UCharCharacterIterator& that); + + /** + * Returns true if the iterators iterate over the same range of the + * same string and are pointing at the same character. + * @param that The ForwardCharacterIterator used to be compared for equality + * @return true if the iterators iterate over the same range of the + * same string and are pointing at the same character. + * @stable ICU 2.0 + */ + virtual UBool operator==(const ForwardCharacterIterator& that) const; + + /** + * Generates a hash code for this iterator. + * @return the hash code. + * @stable ICU 2.0 + */ + virtual int32_t hashCode(void) const; + + /** + * Returns a new UCharCharacterIterator referring to the same + * character in the same range of the same string as this one. The + * caller must delete the new iterator. + * @return the CharacterIterator newly created + * @stable ICU 2.0 + */ + virtual UCharCharacterIterator* clone() const; + + /** + * Sets the iterator to refer to the first code unit in its + * iteration range, and returns that code unit. + * This can be used to begin an iteration with next(). + * @return the first code unit in its iteration range. + * @stable ICU 2.0 + */ + virtual char16_t first(void); + + /** + * Sets the iterator to refer to the first code unit in its + * iteration range, returns that code unit, and moves the position + * to the second code unit. This is an alternative to setToStart() + * for forward iteration with nextPostInc(). + * @return the first code unit in its iteration range + * @stable ICU 2.0 + */ + virtual char16_t firstPostInc(void); + + /** + * Sets the iterator to refer to the first code point in its + * iteration range, and returns that code unit, + * This can be used to begin an iteration with next32(). + * Note that an iteration with next32PostInc(), beginning with, + * e.g., setToStart() or firstPostInc(), is more efficient. + * @return the first code point in its iteration range + * @stable ICU 2.0 + */ + virtual UChar32 first32(void); + + /** + * Sets the iterator to refer to the first code point in its + * iteration range, returns that code point, and moves the position + * to the second code point. This is an alternative to setToStart() + * for forward iteration with next32PostInc(). + * @return the first code point in its iteration range. + * @stable ICU 2.0 + */ + virtual UChar32 first32PostInc(void); + + /** + * Sets the iterator to refer to the last code unit in its + * iteration range, and returns that code unit. + * This can be used to begin an iteration with previous(). + * @return the last code unit in its iteration range. + * @stable ICU 2.0 + */ + virtual char16_t last(void); + + /** + * Sets the iterator to refer to the last code point in its + * iteration range, and returns that code unit. + * This can be used to begin an iteration with previous32(). + * @return the last code point in its iteration range. + * @stable ICU 2.0 + */ + virtual UChar32 last32(void); + + /** + * Sets the iterator to refer to the "position"-th code unit + * in the text-storage object the iterator refers to, and + * returns that code unit. + * @param position the position within the text-storage object + * @return the code unit + * @stable ICU 2.0 + */ + virtual char16_t setIndex(int32_t position); + + /** + * Sets the iterator to refer to the beginning of the code point + * that contains the "position"-th code unit + * in the text-storage object the iterator refers to, and + * returns that code point. + * The current position is adjusted to the beginning of the code point + * (its first code unit). + * @param position the position within the text-storage object + * @return the code unit + * @stable ICU 2.0 + */ + virtual UChar32 setIndex32(int32_t position); + + /** + * Returns the code unit the iterator currently refers to. + * @return the code unit the iterator currently refers to. + * @stable ICU 2.0 + */ + virtual char16_t current(void) const; + + /** + * Returns the code point the iterator currently refers to. + * @return the code point the iterator currently refers to. + * @stable ICU 2.0 + */ + virtual UChar32 current32(void) const; + + /** + * Advances to the next code unit in the iteration range (toward + * endIndex()), and returns that code unit. If there are no more + * code units to return, returns DONE. + * @return the next code unit in the iteration range. + * @stable ICU 2.0 + */ + virtual char16_t next(void); + + /** + * Gets the current code unit for returning and advances to the next code unit + * in the iteration range + * (toward endIndex()). If there are + * no more code units to return, returns DONE. + * @return the current code unit. + * @stable ICU 2.0 + */ + virtual char16_t nextPostInc(void); + + /** + * Advances to the next code point in the iteration range (toward + * endIndex()), and returns that code point. If there are no more + * code points to return, returns DONE. + * Note that iteration with "pre-increment" semantics is less + * efficient than iteration with "post-increment" semantics + * that is provided by next32PostInc(). + * @return the next code point in the iteration range. + * @stable ICU 2.0 + */ + virtual UChar32 next32(void); + + /** + * Gets the current code point for returning and advances to the next code point + * in the iteration range + * (toward endIndex()). If there are + * no more code points to return, returns DONE. + * @return the current point. + * @stable ICU 2.0 + */ + virtual UChar32 next32PostInc(void); + + /** + * Returns false if there are no more code units or code points + * at or after the current position in the iteration range. + * This is used with nextPostInc() or next32PostInc() in forward + * iteration. + * @return false if there are no more code units or code points + * at or after the current position in the iteration range. + * @stable ICU 2.0 + */ + virtual UBool hasNext(); + + /** + * Advances to the previous code unit in the iteration range (toward + * startIndex()), and returns that code unit. If there are no more + * code units to return, returns DONE. + * @return the previous code unit in the iteration range. + * @stable ICU 2.0 + */ + virtual char16_t previous(void); + + /** + * Advances to the previous code point in the iteration range (toward + * startIndex()), and returns that code point. If there are no more + * code points to return, returns DONE. + * @return the previous code point in the iteration range. + * @stable ICU 2.0 + */ + virtual UChar32 previous32(void); + + /** + * Returns false if there are no more code units or code points + * before the current position in the iteration range. + * This is used with previous() or previous32() in backward + * iteration. + * @return false if there are no more code units or code points + * before the current position in the iteration range. + * @stable ICU 2.0 + */ + virtual UBool hasPrevious(); + + /** + * Moves the current position relative to the start or end of the + * iteration range, or relative to the current position itself. + * The movement is expressed in numbers of code units forward + * or backward by specifying a positive or negative delta. + * @param delta the position relative to origin. A positive delta means forward; + * a negative delta means backward. + * @param origin Origin enumeration {kStart, kCurrent, kEnd} + * @return the new position + * @stable ICU 2.0 + */ + virtual int32_t move(int32_t delta, EOrigin origin); + + /** + * Moves the current position relative to the start or end of the + * iteration range, or relative to the current position itself. + * The movement is expressed in numbers of code points forward + * or backward by specifying a positive or negative delta. + * @param delta the position relative to origin. A positive delta means forward; + * a negative delta means backward. + * @param origin Origin enumeration {kStart, kCurrent, kEnd} + * @return the new position + * @stable ICU 2.0 + */ +#ifdef move32 + // One of the system headers right now is sometimes defining a conflicting macro we don't use +#undef move32 +#endif + virtual int32_t move32(int32_t delta, EOrigin origin); + + /** + * Sets the iterator to iterate over a new range of text + * @stable ICU 2.0 + */ + void setText(ConstChar16Ptr newText, int32_t newTextLength); + + /** + * Copies the char16_t array under iteration into the UnicodeString + * referred to by "result". Even if this iterator iterates across + * only a part of this string, the whole string is copied. + * @param result Receives a copy of the text under iteration. + * @stable ICU 2.0 + */ + virtual void getText(UnicodeString& result); + + /** + * Return a class ID for this class (not really public) + * @return a class ID for this class + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Return a class ID for this object (not really public) + * @return a class ID for this object. + * @stable ICU 2.0 + */ + virtual UClassID getDynamicClassID(void) const; + +protected: + /** + * Protected constructor + * @stable ICU 2.0 + */ + UCharCharacterIterator(); + /** + * Protected member text + * @stable ICU 2.0 + */ + const char16_t* text; + +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/uclean.h b/thirdparty/icu4c/common/unicode/uclean.h new file mode 100644 index 0000000000..c2d920a16e --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uclean.h @@ -0,0 +1,262 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* Copyright (C) 2001-2014, International Business Machines +* Corporation and others. All Rights Reserved. +****************************************************************************** +* file name: uclean.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2001July05 +* created by: George Rhoten +*/ + +#ifndef __UCLEAN_H__ +#define __UCLEAN_H__ + +#include "unicode/utypes.h" +/** + * \file + * \brief C API: Initialize and clean up ICU + */ + +/** + * Initialize ICU. + * + * Use of this function is optional. It is OK to simply use ICU + * services and functions without first having initialized + * ICU by calling u_init(). + * + * u_init() will attempt to load some part of ICU's data, and is + * useful as a test for configuration or installation problems that + * leave the ICU data inaccessible. A successful invocation of u_init() + * does not, however, guarantee that all ICU data is accessible. + * + * Multiple calls to u_init() cause no harm, aside from the small amount + * of time required. + * + * In old versions of ICU, u_init() was required in multi-threaded applications + * to ensure the thread safety of ICU. u_init() is no longer needed for this purpose. + * + * @param status An ICU UErrorCode parameter. It must not be <code>NULL</code>. + * An Error will be returned if some required part of ICU data can not + * be loaded or initialized. + * The function returns immediately if the input error code indicates a + * failure, as usual. + * + * @stable ICU 2.6 + */ +U_CAPI void U_EXPORT2 +u_init(UErrorCode *status); + +#ifndef U_HIDE_SYSTEM_API +/** + * Clean up the system resources, such as allocated memory or open files, + * used in all ICU libraries. This will free/delete all memory owned by the + * ICU libraries, and return them to their original load state. All open ICU + * items (collators, resource bundles, converters, etc.) must be closed before + * calling this function, otherwise ICU may not free its allocated memory + * (e.g. close your converters and resource bundles before calling this + * function). Generally, this function should be called once just before + * an application exits. For applications that dynamically load and unload + * the ICU libraries (relatively uncommon), u_cleanup() should be called + * just before the library unload. + * <p> + * u_cleanup() also clears any ICU heap functions, mutex functions or + * trace functions that may have been set for the process. + * This has the effect of restoring ICU to its initial condition, before + * any of these override functions were installed. Refer to + * u_setMemoryFunctions(), u_setMutexFunctions and + * utrace_setFunctions(). If ICU is to be reinitialized after + * calling u_cleanup(), these runtime override functions will need to + * be set up again if they are still required. + * <p> + * u_cleanup() is not thread safe. All other threads should stop using ICU + * before calling this function. + * <p> + * Any open ICU items will be left in an undefined state by u_cleanup(), + * and any subsequent attempt to use such an item will give unpredictable + * results. + * <p> + * After calling u_cleanup(), an application may continue to use ICU by + * calling u_init(). An application must invoke u_init() first from one single + * thread before allowing other threads call u_init(). All threads existing + * at the time of the first thread's call to u_init() must also call + * u_init() themselves before continuing with other ICU operations. + * <p> + * The use of u_cleanup() just before an application terminates is optional, + * but it should be called only once for performance reasons. The primary + * benefit is to eliminate reports of memory or resource leaks originating + * in ICU code from the results generated by heap analysis tools. + * <p> + * <strong>Use this function with great care!</strong> + * </p> + * + * @stable ICU 2.0 + * @system + */ +U_CAPI void U_EXPORT2 +u_cleanup(void); + +U_CDECL_BEGIN +/** + * Pointer type for a user supplied memory allocation function. + * @param context user supplied value, obtained from u_setMemoryFunctions(). + * @param size The number of bytes to be allocated + * @return Pointer to the newly allocated memory, or NULL if the allocation failed. + * @stable ICU 2.8 + * @system + */ +typedef void *U_CALLCONV UMemAllocFn(const void *context, size_t size); +/** + * Pointer type for a user supplied memory re-allocation function. + * @param context user supplied value, obtained from u_setMemoryFunctions(). + * @param size The number of bytes to be allocated + * @return Pointer to the newly allocated memory, or NULL if the allocation failed. + * @stable ICU 2.8 + * @system + */ +typedef void *U_CALLCONV UMemReallocFn(const void *context, void *mem, size_t size); +/** + * Pointer type for a user supplied memory free function. Behavior should be + * similar the standard C library free(). + * @param context user supplied value, obtained from u_setMemoryFunctions(). + * @param mem Pointer to the memory block to be resized + * @param size The new size for the block + * @return Pointer to the resized memory block, or NULL if the resizing failed. + * @stable ICU 2.8 + * @system + */ +typedef void U_CALLCONV UMemFreeFn (const void *context, void *mem); + +/** + * Set the functions that ICU will use for memory allocation. + * Use of this function is optional; by default (without this function), ICU will + * use the standard C library malloc() and free() functions. + * This function can only be used when ICU is in an initial, unused state, before + * u_init() has been called. + * @param context This pointer value will be saved, and then (later) passed as + * a parameter to the memory functions each time they + * are called. + * @param a Pointer to a user-supplied malloc function. + * @param r Pointer to a user-supplied realloc function. + * @param f Pointer to a user-supplied free function. + * @param status Receives error values. + * @stable ICU 2.8 + * @system + */ +U_CAPI void U_EXPORT2 +u_setMemoryFunctions(const void *context, UMemAllocFn * U_CALLCONV_FPTR a, UMemReallocFn * U_CALLCONV_FPTR r, UMemFreeFn * U_CALLCONV_FPTR f, + UErrorCode *status); + +U_CDECL_END + +#ifndef U_HIDE_DEPRECATED_API +/********************************************************************************* + * + * Deprecated Functions + * + * The following functions for user supplied mutexes are no longer supported. + * Any attempt to use them will return a U_UNSUPPORTED_ERROR. + * + **********************************************************************************/ + +/** + * An opaque pointer type that represents an ICU mutex. + * For user-implemented mutexes, the value will typically point to a + * struct or object that implements the mutex. + * @deprecated ICU 52. This type is no longer supported. + * @system + */ +typedef void *UMTX; + +U_CDECL_BEGIN +/** + * Function Pointer type for a user supplied mutex initialization function. + * The user-supplied function will be called by ICU whenever ICU needs to create a + * new mutex. The function implementation should create a mutex, and store a pointer + * to something that uniquely identifies the mutex into the UMTX that is supplied + * as a parameter. + * @param context user supplied value, obtained from u_setMutexFunctions(). + * @param mutex Receives a pointer that identifies the new mutex. + * The mutex init function must set the UMTX to a non-null value. + * Subsequent calls by ICU to lock, unlock, or destroy a mutex will + * identify the mutex by the UMTX value. + * @param status Error status. Report errors back to ICU by setting this variable + * with an error code. + * @deprecated ICU 52. This function is no longer supported. + * @system + */ +typedef void U_CALLCONV UMtxInitFn (const void *context, UMTX *mutex, UErrorCode* status); + + +/** + * Function Pointer type for a user supplied mutex functions. + * One of the user-supplied functions with this signature will be called by ICU + * whenever ICU needs to lock, unlock, or destroy a mutex. + * @param context user supplied value, obtained from u_setMutexFunctions(). + * @param mutex specify the mutex on which to operate. + * @deprecated ICU 52. This function is no longer supported. + * @system + */ +typedef void U_CALLCONV UMtxFn (const void *context, UMTX *mutex); +U_CDECL_END + +/** + * Set the functions that ICU will use for mutex operations + * Use of this function is optional; by default (without this function), ICU will + * directly access system functions for mutex operations + * This function can only be used when ICU is in an initial, unused state, before + * u_init() has been called. + * @param context This pointer value will be saved, and then (later) passed as + * a parameter to the user-supplied mutex functions each time they + * are called. + * @param init Pointer to a mutex initialization function. Must be non-null. + * @param destroy Pointer to the mutex destroy function. Must be non-null. + * @param lock pointer to the mutex lock function. Must be non-null. + * @param unlock Pointer to the mutex unlock function. Must be non-null. + * @param status Receives error values. + * @deprecated ICU 52. This function is no longer supported. + * @system + */ +U_DEPRECATED void U_EXPORT2 +u_setMutexFunctions(const void *context, UMtxInitFn *init, UMtxFn *destroy, UMtxFn *lock, UMtxFn *unlock, + UErrorCode *status); + + +/** + * Pointer type for a user supplied atomic increment or decrement function. + * @param context user supplied value, obtained from u_setAtomicIncDecFunctions(). + * @param p Pointer to a 32 bit int to be incremented or decremented + * @return The value of the variable after the inc or dec operation. + * @deprecated ICU 52. This function is no longer supported. + * @system + */ +typedef int32_t U_CALLCONV UMtxAtomicFn(const void *context, int32_t *p); + +/** + * Set the functions that ICU will use for atomic increment and decrement of int32_t values. + * Use of this function is optional; by default (without this function), ICU will + * use its own internal implementation of atomic increment/decrement. + * This function can only be used when ICU is in an initial, unused state, before + * u_init() has been called. + * @param context This pointer value will be saved, and then (later) passed as + * a parameter to the increment and decrement functions each time they + * are called. This function can only be called + * @param inc Pointer to a function to do an atomic increment operation. Must be non-null. + * @param dec Pointer to a function to do an atomic decrement operation. Must be non-null. + * @param status Receives error values. + * @deprecated ICU 52. This function is no longer supported. + * @system + */ +U_DEPRECATED void U_EXPORT2 +u_setAtomicIncDecFunctions(const void *context, UMtxAtomicFn *inc, UMtxAtomicFn *dec, + UErrorCode *status); + +#endif /* U_HIDE_DEPRECATED_API */ +#endif /* U_HIDE_SYSTEM_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/ucnv.h b/thirdparty/icu4c/common/unicode/ucnv.h new file mode 100644 index 0000000000..58f271cfb5 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucnv.h @@ -0,0 +1,2045 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1999-2014, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** + * ucnv.h: + * External APIs for the ICU's codeset conversion library + * Bertrand A. Damiba + * + * Modification History: + * + * Date Name Description + * 04/04/99 helena Fixed internal header inclusion. + * 05/11/00 helena Added setFallback and usesFallback APIs. + * 06/29/2000 helena Major rewrite of the callback APIs. + * 12/07/2000 srl Update of documentation + */ + +/** + * \file + * \brief C API: Character conversion + * + * <h2>Character Conversion C API</h2> + * + * <p>This API is used to convert codepage or character encoded data to and + * from UTF-16. You can open a converter with {@link ucnv_open() }. With that + * converter, you can get its properties, set options, convert your data and + * close the converter.</p> + * + * <p>Since many software programs recognize different converter names for + * different types of converters, there are other functions in this API to + * iterate over the converter aliases. The functions {@link ucnv_getAvailableName() }, + * {@link ucnv_getAlias() } and {@link ucnv_getStandardName() } are some of the + * more frequently used alias functions to get this information.</p> + * + * <p>When a converter encounters an illegal, irregular, invalid or unmappable character + * its default behavior is to use a substitution character to replace the + * bad byte sequence. This behavior can be changed by using {@link ucnv_setFromUCallBack() } + * or {@link ucnv_setToUCallBack() } on the converter. The header ucnv_err.h defines + * many other callback actions that can be used instead of a character substitution.</p> + * + * <p>More information about this API can be found in our + * <a href="http://icu-project.org/userguide/conversion.html">User's + * Guide</a>.</p> + */ + +#ifndef UCNV_H +#define UCNV_H + +#include "unicode/ucnv_err.h" +#include "unicode/uenum.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +#if !defined(USET_DEFINED) && !defined(U_IN_DOXYGEN) + +#define USET_DEFINED + +/** + * USet is the C API type corresponding to C++ class UnicodeSet. + * It is forward-declared here to avoid including unicode/uset.h file if related + * conversion APIs are not used. + * + * @see ucnv_getUnicodeSet + * @stable ICU 2.4 + */ +typedef struct USet USet; + +#endif + +#if !UCONFIG_NO_CONVERSION + +U_CDECL_BEGIN + +/** Maximum length of a converter name including the terminating NULL @stable ICU 2.0 */ +#define UCNV_MAX_CONVERTER_NAME_LENGTH 60 +/** Maximum length of a converter name including path and terminating NULL @stable ICU 2.0 */ +#define UCNV_MAX_FULL_FILE_NAME_LENGTH (600+UCNV_MAX_CONVERTER_NAME_LENGTH) + +/** Shift in for EBDCDIC_STATEFUL and iso2022 states @stable ICU 2.0 */ +#define UCNV_SI 0x0F +/** Shift out for EBDCDIC_STATEFUL and iso2022 states @stable ICU 2.0 */ +#define UCNV_SO 0x0E + +/** + * Enum for specifying basic types of converters + * @see ucnv_getType + * @stable ICU 2.0 + */ +typedef enum { + /** @stable ICU 2.0 */ + UCNV_UNSUPPORTED_CONVERTER = -1, + /** @stable ICU 2.0 */ + UCNV_SBCS = 0, + /** @stable ICU 2.0 */ + UCNV_DBCS = 1, + /** @stable ICU 2.0 */ + UCNV_MBCS = 2, + /** @stable ICU 2.0 */ + UCNV_LATIN_1 = 3, + /** @stable ICU 2.0 */ + UCNV_UTF8 = 4, + /** @stable ICU 2.0 */ + UCNV_UTF16_BigEndian = 5, + /** @stable ICU 2.0 */ + UCNV_UTF16_LittleEndian = 6, + /** @stable ICU 2.0 */ + UCNV_UTF32_BigEndian = 7, + /** @stable ICU 2.0 */ + UCNV_UTF32_LittleEndian = 8, + /** @stable ICU 2.0 */ + UCNV_EBCDIC_STATEFUL = 9, + /** @stable ICU 2.0 */ + UCNV_ISO_2022 = 10, + + /** @stable ICU 2.0 */ + UCNV_LMBCS_1 = 11, + /** @stable ICU 2.0 */ + UCNV_LMBCS_2, + /** @stable ICU 2.0 */ + UCNV_LMBCS_3, + /** @stable ICU 2.0 */ + UCNV_LMBCS_4, + /** @stable ICU 2.0 */ + UCNV_LMBCS_5, + /** @stable ICU 2.0 */ + UCNV_LMBCS_6, + /** @stable ICU 2.0 */ + UCNV_LMBCS_8, + /** @stable ICU 2.0 */ + UCNV_LMBCS_11, + /** @stable ICU 2.0 */ + UCNV_LMBCS_16, + /** @stable ICU 2.0 */ + UCNV_LMBCS_17, + /** @stable ICU 2.0 */ + UCNV_LMBCS_18, + /** @stable ICU 2.0 */ + UCNV_LMBCS_19, + /** @stable ICU 2.0 */ + UCNV_LMBCS_LAST = UCNV_LMBCS_19, + /** @stable ICU 2.0 */ + UCNV_HZ, + /** @stable ICU 2.0 */ + UCNV_SCSU, + /** @stable ICU 2.0 */ + UCNV_ISCII, + /** @stable ICU 2.0 */ + UCNV_US_ASCII, + /** @stable ICU 2.0 */ + UCNV_UTF7, + /** @stable ICU 2.2 */ + UCNV_BOCU1, + /** @stable ICU 2.2 */ + UCNV_UTF16, + /** @stable ICU 2.2 */ + UCNV_UTF32, + /** @stable ICU 2.2 */ + UCNV_CESU8, + /** @stable ICU 2.4 */ + UCNV_IMAP_MAILBOX, + /** @stable ICU 4.8 */ + UCNV_COMPOUND_TEXT, + + /* Number of converter types for which we have conversion routines. */ + UCNV_NUMBER_OF_SUPPORTED_CONVERTER_TYPES +} UConverterType; + +/** + * Enum for specifying which platform a converter ID refers to. + * The use of platform/CCSID is not recommended. See ucnv_openCCSID(). + * + * @see ucnv_getPlatform + * @see ucnv_openCCSID + * @see ucnv_getCCSID + * @stable ICU 2.0 + */ +typedef enum { + UCNV_UNKNOWN = -1, + UCNV_IBM = 0 +} UConverterPlatform; + +/** + * Function pointer for error callback in the codepage to unicode direction. + * Called when an error has occurred in conversion to unicode, or on open/close of the callback (see reason). + * @param context Pointer to the callback's private data + * @param args Information about the conversion in progress + * @param codeUnits Points to 'length' bytes of the concerned codepage sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param reason Defines the reason the callback was invoked + * @param pErrorCode ICU error code in/out parameter. + * For converter callback functions, set to a conversion error + * before the call, and the callback may reset it to U_ZERO_ERROR. + * @see ucnv_setToUCallBack + * @see UConverterToUnicodeArgs + * @stable ICU 2.0 + */ +typedef void (U_EXPORT2 *UConverterToUCallback) ( + const void* context, + UConverterToUnicodeArgs *args, + const char *codeUnits, + int32_t length, + UConverterCallbackReason reason, + UErrorCode *pErrorCode); + +/** + * Function pointer for error callback in the unicode to codepage direction. + * Called when an error has occurred in conversion from unicode, or on open/close of the callback (see reason). + * @param context Pointer to the callback's private data + * @param args Information about the conversion in progress + * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint. + * @param reason Defines the reason the callback was invoked + * @param pErrorCode ICU error code in/out parameter. + * For converter callback functions, set to a conversion error + * before the call, and the callback may reset it to U_ZERO_ERROR. + * @see ucnv_setFromUCallBack + * @stable ICU 2.0 + */ +typedef void (U_EXPORT2 *UConverterFromUCallback) ( + const void* context, + UConverterFromUnicodeArgs *args, + const UChar* codeUnits, + int32_t length, + UChar32 codePoint, + UConverterCallbackReason reason, + UErrorCode *pErrorCode); + +U_CDECL_END + +/** + * Character that separates converter names from options and options from each other. + * @see ucnv_open + * @stable ICU 2.0 + */ +#define UCNV_OPTION_SEP_CHAR ',' + +/** + * String version of UCNV_OPTION_SEP_CHAR. + * @see ucnv_open + * @stable ICU 2.0 + */ +#define UCNV_OPTION_SEP_STRING "," + +/** + * Character that separates a converter option from its value. + * @see ucnv_open + * @stable ICU 2.0 + */ +#define UCNV_VALUE_SEP_CHAR '=' + +/** + * String version of UCNV_VALUE_SEP_CHAR. + * @see ucnv_open + * @stable ICU 2.0 + */ +#define UCNV_VALUE_SEP_STRING "=" + +/** + * Converter option for specifying a locale. + * For example, ucnv_open("SCSU,locale=ja", &errorCode); + * See convrtrs.txt. + * + * @see ucnv_open + * @stable ICU 2.0 + */ +#define UCNV_LOCALE_OPTION_STRING ",locale=" + +/** + * Converter option for specifying a version selector (0..9) for some converters. + * For example, + * \code + * ucnv_open("UTF-7,version=1", &errorCode); + * \endcode + * See convrtrs.txt. + * + * @see ucnv_open + * @stable ICU 2.4 + */ +#define UCNV_VERSION_OPTION_STRING ",version=" + +/** + * Converter option for EBCDIC SBCS or mixed-SBCS/DBCS (stateful) codepages. + * Swaps Unicode mappings for EBCDIC LF and NL codes, as used on + * S/390 (z/OS) Unix System Services (Open Edition). + * For example, ucnv_open("ibm-1047,swaplfnl", &errorCode); + * See convrtrs.txt. + * + * @see ucnv_open + * @stable ICU 2.4 + */ +#define UCNV_SWAP_LFNL_OPTION_STRING ",swaplfnl" + +/** + * Do a fuzzy compare of two converter/alias names. + * The comparison is case-insensitive, ignores leading zeroes if they are not + * followed by further digits, and ignores all but letters and digits. + * Thus the strings "UTF-8", "utf_8", "u*T@f08" and "Utf 8" are exactly equivalent. + * See section 1.4, Charset Alias Matching in Unicode Technical Standard #22 + * at http://www.unicode.org/reports/tr22/ + * + * @param name1 a converter name or alias, zero-terminated + * @param name2 a converter name or alias, zero-terminated + * @return 0 if the names match, or a negative value if the name1 + * lexically precedes name2, or a positive value if the name1 + * lexically follows name2. + * @stable ICU 2.0 + */ +U_CAPI int U_EXPORT2 +ucnv_compareNames(const char *name1, const char *name2); + + +/** + * Creates a UConverter object with the name of a coded character set specified as a C string. + * The actual name will be resolved with the alias file + * using a case-insensitive string comparison that ignores + * leading zeroes and all non-alphanumeric characters. + * E.g., the names "UTF8", "utf-8", "u*T@f08" and "Utf 8" are all equivalent. + * (See also ucnv_compareNames().) + * If <code>NULL</code> is passed for the converter name, it will create one with the + * getDefaultName return value. + * + * <p>A converter name for ICU 1.5 and above may contain options + * like a locale specification to control the specific behavior of + * the newly instantiated converter. + * The meaning of the options depends on the particular converter. + * If an option is not defined for or recognized by a given converter, then it is ignored.</p> + * + * <p>Options are appended to the converter name string, with a + * <code>UCNV_OPTION_SEP_CHAR</code> between the name and the first option and + * also between adjacent options.</p> + * + * <p>If the alias is ambiguous, then the preferred converter is used + * and the status is set to U_AMBIGUOUS_ALIAS_WARNING.</p> + * + * <p>The conversion behavior and names can vary between platforms. ICU may + * convert some characters differently from other platforms. Details on this topic + * are in the <a href="http://icu-project.org/userguide/conversion.html">User's + * Guide</a>. Aliases starting with a "cp" prefix have no specific meaning + * other than its an alias starting with the letters "cp". Please do not + * associate any meaning to these aliases.</p> + * + * \snippet samples/ucnv/convsamp.cpp ucnv_open + * + * @param converterName Name of the coded character set table. + * This may have options appended to the string. + * IANA alias character set names, IBM CCSIDs starting with "ibm-", + * Windows codepage numbers starting with "windows-" are frequently + * used for this parameter. See ucnv_getAvailableName and + * ucnv_getAlias for a complete list that is available. + * If this parameter is NULL, the default converter will be used. + * @param err outgoing error status <TT>U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR</TT> + * @return the created Unicode converter object, or <TT>NULL</TT> if an error occurred + * @see ucnv_openU + * @see ucnv_openCCSID + * @see ucnv_getAvailableName + * @see ucnv_getAlias + * @see ucnv_getDefaultName + * @see ucnv_close + * @see ucnv_compareNames + * @stable ICU 2.0 + */ +U_CAPI UConverter* U_EXPORT2 +ucnv_open(const char *converterName, UErrorCode *err); + + +/** + * Creates a Unicode converter with the names specified as unicode string. + * The name should be limited to the ASCII-7 alphanumerics range. + * The actual name will be resolved with the alias file + * using a case-insensitive string comparison that ignores + * leading zeroes and all non-alphanumeric characters. + * E.g., the names "UTF8", "utf-8", "u*T@f08" and "Utf 8" are all equivalent. + * (See also ucnv_compareNames().) + * If <TT>NULL</TT> is passed for the converter name, it will create + * one with the ucnv_getDefaultName() return value. + * If the alias is ambiguous, then the preferred converter is used + * and the status is set to U_AMBIGUOUS_ALIAS_WARNING. + * + * <p>See ucnv_open for the complete details</p> + * @param name Name of the UConverter table in a zero terminated + * Unicode string + * @param err outgoing error status <TT>U_MEMORY_ALLOCATION_ERROR, + * U_FILE_ACCESS_ERROR</TT> + * @return the created Unicode converter object, or <TT>NULL</TT> if an + * error occurred + * @see ucnv_open + * @see ucnv_openCCSID + * @see ucnv_close + * @see ucnv_compareNames + * @stable ICU 2.0 + */ +U_CAPI UConverter* U_EXPORT2 +ucnv_openU(const UChar *name, + UErrorCode *err); + +/** + * Creates a UConverter object from a CCSID number and platform pair. + * Note that the usefulness of this function is limited to platforms with numeric + * encoding IDs. Only IBM and Microsoft platforms use numeric (16-bit) identifiers for + * encodings. + * + * In addition, IBM CCSIDs and Unicode conversion tables are not 1:1 related. + * For many IBM CCSIDs there are multiple (up to six) Unicode conversion tables, and + * for some Unicode conversion tables there are multiple CCSIDs. + * Some "alternate" Unicode conversion tables are provided by the + * IBM CDRA conversion table registry. + * The most prominent example of a systematic modification of conversion tables that is + * not provided in the form of conversion table files in the repository is + * that S/390 Unix System Services swaps the codes for Line Feed and New Line in all + * EBCDIC codepages, which requires such a swap in the Unicode conversion tables as well. + * + * Only IBM default conversion tables are accessible with ucnv_openCCSID(). + * ucnv_getCCSID() will return the same CCSID for all conversion tables that are associated + * with that CCSID. + * + * Currently, the only "platform" supported in the ICU converter API is UCNV_IBM. + * + * In summary, the use of CCSIDs and the associated API functions is not recommended. + * + * In order to open a converter with the default IBM CDRA Unicode conversion table, + * you can use this function or use the prefix "ibm-": + * \code + * char name[20]; + * sprintf(name, "ibm-%hu", ccsid); + * cnv=ucnv_open(name, &errorCode); + * \endcode + * + * In order to open a converter with the IBM S/390 Unix System Services variant + * of a Unicode/EBCDIC conversion table, + * you can use the prefix "ibm-" together with the option string UCNV_SWAP_LFNL_OPTION_STRING: + * \code + * char name[20]; + * sprintf(name, "ibm-%hu" UCNV_SWAP_LFNL_OPTION_STRING, ccsid); + * cnv=ucnv_open(name, &errorCode); + * \endcode + * + * In order to open a converter from a Microsoft codepage number, use the prefix "cp": + * \code + * char name[20]; + * sprintf(name, "cp%hu", codepageID); + * cnv=ucnv_open(name, &errorCode); + * \endcode + * + * If the alias is ambiguous, then the preferred converter is used + * and the status is set to U_AMBIGUOUS_ALIAS_WARNING. + * + * @param codepage codepage number to create + * @param platform the platform in which the codepage number exists + * @param err error status <TT>U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR</TT> + * @return the created Unicode converter object, or <TT>NULL</TT> if an error + * occurred. + * @see ucnv_open + * @see ucnv_openU + * @see ucnv_close + * @see ucnv_getCCSID + * @see ucnv_getPlatform + * @see UConverterPlatform + * @stable ICU 2.0 + */ +U_CAPI UConverter* U_EXPORT2 +ucnv_openCCSID(int32_t codepage, + UConverterPlatform platform, + UErrorCode * err); + +/** + * <p>Creates a UConverter object specified from a packageName and a converterName.</p> + * + * <p>The packageName and converterName must point to an ICU udata object, as defined by + * <code> udata_open( packageName, "cnv", converterName, err) </code> or equivalent. + * Typically, packageName will refer to a (.dat) file, or to a package registered with + * udata_setAppData(). Using a full file or directory pathname for packageName is deprecated.</p> + * + * <p>The name will NOT be looked up in the alias mechanism, nor will the converter be + * stored in the converter cache or the alias table. The only way to open further converters + * is call this function multiple times, or use the ucnv_safeClone() function to clone a + * 'primary' converter.</p> + * + * <p>A future version of ICU may add alias table lookups and/or caching + * to this function.</p> + * + * <p>Example Use: + * <code>cnv = ucnv_openPackage("myapp", "myconverter", &err);</code> + * </p> + * + * @param packageName name of the package (equivalent to 'path' in udata_open() call) + * @param converterName name of the data item to be used, without suffix. + * @param err outgoing error status <TT>U_MEMORY_ALLOCATION_ERROR, U_FILE_ACCESS_ERROR</TT> + * @return the created Unicode converter object, or <TT>NULL</TT> if an error occurred + * @see udata_open + * @see ucnv_open + * @see ucnv_safeClone + * @see ucnv_close + * @stable ICU 2.2 + */ +U_CAPI UConverter* U_EXPORT2 +ucnv_openPackage(const char *packageName, const char *converterName, UErrorCode *err); + +/** + * Thread safe converter cloning operation. + * For most efficient operation, pass in a stackBuffer (and a *pBufferSize) + * with at least U_CNV_SAFECLONE_BUFFERSIZE bytes of space. + * If the buffer size is sufficient, then the clone will use the stack buffer; + * otherwise, it will be allocated, and *pBufferSize will indicate + * the actual size. (This should not occur with U_CNV_SAFECLONE_BUFFERSIZE.) + * + * You must ucnv_close() the clone in any case. + * + * If *pBufferSize==0, (regardless of whether stackBuffer==NULL or not) + * then *pBufferSize will be changed to a sufficient size + * for cloning this converter, + * without actually cloning the converter ("pure pre-flighting"). + * + * If *pBufferSize is greater than zero but not large enough for a stack-based + * clone, then the converter is cloned using newly allocated memory + * and *pBufferSize is changed to the necessary size. + * + * If the converter clone fits into the stack buffer but the stack buffer is not + * sufficiently aligned for the clone, then the clone will use an + * adjusted pointer and use an accordingly smaller buffer size. + * + * @param cnv converter to be cloned + * @param stackBuffer <em>Deprecated functionality as of ICU 52, use NULL.</em><br> + * user allocated space for the new clone. If NULL new memory will be allocated. + * If buffer is not large enough, new memory will be allocated. + * Clients can use the U_CNV_SAFECLONE_BUFFERSIZE. This will probably be enough to avoid memory allocations. + * @param pBufferSize <em>Deprecated functionality as of ICU 52, use NULL or 1.</em><br> + * pointer to size of allocated space. + * @param status to indicate whether the operation went on smoothly or there were errors + * An informational status value, U_SAFECLONE_ALLOCATED_WARNING, + * is used if any allocations were necessary. + * However, it is better to check if *pBufferSize grew for checking for + * allocations because warning codes can be overridden by subsequent + * function calls. + * @return pointer to the new clone + * @stable ICU 2.0 + */ +U_CAPI UConverter * U_EXPORT2 +ucnv_safeClone(const UConverter *cnv, + void *stackBuffer, + int32_t *pBufferSize, + UErrorCode *status); + +#ifndef U_HIDE_DEPRECATED_API + +/** + * \def U_CNV_SAFECLONE_BUFFERSIZE + * Definition of a buffer size that is designed to be large enough for + * converters to be cloned with ucnv_safeClone(). + * @deprecated ICU 52. Do not rely on ucnv_safeClone() cloning into any provided buffer. + */ +#define U_CNV_SAFECLONE_BUFFERSIZE 1024 + +#endif /* U_HIDE_DEPRECATED_API */ + +/** + * Deletes the unicode converter and releases resources associated + * with just this instance. + * Does not free up shared converter tables. + * + * @param converter the converter object to be deleted + * @see ucnv_open + * @see ucnv_openU + * @see ucnv_openCCSID + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_close(UConverter * converter); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUConverterPointer + * "Smart pointer" class, closes a UConverter via ucnv_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUConverterPointer, UConverter, ucnv_close); + +U_NAMESPACE_END + +#endif + +/** + * Fills in the output parameter, subChars, with the substitution characters + * as multiple bytes. + * If ucnv_setSubstString() set a Unicode string because the converter is + * stateful, then subChars will be an empty string. + * + * @param converter the Unicode converter + * @param subChars the substitution characters + * @param len on input the capacity of subChars, on output the number + * of bytes copied to it + * @param err the outgoing error status code. + * If the substitution character array is too small, an + * <TT>U_INDEX_OUTOFBOUNDS_ERROR</TT> will be returned. + * @see ucnv_setSubstString + * @see ucnv_setSubstChars + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_getSubstChars(const UConverter *converter, + char *subChars, + int8_t *len, + UErrorCode *err); + +/** + * Sets the substitution chars when converting from unicode to a codepage. The + * substitution is specified as a string of 1-4 bytes, and may contain + * <TT>NULL</TT> bytes. + * The subChars must represent a single character. The caller needs to know the + * byte sequence of a valid character in the converter's charset. + * For some converters, for example some ISO 2022 variants, only single-byte + * substitution characters may be supported. + * The newer ucnv_setSubstString() function relaxes these limitations. + * + * @param converter the Unicode converter + * @param subChars the substitution character byte sequence we want set + * @param len the number of bytes in subChars + * @param err the error status code. <TT>U_INDEX_OUTOFBOUNDS_ERROR </TT> if + * len is bigger than the maximum number of bytes allowed in subchars + * @see ucnv_setSubstString + * @see ucnv_getSubstChars + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_setSubstChars(UConverter *converter, + const char *subChars, + int8_t len, + UErrorCode *err); + +/** + * Set a substitution string for converting from Unicode to a charset. + * The caller need not know the charset byte sequence for each charset. + * + * Unlike ucnv_setSubstChars() which is designed to set a charset byte sequence + * for a single character, this function takes a Unicode string with + * zero, one or more characters, and immediately verifies that the string can be + * converted to the charset. + * If not, or if the result is too long (more than 32 bytes as of ICU 3.6), + * then the function returns with an error accordingly. + * + * Also unlike ucnv_setSubstChars(), this function works for stateful charsets + * by converting on the fly at the point of substitution rather than setting + * a fixed byte sequence. + * + * @param cnv The UConverter object. + * @param s The Unicode string. + * @param length The number of UChars in s, or -1 for a NUL-terminated string. + * @param err Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * + * @see ucnv_setSubstChars + * @see ucnv_getSubstChars + * @stable ICU 3.6 + */ +U_CAPI void U_EXPORT2 +ucnv_setSubstString(UConverter *cnv, + const UChar *s, + int32_t length, + UErrorCode *err); + +/** + * Fills in the output parameter, errBytes, with the error characters from the + * last failing conversion. + * + * @param converter the Unicode converter + * @param errBytes the codepage bytes which were in error + * @param len on input the capacity of errBytes, on output the number of + * bytes which were copied to it + * @param err the error status code. + * If the substitution character array is too small, an + * <TT>U_INDEX_OUTOFBOUNDS_ERROR</TT> will be returned. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_getInvalidChars(const UConverter *converter, + char *errBytes, + int8_t *len, + UErrorCode *err); + +/** + * Fills in the output parameter, errChars, with the error characters from the + * last failing conversion. + * + * @param converter the Unicode converter + * @param errUChars the UChars which were in error + * @param len on input the capacity of errUChars, on output the number of + * UChars which were copied to it + * @param err the error status code. + * If the substitution character array is too small, an + * <TT>U_INDEX_OUTOFBOUNDS_ERROR</TT> will be returned. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_getInvalidUChars(const UConverter *converter, + UChar *errUChars, + int8_t *len, + UErrorCode *err); + +/** + * Resets the state of a converter to the default state. This is used + * in the case of an error, to restart a conversion from a known default state. + * It will also empty the internal output buffers. + * @param converter the Unicode converter + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_reset(UConverter *converter); + +/** + * Resets the to-Unicode part of a converter state to the default state. + * This is used in the case of an error to restart a conversion to + * Unicode to a known default state. It will also empty the internal + * output buffers used for the conversion to Unicode codepoints. + * @param converter the Unicode converter + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_resetToUnicode(UConverter *converter); + +/** + * Resets the from-Unicode part of a converter state to the default state. + * This is used in the case of an error to restart a conversion from + * Unicode to a known default state. It will also empty the internal output + * buffers used for the conversion from Unicode codepoints. + * @param converter the Unicode converter + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_resetFromUnicode(UConverter *converter); + +/** + * Returns the maximum number of bytes that are output per UChar in conversion + * from Unicode using this converter. + * The returned number can be used with UCNV_GET_MAX_BYTES_FOR_STRING + * to calculate the size of a target buffer for conversion from Unicode. + * + * Note: Before ICU 2.8, this function did not return reliable numbers for + * some stateful converters (EBCDIC_STATEFUL, ISO-2022) and LMBCS. + * + * This number may not be the same as the maximum number of bytes per + * "conversion unit". In other words, it may not be the intuitively expected + * number of bytes per character that would be published for a charset, + * and may not fulfill any other purpose than the allocation of an output + * buffer of guaranteed sufficient size for a given input length and converter. + * + * Examples for special cases that are taken into account: + * - Supplementary code points may convert to more bytes than BMP code points. + * This function returns bytes per UChar (UTF-16 code unit), not per + * Unicode code point, for efficient buffer allocation. + * - State-shifting output (SI/SO, escapes, etc.) from stateful converters. + * - When m input UChars are converted to n output bytes, then the maximum m/n + * is taken into account. + * + * The number returned here does not take into account + * (see UCNV_GET_MAX_BYTES_FOR_STRING): + * - callbacks which output more than one charset character sequence per call, + * like escape callbacks + * - initial and final non-character bytes that are output by some converters + * (automatic BOMs, initial escape sequence, final SI, etc.) + * + * Examples for returned values: + * - SBCS charsets: 1 + * - Shift-JIS: 2 + * - UTF-16: 2 (2 per BMP, 4 per surrogate _pair_, BOM not counted) + * - UTF-8: 3 (3 per BMP, 4 per surrogate _pair_) + * - EBCDIC_STATEFUL (EBCDIC mixed SBCS/DBCS): 3 (SO + DBCS) + * - ISO-2022: 3 (always outputs UTF-8) + * - ISO-2022-JP: 6 (4-byte escape sequences + DBCS) + * - ISO-2022-CN: 8 (4-byte designator sequences + 2-byte SS2/SS3 + DBCS) + * + * @param converter The Unicode converter. + * @return The maximum number of bytes per UChar (16 bit code unit) + * that are output by ucnv_fromUnicode(), + * to be used together with UCNV_GET_MAX_BYTES_FOR_STRING + * for buffer allocation. + * + * @see UCNV_GET_MAX_BYTES_FOR_STRING + * @see ucnv_getMinCharSize + * @stable ICU 2.0 + */ +U_CAPI int8_t U_EXPORT2 +ucnv_getMaxCharSize(const UConverter *converter); + +/** + * Calculates the size of a buffer for conversion from Unicode to a charset. + * The calculated size is guaranteed to be sufficient for this conversion. + * + * It takes into account initial and final non-character bytes that are output + * by some converters. + * It does not take into account callbacks which output more than one charset + * character sequence per call, like escape callbacks. + * The default (substitution) callback only outputs one charset character sequence. + * + * @param length Number of UChars to be converted. + * @param maxCharSize Return value from ucnv_getMaxCharSize() for the converter + * that will be used. + * @return Size of a buffer that will be large enough to hold the output bytes of + * converting length UChars with the converter that returned the maxCharSize. + * + * @see ucnv_getMaxCharSize + * @stable ICU 2.8 + */ +#define UCNV_GET_MAX_BYTES_FOR_STRING(length, maxCharSize) \ + (((int32_t)(length)+10)*(int32_t)(maxCharSize)) + +/** + * Returns the minimum byte length (per codepoint) for characters in this codepage. + * This is usually either 1 or 2. + * @param converter the Unicode converter + * @return the minimum number of bytes per codepoint allowed by this particular converter + * @see ucnv_getMaxCharSize + * @stable ICU 2.0 + */ +U_CAPI int8_t U_EXPORT2 +ucnv_getMinCharSize(const UConverter *converter); + +/** + * Returns the display name of the converter passed in based on the Locale + * passed in. If the locale contains no display name, the internal ASCII + * name will be filled in. + * + * @param converter the Unicode converter. + * @param displayLocale is the specific Locale we want to localized for + * @param displayName user provided buffer to be filled in + * @param displayNameCapacity size of displayName Buffer + * @param err error status code + * @return displayNameLength number of UChar needed in displayName + * @see ucnv_getName + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_getDisplayName(const UConverter *converter, + const char *displayLocale, + UChar *displayName, + int32_t displayNameCapacity, + UErrorCode *err); + +/** + * Gets the internal, canonical name of the converter (zero-terminated). + * The lifetime of the returned string will be that of the converter + * passed to this function. + * @param converter the Unicode converter + * @param err UErrorCode status + * @return the internal name of the converter + * @see ucnv_getDisplayName + * @stable ICU 2.0 + */ +U_CAPI const char * U_EXPORT2 +ucnv_getName(const UConverter *converter, UErrorCode *err); + +/** + * Gets a codepage number associated with the converter. This is not guaranteed + * to be the one used to create the converter. Some converters do not represent + * platform registered codepages and return zero for the codepage number. + * The error code fill-in parameter indicates if the codepage number + * is available. + * Does not check if the converter is <TT>NULL</TT> or if converter's data + * table is <TT>NULL</TT>. + * + * Important: The use of CCSIDs is not recommended because it is limited + * to only two platforms in principle and only one (UCNV_IBM) in the current + * ICU converter API. + * Also, CCSIDs are insufficient to identify IBM Unicode conversion tables precisely. + * For more details see ucnv_openCCSID(). + * + * @param converter the Unicode converter + * @param err the error status code. + * @return If any error occurs, -1 will be returned otherwise, the codepage number + * will be returned + * @see ucnv_openCCSID + * @see ucnv_getPlatform + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_getCCSID(const UConverter *converter, + UErrorCode *err); + +/** + * Gets a codepage platform associated with the converter. Currently, + * only <TT>UCNV_IBM</TT> will be returned. + * Does not test if the converter is <TT>NULL</TT> or if converter's data + * table is <TT>NULL</TT>. + * @param converter the Unicode converter + * @param err the error status code. + * @return The codepage platform + * @stable ICU 2.0 + */ +U_CAPI UConverterPlatform U_EXPORT2 +ucnv_getPlatform(const UConverter *converter, + UErrorCode *err); + +/** + * Gets the type of the converter + * e.g. SBCS, MBCS, DBCS, UTF8, UTF16_BE, UTF16_LE, ISO_2022, + * EBCDIC_STATEFUL, LATIN_1 + * @param converter a valid, opened converter + * @return the type of the converter + * @stable ICU 2.0 + */ +U_CAPI UConverterType U_EXPORT2 +ucnv_getType(const UConverter * converter); + +/** + * Gets the "starter" (lead) bytes for converters of type MBCS. + * Will fill in an <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> if converter passed in + * is not MBCS. Fills in an array of type UBool, with the value of the byte + * as offset to the array. For example, if (starters[0x20] == true) at return, + * it means that the byte 0x20 is a starter byte in this converter. + * Context pointers are always owned by the caller. + * + * @param converter a valid, opened converter of type MBCS + * @param starters an array of size 256 to be filled in + * @param err error status, <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> if the + * converter is not a type which can return starters. + * @see ucnv_getType + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_getStarters(const UConverter* converter, + UBool starters[256], + UErrorCode* err); + + +/** + * Selectors for Unicode sets that can be returned by ucnv_getUnicodeSet(). + * @see ucnv_getUnicodeSet + * @stable ICU 2.6 + */ +typedef enum UConverterUnicodeSet { + /** Select the set of roundtrippable Unicode code points. @stable ICU 2.6 */ + UCNV_ROUNDTRIP_SET, + /** Select the set of Unicode code points with roundtrip or fallback mappings. @stable ICU 4.0 */ + UCNV_ROUNDTRIP_AND_FALLBACK_SET, +#ifndef U_HIDE_DEPRECATED_API + /** + * Number of UConverterUnicodeSet selectors. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCNV_SET_COUNT +#endif // U_HIDE_DEPRECATED_API +} UConverterUnicodeSet; + + +/** + * Returns the set of Unicode code points that can be converted by an ICU converter. + * + * Returns one of several kinds of set: + * + * 1. UCNV_ROUNDTRIP_SET + * + * The set of all Unicode code points that can be roundtrip-converted + * (converted without any data loss) with the converter (ucnv_fromUnicode()). + * This set will not include code points that have fallback mappings + * or are only the result of reverse fallback mappings. + * This set will also not include PUA code points with fallbacks, although + * ucnv_fromUnicode() will always uses those mappings despite ucnv_setFallback(). + * See UTR #22 "Character Mapping Markup Language" + * at http://www.unicode.org/reports/tr22/ + * + * This is useful for example for + * - checking that a string or document can be roundtrip-converted with a converter, + * without/before actually performing the conversion + * - testing if a converter can be used for text for typical text for a certain locale, + * by comparing its roundtrip set with the set of ExemplarCharacters from + * ICU's locale data or other sources + * + * 2. UCNV_ROUNDTRIP_AND_FALLBACK_SET + * + * The set of all Unicode code points that can be converted with the converter (ucnv_fromUnicode()) + * when fallbacks are turned on (see ucnv_setFallback()). + * This set includes all code points with roundtrips and fallbacks (but not reverse fallbacks). + * + * In the future, there may be more UConverterUnicodeSet choices to select + * sets with different properties. + * + * @param cnv The converter for which a set is requested. + * @param setFillIn A valid USet *. It will be cleared by this function before + * the converter's specific set is filled into the USet. + * @param whichSet A UConverterUnicodeSet selector; + * currently UCNV_ROUNDTRIP_SET is the only supported value. + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * + * @see UConverterUnicodeSet + * @see uset_open + * @see uset_close + * @stable ICU 2.6 + */ +U_CAPI void U_EXPORT2 +ucnv_getUnicodeSet(const UConverter *cnv, + USet *setFillIn, + UConverterUnicodeSet whichSet, + UErrorCode *pErrorCode); + +/** + * Gets the current calback function used by the converter when an illegal + * or invalid codepage sequence is found. + * Context pointers are always owned by the caller. + * + * @param converter the unicode converter + * @param action fillin: returns the callback function pointer + * @param context fillin: returns the callback's private void* context + * @see ucnv_setToUCallBack + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_getToUCallBack (const UConverter * converter, + UConverterToUCallback *action, + const void **context); + +/** + * Gets the current callback function used by the converter when illegal + * or invalid Unicode sequence is found. + * Context pointers are always owned by the caller. + * + * @param converter the unicode converter + * @param action fillin: returns the callback function pointer + * @param context fillin: returns the callback's private void* context + * @see ucnv_setFromUCallBack + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_getFromUCallBack (const UConverter * converter, + UConverterFromUCallback *action, + const void **context); + +/** + * Changes the callback function used by the converter when + * an illegal or invalid sequence is found. + * Context pointers are always owned by the caller. + * Predefined actions and contexts can be found in the ucnv_err.h header. + * + * @param converter the unicode converter + * @param newAction the new callback function + * @param newContext the new toUnicode callback context pointer. This can be NULL. + * @param oldAction fillin: returns the old callback function pointer. This can be NULL. + * @param oldContext fillin: returns the old callback's private void* context. This can be NULL. + * @param err The error code status + * @see ucnv_getToUCallBack + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_setToUCallBack (UConverter * converter, + UConverterToUCallback newAction, + const void* newContext, + UConverterToUCallback *oldAction, + const void** oldContext, + UErrorCode * err); + +/** + * Changes the current callback function used by the converter when + * an illegal or invalid sequence is found. + * Context pointers are always owned by the caller. + * Predefined actions and contexts can be found in the ucnv_err.h header. + * + * @param converter the unicode converter + * @param newAction the new callback function + * @param newContext the new fromUnicode callback context pointer. This can be NULL. + * @param oldAction fillin: returns the old callback function pointer. This can be NULL. + * @param oldContext fillin: returns the old callback's private void* context. This can be NULL. + * @param err The error code status + * @see ucnv_getFromUCallBack + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_setFromUCallBack (UConverter * converter, + UConverterFromUCallback newAction, + const void *newContext, + UConverterFromUCallback *oldAction, + const void **oldContext, + UErrorCode * err); + +/** + * Converts an array of unicode characters to an array of codepage + * characters. This function is optimized for converting a continuous + * stream of data in buffer-sized chunks, where the entire source and + * target does not fit in available buffers. + * + * The source pointer is an in/out parameter. It starts out pointing where the + * conversion is to begin, and ends up pointing after the last UChar consumed. + * + * Target similarly starts out pointer at the first available byte in the output + * buffer, and ends up pointing after the last byte written to the output. + * + * The converter always attempts to consume the entire source buffer, unless + * (1.) the target buffer is full, or (2.) a failing error is returned from the + * current callback function. When a successful error status has been + * returned, it means that all of the source buffer has been + * consumed. At that point, the caller should reset the source and + * sourceLimit pointers to point to the next chunk. + * + * At the end of the stream (flush==true), the input is completely consumed + * when *source==sourceLimit and no error code is set. + * The converter object is then automatically reset by this function. + * (This means that a converter need not be reset explicitly between data + * streams if it finishes the previous stream without errors.) + * + * This is a <I>stateful</I> conversion. Additionally, even when all source data has + * been consumed, some data may be in the converters' internal state. + * Call this function repeatedly, updating the target pointers with + * the next empty chunk of target in case of a + * <TT>U_BUFFER_OVERFLOW_ERROR</TT>, and updating the source pointers + * with the next chunk of source when a successful error status is + * returned, until there are no more chunks of source data. + * @param converter the Unicode converter + * @param target I/O parameter. Input : Points to the beginning of the buffer to copy + * codepage characters to. Output : points to after the last codepage character copied + * to <TT>target</TT>. + * @param targetLimit the pointer just after last of the <TT>target</TT> buffer + * @param source I/O parameter, pointer to pointer to the source Unicode character buffer. + * @param sourceLimit the pointer just after the last of the source buffer + * @param offsets if NULL is passed, nothing will happen to it, otherwise it needs to have the same number + * of allocated cells as <TT>target</TT>. Will fill in offsets from target to source pointer + * e.g: <TT>offsets[3]</TT> is equal to 6, it means that the <TT>target[3]</TT> was a result of transcoding <TT>source[6]</TT> + * For output data carried across calls, and other data without a specific source character + * (such as from escape sequences or callbacks) -1 will be placed for offsets. + * @param flush set to <TT>true</TT> if the current source buffer is the last available + * chunk of the source, <TT>false</TT> otherwise. Note that if a failing status is returned, + * this function may have to be called multiple times with flush set to <TT>true</TT> until + * the source buffer is consumed. + * @param err the error status. <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> will be set if the + * converter is <TT>NULL</TT>. + * <code>U_BUFFER_OVERFLOW_ERROR</code> will be set if the target is full and there is + * still data to be written to the target. + * @see ucnv_fromUChars + * @see ucnv_convert + * @see ucnv_getMinCharSize + * @see ucnv_setToUCallBack + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_fromUnicode (UConverter * converter, + char **target, + const char *targetLimit, + const UChar ** source, + const UChar * sourceLimit, + int32_t* offsets, + UBool flush, + UErrorCode * err); + +/** + * Converts a buffer of codepage bytes into an array of unicode UChars + * characters. This function is optimized for converting a continuous + * stream of data in buffer-sized chunks, where the entire source and + * target does not fit in available buffers. + * + * The source pointer is an in/out parameter. It starts out pointing where the + * conversion is to begin, and ends up pointing after the last byte of source consumed. + * + * Target similarly starts out pointer at the first available UChar in the output + * buffer, and ends up pointing after the last UChar written to the output. + * It does NOT necessarily keep UChar sequences together. + * + * The converter always attempts to consume the entire source buffer, unless + * (1.) the target buffer is full, or (2.) a failing error is returned from the + * current callback function. When a successful error status has been + * returned, it means that all of the source buffer has been + * consumed. At that point, the caller should reset the source and + * sourceLimit pointers to point to the next chunk. + * + * At the end of the stream (flush==true), the input is completely consumed + * when *source==sourceLimit and no error code is set + * The converter object is then automatically reset by this function. + * (This means that a converter need not be reset explicitly between data + * streams if it finishes the previous stream without errors.) + * + * This is a <I>stateful</I> conversion. Additionally, even when all source data has + * been consumed, some data may be in the converters' internal state. + * Call this function repeatedly, updating the target pointers with + * the next empty chunk of target in case of a + * <TT>U_BUFFER_OVERFLOW_ERROR</TT>, and updating the source pointers + * with the next chunk of source when a successful error status is + * returned, until there are no more chunks of source data. + * @param converter the Unicode converter + * @param target I/O parameter. Input : Points to the beginning of the buffer to copy + * UChars into. Output : points to after the last UChar copied. + * @param targetLimit the pointer just after the end of the <TT>target</TT> buffer + * @param source I/O parameter, pointer to pointer to the source codepage buffer. + * @param sourceLimit the pointer to the byte after the end of the source buffer + * @param offsets if NULL is passed, nothing will happen to it, otherwise it needs to have the same number + * of allocated cells as <TT>target</TT>. Will fill in offsets from target to source pointer + * e.g: <TT>offsets[3]</TT> is equal to 6, it means that the <TT>target[3]</TT> was a result of transcoding <TT>source[6]</TT> + * For output data carried across calls, and other data without a specific source character + * (such as from escape sequences or callbacks) -1 will be placed for offsets. + * @param flush set to <TT>true</TT> if the current source buffer is the last available + * chunk of the source, <TT>false</TT> otherwise. Note that if a failing status is returned, + * this function may have to be called multiple times with flush set to <TT>true</TT> until + * the source buffer is consumed. + * @param err the error status. <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> will be set if the + * converter is <TT>NULL</TT>. + * <code>U_BUFFER_OVERFLOW_ERROR</code> will be set if the target is full and there is + * still data to be written to the target. + * @see ucnv_fromUChars + * @see ucnv_convert + * @see ucnv_getMinCharSize + * @see ucnv_setFromUCallBack + * @see ucnv_getNextUChar + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_toUnicode(UConverter *converter, + UChar **target, + const UChar *targetLimit, + const char **source, + const char *sourceLimit, + int32_t *offsets, + UBool flush, + UErrorCode *err); + +/** + * Convert the Unicode string into a codepage string using an existing UConverter. + * The output string is NUL-terminated if possible. + * + * This function is a more convenient but less powerful version of ucnv_fromUnicode(). + * It is only useful for whole strings, not for streaming conversion. + * + * The maximum output buffer capacity required (barring output from callbacks) will be + * UCNV_GET_MAX_BYTES_FOR_STRING(srcLength, ucnv_getMaxCharSize(cnv)). + * + * @param cnv the converter object to be used (ucnv_resetFromUnicode() will be called) + * @param src the input Unicode string + * @param srcLength the input string length, or -1 if NUL-terminated + * @param dest destination string buffer, can be NULL if destCapacity==0 + * @param destCapacity the number of chars available at dest + * @param pErrorCode normal ICU error code; + * common error codes that may be set by this function include + * U_BUFFER_OVERFLOW_ERROR, U_STRING_NOT_TERMINATED_WARNING, + * U_ILLEGAL_ARGUMENT_ERROR, and conversion errors + * @return the length of the output string, not counting the terminating NUL; + * if the length is greater than destCapacity, then the string will not fit + * and a buffer of the indicated length would need to be passed in + * @see ucnv_fromUnicode + * @see ucnv_convert + * @see UCNV_GET_MAX_BYTES_FOR_STRING + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_fromUChars(UConverter *cnv, + char *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert the codepage string into a Unicode string using an existing UConverter. + * The output string is NUL-terminated if possible. + * + * This function is a more convenient but less powerful version of ucnv_toUnicode(). + * It is only useful for whole strings, not for streaming conversion. + * + * The maximum output buffer capacity required (barring output from callbacks) will be + * 2*srcLength (each char may be converted into a surrogate pair). + * + * @param cnv the converter object to be used (ucnv_resetToUnicode() will be called) + * @param src the input codepage string + * @param srcLength the input string length, or -1 if NUL-terminated + * @param dest destination string buffer, can be NULL if destCapacity==0 + * @param destCapacity the number of UChars available at dest + * @param pErrorCode normal ICU error code; + * common error codes that may be set by this function include + * U_BUFFER_OVERFLOW_ERROR, U_STRING_NOT_TERMINATED_WARNING, + * U_ILLEGAL_ARGUMENT_ERROR, and conversion errors + * @return the length of the output string, not counting the terminating NUL; + * if the length is greater than destCapacity, then the string will not fit + * and a buffer of the indicated length would need to be passed in + * @see ucnv_toUnicode + * @see ucnv_convert + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_toUChars(UConverter *cnv, + UChar *dest, int32_t destCapacity, + const char *src, int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a codepage buffer into Unicode one character at a time. + * The input is completely consumed when the U_INDEX_OUTOFBOUNDS_ERROR is set. + * + * Advantage compared to ucnv_toUnicode() or ucnv_toUChars(): + * - Faster for small amounts of data, for most converters, e.g., + * US-ASCII, ISO-8859-1, UTF-8/16/32, and most "normal" charsets. + * (For complex converters, e.g., SCSU, UTF-7 and ISO 2022 variants, + * it uses ucnv_toUnicode() internally.) + * - Convenient. + * + * Limitations compared to ucnv_toUnicode(): + * - Always assumes flush=true. + * This makes ucnv_getNextUChar() unsuitable for "streaming" conversion, + * that is, for where the input is supplied in multiple buffers, + * because ucnv_getNextUChar() will assume the end of the input at the end + * of the first buffer. + * - Does not provide offset output. + * + * It is possible to "mix" ucnv_getNextUChar() and ucnv_toUnicode() because + * ucnv_getNextUChar() uses the current state of the converter + * (unlike ucnv_toUChars() which always resets first). + * However, if ucnv_getNextUChar() is called after ucnv_toUnicode() + * stopped in the middle of a character sequence (with flush=false), + * then ucnv_getNextUChar() will always use the slower ucnv_toUnicode() + * internally until the next character boundary. + * (This is new in ICU 2.6. In earlier releases, ucnv_getNextUChar() had to + * start at a character boundary.) + * + * Instead of using ucnv_getNextUChar(), it is recommended + * to convert using ucnv_toUnicode() or ucnv_toUChars() + * and then iterate over the text using U16_NEXT() or a UCharIterator (uiter.h) + * or a C++ CharacterIterator or similar. + * This allows streaming conversion and offset output, for example. + * + * <p>Handling of surrogate pairs and supplementary-plane code points:<br> + * There are two different kinds of codepages that provide mappings for surrogate characters: + * <ul> + * <li>Codepages like UTF-8, UTF-32, and GB 18030 provide direct representations for Unicode + * code points U+10000-U+10ffff as well as for single surrogates U+d800-U+dfff. + * Each valid sequence will result in exactly one returned code point. + * If a sequence results in a single surrogate, then that will be returned + * by itself, even if a neighboring sequence encodes the matching surrogate.</li> + * <li>Codepages like SCSU and LMBCS (and UTF-16) provide direct representations only for BMP code points + * including surrogates. Code points in supplementary planes are represented with + * two sequences, each encoding a surrogate. + * For these codepages, matching pairs of surrogates will be combined into single + * code points for returning from this function. + * (Note that SCSU is actually a mix of these codepage types.)</li> + * </ul></p> + * + * @param converter an open UConverter + * @param source the address of a pointer to the codepage buffer, will be + * updated to point after the bytes consumed in the conversion call. + * @param sourceLimit points to the end of the input buffer + * @param err fills in error status (see ucnv_toUnicode) + * <code>U_INDEX_OUTOFBOUNDS_ERROR</code> will be set if the input + * is empty or does not convert to any output (e.g.: pure state-change + * codes SI/SO, escape sequences for ISO 2022, + * or if the callback did not output anything, ...). + * This function will not set a <code>U_BUFFER_OVERFLOW_ERROR</code> because + * the "buffer" is the return code. However, there might be subsequent output + * stored in the converter object + * that will be returned in following calls to this function. + * @return a UChar32 resulting from the partial conversion of source + * @see ucnv_toUnicode + * @see ucnv_toUChars + * @see ucnv_convert + * @stable ICU 2.0 + */ +U_CAPI UChar32 U_EXPORT2 +ucnv_getNextUChar(UConverter * converter, + const char **source, + const char * sourceLimit, + UErrorCode * err); + +/** + * Convert from one external charset to another using two existing UConverters. + * Internally, two conversions - ucnv_toUnicode() and ucnv_fromUnicode() - + * are used, "pivoting" through 16-bit Unicode. + * + * Important: For streaming conversion (multiple function calls for successive + * parts of a text stream), the caller must provide a pivot buffer explicitly, + * and must preserve the pivot buffer and associated pointers from one + * call to another. (The buffer may be moved if its contents and the relative + * pointer positions are preserved.) + * + * There is a similar function, ucnv_convert(), + * which has the following limitations: + * - it takes charset names, not converter objects, so that + * - two converters are opened for each call + * - only single-string conversion is possible, not streaming operation + * - it does not provide enough information to find out, + * in case of failure, whether the toUnicode or + * the fromUnicode conversion failed + * + * By contrast, ucnv_convertEx() + * - takes UConverter parameters instead of charset names + * - fully exposes the pivot buffer for streaming conversion and complete error handling + * + * ucnv_convertEx() also provides further convenience: + * - an option to reset the converters at the beginning + * (if reset==true, see parameters; + * also sets *pivotTarget=*pivotSource=pivotStart) + * - allow NUL-terminated input + * (only a single NUL byte, will not work for charsets with multi-byte NULs) + * (if sourceLimit==NULL, see parameters) + * - terminate with a NUL on output + * (only a single NUL byte, not useful for charsets with multi-byte NULs), + * or set U_STRING_NOT_TERMINATED_WARNING if the output exactly fills + * the target buffer + * - the pivot buffer can be provided internally; + * possible only for whole-string conversion, not streaming conversion; + * in this case, the caller will not be able to get details about where an + * error occurred + * (if pivotStart==NULL, see below) + * + * The function returns when one of the following is true: + * - the entire source text has been converted successfully to the target buffer + * - a target buffer overflow occurred (U_BUFFER_OVERFLOW_ERROR) + * - a conversion error occurred + * (other U_FAILURE(), see description of pErrorCode) + * + * Limitation compared to the direct use of + * ucnv_fromUnicode() and ucnv_toUnicode(): + * ucnv_convertEx() does not provide offset information. + * + * Limitation compared to ucnv_fromUChars() and ucnv_toUChars(): + * ucnv_convertEx() does not support preflighting directly. + * + * Sample code for converting a single string from + * one external charset to UTF-8, ignoring the location of errors: + * + * \code + * int32_t + * myToUTF8(UConverter *cnv, + * const char *s, int32_t length, + * char *u8, int32_t capacity, + * UErrorCode *pErrorCode) { + * UConverter *utf8Cnv; + * char *target; + * + * if(U_FAILURE(*pErrorCode)) { + * return 0; + * } + * + * utf8Cnv=myGetCachedUTF8Converter(pErrorCode); + * if(U_FAILURE(*pErrorCode)) { + * return 0; + * } + * + * if(length<0) { + * length=strlen(s); + * } + * target=u8; + * ucnv_convertEx(utf8Cnv, cnv, + * &target, u8+capacity, + * &s, s+length, + * NULL, NULL, NULL, NULL, + * true, true, + * pErrorCode); + * + * myReleaseCachedUTF8Converter(utf8Cnv); + * + * // return the output string length, but without preflighting + * return (int32_t)(target-u8); + * } + * \endcode + * + * @param targetCnv Output converter, used to convert from the UTF-16 pivot + * to the target using ucnv_fromUnicode(). + * @param sourceCnv Input converter, used to convert from the source to + * the UTF-16 pivot using ucnv_toUnicode(). + * @param target I/O parameter, same as for ucnv_fromUChars(). + * Input: *target points to the beginning of the target buffer. + * Output: *target points to the first unit after the last char written. + * @param targetLimit Pointer to the first unit after the target buffer. + * @param source I/O parameter, same as for ucnv_toUChars(). + * Input: *source points to the beginning of the source buffer. + * Output: *source points to the first unit after the last char read. + * @param sourceLimit Pointer to the first unit after the source buffer. + * @param pivotStart Pointer to the UTF-16 pivot buffer. If pivotStart==NULL, + * then an internal buffer is used and the other pivot + * arguments are ignored and can be NULL as well. + * @param pivotSource I/O parameter, same as source in ucnv_fromUChars() for + * conversion from the pivot buffer to the target buffer. + * @param pivotTarget I/O parameter, same as target in ucnv_toUChars() for + * conversion from the source buffer to the pivot buffer. + * It must be pivotStart<=*pivotSource<=*pivotTarget<=pivotLimit + * and pivotStart<pivotLimit (unless pivotStart==NULL). + * @param pivotLimit Pointer to the first unit after the pivot buffer. + * @param reset If true, then ucnv_resetToUnicode(sourceCnv) and + * ucnv_resetFromUnicode(targetCnv) are called, and the + * pivot pointers are reset (*pivotTarget=*pivotSource=pivotStart). + * @param flush If true, indicates the end of the input. + * Passed directly to ucnv_toUnicode(), and carried over to + * ucnv_fromUnicode() when the source is empty as well. + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * U_BUFFER_OVERFLOW_ERROR always refers to the target buffer + * because overflows into the pivot buffer are handled internally. + * Other conversion errors are from the source-to-pivot + * conversion if *pivotSource==pivotStart, otherwise from + * the pivot-to-target conversion. + * + * @see ucnv_convert + * @see ucnv_fromAlgorithmic + * @see ucnv_toAlgorithmic + * @see ucnv_fromUnicode + * @see ucnv_toUnicode + * @see ucnv_fromUChars + * @see ucnv_toUChars + * @stable ICU 2.6 + */ +U_CAPI void U_EXPORT2 +ucnv_convertEx(UConverter *targetCnv, UConverter *sourceCnv, + char **target, const char *targetLimit, + const char **source, const char *sourceLimit, + UChar *pivotStart, UChar **pivotSource, + UChar **pivotTarget, const UChar *pivotLimit, + UBool reset, UBool flush, + UErrorCode *pErrorCode); + +/** + * Convert from one external charset to another. + * Internally, two converters are opened according to the name arguments, + * then the text is converted to and from the 16-bit Unicode "pivot" + * using ucnv_convertEx(), then the converters are closed again. + * + * This is a convenience function, not an efficient way to convert a lot of text: + * ucnv_convert() + * - takes charset names, not converter objects, so that + * - two converters are opened for each call + * - only single-string conversion is possible, not streaming operation + * - does not provide enough information to find out, + * in case of failure, whether the toUnicode or + * the fromUnicode conversion failed + * - allows NUL-terminated input + * (only a single NUL byte, will not work for charsets with multi-byte NULs) + * (if sourceLength==-1, see parameters) + * - terminate with a NUL on output + * (only a single NUL byte, not useful for charsets with multi-byte NULs), + * or set U_STRING_NOT_TERMINATED_WARNING if the output exactly fills + * the target buffer + * - a pivot buffer is provided internally + * + * The function returns when one of the following is true: + * - the entire source text has been converted successfully to the target buffer + * and either the target buffer is terminated with a single NUL byte + * or the error code is set to U_STRING_NOT_TERMINATED_WARNING + * - a target buffer overflow occurred (U_BUFFER_OVERFLOW_ERROR) + * and the full output string length is returned ("preflighting") + * - a conversion error occurred + * (other U_FAILURE(), see description of pErrorCode) + * + * @param toConverterName The name of the converter that is used to convert + * from the UTF-16 pivot buffer to the target. + * @param fromConverterName The name of the converter that is used to convert + * from the source to the UTF-16 pivot buffer. + * @param target Pointer to the output buffer. + * @param targetCapacity Capacity of the target, in bytes. + * @param source Pointer to the input buffer. + * @param sourceLength Length of the input text, in bytes, or -1 for NUL-terminated input. + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Length of the complete output text in bytes, even if it exceeds the targetCapacity + * and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see ucnv_convertEx + * @see ucnv_fromAlgorithmic + * @see ucnv_toAlgorithmic + * @see ucnv_fromUnicode + * @see ucnv_toUnicode + * @see ucnv_fromUChars + * @see ucnv_toUChars + * @see ucnv_getNextUChar + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_convert(const char *toConverterName, + const char *fromConverterName, + char *target, + int32_t targetCapacity, + const char *source, + int32_t sourceLength, + UErrorCode *pErrorCode); + +/** + * Convert from one external charset to another. + * Internally, the text is converted to and from the 16-bit Unicode "pivot" + * using ucnv_convertEx(). ucnv_toAlgorithmic() works exactly like ucnv_convert() + * except that the two converters need not be looked up and opened completely. + * + * The source-to-pivot conversion uses the cnv converter parameter. + * The pivot-to-target conversion uses a purely algorithmic converter + * according to the specified type, e.g., UCNV_UTF8 for a UTF-8 converter. + * + * Internally, the algorithmic converter is opened and closed for each + * function call, which is more efficient than using the public ucnv_open() + * but somewhat less efficient than only resetting an existing converter + * and using ucnv_convertEx(). + * + * This function is more convenient than ucnv_convertEx() for single-string + * conversions, especially when "preflighting" is desired (returning the length + * of the complete output even if it does not fit into the target buffer; + * see the User Guide Strings chapter). See ucnv_convert() for details. + * + * @param algorithmicType UConverterType constant identifying the desired target + * charset as a purely algorithmic converter. + * Those are converters for Unicode charsets like + * UTF-8, BOCU-1, SCSU, UTF-7, IMAP-mailbox-name, etc., + * as well as US-ASCII and ISO-8859-1. + * @param cnv The converter that is used to convert + * from the source to the UTF-16 pivot buffer. + * @param target Pointer to the output buffer. + * @param targetCapacity Capacity of the target, in bytes. + * @param source Pointer to the input buffer. + * @param sourceLength Length of the input text, in bytes + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Length of the complete output text in bytes, even if it exceeds the targetCapacity + * and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see ucnv_fromAlgorithmic + * @see ucnv_convert + * @see ucnv_convertEx + * @see ucnv_fromUnicode + * @see ucnv_toUnicode + * @see ucnv_fromUChars + * @see ucnv_toUChars + * @stable ICU 2.6 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_toAlgorithmic(UConverterType algorithmicType, + UConverter *cnv, + char *target, int32_t targetCapacity, + const char *source, int32_t sourceLength, + UErrorCode *pErrorCode); + +/** + * Convert from one external charset to another. + * Internally, the text is converted to and from the 16-bit Unicode "pivot" + * using ucnv_convertEx(). ucnv_fromAlgorithmic() works exactly like ucnv_convert() + * except that the two converters need not be looked up and opened completely. + * + * The source-to-pivot conversion uses a purely algorithmic converter + * according to the specified type, e.g., UCNV_UTF8 for a UTF-8 converter. + * The pivot-to-target conversion uses the cnv converter parameter. + * + * Internally, the algorithmic converter is opened and closed for each + * function call, which is more efficient than using the public ucnv_open() + * but somewhat less efficient than only resetting an existing converter + * and using ucnv_convertEx(). + * + * This function is more convenient than ucnv_convertEx() for single-string + * conversions, especially when "preflighting" is desired (returning the length + * of the complete output even if it does not fit into the target buffer; + * see the User Guide Strings chapter). See ucnv_convert() for details. + * + * @param cnv The converter that is used to convert + * from the UTF-16 pivot buffer to the target. + * @param algorithmicType UConverterType constant identifying the desired source + * charset as a purely algorithmic converter. + * Those are converters for Unicode charsets like + * UTF-8, BOCU-1, SCSU, UTF-7, IMAP-mailbox-name, etc., + * as well as US-ASCII and ISO-8859-1. + * @param target Pointer to the output buffer. + * @param targetCapacity Capacity of the target, in bytes. + * @param source Pointer to the input buffer. + * @param sourceLength Length of the input text, in bytes + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Length of the complete output text in bytes, even if it exceeds the targetCapacity + * and a U_BUFFER_OVERFLOW_ERROR is set. + * + * @see ucnv_fromAlgorithmic + * @see ucnv_convert + * @see ucnv_convertEx + * @see ucnv_fromUnicode + * @see ucnv_toUnicode + * @see ucnv_fromUChars + * @see ucnv_toUChars + * @stable ICU 2.6 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_fromAlgorithmic(UConverter *cnv, + UConverterType algorithmicType, + char *target, int32_t targetCapacity, + const char *source, int32_t sourceLength, + UErrorCode *pErrorCode); + +/** + * Frees up memory occupied by unused, cached converter shared data. + * + * @return the number of cached converters successfully deleted + * @see ucnv_close + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_flushCache(void); + +/** + * Returns the number of available converters, as per the alias file. + * + * @return the number of available converters + * @see ucnv_getAvailableName + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_countAvailable(void); + +/** + * Gets the canonical converter name of the specified converter from a list of + * all available converters contaied in the alias file. All converters + * in this list can be opened. + * + * @param n the index to a converter available on the system (in the range <TT>[0..ucnv_countAvaiable()]</TT>) + * @return a pointer a string (library owned), or <TT>NULL</TT> if the index is out of bounds. + * @see ucnv_countAvailable + * @stable ICU 2.0 + */ +U_CAPI const char* U_EXPORT2 +ucnv_getAvailableName(int32_t n); + +/** + * Returns a UEnumeration to enumerate all of the canonical converter + * names, as per the alias file, regardless of the ability to open each + * converter. + * + * @return A UEnumeration object for getting all the recognized canonical + * converter names. + * @see ucnv_getAvailableName + * @see uenum_close + * @see uenum_next + * @stable ICU 2.4 + */ +U_CAPI UEnumeration * U_EXPORT2 +ucnv_openAllNames(UErrorCode *pErrorCode); + +/** + * Gives the number of aliases for a given converter or alias name. + * If the alias is ambiguous, then the preferred converter is used + * and the status is set to U_AMBIGUOUS_ALIAS_WARNING. + * This method only enumerates the listed entries in the alias file. + * @param alias alias name + * @param pErrorCode error status + * @return number of names on alias list for given alias + * @stable ICU 2.0 + */ +U_CAPI uint16_t U_EXPORT2 +ucnv_countAliases(const char *alias, UErrorCode *pErrorCode); + +/** + * Gives the name of the alias at given index of alias list. + * This method only enumerates the listed entries in the alias file. + * If the alias is ambiguous, then the preferred converter is used + * and the status is set to U_AMBIGUOUS_ALIAS_WARNING. + * @param alias alias name + * @param n index in alias list + * @param pErrorCode result of operation + * @return returns the name of the alias at given index + * @see ucnv_countAliases + * @stable ICU 2.0 + */ +U_CAPI const char * U_EXPORT2 +ucnv_getAlias(const char *alias, uint16_t n, UErrorCode *pErrorCode); + +/** + * Fill-up the list of alias names for the given alias. + * This method only enumerates the listed entries in the alias file. + * If the alias is ambiguous, then the preferred converter is used + * and the status is set to U_AMBIGUOUS_ALIAS_WARNING. + * @param alias alias name + * @param aliases fill-in list, aliases is a pointer to an array of + * <code>ucnv_countAliases()</code> string-pointers + * (<code>const char *</code>) that will be filled in. + * The strings themselves are owned by the library. + * @param pErrorCode result of operation + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_getAliases(const char *alias, const char **aliases, UErrorCode *pErrorCode); + +/** + * Return a new UEnumeration object for enumerating all the + * alias names for a given converter that are recognized by a standard. + * This method only enumerates the listed entries in the alias file. + * The convrtrs.txt file can be modified to change the results of + * this function. + * The first result in this list is the same result given by + * <code>ucnv_getStandardName</code>, which is the default alias for + * the specified standard name. The returned object must be closed with + * <code>uenum_close</code> when you are done with the object. + * + * @param convName original converter name + * @param standard name of the standard governing the names; MIME and IANA + * are such standards + * @param pErrorCode The error code + * @return A UEnumeration object for getting all aliases that are recognized + * by a standard. If any of the parameters are invalid, NULL + * is returned. + * @see ucnv_getStandardName + * @see uenum_close + * @see uenum_next + * @stable ICU 2.2 + */ +U_CAPI UEnumeration * U_EXPORT2 +ucnv_openStandardNames(const char *convName, + const char *standard, + UErrorCode *pErrorCode); + +/** + * Gives the number of standards associated to converter names. + * @return number of standards + * @stable ICU 2.0 + */ +U_CAPI uint16_t U_EXPORT2 +ucnv_countStandards(void); + +/** + * Gives the name of the standard at given index of standard list. + * @param n index in standard list + * @param pErrorCode result of operation + * @return returns the name of the standard at given index. Owned by the library. + * @stable ICU 2.0 + */ +U_CAPI const char * U_EXPORT2 +ucnv_getStandard(uint16_t n, UErrorCode *pErrorCode); + +/** + * Returns a standard name for a given converter name. + * <p> + * Example alias table:<br> + * conv alias1 { STANDARD1 } alias2 { STANDARD1* } + * <p> + * Result of ucnv_getStandardName("conv", "STANDARD1") from example + * alias table:<br> + * <b>"alias2"</b> + * + * @param name original converter name + * @param standard name of the standard governing the names; MIME and IANA + * are such standards + * @param pErrorCode result of operation + * @return returns the standard converter name; + * if a standard converter name cannot be determined, + * then <code>NULL</code> is returned. Owned by the library. + * @stable ICU 2.0 + */ +U_CAPI const char * U_EXPORT2 +ucnv_getStandardName(const char *name, const char *standard, UErrorCode *pErrorCode); + +/** + * This function will return the internal canonical converter name of the + * tagged alias. This is the opposite of ucnv_openStandardNames, which + * returns the tagged alias given the canonical name. + * <p> + * Example alias table:<br> + * conv alias1 { STANDARD1 } alias2 { STANDARD1* } + * <p> + * Result of ucnv_getStandardName("alias1", "STANDARD1") from example + * alias table:<br> + * <b>"conv"</b> + * + * @return returns the canonical converter name; + * if a standard or alias name cannot be determined, + * then <code>NULL</code> is returned. The returned string is + * owned by the library. + * @see ucnv_getStandardName + * @stable ICU 2.4 + */ +U_CAPI const char * U_EXPORT2 +ucnv_getCanonicalName(const char *alias, const char *standard, UErrorCode *pErrorCode); + +/** + * Returns the current default converter name. If you want to open + * a default converter, you do not need to use this function. + * It is faster if you pass a NULL argument to ucnv_open the + * default converter. + * + * If U_CHARSET_IS_UTF8 is defined to 1 in utypes.h then this function + * always returns "UTF-8". + * + * @return returns the current default converter name. + * Storage owned by the library + * @see ucnv_setDefaultName + * @stable ICU 2.0 + */ +U_CAPI const char * U_EXPORT2 +ucnv_getDefaultName(void); + +#ifndef U_HIDE_SYSTEM_API +/** + * This function is not thread safe. DO NOT call this function when ANY ICU + * function is being used from more than one thread! This function sets the + * current default converter name. If this function needs to be called, it + * should be called during application initialization. Most of the time, the + * results from ucnv_getDefaultName() or ucnv_open with a NULL string argument + * is sufficient for your application. + * + * If U_CHARSET_IS_UTF8 is defined to 1 in utypes.h then this function + * does nothing. + * + * @param name the converter name to be the default (must be known by ICU). + * @see ucnv_getDefaultName + * @system + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_setDefaultName(const char *name); +#endif /* U_HIDE_SYSTEM_API */ + +/** + * Fixes the backslash character mismapping. For example, in SJIS, the backslash + * character in the ASCII portion is also used to represent the yen currency sign. + * When mapping from Unicode character 0x005C, it's unclear whether to map the + * character back to yen or backslash in SJIS. This function will take the input + * buffer and replace all the yen sign characters with backslash. This is necessary + * when the user tries to open a file with the input buffer on Windows. + * This function will test the converter to see whether such mapping is + * required. You can sometimes avoid using this function by using the correct version + * of Shift-JIS. + * + * @param cnv The converter representing the target codepage. + * @param source the input buffer to be fixed + * @param sourceLen the length of the input buffer + * @see ucnv_isAmbiguous + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_fixFileSeparator(const UConverter *cnv, UChar *source, int32_t sourceLen); + +/** + * Determines if the converter contains ambiguous mappings of the same + * character or not. + * @param cnv the converter to be tested + * @return true if the converter contains ambiguous mapping of the same + * character, false otherwise. + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +ucnv_isAmbiguous(const UConverter *cnv); + +/** + * Sets the converter to use fallback mappings or not. + * Regardless of this flag, the converter will always use + * fallbacks from Unicode Private Use code points, as well as + * reverse fallbacks (to Unicode). + * For details see ".ucm File Format" + * in the Conversion Data chapter of the ICU User Guide: + * http://www.icu-project.org/userguide/conversion-data.html#ucmformat + * + * @param cnv The converter to set the fallback mapping usage on. + * @param usesFallback true if the user wants the converter to take advantage of the fallback + * mapping, false otherwise. + * @stable ICU 2.0 + * @see ucnv_usesFallback + */ +U_CAPI void U_EXPORT2 +ucnv_setFallback(UConverter *cnv, UBool usesFallback); + +/** + * Determines if the converter uses fallback mappings or not. + * This flag has restrictions, see ucnv_setFallback(). + * + * @param cnv The converter to be tested + * @return true if the converter uses fallback, false otherwise. + * @stable ICU 2.0 + * @see ucnv_setFallback + */ +U_CAPI UBool U_EXPORT2 +ucnv_usesFallback(const UConverter *cnv); + +/** + * Detects Unicode signature byte sequences at the start of the byte stream + * and returns the charset name of the indicated Unicode charset. + * NULL is returned when no Unicode signature is recognized. + * The number of bytes in the signature is output as well. + * + * The caller can ucnv_open() a converter using the charset name. + * The first code unit (UChar) from the start of the stream will be U+FEFF + * (the Unicode BOM/signature character) and can usually be ignored. + * + * For most Unicode charsets it is also possible to ignore the indicated + * number of initial stream bytes and start converting after them. + * However, there are stateful Unicode charsets (UTF-7 and BOCU-1) for which + * this will not work. Therefore, it is best to ignore the first output UChar + * instead of the input signature bytes. + * <p> + * Usage: + * \snippet samples/ucnv/convsamp.cpp ucnv_detectUnicodeSignature + * + * @param source The source string in which the signature should be detected. + * @param sourceLength Length of the input string, or -1 if terminated with a NUL byte. + * @param signatureLength A pointer to int32_t to receive the number of bytes that make up the signature + * of the detected UTF. 0 if not detected. + * Can be a NULL pointer. + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return The name of the encoding detected. NULL if encoding is not detected. + * @stable ICU 2.4 + */ +U_CAPI const char* U_EXPORT2 +ucnv_detectUnicodeSignature(const char* source, + int32_t sourceLength, + int32_t *signatureLength, + UErrorCode *pErrorCode); + +/** + * Returns the number of UChars held in the converter's internal state + * because more input is needed for completing the conversion. This function is + * useful for mapping semantics of ICU's converter interface to those of iconv, + * and this information is not needed for normal conversion. + * @param cnv The converter in which the input is held + * @param status ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return The number of UChars in the state. -1 if an error is encountered. + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_fromUCountPending(const UConverter* cnv, UErrorCode* status); + +/** + * Returns the number of chars held in the converter's internal state + * because more input is needed for completing the conversion. This function is + * useful for mapping semantics of ICU's converter interface to those of iconv, + * and this information is not needed for normal conversion. + * @param cnv The converter in which the input is held as internal state + * @param status ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return The number of chars in the state. -1 if an error is encountered. + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +ucnv_toUCountPending(const UConverter* cnv, UErrorCode* status); + +/** + * Returns whether or not the charset of the converter has a fixed number of bytes + * per charset character. + * An example of this are converters that are of the type UCNV_SBCS or UCNV_DBCS. + * Another example is UTF-32 which is always 4 bytes per character. + * A Unicode code point may be represented by more than one UTF-8 or UTF-16 code unit + * but a UTF-32 converter encodes each code point with 4 bytes. + * Note: This method is not intended to be used to determine whether the charset has a + * fixed ratio of bytes to Unicode codes <i>units</i> for any particular Unicode encoding form. + * false is returned with the UErrorCode if error occurs or cnv is NULL. + * @param cnv The converter to be tested + * @param status ICU error code in/out paramter + * @return true if the converter is fixed-width + * @stable ICU 4.8 + */ +U_CAPI UBool U_EXPORT2 +ucnv_isFixedWidth(UConverter *cnv, UErrorCode *status); + +#endif + +#endif +/*_UCNV*/ diff --git a/thirdparty/icu4c/common/unicode/ucnv_cb.h b/thirdparty/icu4c/common/unicode/ucnv_cb.h new file mode 100644 index 0000000000..41845d1bca --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucnv_cb.h @@ -0,0 +1,164 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 2000-2004, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** + * ucnv_cb.h: + * External APIs for the ICU's codeset conversion library + * Helena Shih + * + * Modification History: + * + * Date Name Description + */ + +/** + * \file + * \brief C UConverter functions to aid the writers of callbacks + * + * <h2> Callback API for UConverter </h2> + * + * These functions are provided here for the convenience of the callback + * writer. If you are just looking for callback functions to use, please + * see ucnv_err.h. DO NOT call these functions directly when you are + * working with converters, unless your code has been called as a callback + * via ucnv_setFromUCallback or ucnv_setToUCallback !! + * + * A note about error codes and overflow. Unlike other ICU functions, + * these functions do not expect the error status to be U_ZERO_ERROR. + * Callbacks must be much more careful about their error codes. + * The error codes used here are in/out parameters, which should be passed + * back in the callback's error parameter. + * + * For example, if you call ucnv_cbfromUWriteBytes to write data out + * to the output codepage, it may return U_BUFFER_OVERFLOW_ERROR if + * the data did not fit in the target. But this isn't a failing error, + * in fact, ucnv_cbfromUWriteBytes may be called AGAIN with the error + * status still U_BUFFER_OVERFLOW_ERROR to attempt to write further bytes, + * which will also go into the internal overflow buffers. + * + * Concerning offsets, the 'offset' parameters here are relative to the start + * of SOURCE. For example, Suppose the string "ABCD" was being converted + * from Unicode into a codepage which doesn't have a mapping for 'B'. + * 'A' will be written out correctly, but + * The FromU Callback will be called on an unassigned character for 'B'. + * At this point, this is the state of the world: + * Target: A [..] [points after A] + * Source: A B [C] D [points to C - B has been consumed] + * 0 1 2 3 + * codePoint = "B" [the unassigned codepoint] + * + * Now, suppose a callback wants to write the substitution character '?' to + * the target. It calls ucnv_cbFromUWriteBytes() to write the ?. + * It should pass ZERO as the offset, because the offset as far as the + * callback is concerned is relative to the SOURCE pointer [which points + * before 'C'.] If the callback goes into the args and consumes 'C' also, + * it would call FromUWriteBytes with an offset of 1 (and advance the source + * pointer). + * + */ + +#ifndef UCNV_CB_H +#define UCNV_CB_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_CONVERSION + +#include "unicode/ucnv.h" +#include "unicode/ucnv_err.h" + +/** + * ONLY used by FromU callback functions. + * Writes out the specified byte output bytes to the target byte buffer or to converter internal buffers. + * + * @param args callback fromUnicode arguments + * @param source source bytes to write + * @param length length of bytes to write + * @param offsetIndex the relative offset index from callback. + * @param err error status. If <TT>U_BUFFER_OVERFLOW</TT> is returned, then U_BUFFER_OVERFLOW <STRONG>must</STRONG> + * be returned to the user, because it means that not all data could be written into the target buffer, and some is + * in the converter error buffer. + * @see ucnv_cbFromUWriteSub + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_cbFromUWriteBytes (UConverterFromUnicodeArgs *args, + const char* source, + int32_t length, + int32_t offsetIndex, + UErrorCode * err); + +/** + * ONLY used by FromU callback functions. + * This function will write out the correct substitution character sequence + * to the target. + * + * @param args callback fromUnicode arguments + * @param offsetIndex the relative offset index from the current source pointer to be used + * @param err error status. If <TT>U_BUFFER_OVERFLOW</TT> is returned, then U_BUFFER_OVERFLOW <STRONG>must</STRONG> + * be returned to the user, because it means that not all data could be written into the target buffer, and some is + * in the converter error buffer. + * @see ucnv_cbFromUWriteBytes + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ucnv_cbFromUWriteSub (UConverterFromUnicodeArgs *args, + int32_t offsetIndex, + UErrorCode * err); + +/** + * ONLY used by fromU callback functions. + * This function will write out the error character(s) to the target UChar buffer. + * + * @param args callback fromUnicode arguments + * @param source pointer to pointer to first UChar to write [on exit: 1 after last UChar processed] + * @param sourceLimit pointer after last UChar to write + * @param offsetIndex the relative offset index from callback which will be set + * @param err error status <TT>U_BUFFER_OVERFLOW</TT> + * @see ucnv_cbToUWriteSub + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 ucnv_cbFromUWriteUChars(UConverterFromUnicodeArgs *args, + const UChar** source, + const UChar* sourceLimit, + int32_t offsetIndex, + UErrorCode * err); + +/** + * ONLY used by ToU callback functions. + * This function will write out the specified characters to the target + * UChar buffer. + * + * @param args callback toUnicode arguments + * @param source source string to write + * @param length the length of source string + * @param offsetIndex the relative offset index which will be written. + * @param err error status <TT>U_BUFFER_OVERFLOW</TT> + * @see ucnv_cbToUWriteSub + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 ucnv_cbToUWriteUChars (UConverterToUnicodeArgs *args, + const UChar* source, + int32_t length, + int32_t offsetIndex, + UErrorCode * err); + +/** + * ONLY used by ToU callback functions. + * This function will write out the Unicode substitution character (U+FFFD). + * + * @param args callback fromUnicode arguments + * @param offsetIndex the relative offset index from callback. + * @param err error status <TT>U_BUFFER_OVERFLOW</TT> + * @see ucnv_cbToUWriteUChars + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 ucnv_cbToUWriteSub (UConverterToUnicodeArgs *args, + int32_t offsetIndex, + UErrorCode * err); +#endif + +#endif diff --git a/thirdparty/icu4c/common/unicode/ucnv_err.h b/thirdparty/icu4c/common/unicode/ucnv_err.h new file mode 100644 index 0000000000..7209ba5f7b --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucnv_err.h @@ -0,0 +1,465 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1999-2009, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** + * + * + * ucnv_err.h: + */ + +/** + * \file + * \brief C UConverter predefined error callbacks + * + * <h2>Error Behaviour Functions</h2> + * Defines some error behaviour functions called by ucnv_{from,to}Unicode + * These are provided as part of ICU and many are stable, but they + * can also be considered only as an example of what can be done with + * callbacks. You may of course write your own. + * + * If you want to write your own, you may also find the functions from + * ucnv_cb.h useful when writing your own callbacks. + * + * These functions, although public, should NEVER be called directly. + * They should be used as parameters to the ucnv_setFromUCallback + * and ucnv_setToUCallback functions, to set the behaviour of a converter + * when it encounters ILLEGAL/UNMAPPED/INVALID sequences. + * + * usage example: 'STOP' doesn't need any context, but newContext + * could be set to something other than 'NULL' if needed. The available + * contexts in this header can modify the default behavior of the callback. + * + * \code + * UErrorCode err = U_ZERO_ERROR; + * UConverter *myConverter = ucnv_open("ibm-949", &err); + * const void *oldContext; + * UConverterFromUCallback oldAction; + * + * + * if (U_SUCCESS(err)) + * { + * ucnv_setFromUCallBack(myConverter, + * UCNV_FROM_U_CALLBACK_STOP, + * NULL, + * &oldAction, + * &oldContext, + * &status); + * } + * \endcode + * + * The code above tells "myConverter" to stop when it encounters an + * ILLEGAL/TRUNCATED/INVALID sequences when it is used to convert from + * Unicode -> Codepage. The behavior from Codepage to Unicode is not changed, + * and ucnv_setToUCallBack would need to be called in order to change + * that behavior too. + * + * Here is an example with a context: + * + * \code + * UErrorCode err = U_ZERO_ERROR; + * UConverter *myConverter = ucnv_open("ibm-949", &err); + * const void *oldContext; + * UConverterFromUCallback oldAction; + * + * + * if (U_SUCCESS(err)) + * { + * ucnv_setToUCallBack(myConverter, + * UCNV_TO_U_CALLBACK_SUBSTITUTE, + * UCNV_SUB_STOP_ON_ILLEGAL, + * &oldAction, + * &oldContext, + * &status); + * } + * \endcode + * + * The code above tells "myConverter" to stop when it encounters an + * ILLEGAL/TRUNCATED/INVALID sequences when it is used to convert from + * Codepage -> Unicode. Any unmapped and legal characters will be + * substituted to be the default substitution character. + */ + +#ifndef UCNV_ERR_H +#define UCNV_ERR_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_CONVERSION + +/** Forward declaring the UConverter structure. @stable ICU 2.0 */ +struct UConverter; + +/** @stable ICU 2.0 */ +typedef struct UConverter UConverter; + +/** + * FROM_U, TO_U context options for sub callback + * @stable ICU 2.0 + */ +#define UCNV_SUB_STOP_ON_ILLEGAL "i" + +/** + * FROM_U, TO_U context options for skip callback + * @stable ICU 2.0 + */ +#define UCNV_SKIP_STOP_ON_ILLEGAL "i" + +/** + * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to ICU (%UXXXX) + * @stable ICU 2.0 + */ +#define UCNV_ESCAPE_ICU NULL +/** + * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to JAVA (\\uXXXX) + * @stable ICU 2.0 + */ +#define UCNV_ESCAPE_JAVA "J" +/** + * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to C (\\uXXXX \\UXXXXXXXX) + * TO_U_CALLBACK_ESCAPE option to escape the character value according to C (\\xXXXX) + * @stable ICU 2.0 + */ +#define UCNV_ESCAPE_C "C" +/** + * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to XML Decimal escape \htmlonly(&#DDDD;)\endhtmlonly + * TO_U_CALLBACK_ESCAPE context option to escape the character value according to XML Decimal escape \htmlonly(&#DDDD;)\endhtmlonly + * @stable ICU 2.0 + */ +#define UCNV_ESCAPE_XML_DEC "D" +/** + * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to XML Hex escape \htmlonly(&#xXXXX;)\endhtmlonly + * TO_U_CALLBACK_ESCAPE context option to escape the character value according to XML Hex escape \htmlonly(&#xXXXX;)\endhtmlonly + * @stable ICU 2.0 + */ +#define UCNV_ESCAPE_XML_HEX "X" +/** + * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to Unicode (U+XXXXX) + * @stable ICU 2.0 + */ +#define UCNV_ESCAPE_UNICODE "U" + +/** + * FROM_U_CALLBACK_ESCAPE context option to escape the code unit according to CSS2 conventions (\\HH..H<space>, that is, + * a backslash, 1..6 hex digits, and a space) + * @stable ICU 4.0 + */ +#define UCNV_ESCAPE_CSS2 "S" + +/** + * The process condition code to be used with the callbacks. + * Codes which are greater than UCNV_IRREGULAR should be + * passed on to any chained callbacks. + * @stable ICU 2.0 + */ +typedef enum { + UCNV_UNASSIGNED = 0, /**< The code point is unassigned. + The error code U_INVALID_CHAR_FOUND will be set. */ + UCNV_ILLEGAL = 1, /**< The code point is illegal. For example, + \\x81\\x2E is illegal in SJIS because \\x2E + is not a valid trail byte for the \\x81 + lead byte. + Also, starting with Unicode 3.0.1, non-shortest byte sequences + in UTF-8 (like \\xC1\\xA1 instead of \\x61 for U+0061) + are also illegal, not just irregular. + The error code U_ILLEGAL_CHAR_FOUND will be set. */ + UCNV_IRREGULAR = 2, /**< The codepoint is not a regular sequence in + the encoding. For example, \\xED\\xA0\\x80..\\xED\\xBF\\xBF + are irregular UTF-8 byte sequences for single surrogate + code points. + The error code U_INVALID_CHAR_FOUND will be set. */ + UCNV_RESET = 3, /**< The callback is called with this reason when a + 'reset' has occurred. Callback should reset all + state. */ + UCNV_CLOSE = 4, /**< Called when the converter is closed. The + callback should release any allocated memory.*/ + UCNV_CLONE = 5 /**< Called when ucnv_safeClone() is called on the + converter. the pointer available as the + 'context' is an alias to the original converters' + context pointer. If the context must be owned + by the new converter, the callback must clone + the data and call ucnv_setFromUCallback + (or setToUCallback) with the correct pointer. + @stable ICU 2.2 + */ +} UConverterCallbackReason; + + +/** + * The structure for the fromUnicode callback function parameter. + * @stable ICU 2.0 + */ +typedef struct { + uint16_t size; /**< The size of this struct. @stable ICU 2.0 */ + UBool flush; /**< The internal state of converter will be reset and data flushed if set to true. @stable ICU 2.0 */ + UConverter *converter; /**< Pointer to the converter that is opened and to which this struct is passed as an argument. @stable ICU 2.0 */ + const UChar *source; /**< Pointer to the source source buffer. @stable ICU 2.0 */ + const UChar *sourceLimit; /**< Pointer to the limit (end + 1) of source buffer. @stable ICU 2.0 */ + char *target; /**< Pointer to the target buffer. @stable ICU 2.0 */ + const char *targetLimit; /**< Pointer to the limit (end + 1) of target buffer. @stable ICU 2.0 */ + int32_t *offsets; /**< Pointer to the buffer that receives the offsets. *offset = blah ; offset++;. @stable ICU 2.0 */ +} UConverterFromUnicodeArgs; + + +/** + * The structure for the toUnicode callback function parameter. + * @stable ICU 2.0 + */ +typedef struct { + uint16_t size; /**< The size of this struct @stable ICU 2.0 */ + UBool flush; /**< The internal state of converter will be reset and data flushed if set to true. @stable ICU 2.0 */ + UConverter *converter; /**< Pointer to the converter that is opened and to which this struct is passed as an argument. @stable ICU 2.0 */ + const char *source; /**< Pointer to the source source buffer. @stable ICU 2.0 */ + const char *sourceLimit; /**< Pointer to the limit (end + 1) of source buffer. @stable ICU 2.0 */ + UChar *target; /**< Pointer to the target buffer. @stable ICU 2.0 */ + const UChar *targetLimit; /**< Pointer to the limit (end + 1) of target buffer. @stable ICU 2.0 */ + int32_t *offsets; /**< Pointer to the buffer that receives the offsets. *offset = blah ; offset++;. @stable ICU 2.0 */ +} UConverterToUnicodeArgs; + + +/** + * DO NOT CALL THIS FUNCTION DIRECTLY! + * This From Unicode callback STOPS at the ILLEGAL_SEQUENCE, + * returning the error code back to the caller immediately. + * + * @param context Pointer to the callback's private data + * @param fromUArgs Information about the conversion in progress + * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint. + * @param reason Defines the reason the callback was invoked + * @param err This should always be set to a failure status prior to calling. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_STOP ( + const void *context, + UConverterFromUnicodeArgs *fromUArgs, + const UChar* codeUnits, + int32_t length, + UChar32 codePoint, + UConverterCallbackReason reason, + UErrorCode * err); + + + +/** + * DO NOT CALL THIS FUNCTION DIRECTLY! + * This To Unicode callback STOPS at the ILLEGAL_SEQUENCE, + * returning the error code back to the caller immediately. + * + * @param context Pointer to the callback's private data + * @param toUArgs Information about the conversion in progress + * @param codeUnits Points to 'length' bytes of the concerned codepage sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param reason Defines the reason the callback was invoked + * @param err This should always be set to a failure status prior to calling. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_STOP ( + const void *context, + UConverterToUnicodeArgs *toUArgs, + const char* codeUnits, + int32_t length, + UConverterCallbackReason reason, + UErrorCode * err); + +/** + * DO NOT CALL THIS FUNCTION DIRECTLY! + * This From Unicode callback skips any ILLEGAL_SEQUENCE, or + * skips only UNASSINGED_SEQUENCE depending on the context parameter + * simply ignoring those characters. + * + * @param context The function currently recognizes the callback options: + * UCNV_SKIP_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE, + * returning the error code back to the caller immediately. + * NULL: Skips any ILLEGAL_SEQUENCE + * @param fromUArgs Information about the conversion in progress + * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint. + * @param reason Defines the reason the callback was invoked + * @param err Return value will be set to success if the callback was handled, + * otherwise this value will be set to a failure status. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SKIP ( + const void *context, + UConverterFromUnicodeArgs *fromUArgs, + const UChar* codeUnits, + int32_t length, + UChar32 codePoint, + UConverterCallbackReason reason, + UErrorCode * err); + +/** + * DO NOT CALL THIS FUNCTION DIRECTLY! + * This From Unicode callback will Substitute the ILLEGAL SEQUENCE, or + * UNASSIGNED_SEQUENCE depending on context parameter, with the + * current substitution string for the converter. This is the default + * callback. + * + * @param context The function currently recognizes the callback options: + * UCNV_SUB_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE, + * returning the error code back to the caller immediately. + * NULL: Substitutes any ILLEGAL_SEQUENCE + * @param fromUArgs Information about the conversion in progress + * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint. + * @param reason Defines the reason the callback was invoked + * @param err Return value will be set to success if the callback was handled, + * otherwise this value will be set to a failure status. + * @see ucnv_setSubstChars + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SUBSTITUTE ( + const void *context, + UConverterFromUnicodeArgs *fromUArgs, + const UChar* codeUnits, + int32_t length, + UChar32 codePoint, + UConverterCallbackReason reason, + UErrorCode * err); + +/** + * DO NOT CALL THIS FUNCTION DIRECTLY! + * This From Unicode callback will Substitute the ILLEGAL SEQUENCE with the + * hexadecimal representation of the illegal codepoints + * + * @param context The function currently recognizes the callback options: + * <ul> + * <li>UCNV_ESCAPE_ICU: Substitues the ILLEGAL SEQUENCE with the hexadecimal + * representation in the format %UXXXX, e.g. "%uFFFE%u00AC%uC8FE"). + * In the Event the converter doesn't support the characters {%,U}[A-F][0-9], + * it will substitute the illegal sequence with the substitution characters. + * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as + * %UD84D%UDC56</li> + * <li>UCNV_ESCAPE_JAVA: Substitues the ILLEGAL SEQUENCE with the hexadecimal + * representation in the format \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE"). + * In the Event the converter doesn't support the characters {\,u}[A-F][0-9], + * it will substitute the illegal sequence with the substitution characters. + * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as + * \\uD84D\\uDC56</li> + * <li>UCNV_ESCAPE_C: Substitues the ILLEGAL SEQUENCE with the hexadecimal + * representation in the format \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE"). + * In the Event the converter doesn't support the characters {\,u,U}[A-F][0-9], + * it will substitute the illegal sequence with the substitution characters. + * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as + * \\U00023456</li> + * <li>UCNV_ESCAPE_XML_DEC: Substitues the ILLEGAL SEQUENCE with the decimal + * representation in the format \htmlonly&#DDDDDDDD;, e.g. "&#65534;&#172;&#51454;")\endhtmlonly. + * In the Event the converter doesn't support the characters {&,#}[0-9], + * it will substitute the illegal sequence with the substitution characters. + * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as + * &#144470; and Zero padding is ignored.</li> + * <li>UCNV_ESCAPE_XML_HEX:Substitues the ILLEGAL SEQUENCE with the decimal + * representation in the format \htmlonly&#xXXXX; e.g. "&#xFFFE;&#x00AC;&#xC8FE;")\endhtmlonly. + * In the Event the converter doesn't support the characters {&,#,x}[0-9], + * it will substitute the illegal sequence with the substitution characters. + * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as + * \htmlonly&#x23456;\endhtmlonly</li> + * </ul> + * @param fromUArgs Information about the conversion in progress + * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint. + * @param reason Defines the reason the callback was invoked + * @param err Return value will be set to success if the callback was handled, + * otherwise this value will be set to a failure status. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_ESCAPE ( + const void *context, + UConverterFromUnicodeArgs *fromUArgs, + const UChar* codeUnits, + int32_t length, + UChar32 codePoint, + UConverterCallbackReason reason, + UErrorCode * err); + + +/** + * DO NOT CALL THIS FUNCTION DIRECTLY! + * This To Unicode callback skips any ILLEGAL_SEQUENCE, or + * skips only UNASSINGED_SEQUENCE depending on the context parameter + * simply ignoring those characters. + * + * @param context The function currently recognizes the callback options: + * UCNV_SKIP_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE, + * returning the error code back to the caller immediately. + * NULL: Skips any ILLEGAL_SEQUENCE + * @param toUArgs Information about the conversion in progress + * @param codeUnits Points to 'length' bytes of the concerned codepage sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param reason Defines the reason the callback was invoked + * @param err Return value will be set to success if the callback was handled, + * otherwise this value will be set to a failure status. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SKIP ( + const void *context, + UConverterToUnicodeArgs *toUArgs, + const char* codeUnits, + int32_t length, + UConverterCallbackReason reason, + UErrorCode * err); + +/** + * DO NOT CALL THIS FUNCTION DIRECTLY! + * This To Unicode callback will Substitute the ILLEGAL SEQUENCE,or + * UNASSIGNED_SEQUENCE depending on context parameter, with the + * Unicode substitution character, U+FFFD. + * + * @param context The function currently recognizes the callback options: + * UCNV_SUB_STOP_ON_ILLEGAL: STOPS at the ILLEGAL_SEQUENCE, + * returning the error code back to the caller immediately. + * NULL: Substitutes any ILLEGAL_SEQUENCE + * @param toUArgs Information about the conversion in progress + * @param codeUnits Points to 'length' bytes of the concerned codepage sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param reason Defines the reason the callback was invoked + * @param err Return value will be set to success if the callback was handled, + * otherwise this value will be set to a failure status. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_SUBSTITUTE ( + const void *context, + UConverterToUnicodeArgs *toUArgs, + const char* codeUnits, + int32_t length, + UConverterCallbackReason reason, + UErrorCode * err); + +/** + * DO NOT CALL THIS FUNCTION DIRECTLY! + * This To Unicode callback will Substitute the ILLEGAL SEQUENCE with the + * hexadecimal representation of the illegal bytes + * (in the format %XNN, e.g. "%XFF%X0A%XC8%X03"). + * + * @param context This function currently recognizes the callback options: + * UCNV_ESCAPE_ICU, UCNV_ESCAPE_JAVA, UCNV_ESCAPE_C, UCNV_ESCAPE_XML_DEC, + * UCNV_ESCAPE_XML_HEX and UCNV_ESCAPE_UNICODE. + * @param toUArgs Information about the conversion in progress + * @param codeUnits Points to 'length' bytes of the concerned codepage sequence + * @param length Size (in bytes) of the concerned codepage sequence + * @param reason Defines the reason the callback was invoked + * @param err Return value will be set to success if the callback was handled, + * otherwise this value will be set to a failure status. + * @stable ICU 2.0 + */ + +U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_ESCAPE ( + const void *context, + UConverterToUnicodeArgs *toUArgs, + const char* codeUnits, + int32_t length, + UConverterCallbackReason reason, + UErrorCode * err); + +#endif + +#endif + +/*UCNV_ERR_H*/ diff --git a/thirdparty/icu4c/common/unicode/ucnvsel.h b/thirdparty/icu4c/common/unicode/ucnvsel.h new file mode 100644 index 0000000000..5e0a71cf35 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucnvsel.h @@ -0,0 +1,192 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2008-2011, International Business Machines +* Corporation, Google and others. All Rights Reserved. +* +******************************************************************************* +*/ +/* + * Author : eldawy@google.com (Mohamed Eldawy) + * ucnvsel.h + * + * Purpose: To generate a list of encodings capable of handling + * a given Unicode text + * + * Started 09-April-2008 + */ + +#ifndef __ICU_UCNV_SEL_H__ +#define __ICU_UCNV_SEL_H__ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_CONVERSION + +#include "unicode/uset.h" +#include "unicode/utf16.h" +#include "unicode/uenum.h" +#include "unicode/ucnv.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * \file + * + * A converter selector is built with a set of encoding/charset names + * and given an input string returns the set of names of the + * corresponding converters which can convert the string. + * + * A converter selector can be serialized into a buffer and reopened + * from the serialized form. + */ + +/** + * @{ + * The selector data structure + */ +struct UConverterSelector; +typedef struct UConverterSelector UConverterSelector; +/** @} */ + +/** + * Open a selector. + * If converterListSize is 0, build for all available converters. + * If excludedCodePoints is NULL, don't exclude any code points. + * + * @param converterList a pointer to encoding names needed to be involved. + * Can be NULL if converterListSize==0. + * The list and the names will be cloned, and the caller + * retains ownership of the original. + * @param converterListSize number of encodings in above list. + * If 0, builds a selector for all available converters. + * @param excludedCodePoints a set of code points to be excluded from consideration. + * That is, excluded code points in a string do not change + * the selection result. (They might be handled by a callback.) + * Use NULL to exclude nothing. + * @param whichSet what converter set to use? Use this to determine whether + * to consider only roundtrip mappings or also fallbacks. + * @param status an in/out ICU UErrorCode + * @return the new selector + * + * @stable ICU 4.2 + */ +U_CAPI UConverterSelector* U_EXPORT2 +ucnvsel_open(const char* const* converterList, int32_t converterListSize, + const USet* excludedCodePoints, + const UConverterUnicodeSet whichSet, UErrorCode* status); + +/** + * Closes a selector. + * If any Enumerations were returned by ucnv_select*, they become invalid. + * They can be closed before or after calling ucnv_closeSelector, + * but should never be used after the selector is closed. + * + * @see ucnv_selectForString + * @see ucnv_selectForUTF8 + * + * @param sel selector to close + * + * @stable ICU 4.2 + */ +U_CAPI void U_EXPORT2 +ucnvsel_close(UConverterSelector *sel); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUConverterSelectorPointer + * "Smart pointer" class, closes a UConverterSelector via ucnvsel_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUConverterSelectorPointer, UConverterSelector, ucnvsel_close); + +U_NAMESPACE_END + +#endif + +/** + * Open a selector from its serialized form. + * The buffer must remain valid and unchanged for the lifetime of the selector. + * This is much faster than creating a selector from scratch. + * Using a serialized form from a different machine (endianness/charset) is supported. + * + * @param buffer pointer to the serialized form of a converter selector; + * must be 32-bit-aligned + * @param length the capacity of this buffer (can be equal to or larger than + * the actual data length) + * @param status an in/out ICU UErrorCode + * @return the new selector + * + * @stable ICU 4.2 + */ +U_CAPI UConverterSelector* U_EXPORT2 +ucnvsel_openFromSerialized(const void* buffer, int32_t length, UErrorCode* status); + +/** + * Serialize a selector into a linear buffer. + * The serialized form is portable to different machines. + * + * @param sel selector to consider + * @param buffer pointer to 32-bit-aligned memory to be filled with the + * serialized form of this converter selector + * @param bufferCapacity the capacity of this buffer + * @param status an in/out ICU UErrorCode + * @return the required buffer capacity to hold serialize data (even if the call fails + * with a U_BUFFER_OVERFLOW_ERROR, it will return the required capacity) + * + * @stable ICU 4.2 + */ +U_CAPI int32_t U_EXPORT2 +ucnvsel_serialize(const UConverterSelector* sel, + void* buffer, int32_t bufferCapacity, UErrorCode* status); + +/** + * Select converters that can map all characters in a UTF-16 string, + * ignoring the excluded code points. + * + * @param sel a selector + * @param s UTF-16 string + * @param length length of the string, or -1 if NUL-terminated + * @param status an in/out ICU UErrorCode + * @return an enumeration containing encoding names. + * The returned encoding names and their order will be the same as + * supplied when building the selector. + * + * @stable ICU 4.2 + */ +U_CAPI UEnumeration * U_EXPORT2 +ucnvsel_selectForString(const UConverterSelector* sel, + const UChar *s, int32_t length, UErrorCode *status); + +/** + * Select converters that can map all characters in a UTF-8 string, + * ignoring the excluded code points. + * + * @param sel a selector + * @param s UTF-8 string + * @param length length of the string, or -1 if NUL-terminated + * @param status an in/out ICU UErrorCode + * @return an enumeration containing encoding names. + * The returned encoding names and their order will be the same as + * supplied when building the selector. + * + * @stable ICU 4.2 + */ +U_CAPI UEnumeration * U_EXPORT2 +ucnvsel_selectForUTF8(const UConverterSelector* sel, + const char *s, int32_t length, UErrorCode *status); + +#endif /* !UCONFIG_NO_CONVERSION */ + +#endif /* __ICU_UCNV_SEL_H__ */ diff --git a/thirdparty/icu4c/common/unicode/uconfig.h b/thirdparty/icu4c/common/unicode/uconfig.h new file mode 100644 index 0000000000..bbc232d1ed --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uconfig.h @@ -0,0 +1,456 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 2002-2016, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* file name: uconfig.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2002sep19 +* created by: Markus W. Scherer +*/ + +#ifndef __UCONFIG_H__ +#define __UCONFIG_H__ + + +/*! + * \file + * \brief User-configurable settings + * + * Miscellaneous switches: + * + * A number of macros affect a variety of minor aspects of ICU. + * Most of them used to be defined elsewhere (e.g., in utypes.h or platform.h) + * and moved here to make them easier to find. + * + * Switches for excluding parts of ICU library code modules: + * + * Changing these macros allows building partial, smaller libraries for special purposes. + * By default, all modules are built. + * The switches are fairly coarse, controlling large modules. + * Basic services cannot be turned off. + * + * Building with any of these options does not guarantee that the + * ICU build process will completely work. It is recommended that + * the ICU libraries and data be built using the normal build. + * At that time you should remove the data used by those services. + * After building the ICU data library, you should rebuild the ICU + * libraries with these switches customized to your needs. + * + * @stable ICU 2.4 + */ + +/** + * If this switch is defined, ICU will attempt to load a header file named "uconfig_local.h" + * prior to determining default settings for uconfig variables. + * + * @internal ICU 4.0 + */ +#if defined(UCONFIG_USE_LOCAL) +#include "uconfig_local.h" +#endif + +/** + * \def U_DEBUG + * Determines whether to include debugging code. + * Automatically set on Windows, but most compilers do not have + * related predefined macros. + * @internal + */ +#ifdef U_DEBUG + /* Use the predefined value. */ +#elif defined(_DEBUG) + /* + * _DEBUG is defined by Visual Studio debug compilation. + * Do *not* test for its NDEBUG macro: It is an orthogonal macro + * which disables assert(). + */ +# define U_DEBUG 1 +# else +# define U_DEBUG 0 +#endif + +/** + * Determines whether to enable auto cleanup of libraries. + * @internal + */ +#ifndef UCLN_NO_AUTO_CLEANUP +#define UCLN_NO_AUTO_CLEANUP 1 +#endif + +/** + * \def U_DISABLE_RENAMING + * Determines whether to disable renaming or not. + * @internal + */ +#ifndef U_DISABLE_RENAMING +#define U_DISABLE_RENAMING 0 +#endif + +/** + * \def U_NO_DEFAULT_INCLUDE_UTF_HEADERS + * Determines whether utypes.h includes utf.h, utf8.h, utf16.h and utf_old.h. + * utypes.h includes those headers if this macro is defined to 0. + * Otherwise, each those headers must be included explicitly when using one of their macros. + * Defaults to 0 for backward compatibility, except inside ICU. + * @stable ICU 49 + */ +#ifdef U_NO_DEFAULT_INCLUDE_UTF_HEADERS + /* Use the predefined value. */ +#elif defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || \ + defined(U_IO_IMPLEMENTATION) || defined(U_LAYOUT_IMPLEMENTATION) || defined(U_LAYOUTEX_IMPLEMENTATION) || \ + defined(U_TOOLUTIL_IMPLEMENTATION) +# define U_NO_DEFAULT_INCLUDE_UTF_HEADERS 1 +#else +# define U_NO_DEFAULT_INCLUDE_UTF_HEADERS 0 +#endif + +/** + * \def U_OVERRIDE_CXX_ALLOCATION + * Determines whether to override new and delete. + * ICU is normally built such that all of its C++ classes, via their UMemory base, + * override operators new and delete to use its internal, customizable, + * non-exception-throwing memory allocation functions. (Default value 1 for this macro.) + * + * This is especially important when the application and its libraries use multiple heaps. + * For example, on Windows, this allows the ICU DLL to be used by + * applications that statically link the C Runtime library. + * + * @stable ICU 2.2 + */ +#ifndef U_OVERRIDE_CXX_ALLOCATION +#define U_OVERRIDE_CXX_ALLOCATION 1 +#endif + +/** + * \def U_ENABLE_TRACING + * Determines whether to enable tracing. + * @internal + */ +#ifndef U_ENABLE_TRACING +#define U_ENABLE_TRACING 0 +#endif + +/** + * \def UCONFIG_ENABLE_PLUGINS + * Determines whether to enable ICU plugins. + * @internal + */ +#ifndef UCONFIG_ENABLE_PLUGINS +#define UCONFIG_ENABLE_PLUGINS 0 +#endif + +/** + * \def U_ENABLE_DYLOAD + * Whether to enable Dynamic loading in ICU. + * @internal + */ +#ifndef U_ENABLE_DYLOAD +#define U_ENABLE_DYLOAD 1 +#endif + +/** + * \def U_CHECK_DYLOAD + * Whether to test Dynamic loading as an OS capability. + * @internal + */ +#ifndef U_CHECK_DYLOAD +#define U_CHECK_DYLOAD 1 +#endif + +/** + * \def U_DEFAULT_SHOW_DRAFT + * Do we allow ICU users to use the draft APIs by default? + * @internal + */ +#ifndef U_DEFAULT_SHOW_DRAFT +#define U_DEFAULT_SHOW_DRAFT 1 +#endif + +/*===========================================================================*/ +/* Custom icu entry point renaming */ +/*===========================================================================*/ + +/** + * \def U_HAVE_LIB_SUFFIX + * 1 if a custom library suffix is set. + * @internal + */ +#ifdef U_HAVE_LIB_SUFFIX + /* Use the predefined value. */ +#elif defined(U_LIB_SUFFIX_C_NAME) || defined(U_IN_DOXYGEN) +# define U_HAVE_LIB_SUFFIX 1 +#endif + +/** + * \def U_LIB_SUFFIX_C_NAME_STRING + * Defines the library suffix as a string with C syntax. + * @internal + */ +#ifdef U_LIB_SUFFIX_C_NAME_STRING + /* Use the predefined value. */ +#elif defined(U_LIB_SUFFIX_C_NAME) +# define CONVERT_TO_STRING(s) #s +# define U_LIB_SUFFIX_C_NAME_STRING CONVERT_TO_STRING(U_LIB_SUFFIX_C_NAME) +#else +# define U_LIB_SUFFIX_C_NAME_STRING "" +#endif + +/* common/i18n library switches --------------------------------------------- */ + +/** + * \def UCONFIG_ONLY_COLLATION + * This switch turns off modules that are not needed for collation. + * + * It does not turn off legacy conversion because that is necessary + * for ICU to work on EBCDIC platforms (for the default converter). + * If you want "only collation" and do not build for EBCDIC, + * then you can define UCONFIG_NO_CONVERSION or UCONFIG_NO_LEGACY_CONVERSION to 1 as well. + * + * @stable ICU 2.4 + */ +#ifndef UCONFIG_ONLY_COLLATION +# define UCONFIG_ONLY_COLLATION 0 +#endif + +#if UCONFIG_ONLY_COLLATION + /* common library */ +# define UCONFIG_NO_BREAK_ITERATION 1 +# define UCONFIG_NO_IDNA 1 + + /* i18n library */ +# if UCONFIG_NO_COLLATION +# error Contradictory collation switches in uconfig.h. +# endif +# define UCONFIG_NO_FORMATTING 1 +# define UCONFIG_NO_TRANSLITERATION 1 +# define UCONFIG_NO_REGULAR_EXPRESSIONS 1 +#endif + +/* common library switches -------------------------------------------------- */ + +/** + * \def UCONFIG_NO_FILE_IO + * This switch turns off all file access in the common library + * where file access is only used for data loading. + * ICU data must then be provided in the form of a data DLL (or with an + * equivalent way to link to the data residing in an executable, + * as in building a combined library with both the common library's code and + * the data), or via udata_setCommonData(). + * Application data must be provided via udata_setAppData() or by using + * "open" functions that take pointers to data, for example ucol_openBinary(). + * + * File access is not used at all in the i18n library. + * + * File access cannot be turned off for the icuio library or for the ICU + * test suites and ICU tools. + * + * @stable ICU 3.6 + */ +#ifndef UCONFIG_NO_FILE_IO +# define UCONFIG_NO_FILE_IO 0 +#endif + +#if UCONFIG_NO_FILE_IO && defined(U_TIMEZONE_FILES_DIR) +# error Contradictory file io switches in uconfig.h. +#endif + +/** + * \def UCONFIG_NO_CONVERSION + * ICU will not completely build (compiling the tools fails) with this + * switch turned on. + * This switch turns off all converters. + * + * You may want to use this together with U_CHARSET_IS_UTF8 defined to 1 + * in utypes.h if char* strings in your environment are always in UTF-8. + * + * @stable ICU 3.2 + * @see U_CHARSET_IS_UTF8 + */ +#ifndef UCONFIG_NO_CONVERSION +# define UCONFIG_NO_CONVERSION 0 +#endif + +#if UCONFIG_NO_CONVERSION +# define UCONFIG_NO_LEGACY_CONVERSION 1 +#endif + +/** + * \def UCONFIG_ONLY_HTML_CONVERSION + * This switch turns off all of the converters NOT listed in + * the HTML encoding standard: + * http://www.w3.org/TR/encoding/#names-and-labels + * + * This is not possible on EBCDIC platforms + * because they need ibm-37 or ibm-1047 default converters. + * + * @stable ICU 55 + */ +#ifndef UCONFIG_ONLY_HTML_CONVERSION +# define UCONFIG_ONLY_HTML_CONVERSION 0 +#endif + +/** + * \def UCONFIG_NO_LEGACY_CONVERSION + * This switch turns off all converters except for + * - Unicode charsets (UTF-7/8/16/32, CESU-8, SCSU, BOCU-1) + * - US-ASCII + * - ISO-8859-1 + * + * Turning off legacy conversion is not possible on EBCDIC platforms + * because they need ibm-37 or ibm-1047 default converters. + * + * @stable ICU 2.4 + */ +#ifndef UCONFIG_NO_LEGACY_CONVERSION +# define UCONFIG_NO_LEGACY_CONVERSION 0 +#endif + +/** + * \def UCONFIG_NO_NORMALIZATION + * This switch turns off normalization. + * It implies turning off several other services as well, for example + * collation and IDNA. + * + * @stable ICU 2.6 + */ +#ifndef UCONFIG_NO_NORMALIZATION +# define UCONFIG_NO_NORMALIZATION 0 +#endif + +#if UCONFIG_NO_NORMALIZATION + /* common library */ + /* ICU 50 CJK dictionary BreakIterator uses normalization */ +# define UCONFIG_NO_BREAK_ITERATION 1 + /* IDNA (UTS #46) is implemented via normalization */ +# define UCONFIG_NO_IDNA 1 + + /* i18n library */ +# if UCONFIG_ONLY_COLLATION +# error Contradictory collation switches in uconfig.h. +# endif +# define UCONFIG_NO_COLLATION 1 +# define UCONFIG_NO_TRANSLITERATION 1 +#endif + +/** + * \def UCONFIG_NO_BREAK_ITERATION + * This switch turns off break iteration. + * + * @stable ICU 2.4 + */ +#ifndef UCONFIG_NO_BREAK_ITERATION +# define UCONFIG_NO_BREAK_ITERATION 0 +#endif + +/** + * \def UCONFIG_NO_IDNA + * This switch turns off IDNA. + * + * @stable ICU 2.6 + */ +#ifndef UCONFIG_NO_IDNA +# define UCONFIG_NO_IDNA 0 +#endif + +/** + * \def UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE + * Determines the default UMessagePatternApostropheMode. + * See the documentation for that enum. + * + * @stable ICU 4.8 + */ +#ifndef UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE +# define UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE UMSGPAT_APOS_DOUBLE_OPTIONAL +#endif + +/** + * \def UCONFIG_USE_WINDOWS_LCID_MAPPING_API + * On platforms where U_PLATFORM_HAS_WIN32_API is true, this switch determines + * if the Windows platform APIs are used for LCID<->Locale Name conversions. + * Otherwise, only the built-in ICU tables are used. + * + * @internal ICU 64 + */ +#ifndef UCONFIG_USE_WINDOWS_LCID_MAPPING_API +# define UCONFIG_USE_WINDOWS_LCID_MAPPING_API 1 +#endif + +/* i18n library switches ---------------------------------------------------- */ + +/** + * \def UCONFIG_NO_COLLATION + * This switch turns off collation and collation-based string search. + * + * @stable ICU 2.4 + */ +#ifndef UCONFIG_NO_COLLATION +# define UCONFIG_NO_COLLATION 0 +#endif + +/** + * \def UCONFIG_NO_FORMATTING + * This switch turns off formatting and calendar/timezone services. + * + * @stable ICU 2.4 + */ +#ifndef UCONFIG_NO_FORMATTING +# define UCONFIG_NO_FORMATTING 0 +#endif + +/** + * \def UCONFIG_NO_TRANSLITERATION + * This switch turns off transliteration. + * + * @stable ICU 2.4 + */ +#ifndef UCONFIG_NO_TRANSLITERATION +# define UCONFIG_NO_TRANSLITERATION 0 +#endif + +/** + * \def UCONFIG_NO_REGULAR_EXPRESSIONS + * This switch turns off regular expressions. + * + * @stable ICU 2.4 + */ +#ifndef UCONFIG_NO_REGULAR_EXPRESSIONS +# define UCONFIG_NO_REGULAR_EXPRESSIONS 0 +#endif + +/** + * \def UCONFIG_NO_SERVICE + * This switch turns off service registration. + * + * @stable ICU 3.2 + */ +#ifndef UCONFIG_NO_SERVICE +# define UCONFIG_NO_SERVICE 0 +#endif + +/** + * \def UCONFIG_HAVE_PARSEALLINPUT + * This switch turns on the "parse all input" attribute. Binary incompatible. + * + * @internal + */ +#ifndef UCONFIG_HAVE_PARSEALLINPUT +# define UCONFIG_HAVE_PARSEALLINPUT 1 +#endif + +/** + * \def UCONFIG_NO_FILTERED_BREAK_ITERATION + * This switch turns off filtered break iteration code. + * + * @internal + */ +#ifndef UCONFIG_NO_FILTERED_BREAK_ITERATION +# define UCONFIG_NO_FILTERED_BREAK_ITERATION 0 +#endif + +#endif // __UCONFIG_H__ diff --git a/thirdparty/icu4c/common/unicode/ucpmap.h b/thirdparty/icu4c/common/unicode/ucpmap.h new file mode 100644 index 0000000000..31e1365cac --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucpmap.h @@ -0,0 +1,159 @@ +// © 2018 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// ucpmap.h +// created: 2018sep03 Markus W. Scherer + +#ifndef __UCPMAP_H__ +#define __UCPMAP_H__ + +#include "unicode/utypes.h" + +U_CDECL_BEGIN + +/** + * \file + * + * This file defines an abstract map from Unicode code points to integer values. + * + * @see UCPMap + * @see UCPTrie + * @see UMutableCPTrie + */ + +/** + * Abstract map from Unicode code points (U+0000..U+10FFFF) to integer values. + * + * @see UCPTrie + * @see UMutableCPTrie + * @stable ICU 63 + */ +typedef struct UCPMap UCPMap; + +/** + * Selectors for how ucpmap_getRange() etc. should report value ranges overlapping with surrogates. + * Most users should use UCPMAP_RANGE_NORMAL. + * + * @see ucpmap_getRange + * @see ucptrie_getRange + * @see umutablecptrie_getRange + * @stable ICU 63 + */ +enum UCPMapRangeOption { + /** + * ucpmap_getRange() enumerates all same-value ranges as stored in the map. + * Most users should use this option. + * @stable ICU 63 + */ + UCPMAP_RANGE_NORMAL, + /** + * ucpmap_getRange() enumerates all same-value ranges as stored in the map, + * except that lead surrogates (U+D800..U+DBFF) are treated as having the + * surrogateValue, which is passed to getRange() as a separate parameter. + * The surrogateValue is not transformed via filter(). + * See U_IS_LEAD(c). + * + * Most users should use UCPMAP_RANGE_NORMAL instead. + * + * This option is useful for maps that map surrogate code *units* to + * special values optimized for UTF-16 string processing + * or for special error behavior for unpaired surrogates, + * but those values are not to be associated with the lead surrogate code *points*. + * @stable ICU 63 + */ + UCPMAP_RANGE_FIXED_LEAD_SURROGATES, + /** + * ucpmap_getRange() enumerates all same-value ranges as stored in the map, + * except that all surrogates (U+D800..U+DFFF) are treated as having the + * surrogateValue, which is passed to getRange() as a separate parameter. + * The surrogateValue is not transformed via filter(). + * See U_IS_SURROGATE(c). + * + * Most users should use UCPMAP_RANGE_NORMAL instead. + * + * This option is useful for maps that map surrogate code *units* to + * special values optimized for UTF-16 string processing + * or for special error behavior for unpaired surrogates, + * but those values are not to be associated with the lead surrogate code *points*. + * @stable ICU 63 + */ + UCPMAP_RANGE_FIXED_ALL_SURROGATES +}; +#ifndef U_IN_DOXYGEN +typedef enum UCPMapRangeOption UCPMapRangeOption; +#endif + +/** + * Returns the value for a code point as stored in the map, with range checking. + * Returns an implementation-defined error value if c is not in the range 0..U+10FFFF. + * + * @param map the map + * @param c the code point + * @return the map value, + * or an implementation-defined error value if the code point is not in the range 0..U+10FFFF + * @stable ICU 63 + */ +U_CAPI uint32_t U_EXPORT2 +ucpmap_get(const UCPMap *map, UChar32 c); + +/** + * Callback function type: Modifies a map value. + * Optionally called by ucpmap_getRange()/ucptrie_getRange()/umutablecptrie_getRange(). + * The modified value will be returned by the getRange function. + * + * Can be used to ignore some of the value bits, + * make a filter for one of several values, + * return a value index computed from the map value, etc. + * + * @param context an opaque pointer, as passed into the getRange function + * @param value a value from the map + * @return the modified value + * @stable ICU 63 + */ +typedef uint32_t U_CALLCONV +UCPMapValueFilter(const void *context, uint32_t value); + +/** + * Returns the last code point such that all those from start to there have the same value. + * Can be used to efficiently iterate over all same-value ranges in a map. + * (This is normally faster than iterating over code points and get()ting each value, + * but much slower than a data structure that stores ranges directly.) + * + * If the UCPMapValueFilter function pointer is not NULL, then + * the value to be delivered is passed through that function, and the return value is the end + * of the range where all values are modified to the same actual value. + * The value is unchanged if that function pointer is NULL. + * + * Example: + * \code + * UChar32 start = 0, end; + * uint32_t value; + * while ((end = ucpmap_getRange(map, start, UCPMAP_RANGE_NORMAL, 0, + * NULL, NULL, &value)) >= 0) { + * // Work with the range start..end and its value. + * start = end + 1; + * } + * \endcode + * + * @param map the map + * @param start range start + * @param option defines whether surrogates are treated normally, + * or as having the surrogateValue; usually UCPMAP_RANGE_NORMAL + * @param surrogateValue value for surrogates; ignored if option==UCPMAP_RANGE_NORMAL + * @param filter a pointer to a function that may modify the map data value, + * or NULL if the values from the map are to be used unmodified + * @param context an opaque pointer that is passed on to the filter function + * @param pValue if not NULL, receives the value that every code point start..end has; + * may have been modified by filter(context, map value) + * if that function pointer is not NULL + * @return the range end code point, or -1 if start is not a valid code point + * @stable ICU 63 + */ +U_CAPI UChar32 U_EXPORT2 +ucpmap_getRange(const UCPMap *map, UChar32 start, + UCPMapRangeOption option, uint32_t surrogateValue, + UCPMapValueFilter *filter, const void *context, uint32_t *pValue); + +U_CDECL_END + +#endif diff --git a/thirdparty/icu4c/common/unicode/ucptrie.h b/thirdparty/icu4c/common/unicode/ucptrie.h new file mode 100644 index 0000000000..b95491b183 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucptrie.h @@ -0,0 +1,646 @@ +// © 2017 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// ucptrie.h (modified from utrie2.h) +// created: 2017dec29 Markus W. Scherer + +#ifndef __UCPTRIE_H__ +#define __UCPTRIE_H__ + +#include "unicode/utypes.h" +#include "unicode/ucpmap.h" +#include "unicode/utf8.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +U_CDECL_BEGIN + +/** + * \file + * + * This file defines an immutable Unicode code point trie. + * + * @see UCPTrie + * @see UMutableCPTrie + */ + +#ifndef U_IN_DOXYGEN +/** @internal */ +typedef union UCPTrieData { + /** @internal */ + const void *ptr0; + /** @internal */ + const uint16_t *ptr16; + /** @internal */ + const uint32_t *ptr32; + /** @internal */ + const uint8_t *ptr8; +} UCPTrieData; +#endif + +/** + * Immutable Unicode code point trie structure. + * Fast, reasonably compact, map from Unicode code points (U+0000..U+10FFFF) to integer values. + * For details see http://site.icu-project.org/design/struct/utrie + * + * Do not access UCPTrie fields directly; use public functions and macros. + * Functions are easy to use: They support all trie types and value widths. + * + * When performance is really important, macros provide faster access. + * Most macros are specific to either "fast" or "small" tries, see UCPTrieType. + * There are "fast" macros for special optimized use cases. + * + * The macros will return bogus values, or may crash, if used on the wrong type or value width. + * + * @see UMutableCPTrie + * @stable ICU 63 + */ +struct UCPTrie { +#ifndef U_IN_DOXYGEN + /** @internal */ + const uint16_t *index; + /** @internal */ + UCPTrieData data; + + /** @internal */ + int32_t indexLength; + /** @internal */ + int32_t dataLength; + /** Start of the last range which ends at U+10FFFF. @internal */ + UChar32 highStart; + /** highStart>>12 @internal */ + uint16_t shifted12HighStart; + + /** @internal */ + int8_t type; // UCPTrieType + /** @internal */ + int8_t valueWidth; // UCPTrieValueWidth + + /** padding/reserved @internal */ + uint32_t reserved32; + /** padding/reserved @internal */ + uint16_t reserved16; + + /** + * Internal index-3 null block offset. + * Set to an impossibly high value (e.g., 0xffff) if there is no dedicated index-3 null block. + * @internal + */ + uint16_t index3NullOffset; + /** + * Internal data null block offset, not shifted. + * Set to an impossibly high value (e.g., 0xfffff) if there is no dedicated data null block. + * @internal + */ + int32_t dataNullOffset; + /** @internal */ + uint32_t nullValue; + +#ifdef UCPTRIE_DEBUG + /** @internal */ + const char *name; +#endif +#endif +}; +#ifndef U_IN_DOXYGEN +typedef struct UCPTrie UCPTrie; +#endif + +/** + * Selectors for the type of a UCPTrie. + * Different trade-offs for size vs. speed. + * + * @see umutablecptrie_buildImmutable + * @see ucptrie_openFromBinary + * @see ucptrie_getType + * @stable ICU 63 + */ +enum UCPTrieType { + /** + * For ucptrie_openFromBinary() to accept any type. + * ucptrie_getType() will return the actual type. + * @stable ICU 63 + */ + UCPTRIE_TYPE_ANY = -1, + /** + * Fast/simple/larger BMP data structure. Use functions and "fast" macros. + * @stable ICU 63 + */ + UCPTRIE_TYPE_FAST, + /** + * Small/slower BMP data structure. Use functions and "small" macros. + * @stable ICU 63 + */ + UCPTRIE_TYPE_SMALL +}; +#ifndef U_IN_DOXYGEN +typedef enum UCPTrieType UCPTrieType; +#endif + +/** + * Selectors for the number of bits in a UCPTrie data value. + * + * @see umutablecptrie_buildImmutable + * @see ucptrie_openFromBinary + * @see ucptrie_getValueWidth + * @stable ICU 63 + */ +enum UCPTrieValueWidth { + /** + * For ucptrie_openFromBinary() to accept any data value width. + * ucptrie_getValueWidth() will return the actual data value width. + * @stable ICU 63 + */ + UCPTRIE_VALUE_BITS_ANY = -1, + /** + * The trie stores 16 bits per data value. + * It returns them as unsigned values 0..0xffff=65535. + * @stable ICU 63 + */ + UCPTRIE_VALUE_BITS_16, + /** + * The trie stores 32 bits per data value. + * @stable ICU 63 + */ + UCPTRIE_VALUE_BITS_32, + /** + * The trie stores 8 bits per data value. + * It returns them as unsigned values 0..0xff=255. + * @stable ICU 63 + */ + UCPTRIE_VALUE_BITS_8 +}; +#ifndef U_IN_DOXYGEN +typedef enum UCPTrieValueWidth UCPTrieValueWidth; +#endif + +/** + * Opens a trie from its binary form, stored in 32-bit-aligned memory. + * Inverse of ucptrie_toBinary(). + * + * The memory must remain valid and unchanged as long as the trie is used. + * You must ucptrie_close() the trie once you are done using it. + * + * @param type selects the trie type; results in an + * U_INVALID_FORMAT_ERROR if it does not match the binary data; + * use UCPTRIE_TYPE_ANY to accept any type + * @param valueWidth selects the number of bits in a data value; results in an + * U_INVALID_FORMAT_ERROR if it does not match the binary data; + * use UCPTRIE_VALUE_BITS_ANY to accept any data value width + * @param data a pointer to 32-bit-aligned memory containing the binary data of a UCPTrie + * @param length the number of bytes available at data; + * can be more than necessary + * @param pActualLength receives the actual number of bytes at data taken up by the trie data; + * can be NULL + * @param pErrorCode an in/out ICU UErrorCode + * @return the trie + * + * @see umutablecptrie_open + * @see umutablecptrie_buildImmutable + * @see ucptrie_toBinary + * @stable ICU 63 + */ +U_CAPI UCPTrie * U_EXPORT2 +ucptrie_openFromBinary(UCPTrieType type, UCPTrieValueWidth valueWidth, + const void *data, int32_t length, int32_t *pActualLength, + UErrorCode *pErrorCode); + +/** + * Closes a trie and releases associated memory. + * + * @param trie the trie + * @stable ICU 63 + */ +U_CAPI void U_EXPORT2 +ucptrie_close(UCPTrie *trie); + +/** + * Returns the trie type. + * + * @param trie the trie + * @return the trie type + * @see ucptrie_openFromBinary + * @see UCPTRIE_TYPE_ANY + * @stable ICU 63 + */ +U_CAPI UCPTrieType U_EXPORT2 +ucptrie_getType(const UCPTrie *trie); + +/** + * Returns the number of bits in a trie data value. + * + * @param trie the trie + * @return the number of bits in a trie data value + * @see ucptrie_openFromBinary + * @see UCPTRIE_VALUE_BITS_ANY + * @stable ICU 63 + */ +U_CAPI UCPTrieValueWidth U_EXPORT2 +ucptrie_getValueWidth(const UCPTrie *trie); + +/** + * Returns the value for a code point as stored in the trie, with range checking. + * Returns the trie error value if c is not in the range 0..U+10FFFF. + * + * Easier to use than UCPTRIE_FAST_GET() and similar macros but slower. + * Easier to use because, unlike the macros, this function works on all UCPTrie + * objects, for all types and value widths. + * + * @param trie the trie + * @param c the code point + * @return the trie value, + * or the trie error value if the code point is not in the range 0..U+10FFFF + * @stable ICU 63 + */ +U_CAPI uint32_t U_EXPORT2 +ucptrie_get(const UCPTrie *trie, UChar32 c); + +/** + * Returns the last code point such that all those from start to there have the same value. + * Can be used to efficiently iterate over all same-value ranges in a trie. + * (This is normally faster than iterating over code points and get()ting each value, + * but much slower than a data structure that stores ranges directly.) + * + * If the UCPMapValueFilter function pointer is not NULL, then + * the value to be delivered is passed through that function, and the return value is the end + * of the range where all values are modified to the same actual value. + * The value is unchanged if that function pointer is NULL. + * + * Example: + * \code + * UChar32 start = 0, end; + * uint32_t value; + * while ((end = ucptrie_getRange(trie, start, UCPMAP_RANGE_NORMAL, 0, + * NULL, NULL, &value)) >= 0) { + * // Work with the range start..end and its value. + * start = end + 1; + * } + * \endcode + * + * @param trie the trie + * @param start range start + * @param option defines whether surrogates are treated normally, + * or as having the surrogateValue; usually UCPMAP_RANGE_NORMAL + * @param surrogateValue value for surrogates; ignored if option==UCPMAP_RANGE_NORMAL + * @param filter a pointer to a function that may modify the trie data value, + * or NULL if the values from the trie are to be used unmodified + * @param context an opaque pointer that is passed on to the filter function + * @param pValue if not NULL, receives the value that every code point start..end has; + * may have been modified by filter(context, trie value) + * if that function pointer is not NULL + * @return the range end code point, or -1 if start is not a valid code point + * @stable ICU 63 + */ +U_CAPI UChar32 U_EXPORT2 +ucptrie_getRange(const UCPTrie *trie, UChar32 start, + UCPMapRangeOption option, uint32_t surrogateValue, + UCPMapValueFilter *filter, const void *context, uint32_t *pValue); + +/** + * Writes a memory-mappable form of the trie into 32-bit aligned memory. + * Inverse of ucptrie_openFromBinary(). + * + * @param trie the trie + * @param data a pointer to 32-bit-aligned memory to be filled with the trie data; + * can be NULL if capacity==0 + * @param capacity the number of bytes available at data, or 0 for pure preflighting + * @param pErrorCode an in/out ICU UErrorCode; + * U_BUFFER_OVERFLOW_ERROR if the capacity is too small + * @return the number of bytes written or (if buffer overflow) needed for the trie + * + * @see ucptrie_openFromBinary() + * @stable ICU 63 + */ +U_CAPI int32_t U_EXPORT2 +ucptrie_toBinary(const UCPTrie *trie, void *data, int32_t capacity, UErrorCode *pErrorCode); + +/** + * Macro parameter value for a trie with 16-bit data values. + * Use the name of this macro as a "dataAccess" parameter in other macros. + * Do not use this macro in any other way. + * + * @see UCPTRIE_VALUE_BITS_16 + * @stable ICU 63 + */ +#define UCPTRIE_16(trie, i) ((trie)->data.ptr16[i]) + +/** + * Macro parameter value for a trie with 32-bit data values. + * Use the name of this macro as a "dataAccess" parameter in other macros. + * Do not use this macro in any other way. + * + * @see UCPTRIE_VALUE_BITS_32 + * @stable ICU 63 + */ +#define UCPTRIE_32(trie, i) ((trie)->data.ptr32[i]) + +/** + * Macro parameter value for a trie with 8-bit data values. + * Use the name of this macro as a "dataAccess" parameter in other macros. + * Do not use this macro in any other way. + * + * @see UCPTRIE_VALUE_BITS_8 + * @stable ICU 63 + */ +#define UCPTRIE_8(trie, i) ((trie)->data.ptr8[i]) + +/** + * Returns a trie value for a code point, with range checking. + * Returns the trie error value if c is not in the range 0..U+10FFFF. + * + * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param c (UChar32, in) the input code point + * @return The code point's trie value. + * @stable ICU 63 + */ +#define UCPTRIE_FAST_GET(trie, dataAccess, c) dataAccess(trie, _UCPTRIE_CP_INDEX(trie, 0xffff, c)) + +/** + * Returns a 16-bit trie value for a code point, with range checking. + * Returns the trie error value if c is not in the range U+0000..U+10FFFF. + * + * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_SMALL + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param c (UChar32, in) the input code point + * @return The code point's trie value. + * @stable ICU 63 + */ +#define UCPTRIE_SMALL_GET(trie, dataAccess, c) \ + dataAccess(trie, _UCPTRIE_CP_INDEX(trie, UCPTRIE_SMALL_MAX, c)) + +/** + * UTF-16: Reads the next code point (UChar32 c, out), post-increments src, + * and gets a value from the trie. + * Sets the trie error value if c is an unpaired surrogate. + * + * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param src (const UChar *, in/out) the source text pointer + * @param limit (const UChar *, in) the limit pointer for the text, or NULL if NUL-terminated + * @param c (UChar32, out) variable for the code point + * @param result (out) variable for the trie lookup result + * @stable ICU 63 + */ +#define UCPTRIE_FAST_U16_NEXT(trie, dataAccess, src, limit, c, result) UPRV_BLOCK_MACRO_BEGIN { \ + (c) = *(src)++; \ + int32_t __index; \ + if (!U16_IS_SURROGATE(c)) { \ + __index = _UCPTRIE_FAST_INDEX(trie, c); \ + } else { \ + uint16_t __c2; \ + if (U16_IS_SURROGATE_LEAD(c) && (src) != (limit) && U16_IS_TRAIL(__c2 = *(src))) { \ + ++(src); \ + (c) = U16_GET_SUPPLEMENTARY((c), __c2); \ + __index = _UCPTRIE_SMALL_INDEX(trie, c); \ + } else { \ + __index = (trie)->dataLength - UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET; \ + } \ + } \ + (result) = dataAccess(trie, __index); \ +} UPRV_BLOCK_MACRO_END + +/** + * UTF-16: Reads the previous code point (UChar32 c, out), pre-decrements src, + * and gets a value from the trie. + * Sets the trie error value if c is an unpaired surrogate. + * + * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param start (const UChar *, in) the start pointer for the text + * @param src (const UChar *, in/out) the source text pointer + * @param c (UChar32, out) variable for the code point + * @param result (out) variable for the trie lookup result + * @stable ICU 63 + */ +#define UCPTRIE_FAST_U16_PREV(trie, dataAccess, start, src, c, result) UPRV_BLOCK_MACRO_BEGIN { \ + (c) = *--(src); \ + int32_t __index; \ + if (!U16_IS_SURROGATE(c)) { \ + __index = _UCPTRIE_FAST_INDEX(trie, c); \ + } else { \ + uint16_t __c2; \ + if (U16_IS_SURROGATE_TRAIL(c) && (src) != (start) && U16_IS_LEAD(__c2 = *((src) - 1))) { \ + --(src); \ + (c) = U16_GET_SUPPLEMENTARY(__c2, (c)); \ + __index = _UCPTRIE_SMALL_INDEX(trie, c); \ + } else { \ + __index = (trie)->dataLength - UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET; \ + } \ + } \ + (result) = dataAccess(trie, __index); \ +} UPRV_BLOCK_MACRO_END + +/** + * UTF-8: Post-increments src and gets a value from the trie. + * Sets the trie error value for an ill-formed byte sequence. + * + * Unlike UCPTRIE_FAST_U16_NEXT() this UTF-8 macro does not provide the code point + * because it would be more work to do so and is often not needed. + * If the trie value differs from the error value, then the byte sequence is well-formed, + * and the code point can be assembled without revalidation. + * + * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param src (const char *, in/out) the source text pointer + * @param limit (const char *, in) the limit pointer for the text (must not be NULL) + * @param result (out) variable for the trie lookup result + * @stable ICU 63 + */ +#define UCPTRIE_FAST_U8_NEXT(trie, dataAccess, src, limit, result) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __lead = (uint8_t)*(src)++; \ + if (!U8_IS_SINGLE(__lead)) { \ + uint8_t __t1, __t2, __t3; \ + if ((src) != (limit) && \ + (__lead >= 0xe0 ? \ + __lead < 0xf0 ? /* U+0800..U+FFFF except surrogates */ \ + U8_LEAD3_T1_BITS[__lead &= 0xf] & (1 << ((__t1 = *(src)) >> 5)) && \ + ++(src) != (limit) && (__t2 = *(src) - 0x80) <= 0x3f && \ + (__lead = ((int32_t)(trie)->index[(__lead << 6) + (__t1 & 0x3f)]) + __t2, 1) \ + : /* U+10000..U+10FFFF */ \ + (__lead -= 0xf0) <= 4 && \ + U8_LEAD4_T1_BITS[(__t1 = *(src)) >> 4] & (1 << __lead) && \ + (__lead = (__lead << 6) | (__t1 & 0x3f), ++(src) != (limit)) && \ + (__t2 = *(src) - 0x80) <= 0x3f && \ + ++(src) != (limit) && (__t3 = *(src) - 0x80) <= 0x3f && \ + (__lead = __lead >= (trie)->shifted12HighStart ? \ + (trie)->dataLength - UCPTRIE_HIGH_VALUE_NEG_DATA_OFFSET : \ + ucptrie_internalSmallU8Index((trie), __lead, __t2, __t3), 1) \ + : /* U+0080..U+07FF */ \ + __lead >= 0xc2 && (__t1 = *(src) - 0x80) <= 0x3f && \ + (__lead = (int32_t)(trie)->index[__lead & 0x1f] + __t1, 1))) { \ + ++(src); \ + } else { \ + __lead = (trie)->dataLength - UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET; /* ill-formed*/ \ + } \ + } \ + (result) = dataAccess(trie, __lead); \ +} UPRV_BLOCK_MACRO_END + +/** + * UTF-8: Pre-decrements src and gets a value from the trie. + * Sets the trie error value for an ill-formed byte sequence. + * + * Unlike UCPTRIE_FAST_U16_PREV() this UTF-8 macro does not provide the code point + * because it would be more work to do so and is often not needed. + * If the trie value differs from the error value, then the byte sequence is well-formed, + * and the code point can be assembled without revalidation. + * + * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param start (const char *, in) the start pointer for the text + * @param src (const char *, in/out) the source text pointer + * @param result (out) variable for the trie lookup result + * @stable ICU 63 + */ +#define UCPTRIE_FAST_U8_PREV(trie, dataAccess, start, src, result) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __index = (uint8_t)*--(src); \ + if (!U8_IS_SINGLE(__index)) { \ + __index = ucptrie_internalU8PrevIndex((trie), __index, (const uint8_t *)(start), \ + (const uint8_t *)(src)); \ + (src) -= __index & 7; \ + __index >>= 3; \ + } \ + (result) = dataAccess(trie, __index); \ +} UPRV_BLOCK_MACRO_END + +/** + * Returns a trie value for an ASCII code point, without range checking. + * + * @param trie (const UCPTrie *, in) the trie (of either fast or small type) + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param c (UChar32, in) the input code point; must be U+0000..U+007F + * @return The ASCII code point's trie value. + * @stable ICU 63 + */ +#define UCPTRIE_ASCII_GET(trie, dataAccess, c) dataAccess(trie, c) + +/** + * Returns a trie value for a BMP code point (U+0000..U+FFFF), without range checking. + * Can be used to look up a value for a UTF-16 code unit if other parts of + * the string processing check for surrogates. + * + * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param c (UChar32, in) the input code point, must be U+0000..U+FFFF + * @return The BMP code point's trie value. + * @stable ICU 63 + */ +#define UCPTRIE_FAST_BMP_GET(trie, dataAccess, c) dataAccess(trie, _UCPTRIE_FAST_INDEX(trie, c)) + +/** + * Returns a trie value for a supplementary code point (U+10000..U+10FFFF), + * without range checking. + * + * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST + * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width + * @param c (UChar32, in) the input code point, must be U+10000..U+10FFFF + * @return The supplementary code point's trie value. + * @stable ICU 63 + */ +#define UCPTRIE_FAST_SUPP_GET(trie, dataAccess, c) dataAccess(trie, _UCPTRIE_SMALL_INDEX(trie, c)) + +/* Internal definitions ----------------------------------------------------- */ + +#ifndef U_IN_DOXYGEN + +/** + * Internal implementation constants. + * These are needed for the API macros, but users should not use these directly. + * @internal + */ +enum { + /** @internal */ + UCPTRIE_FAST_SHIFT = 6, + + /** Number of entries in a data block for code points below the fast limit. 64=0x40 @internal */ + UCPTRIE_FAST_DATA_BLOCK_LENGTH = 1 << UCPTRIE_FAST_SHIFT, + + /** Mask for getting the lower bits for the in-fast-data-block offset. @internal */ + UCPTRIE_FAST_DATA_MASK = UCPTRIE_FAST_DATA_BLOCK_LENGTH - 1, + + /** @internal */ + UCPTRIE_SMALL_MAX = 0xfff, + + /** + * Offset from dataLength (to be subtracted) for fetching the + * value returned for out-of-range code points and ill-formed UTF-8/16. + * @internal + */ + UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET = 1, + /** + * Offset from dataLength (to be subtracted) for fetching the + * value returned for code points highStart..U+10FFFF. + * @internal + */ + UCPTRIE_HIGH_VALUE_NEG_DATA_OFFSET = 2 +}; + +/* Internal functions and macros -------------------------------------------- */ +// Do not conditionalize with #ifndef U_HIDE_INTERNAL_API, needed for public API + +/** @internal */ +U_CAPI int32_t U_EXPORT2 +ucptrie_internalSmallIndex(const UCPTrie *trie, UChar32 c); + +/** @internal */ +U_CAPI int32_t U_EXPORT2 +ucptrie_internalSmallU8Index(const UCPTrie *trie, int32_t lt1, uint8_t t2, uint8_t t3); + +/** + * Internal function for part of the UCPTRIE_FAST_U8_PREVxx() macro implementations. + * Do not call directly. + * @internal + */ +U_CAPI int32_t U_EXPORT2 +ucptrie_internalU8PrevIndex(const UCPTrie *trie, UChar32 c, + const uint8_t *start, const uint8_t *src); + +/** Internal trie getter for a code point below the fast limit. Returns the data index. @internal */ +#define _UCPTRIE_FAST_INDEX(trie, c) \ + ((int32_t)(trie)->index[(c) >> UCPTRIE_FAST_SHIFT] + ((c) & UCPTRIE_FAST_DATA_MASK)) + +/** Internal trie getter for a code point at or above the fast limit. Returns the data index. @internal */ +#define _UCPTRIE_SMALL_INDEX(trie, c) \ + ((c) >= (trie)->highStart ? \ + (trie)->dataLength - UCPTRIE_HIGH_VALUE_NEG_DATA_OFFSET : \ + ucptrie_internalSmallIndex(trie, c)) + +/** + * Internal trie getter for a code point, with checking that c is in U+0000..10FFFF. + * Returns the data index. + * @internal + */ +#define _UCPTRIE_CP_INDEX(trie, fastMax, c) \ + ((uint32_t)(c) <= (uint32_t)(fastMax) ? \ + _UCPTRIE_FAST_INDEX(trie, c) : \ + (uint32_t)(c) <= 0x10ffff ? \ + _UCPTRIE_SMALL_INDEX(trie, c) : \ + (trie)->dataLength - UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET) + +U_CDECL_END + +#endif // U_IN_DOXYGEN + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUCPTriePointer + * "Smart pointer" class, closes a UCPTrie via ucptrie_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 63 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUCPTriePointer, UCPTrie, ucptrie_close); + +U_NAMESPACE_END + +#endif // U_SHOW_CPLUSPLUS_API + +#endif diff --git a/thirdparty/icu4c/common/unicode/ucurr.h b/thirdparty/icu4c/common/unicode/ucurr.h new file mode 100644 index 0000000000..35c2a39389 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ucurr.h @@ -0,0 +1,468 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (c) 2002-2016, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +*/ +#ifndef _UCURR_H_ +#define _UCURR_H_ + +#include "unicode/utypes.h" +#include "unicode/uenum.h" + +/** + * \file + * \brief C API: Encapsulates information about a currency. + * + * The ucurr API encapsulates information about a currency, as defined by + * ISO 4217. A currency is represented by a 3-character string + * containing its ISO 4217 code. This API can return various data + * necessary the proper display of a currency: + * + * <ul><li>A display symbol, for a specific locale + * <li>The number of fraction digits to display + * <li>A rounding increment + * </ul> + * + * The <tt>DecimalFormat</tt> class uses these data to display + * currencies. + * @author Alan Liu + * @since ICU 2.2 + */ + +#if !UCONFIG_NO_FORMATTING + +/** + * Currency Usage used for Decimal Format + * @stable ICU 54 + */ +enum UCurrencyUsage { + /** + * a setting to specify currency usage which determines currency digit + * and rounding for standard usage, for example: "50.00 NT$" + * used as DEFAULT value + * @stable ICU 54 + */ + UCURR_USAGE_STANDARD=0, + /** + * a setting to specify currency usage which determines currency digit + * and rounding for cash usage, for example: "50 NT$" + * @stable ICU 54 + */ + UCURR_USAGE_CASH=1, +#ifndef U_HIDE_DEPRECATED_API + /** + * One higher than the last enum UCurrencyUsage constant. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UCURR_USAGE_COUNT=2 +#endif // U_HIDE_DEPRECATED_API +}; +/** Currency Usage used for Decimal Format */ +typedef enum UCurrencyUsage UCurrencyUsage; + +/** + * Finds a currency code for the given locale. + * @param locale the locale for which to retrieve a currency code. + * Currency can be specified by the "currency" keyword + * in which case it overrides the default currency code + * @param buff fill in buffer. Can be NULL for preflighting. + * @param buffCapacity capacity of the fill in buffer. Can be 0 for + * preflighting. If it is non-zero, the buff parameter + * must not be NULL. + * @param ec error code + * @return length of the currency string. It should always be 3. If 0, + * currency couldn't be found or the input values are + * invalid. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +ucurr_forLocale(const char* locale, + UChar* buff, + int32_t buffCapacity, + UErrorCode* ec); + +/** + * Selector constants for ucurr_getName(). + * + * @see ucurr_getName + * @stable ICU 2.6 + */ +typedef enum UCurrNameStyle { + /** + * Selector for ucurr_getName indicating a symbolic name for a + * currency, such as "$" for USD. + * @stable ICU 2.6 + */ + UCURR_SYMBOL_NAME, + + /** + * Selector for ucurr_getName indicating the long name for a + * currency, such as "US Dollar" for USD. + * @stable ICU 2.6 + */ + UCURR_LONG_NAME, + + /** + * Selector for getName() indicating the narrow currency symbol. + * The narrow currency symbol is similar to the regular currency + * symbol, but it always takes the shortest form: for example, + * "$" instead of "US$" for USD in en-CA. + * + * @stable ICU 61 + */ + UCURR_NARROW_SYMBOL_NAME, + +#ifndef U_HIDE_DRAFT_API + /** + * Selector for getName() indicating the formal currency symbol. + * The formal currency symbol is similar to the regular currency + * symbol, but it always takes the form used in formal settings + * such as banking; for example, "NT$" instead of "$" for TWD in zh-TW. + * + * @draft ICU 68 + */ + UCURR_FORMAL_SYMBOL_NAME, + + /** + * Selector for getName() indicating the variant currency symbol. + * The variant symbol for a currency is an alternative symbol + * that is not necessarily as widely used as the regular symbol. + * + * @draft ICU 68 + */ + UCURR_VARIANT_SYMBOL_NAME +#endif // U_HIDE_DRAFT_API + +} UCurrNameStyle; + +#if !UCONFIG_NO_SERVICE +/** + * @stable ICU 2.6 + */ +typedef const void* UCurrRegistryKey; + +/** + * Register an (existing) ISO 4217 currency code for the given locale. + * Only the country code and the two variants EURO and PRE_EURO are + * recognized. + * @param isoCode the three-letter ISO 4217 currency code + * @param locale the locale for which to register this currency code + * @param status the in/out status code + * @return a registry key that can be used to unregister this currency code, or NULL + * if there was an error. + * @stable ICU 2.6 + */ +U_CAPI UCurrRegistryKey U_EXPORT2 +ucurr_register(const UChar* isoCode, + const char* locale, + UErrorCode* status); +/** + * Unregister the previously-registered currency definitions using the + * URegistryKey returned from ucurr_register. Key becomes invalid after + * a successful call and should not be used again. Any currency + * that might have been hidden by the original ucurr_register call is + * restored. + * @param key the registry key returned by a previous call to ucurr_register + * @param status the in/out status code, no special meanings are assigned + * @return true if the currency for this key was successfully unregistered + * @stable ICU 2.6 + */ +U_CAPI UBool U_EXPORT2 +ucurr_unregister(UCurrRegistryKey key, UErrorCode* status); +#endif /* UCONFIG_NO_SERVICE */ + +/** + * Returns the display name for the given currency in the + * given locale. For example, the display name for the USD + * currency object in the en_US locale is "$". + * @param currency null-terminated 3-letter ISO 4217 code + * @param locale locale in which to display currency + * @param nameStyle selector for which kind of name to return + * @param isChoiceFormat always set to false, or can be NULL; + * display names are static strings; + * since ICU 4.4, ChoiceFormat patterns are no longer supported + * @param len fill-in parameter to receive length of result + * @param ec error code + * @return pointer to display string of 'len' UChars. If the resource + * data contains no entry for 'currency', then 'currency' itself is + * returned. + * @stable ICU 2.6 + */ +U_CAPI const UChar* U_EXPORT2 +ucurr_getName(const UChar* currency, + const char* locale, + UCurrNameStyle nameStyle, + UBool* isChoiceFormat, + int32_t* len, + UErrorCode* ec); + +/** + * Returns the plural name for the given currency in the + * given locale. For example, the plural name for the USD + * currency object in the en_US locale is "US dollar" or "US dollars". + * @param currency null-terminated 3-letter ISO 4217 code + * @param locale locale in which to display currency + * @param isChoiceFormat always set to false, or can be NULL; + * display names are static strings; + * since ICU 4.4, ChoiceFormat patterns are no longer supported + * @param pluralCount plural count + * @param len fill-in parameter to receive length of result + * @param ec error code + * @return pointer to display string of 'len' UChars. If the resource + * data contains no entry for 'currency', then 'currency' itself is + * returned. + * @stable ICU 4.2 + */ +U_CAPI const UChar* U_EXPORT2 +ucurr_getPluralName(const UChar* currency, + const char* locale, + UBool* isChoiceFormat, + const char* pluralCount, + int32_t* len, + UErrorCode* ec); + +/** + * Returns the number of the number of fraction digits that should + * be displayed for the given currency. + * This is equivalent to ucurr_getDefaultFractionDigitsForUsage(currency,UCURR_USAGE_STANDARD,ec); + * + * Important: The number of fraction digits for a given currency is NOT + * guaranteed to be constant across versions of ICU or CLDR. For example, + * do NOT use this value as a mechanism for deciding the magnitude used + * to store currency values in a database. You should use this value for + * display purposes only. + * + * @param currency null-terminated 3-letter ISO 4217 code + * @param ec input-output error code + * @return a non-negative number of fraction digits to be + * displayed, or 0 if there is an error + * @stable ICU 3.0 + */ +U_CAPI int32_t U_EXPORT2 +ucurr_getDefaultFractionDigits(const UChar* currency, + UErrorCode* ec); + +/** + * Returns the number of the number of fraction digits that should + * be displayed for the given currency with usage. + * + * Important: The number of fraction digits for a given currency is NOT + * guaranteed to be constant across versions of ICU or CLDR. For example, + * do NOT use this value as a mechanism for deciding the magnitude used + * to store currency values in a database. You should use this value for + * display purposes only. + * + * @param currency null-terminated 3-letter ISO 4217 code + * @param usage enum usage for the currency + * @param ec input-output error code + * @return a non-negative number of fraction digits to be + * displayed, or 0 if there is an error + * @stable ICU 54 + */ +U_CAPI int32_t U_EXPORT2 +ucurr_getDefaultFractionDigitsForUsage(const UChar* currency, + const UCurrencyUsage usage, + UErrorCode* ec); + +/** + * Returns the rounding increment for the given currency, or 0.0 if no + * rounding is done by the currency. + * This is equivalent to ucurr_getRoundingIncrementForUsage(currency,UCURR_USAGE_STANDARD,ec); + * @param currency null-terminated 3-letter ISO 4217 code + * @param ec input-output error code + * @return the non-negative rounding increment, or 0.0 if none, + * or 0.0 if there is an error + * @stable ICU 3.0 + */ +U_CAPI double U_EXPORT2 +ucurr_getRoundingIncrement(const UChar* currency, + UErrorCode* ec); + +/** + * Returns the rounding increment for the given currency, or 0.0 if no + * rounding is done by the currency given usage. + * @param currency null-terminated 3-letter ISO 4217 code + * @param usage enum usage for the currency + * @param ec input-output error code + * @return the non-negative rounding increment, or 0.0 if none, + * or 0.0 if there is an error + * @stable ICU 54 + */ +U_CAPI double U_EXPORT2 +ucurr_getRoundingIncrementForUsage(const UChar* currency, + const UCurrencyUsage usage, + UErrorCode* ec); + +/** + * Selector constants for ucurr_openCurrencies(). + * + * @see ucurr_openCurrencies + * @stable ICU 3.2 + */ +typedef enum UCurrCurrencyType { + /** + * Select all ISO-4217 currency codes. + * @stable ICU 3.2 + */ + UCURR_ALL = INT32_MAX, + /** + * Select only ISO-4217 commonly used currency codes. + * These currencies can be found in common use, and they usually have + * bank notes or coins associated with the currency code. + * This does not include fund codes, precious metals and other + * various ISO-4217 codes limited to special financial products. + * @stable ICU 3.2 + */ + UCURR_COMMON = 1, + /** + * Select ISO-4217 uncommon currency codes. + * These codes respresent fund codes, precious metals and other + * various ISO-4217 codes limited to special financial products. + * A fund code is a monetary resource associated with a currency. + * @stable ICU 3.2 + */ + UCURR_UNCOMMON = 2, + /** + * Select only deprecated ISO-4217 codes. + * These codes are no longer in general public use. + * @stable ICU 3.2 + */ + UCURR_DEPRECATED = 4, + /** + * Select only non-deprecated ISO-4217 codes. + * These codes are in general public use. + * @stable ICU 3.2 + */ + UCURR_NON_DEPRECATED = 8 +} UCurrCurrencyType; + +/** + * Provides a UEnumeration object for listing ISO-4217 codes. + * @param currType You can use one of several UCurrCurrencyType values for this + * variable. You can also | (or) them together to get a specific list of + * currencies. Most people will want to use the (UCURR_COMMON|UCURR_NON_DEPRECATED) value to + * get a list of current currencies. + * @param pErrorCode Error code + * @stable ICU 3.2 + */ +U_CAPI UEnumeration * U_EXPORT2 +ucurr_openISOCurrencies(uint32_t currType, UErrorCode *pErrorCode); + +/** + * Queries if the given ISO 4217 3-letter code is available on the specified date range. + * + * Note: For checking availability of a currency on a specific date, specify the date on both 'from' and 'to' + * + * When 'from' is U_DATE_MIN and 'to' is U_DATE_MAX, this method checks if the specified currency is available any time. + * If 'from' and 'to' are same UDate value, this method checks if the specified currency is available on that date. + * + * @param isoCode + * The ISO 4217 3-letter code. + * + * @param from + * The lower bound of the date range, inclusive. When 'from' is U_DATE_MIN, check the availability + * of the currency any date before 'to' + * + * @param to + * The upper bound of the date range, inclusive. When 'to' is U_DATE_MAX, check the availability of + * the currency any date after 'from' + * + * @param errorCode + * ICU error code + * + * @return true if the given ISO 4217 3-letter code is supported on the specified date range. + * + * @stable ICU 4.8 + */ +U_CAPI UBool U_EXPORT2 +ucurr_isAvailable(const UChar* isoCode, + UDate from, + UDate to, + UErrorCode* errorCode); + +/** + * Finds the number of valid currency codes for the + * given locale and date. + * @param locale the locale for which to retrieve the + * currency count. + * @param date the date for which to retrieve the + * currency count for the given locale. + * @param ec error code + * @return the number of currency codes for the + * given locale and date. If 0, currency + * codes couldn't be found for the input + * values are invalid. + * @stable ICU 4.0 + */ +U_CAPI int32_t U_EXPORT2 +ucurr_countCurrencies(const char* locale, + UDate date, + UErrorCode* ec); + +/** + * Finds a currency code for the given locale and date + * @param locale the locale for which to retrieve a currency code. + * Currency can be specified by the "currency" keyword + * in which case it overrides the default currency code + * @param date the date for which to retrieve a currency code for + * the given locale. + * @param index the index within the available list of currency codes + * for the given locale on the given date. + * @param buff fill in buffer. Can be NULL for preflighting. + * @param buffCapacity capacity of the fill in buffer. Can be 0 for + * preflighting. If it is non-zero, the buff parameter + * must not be NULL. + * @param ec error code + * @return length of the currency string. It should always be 3. + * If 0, currency couldn't be found or the input values are + * invalid. + * @stable ICU 4.0 + */ +U_CAPI int32_t U_EXPORT2 +ucurr_forLocaleAndDate(const char* locale, + UDate date, + int32_t index, + UChar* buff, + int32_t buffCapacity, + UErrorCode* ec); + +/** + * Given a key and a locale, returns an array of string values in a preferred + * order that would make a difference. These are all and only those values where + * the open (creation) of the service with the locale formed from the input locale + * plus input keyword and that value has different behavior than creation with the + * input locale alone. + * @param key one of the keys supported by this service. For now, only + * "currency" is supported. + * @param locale the locale + * @param commonlyUsed if set to true it will return only commonly used values + * with the given locale in preferred order. Otherwise, + * it will return all the available values for the locale. + * @param status error status + * @return a string enumeration over keyword values for the given key and the locale. + * @stable ICU 4.2 + */ +U_CAPI UEnumeration* U_EXPORT2 +ucurr_getKeywordValuesForLocale(const char* key, + const char* locale, + UBool commonlyUsed, + UErrorCode* status); + +/** + * Returns the ISO 4217 numeric code for the currency. + * <p>Note: If the ISO 4217 numeric code is not assigned for the currency or + * the currency is unknown, this function returns 0. + * + * @param currency null-terminated 3-letter ISO 4217 code + * @return The ISO 4217 numeric code of the currency + * @stable ICU 49 + */ +U_CAPI int32_t U_EXPORT2 +ucurr_getNumericCode(const UChar* currency); + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/udata.h b/thirdparty/icu4c/common/unicode/udata.h new file mode 100644 index 0000000000..6caa849c42 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/udata.h @@ -0,0 +1,440 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1999-2014, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* file name: udata.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999oct25 +* created by: Markus W. Scherer +*/ + +#ifndef __UDATA_H__ +#define __UDATA_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +U_CDECL_BEGIN + +/** + * \file + * \brief C API: Data loading interface + * + * <h2>Information about data loading interface</h2> + * + * This API is used to find and efficiently load data for ICU and applications + * using ICU. It provides an abstract interface that specifies a data type and + * name to find and load the data. Normally this API is used by other ICU APIs + * to load required data out of the ICU data library, but it can be used to + * load data out of other places. + * + * See the User Guide Data Management chapter. + */ + +#ifndef U_HIDE_INTERNAL_API +/** + * Character used to separate package names from tree names + * @internal ICU 3.0 + */ +#define U_TREE_SEPARATOR '-' + +/** + * String used to separate package names from tree names + * @internal ICU 3.0 + */ +#define U_TREE_SEPARATOR_STRING "-" + +/** + * Character used to separate parts of entry names + * @internal ICU 3.0 + */ +#define U_TREE_ENTRY_SEP_CHAR '/' + +/** + * String used to separate parts of entry names + * @internal ICU 3.0 + */ +#define U_TREE_ENTRY_SEP_STRING "/" + +/** + * Alias for standard ICU data + * @internal ICU 3.0 + */ +#define U_ICUDATA_ALIAS "ICUDATA" + +#endif /* U_HIDE_INTERNAL_API */ + +/** + * UDataInfo contains the properties about the requested data. + * This is meta data. + * + * <p>This structure may grow in the future, indicated by the + * <code>size</code> field.</p> + * + * <p>ICU data must be at least 8-aligned, and should be 16-aligned. + * The UDataInfo struct begins 4 bytes after the start of the data item, + * so it is 4-aligned. + * + * <p>The platform data property fields help determine if a data + * file can be efficiently used on a given machine. + * The particular fields are of importance only if the data + * is affected by the properties - if there is integer data + * with word sizes > 1 byte, char* text, or UChar* text.</p> + * + * <p>The implementation for the <code>udata_open[Choice]()</code> + * functions may reject data based on the value in <code>isBigEndian</code>. + * No other field is used by the <code>udata</code> API implementation.</p> + * + * <p>The <code>dataFormat</code> may be used to identify + * the kind of data, e.g. a converter table.</p> + * + * <p>The <code>formatVersion</code> field should be used to + * make sure that the format can be interpreted. + * It may be a good idea to check only for the one or two highest + * of the version elements to allow the data memory to + * get more or somewhat rearranged contents, for as long + * as the using code can still interpret the older contents.</p> + * + * <p>The <code>dataVersion</code> field is intended to be a + * common place to store the source version of the data; + * for data from the Unicode character database, this could + * reflect the Unicode version.</p> + * + * @stable ICU 2.0 + */ +typedef struct { + /** sizeof(UDataInfo) + * @stable ICU 2.0 */ + uint16_t size; + + /** unused, set to 0 + * @stable ICU 2.0*/ + uint16_t reservedWord; + + /* platform data properties */ + /** 0 for little-endian machine, 1 for big-endian + * @stable ICU 2.0 */ + uint8_t isBigEndian; + + /** see U_CHARSET_FAMILY values in utypes.h + * @stable ICU 2.0*/ + uint8_t charsetFamily; + + /** sizeof(UChar), one of { 1, 2, 4 } + * @stable ICU 2.0*/ + uint8_t sizeofUChar; + + /** unused, set to 0 + * @stable ICU 2.0*/ + uint8_t reservedByte; + + /** data format identifier + * @stable ICU 2.0*/ + uint8_t dataFormat[4]; + + /** versions: [0] major [1] minor [2] milli [3] micro + * @stable ICU 2.0*/ + uint8_t formatVersion[4]; + + /** versions: [0] major [1] minor [2] milli [3] micro + * @stable ICU 2.0*/ + uint8_t dataVersion[4]; +} UDataInfo; + +/* API for reading data -----------------------------------------------------*/ + +/** + * Forward declaration of the data memory type. + * @stable ICU 2.0 + */ +typedef struct UDataMemory UDataMemory; + +/** + * Callback function for udata_openChoice(). + * @param context parameter passed into <code>udata_openChoice()</code>. + * @param type The type of the data as passed into <code>udata_openChoice()</code>. + * It may be <code>NULL</code>. + * @param name The name of the data as passed into <code>udata_openChoice()</code>. + * @param pInfo A pointer to the <code>UDataInfo</code> structure + * of data that has been loaded and will be returned + * by <code>udata_openChoice()</code> if this function + * returns <code>true</code>. + * @return true if the current data memory is acceptable + * @stable ICU 2.0 + */ +typedef UBool U_CALLCONV +UDataMemoryIsAcceptable(void *context, + const char *type, const char *name, + const UDataInfo *pInfo); + + +/** + * Convenience function. + * This function works the same as <code>udata_openChoice</code> + * except that any data that matches the type and name + * is assumed to be acceptable. + * @param path Specifies an absolute path and/or a basename for the + * finding of the data in the file system. + * <code>NULL</code> for ICU data. + * @param type A string that specifies the type of data to be loaded. + * For example, resource bundles are loaded with type "res", + * conversion tables with type "cnv". + * This may be <code>NULL</code> or empty. + * @param name A string that specifies the name of the data. + * @param pErrorCode An ICU UErrorCode parameter. It must not be <code>NULL</code>. + * @return A pointer (handle) to a data memory object, or <code>NULL</code> + * if an error occurs. Call <code>udata_getMemory()</code> + * to get a pointer to the actual data. + * + * @see udata_openChoice + * @stable ICU 2.0 + */ +U_CAPI UDataMemory * U_EXPORT2 +udata_open(const char *path, const char *type, const char *name, + UErrorCode *pErrorCode); + +/** + * Data loading function. + * This function is used to find and load efficiently data for + * ICU and applications using ICU. + * It provides an abstract interface that allows to specify a data + * type and name to find and load the data. + * + * <p>The implementation depends on platform properties and user preferences + * and may involve loading shared libraries (DLLs), mapping + * files into memory, or fopen()/fread() files. + * It may also involve using static memory or database queries etc. + * Several or all data items may be combined into one entity + * (DLL, memory-mappable file).</p> + * + * <p>The data is always preceded by a header that includes + * a <code>UDataInfo</code> structure. + * The caller's <code>isAcceptable()</code> function is called to make + * sure that the data is useful. It may be called several times if it + * rejects the data and there is more than one location with data + * matching the type and name.</p> + * + * <p>If <code>path==NULL</code>, then ICU data is loaded. + * Otherwise, it is separated into a basename and a basename-less directory string. + * The basename is used as the data package name, and the directory is + * logically prepended to the ICU data directory string.</p> + * + * <p>For details about ICU data loading see the User Guide + * Data Management chapter. (http://icu-project.org/userguide/icudata.html)</p> + * + * @param path Specifies an absolute path and/or a basename for the + * finding of the data in the file system. + * <code>NULL</code> for ICU data. + * @param type A string that specifies the type of data to be loaded. + * For example, resource bundles are loaded with type "res", + * conversion tables with type "cnv". + * This may be <code>NULL</code> or empty. + * @param name A string that specifies the name of the data. + * @param isAcceptable This function is called to verify that loaded data + * is useful for the client code. If it returns false + * for all data items, then <code>udata_openChoice()</code> + * will return with an error. + * @param context Arbitrary parameter to be passed into isAcceptable. + * @param pErrorCode An ICU UErrorCode parameter. It must not be <code>NULL</code>. + * @return A pointer (handle) to a data memory object, or <code>NULL</code> + * if an error occurs. Call <code>udata_getMemory()</code> + * to get a pointer to the actual data. + * @stable ICU 2.0 + */ +U_CAPI UDataMemory * U_EXPORT2 +udata_openChoice(const char *path, const char *type, const char *name, + UDataMemoryIsAcceptable *isAcceptable, void *context, + UErrorCode *pErrorCode); + +/** + * Close the data memory. + * This function must be called to allow the system to + * release resources associated with this data memory. + * @param pData The pointer to data memory object + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +udata_close(UDataMemory *pData); + +/** + * Get the pointer to the actual data inside the data memory. + * The data is read-only. + * + * ICU data must be at least 8-aligned, and should be 16-aligned. + * + * @param pData The pointer to data memory object + * @stable ICU 2.0 + */ +U_CAPI const void * U_EXPORT2 +udata_getMemory(UDataMemory *pData); + +/** + * Get the information from the data memory header. + * This allows to get access to the header containing + * platform data properties etc. which is not part of + * the data itself and can therefore not be accessed + * via the pointer that <code>udata_getMemory()</code> returns. + * + * @param pData pointer to the data memory object + * @param pInfo pointer to a UDataInfo object; + * its <code>size</code> field must be set correctly, + * typically to <code>sizeof(UDataInfo)</code>. + * + * <code>*pInfo</code> will be filled with the UDataInfo structure + * in the data memory object. If this structure is smaller than + * <code>pInfo->size</code>, then the <code>size</code> will be + * adjusted and only part of the structure will be filled. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +udata_getInfo(UDataMemory *pData, UDataInfo *pInfo); + +/** + * This function bypasses the normal ICU data loading process and + * allows you to force ICU's system data to come out of a user-specified + * area in memory. + * + * ICU data must be at least 8-aligned, and should be 16-aligned. + * See https://unicode-org.github.io/icu/userguide/icudata + * + * The format of this data is that of the icu common data file, as is + * generated by the pkgdata tool with mode=common or mode=dll. + * You can read in a whole common mode file and pass the address to the start of the + * data, or (with the appropriate link options) pass in the pointer to + * the data that has been loaded from a dll by the operating system, + * as shown in this code: + * + * extern const char U_IMPORT U_ICUDATA_ENTRY_POINT []; + * // U_ICUDATA_ENTRY_POINT is same as entry point specified to pkgdata tool + * UErrorCode status = U_ZERO_ERROR; + * + * udata_setCommonData(&U_ICUDATA_ENTRY_POINT, &status); + * + * It is important that the declaration be as above. The entry point + * must not be declared as an extern void*. + * + * Starting with ICU 4.4, it is possible to set several data packages, + * one per call to this function. + * udata_open() will look for data in the multiple data packages in the order + * in which they were set. + * The position of the linked-in or default-name ICU .data package in the + * search list depends on when the first data item is loaded that is not contained + * in the already explicitly set packages. + * If data was loaded implicitly before the first call to this function + * (for example, via opening a converter, constructing a UnicodeString + * from default-codepage data, using formatting or collation APIs, etc.), + * then the default data will be first in the list. + * + * This function has no effect on application (non ICU) data. See udata_setAppData() + * for similar functionality for application data. + * + * @param data pointer to ICU common data + * @param err outgoing error status <code>U_USING_DEFAULT_WARNING, U_UNSUPPORTED_ERROR</code> + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +udata_setCommonData(const void *data, UErrorCode *err); + + +/** + * This function bypasses the normal ICU data loading process for application-specific + * data and allows you to force the it to come out of a user-specified + * pointer. + * + * ICU data must be at least 8-aligned, and should be 16-aligned. + * See https://unicode-org.github.io/icu/userguide/icudata + * + * The format of this data is that of the icu common data file, like 'icudt26l.dat' + * or the corresponding shared library (DLL) file. + * The application must read in or otherwise construct an image of the data and then + * pass the address of it to this function. + * + * + * Warning: setAppData will set a U_USING_DEFAULT_WARNING code if + * data with the specifed path that has already been opened, or + * if setAppData with the same path has already been called. + * Any such calls to setAppData will have no effect. + * + * + * @param packageName the package name by which the application will refer + * to (open) this data + * @param data pointer to the data + * @param err outgoing error status <code>U_USING_DEFAULT_WARNING, U_UNSUPPORTED_ERROR</code> + * @see udata_setCommonData + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +udata_setAppData(const char *packageName, const void *data, UErrorCode *err); + +/** + * Possible settings for udata_setFileAccess() + * @see udata_setFileAccess + * @stable ICU 3.4 + */ +typedef enum UDataFileAccess { + /** ICU looks for data in single files first, then in packages. (default) @stable ICU 3.4 */ + UDATA_FILES_FIRST, + /** An alias for the default access mode. @stable ICU 3.4 */ + UDATA_DEFAULT_ACCESS = UDATA_FILES_FIRST, + /** ICU only loads data from packages, not from single files. @stable ICU 3.4 */ + UDATA_ONLY_PACKAGES, + /** ICU loads data from packages first, and only from single files + if the data cannot be found in a package. @stable ICU 3.4 */ + UDATA_PACKAGES_FIRST, + /** ICU does not access the file system for data loading. @stable ICU 3.4 */ + UDATA_NO_FILES, +#ifndef U_HIDE_DEPRECATED_API + /** + * Number of real UDataFileAccess values. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UDATA_FILE_ACCESS_COUNT +#endif // U_HIDE_DEPRECATED_API +} UDataFileAccess; + +/** + * This function may be called to control how ICU loads data. It must be called + * before any ICU data is loaded, including application data loaded with + * ures/ResourceBundle or udata APIs. This function is not multithread safe. + * The results of calling it while other threads are loading data are undefined. + * @param access The type of file access to be used + * @param status Error code. + * @see UDataFileAccess + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +udata_setFileAccess(UDataFileAccess access, UErrorCode *status); + +U_CDECL_END + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUDataMemoryPointer + * "Smart pointer" class, closes a UDataMemory via udata_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUDataMemoryPointer, UDataMemory, udata_close); + +U_NAMESPACE_END + +#endif // U_SHOW_CPLUSPLUS_API + +#endif diff --git a/thirdparty/icu4c/common/unicode/udisplaycontext.h b/thirdparty/icu4c/common/unicode/udisplaycontext.h new file mode 100644 index 0000000000..6e14217980 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/udisplaycontext.h @@ -0,0 +1,173 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +***************************************************************************************** +* Copyright (C) 2014-2016, International Business Machines +* Corporation and others. All Rights Reserved. +***************************************************************************************** +*/ + +#ifndef UDISPLAYCONTEXT_H +#define UDISPLAYCONTEXT_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_FORMATTING + +/** + * \file + * \brief C API: Display context types (enum values) + */ + +/** + * Display context types, for getting values of a particular setting. + * Note, the specific numeric values are internal and may change. + * @stable ICU 51 + */ +enum UDisplayContextType { + /** + * Type to retrieve the dialect handling setting, e.g. + * UDISPCTX_STANDARD_NAMES or UDISPCTX_DIALECT_NAMES. + * @stable ICU 51 + */ + UDISPCTX_TYPE_DIALECT_HANDLING = 0, + /** + * Type to retrieve the capitalization context setting, e.g. + * UDISPCTX_CAPITALIZATION_NONE, UDISPCTX_CAPITALIZATION_FOR_MIDDLE_OF_SENTENCE, + * UDISPCTX_CAPITALIZATION_FOR_BEGINNING_OF_SENTENCE, etc. + * @stable ICU 51 + */ + UDISPCTX_TYPE_CAPITALIZATION = 1, + /** + * Type to retrieve the display length setting, e.g. + * UDISPCTX_LENGTH_FULL, UDISPCTX_LENGTH_SHORT. + * @stable ICU 54 + */ + UDISPCTX_TYPE_DISPLAY_LENGTH = 2, + /** + * Type to retrieve the substitute handling setting, e.g. + * UDISPCTX_SUBSTITUTE, UDISPCTX_NO_SUBSTITUTE. + * @stable ICU 58 + */ + UDISPCTX_TYPE_SUBSTITUTE_HANDLING = 3 +}; +/** +* @stable ICU 51 +*/ +typedef enum UDisplayContextType UDisplayContextType; + +/** + * Display context settings. + * Note, the specific numeric values are internal and may change. + * @stable ICU 51 + */ +enum UDisplayContext { + /** + * ================================ + * DIALECT_HANDLING can be set to one of UDISPCTX_STANDARD_NAMES or + * UDISPCTX_DIALECT_NAMES. Use UDisplayContextType UDISPCTX_TYPE_DIALECT_HANDLING + * to get the value. + */ + /** + * A possible setting for DIALECT_HANDLING: + * use standard names when generating a locale name, + * e.g. en_GB displays as 'English (United Kingdom)'. + * @stable ICU 51 + */ + UDISPCTX_STANDARD_NAMES = (UDISPCTX_TYPE_DIALECT_HANDLING<<8) + 0, + /** + * A possible setting for DIALECT_HANDLING: + * use dialect names, when generating a locale name, + * e.g. en_GB displays as 'British English'. + * @stable ICU 51 + */ + UDISPCTX_DIALECT_NAMES = (UDISPCTX_TYPE_DIALECT_HANDLING<<8) + 1, + /** + * ================================ + * CAPITALIZATION can be set to one of UDISPCTX_CAPITALIZATION_NONE, + * UDISPCTX_CAPITALIZATION_FOR_MIDDLE_OF_SENTENCE, + * UDISPCTX_CAPITALIZATION_FOR_BEGINNING_OF_SENTENCE, + * UDISPCTX_CAPITALIZATION_FOR_UI_LIST_OR_MENU, or + * UDISPCTX_CAPITALIZATION_FOR_STANDALONE. + * Use UDisplayContextType UDISPCTX_TYPE_CAPITALIZATION to get the value. + */ + /** + * The capitalization context to be used is unknown (this is the default value). + * @stable ICU 51 + */ + UDISPCTX_CAPITALIZATION_NONE = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 0, + /** + * The capitalization context if a date, date symbol or display name is to be + * formatted with capitalization appropriate for the middle of a sentence. + * @stable ICU 51 + */ + UDISPCTX_CAPITALIZATION_FOR_MIDDLE_OF_SENTENCE = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 1, + /** + * The capitalization context if a date, date symbol or display name is to be + * formatted with capitalization appropriate for the beginning of a sentence. + * @stable ICU 51 + */ + UDISPCTX_CAPITALIZATION_FOR_BEGINNING_OF_SENTENCE = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 2, + /** + * The capitalization context if a date, date symbol or display name is to be + * formatted with capitalization appropriate for a user-interface list or menu item. + * @stable ICU 51 + */ + UDISPCTX_CAPITALIZATION_FOR_UI_LIST_OR_MENU = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 3, + /** + * The capitalization context if a date, date symbol or display name is to be + * formatted with capitalization appropriate for stand-alone usage such as an + * isolated name on a calendar page. + * @stable ICU 51 + */ + UDISPCTX_CAPITALIZATION_FOR_STANDALONE = (UDISPCTX_TYPE_CAPITALIZATION<<8) + 4, + /** + * ================================ + * DISPLAY_LENGTH can be set to one of UDISPCTX_LENGTH_FULL or + * UDISPCTX_LENGTH_SHORT. Use UDisplayContextType UDISPCTX_TYPE_DISPLAY_LENGTH + * to get the value. + */ + /** + * A possible setting for DISPLAY_LENGTH: + * use full names when generating a locale name, + * e.g. "United States" for US. + * @stable ICU 54 + */ + UDISPCTX_LENGTH_FULL = (UDISPCTX_TYPE_DISPLAY_LENGTH<<8) + 0, + /** + * A possible setting for DISPLAY_LENGTH: + * use short names when generating a locale name, + * e.g. "U.S." for US. + * @stable ICU 54 + */ + UDISPCTX_LENGTH_SHORT = (UDISPCTX_TYPE_DISPLAY_LENGTH<<8) + 1, + /** + * ================================ + * SUBSTITUTE_HANDLING can be set to one of UDISPCTX_SUBSTITUTE or + * UDISPCTX_NO_SUBSTITUTE. Use UDisplayContextType UDISPCTX_TYPE_SUBSTITUTE_HANDLING + * to get the value. + */ + /** + * A possible setting for SUBSTITUTE_HANDLING: + * Returns a fallback value (e.g., the input code) when no data is available. + * This is the default value. + * @stable ICU 58 + */ + UDISPCTX_SUBSTITUTE = (UDISPCTX_TYPE_SUBSTITUTE_HANDLING<<8) + 0, + /** + * A possible setting for SUBSTITUTE_HANDLING: + * Returns a null value with error code set to U_ILLEGAL_ARGUMENT_ERROR when no + * data is available. + * @stable ICU 58 + */ + UDISPCTX_NO_SUBSTITUTE = (UDISPCTX_TYPE_SUBSTITUTE_HANDLING<<8) + 1 + +}; +/** +* @stable ICU 51 +*/ +typedef enum UDisplayContext UDisplayContext; + +#endif /* #if !UCONFIG_NO_FORMATTING */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/uenum.h b/thirdparty/icu4c/common/unicode/uenum.h new file mode 100644 index 0000000000..d9c893e06d --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uenum.h @@ -0,0 +1,209 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2002-2013, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: uenum.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:2 +* +* created on: 2002jul08 +* created by: Vladimir Weinstein +*/ + +#ifndef __UENUM_H +#define __UENUM_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" + +U_NAMESPACE_BEGIN +class StringEnumeration; +U_NAMESPACE_END +#endif // U_SHOW_CPLUSPLUS_API + +/** + * \file + * \brief C API: String Enumeration + */ + +/** + * An enumeration object. + * For usage in C programs. + * @stable ICU 2.2 + */ +struct UEnumeration; +/** structure representing an enumeration object instance @stable ICU 2.2 */ +typedef struct UEnumeration UEnumeration; + +/** + * Disposes of resources in use by the iterator. If en is NULL, + * does nothing. After this call, any char* or UChar* pointer + * returned by uenum_unext() or uenum_next() is invalid. + * @param en UEnumeration structure pointer + * @stable ICU 2.2 + */ +U_CAPI void U_EXPORT2 +uenum_close(UEnumeration* en); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUEnumerationPointer + * "Smart pointer" class, closes a UEnumeration via uenum_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUEnumerationPointer, UEnumeration, uenum_close); + +U_NAMESPACE_END + +#endif + +/** + * Returns the number of elements that the iterator traverses. If + * the iterator is out-of-sync with its service, status is set to + * U_ENUM_OUT_OF_SYNC_ERROR. + * This is a convenience function. It can end up being very + * expensive as all the items might have to be pre-fetched (depending + * on the type of data being traversed). Use with caution and only + * when necessary. + * @param en UEnumeration structure pointer + * @param status error code, can be U_ENUM_OUT_OF_SYNC_ERROR if the + * iterator is out of sync. + * @return number of elements in the iterator + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +uenum_count(UEnumeration* en, UErrorCode* status); + +/** + * Returns the next element in the iterator's list. If there are + * no more elements, returns NULL. If the iterator is out-of-sync + * with its service, status is set to U_ENUM_OUT_OF_SYNC_ERROR and + * NULL is returned. If the native service string is a char* string, + * it is converted to UChar* with the invariant converter. + * The result is terminated by (UChar)0. + * @param en the iterator object + * @param resultLength pointer to receive the length of the result + * (not including the terminating \\0). + * If the pointer is NULL it is ignored. + * @param status the error code, set to U_ENUM_OUT_OF_SYNC_ERROR if + * the iterator is out of sync with its service. + * @return a pointer to the string. The string will be + * zero-terminated. The return pointer is owned by this iterator + * and must not be deleted by the caller. The pointer is valid + * until the next call to any uenum_... method, including + * uenum_next() or uenum_unext(). When all strings have been + * traversed, returns NULL. + * @stable ICU 2.2 + */ +U_CAPI const UChar* U_EXPORT2 +uenum_unext(UEnumeration* en, + int32_t* resultLength, + UErrorCode* status); + +/** + * Returns the next element in the iterator's list. If there are + * no more elements, returns NULL. If the iterator is out-of-sync + * with its service, status is set to U_ENUM_OUT_OF_SYNC_ERROR and + * NULL is returned. If the native service string is a UChar* + * string, it is converted to char* with the invariant converter. + * The result is terminated by (char)0. If the conversion fails + * (because a character cannot be converted) then status is set to + * U_INVARIANT_CONVERSION_ERROR and the return value is undefined + * (but non-NULL). + * @param en the iterator object + * @param resultLength pointer to receive the length of the result + * (not including the terminating \\0). + * If the pointer is NULL it is ignored. + * @param status the error code, set to U_ENUM_OUT_OF_SYNC_ERROR if + * the iterator is out of sync with its service. Set to + * U_INVARIANT_CONVERSION_ERROR if the underlying native string is + * UChar* and conversion to char* with the invariant converter + * fails. This error pertains only to current string, so iteration + * might be able to continue successfully. + * @return a pointer to the string. The string will be + * zero-terminated. The return pointer is owned by this iterator + * and must not be deleted by the caller. The pointer is valid + * until the next call to any uenum_... method, including + * uenum_next() or uenum_unext(). When all strings have been + * traversed, returns NULL. + * @stable ICU 2.2 + */ +U_CAPI const char* U_EXPORT2 +uenum_next(UEnumeration* en, + int32_t* resultLength, + UErrorCode* status); + +/** + * Resets the iterator to the current list of service IDs. This + * re-establishes sync with the service and rewinds the iterator + * to start at the first element. + * @param en the iterator object + * @param status the error code, set to U_ENUM_OUT_OF_SYNC_ERROR if + * the iterator is out of sync with its service. + * @stable ICU 2.2 + */ +U_CAPI void U_EXPORT2 +uenum_reset(UEnumeration* en, UErrorCode* status); + +#if U_SHOW_CPLUSPLUS_API + +/** + * Given a StringEnumeration, wrap it in a UEnumeration. The + * StringEnumeration is adopted; after this call, the caller must not + * delete it (regardless of error status). + * @param adopted the C++ StringEnumeration to be wrapped in a UEnumeration. + * @param ec the error code. + * @return a UEnumeration wrapping the adopted StringEnumeration. + * @stable ICU 4.2 + */ +U_CAPI UEnumeration* U_EXPORT2 +uenum_openFromStringEnumeration(icu::StringEnumeration* adopted, UErrorCode* ec); + +#endif + +/** + * Given an array of const UChar* strings, return a UEnumeration. String pointers from 0..count-1 must not be null. + * Do not free or modify either the string array or the characters it points to until this object has been destroyed with uenum_close. + * \snippet test/cintltst/uenumtst.c uenum_openUCharStringsEnumeration + * @param strings array of const UChar* strings (each null terminated). All storage is owned by the caller. + * @param count length of the array + * @param ec error code + * @return the new UEnumeration object. Caller is responsible for calling uenum_close to free memory. + * @see uenum_close + * @stable ICU 50 + */ +U_CAPI UEnumeration* U_EXPORT2 +uenum_openUCharStringsEnumeration(const UChar* const strings[], int32_t count, + UErrorCode* ec); + +/** + * Given an array of const char* strings (invariant chars only), return a UEnumeration. String pointers from 0..count-1 must not be null. + * Do not free or modify either the string array or the characters it points to until this object has been destroyed with uenum_close. + * \snippet test/cintltst/uenumtst.c uenum_openCharStringsEnumeration + * @param strings array of char* strings (each null terminated). All storage is owned by the caller. + * @param count length of the array + * @param ec error code + * @return the new UEnumeration object. Caller is responsible for calling uenum_close to free memory + * @see uenum_close + * @stable ICU 50 + */ +U_CAPI UEnumeration* U_EXPORT2 +uenum_openCharStringsEnumeration(const char* const strings[], int32_t count, + UErrorCode* ec); + +#endif diff --git a/thirdparty/icu4c/common/unicode/uidna.h b/thirdparty/icu4c/common/unicode/uidna.h new file mode 100644 index 0000000000..24a81ceadd --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uidna.h @@ -0,0 +1,776 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* + ******************************************************************************* + * + * Copyright (C) 2003-2014, International Business Machines + * Corporation and others. All Rights Reserved. + * + ******************************************************************************* + * file name: uidna.h + * encoding: UTF-8 + * tab size: 8 (not used) + * indentation:4 + * + * created on: 2003feb1 + * created by: Ram Viswanadha + */ + +#ifndef __UIDNA_H__ +#define __UIDNA_H__ + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_IDNA + +#include <stdbool.h> +#include "unicode/parseerr.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * \file + * \brief C API: Internationalizing Domain Names in Applications (IDNA) + * + * IDNA2008 is implemented according to UTS #46, see the IDNA C++ class in idna.h. + * + * The C API functions which do take a UIDNA * service object pointer + * implement UTS #46 and IDNA2008. + * + * IDNA2003 is obsolete. + * The C API functions which do not take a service object pointer + * implement IDNA2003. They are all deprecated. + */ + +/* + * IDNA option bit set values. + */ +enum { + /** + * Default options value: None of the other options are set. + * For use in static worker and factory methods. + * @stable ICU 2.6 + */ + UIDNA_DEFAULT=0, +#ifndef U_HIDE_DEPRECATED_API + /** + * Option to allow unassigned code points in domain names and labels. + * For use in static worker and factory methods. + * <p>This option is ignored by the UTS46 implementation. + * (UTS #46 disallows unassigned code points.) + * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. + */ + UIDNA_ALLOW_UNASSIGNED=1, +#endif /* U_HIDE_DEPRECATED_API */ + /** + * Option to check whether the input conforms to the STD3 ASCII rules, + * for example the restriction of labels to LDH characters + * (ASCII Letters, Digits and Hyphen-Minus). + * For use in static worker and factory methods. + * @stable ICU 2.6 + */ + UIDNA_USE_STD3_RULES=2, + /** + * IDNA option to check for whether the input conforms to the BiDi rules. + * For use in static worker and factory methods. + * <p>This option is ignored by the IDNA2003 implementation. + * (IDNA2003 always performs a BiDi check.) + * @stable ICU 4.6 + */ + UIDNA_CHECK_BIDI=4, + /** + * IDNA option to check for whether the input conforms to the CONTEXTJ rules. + * For use in static worker and factory methods. + * <p>This option is ignored by the IDNA2003 implementation. + * (The CONTEXTJ check is new in IDNA2008.) + * @stable ICU 4.6 + */ + UIDNA_CHECK_CONTEXTJ=8, + /** + * IDNA option for nontransitional processing in ToASCII(). + * For use in static worker and factory methods. + * <p>By default, ToASCII() uses transitional processing. + * <p>This option is ignored by the IDNA2003 implementation. + * (This is only relevant for compatibility of newer IDNA implementations with IDNA2003.) + * @stable ICU 4.6 + */ + UIDNA_NONTRANSITIONAL_TO_ASCII=0x10, + /** + * IDNA option for nontransitional processing in ToUnicode(). + * For use in static worker and factory methods. + * <p>By default, ToUnicode() uses transitional processing. + * <p>This option is ignored by the IDNA2003 implementation. + * (This is only relevant for compatibility of newer IDNA implementations with IDNA2003.) + * @stable ICU 4.6 + */ + UIDNA_NONTRANSITIONAL_TO_UNICODE=0x20, + /** + * IDNA option to check for whether the input conforms to the CONTEXTO rules. + * For use in static worker and factory methods. + * <p>This option is ignored by the IDNA2003 implementation. + * (The CONTEXTO check is new in IDNA2008.) + * <p>This is for use by registries for IDNA2008 conformance. + * UTS #46 does not require the CONTEXTO check. + * @stable ICU 49 + */ + UIDNA_CHECK_CONTEXTO=0x40 +}; + +/** + * Opaque C service object type for the new IDNA API. + * @stable ICU 4.6 + */ +struct UIDNA; +typedef struct UIDNA UIDNA; /**< C typedef for struct UIDNA. @stable ICU 4.6 */ + +/** + * Returns a UIDNA instance which implements UTS #46. + * Returns an unmodifiable instance, owned by the caller. + * Cache it for multiple operations, and uidna_close() it when done. + * The instance is thread-safe, that is, it can be used concurrently. + * + * For details about the UTS #46 implementation see the IDNA C++ class in idna.h. + * + * @param options Bit set to modify the processing and error checking. + * See option bit set values in uidna.h. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the UTS #46 UIDNA instance, if successful + * @stable ICU 4.6 + */ +U_CAPI UIDNA * U_EXPORT2 +uidna_openUTS46(uint32_t options, UErrorCode *pErrorCode); + +/** + * Closes a UIDNA instance. + * @param idna UIDNA instance to be closed + * @stable ICU 4.6 + */ +U_CAPI void U_EXPORT2 +uidna_close(UIDNA *idna); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUIDNAPointer + * "Smart pointer" class, closes a UIDNA via uidna_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.6 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUIDNAPointer, UIDNA, uidna_close); + +U_NAMESPACE_END + +#endif + +/** + * Output container for IDNA processing errors. + * Initialize with UIDNA_INFO_INITIALIZER: + * \code + * UIDNAInfo info = UIDNA_INFO_INITIALIZER; + * int32_t length = uidna_nameToASCII(..., &info, &errorCode); + * if(U_SUCCESS(errorCode) && info.errors!=0) { ... } + * \endcode + * @stable ICU 4.6 + */ +typedef struct UIDNAInfo { + /** sizeof(UIDNAInfo) @stable ICU 4.6 */ + int16_t size; + /** + * Set to true if transitional and nontransitional processing produce different results. + * For details see C++ IDNAInfo::isTransitionalDifferent(). + * @stable ICU 4.6 + */ + UBool isTransitionalDifferent; + UBool reservedB3; /**< Reserved field, do not use. @internal */ + /** + * Bit set indicating IDNA processing errors. 0 if no errors. + * See UIDNA_ERROR_... constants. + * @stable ICU 4.6 + */ + uint32_t errors; + int32_t reservedI2; /**< Reserved field, do not use. @internal */ + int32_t reservedI3; /**< Reserved field, do not use. @internal */ +} UIDNAInfo; + +/** + * Static initializer for a UIDNAInfo struct. + * @stable ICU 4.6 + */ +#define UIDNA_INFO_INITIALIZER { \ + (int16_t)sizeof(UIDNAInfo), \ + false, false, \ + 0, 0, 0 } + +/** + * Converts a single domain name label into its ASCII form for DNS lookup. + * If any processing step fails, then pInfo->errors will be non-zero and + * the result might not be an ASCII string. + * The label might be modified according to the types of errors. + * Labels with severe errors will be left in (or turned into) their Unicode form. + * + * The UErrorCode indicates an error only in exceptional cases, + * such as a U_MEMORY_ALLOCATION_ERROR. + * + * @param idna UIDNA instance + * @param label Input domain name label + * @param length Label length, or -1 if NUL-terminated + * @param dest Destination string buffer + * @param capacity Destination buffer capacity + * @param pInfo Output container of IDNA processing details. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return destination string length + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +uidna_labelToASCII(const UIDNA *idna, + const UChar *label, int32_t length, + UChar *dest, int32_t capacity, + UIDNAInfo *pInfo, UErrorCode *pErrorCode); + +/** + * Converts a single domain name label into its Unicode form for human-readable display. + * If any processing step fails, then pInfo->errors will be non-zero. + * The label might be modified according to the types of errors. + * + * The UErrorCode indicates an error only in exceptional cases, + * such as a U_MEMORY_ALLOCATION_ERROR. + * + * @param idna UIDNA instance + * @param label Input domain name label + * @param length Label length, or -1 if NUL-terminated + * @param dest Destination string buffer + * @param capacity Destination buffer capacity + * @param pInfo Output container of IDNA processing details. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return destination string length + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +uidna_labelToUnicode(const UIDNA *idna, + const UChar *label, int32_t length, + UChar *dest, int32_t capacity, + UIDNAInfo *pInfo, UErrorCode *pErrorCode); + +/** + * Converts a whole domain name into its ASCII form for DNS lookup. + * If any processing step fails, then pInfo->errors will be non-zero and + * the result might not be an ASCII string. + * The domain name might be modified according to the types of errors. + * Labels with severe errors will be left in (or turned into) their Unicode form. + * + * The UErrorCode indicates an error only in exceptional cases, + * such as a U_MEMORY_ALLOCATION_ERROR. + * + * @param idna UIDNA instance + * @param name Input domain name + * @param length Domain name length, or -1 if NUL-terminated + * @param dest Destination string buffer + * @param capacity Destination buffer capacity + * @param pInfo Output container of IDNA processing details. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return destination string length + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +uidna_nameToASCII(const UIDNA *idna, + const UChar *name, int32_t length, + UChar *dest, int32_t capacity, + UIDNAInfo *pInfo, UErrorCode *pErrorCode); + +/** + * Converts a whole domain name into its Unicode form for human-readable display. + * If any processing step fails, then pInfo->errors will be non-zero. + * The domain name might be modified according to the types of errors. + * + * The UErrorCode indicates an error only in exceptional cases, + * such as a U_MEMORY_ALLOCATION_ERROR. + * + * @param idna UIDNA instance + * @param name Input domain name + * @param length Domain name length, or -1 if NUL-terminated + * @param dest Destination string buffer + * @param capacity Destination buffer capacity + * @param pInfo Output container of IDNA processing details. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return destination string length + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +uidna_nameToUnicode(const UIDNA *idna, + const UChar *name, int32_t length, + UChar *dest, int32_t capacity, + UIDNAInfo *pInfo, UErrorCode *pErrorCode); + +/* UTF-8 versions of the processing methods --------------------------------- */ + +/** + * Converts a single domain name label into its ASCII form for DNS lookup. + * UTF-8 version of uidna_labelToASCII(), same behavior. + * + * @param idna UIDNA instance + * @param label Input domain name label + * @param length Label length, or -1 if NUL-terminated + * @param dest Destination string buffer + * @param capacity Destination buffer capacity + * @param pInfo Output container of IDNA processing details. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return destination string length + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +uidna_labelToASCII_UTF8(const UIDNA *idna, + const char *label, int32_t length, + char *dest, int32_t capacity, + UIDNAInfo *pInfo, UErrorCode *pErrorCode); + +/** + * Converts a single domain name label into its Unicode form for human-readable display. + * UTF-8 version of uidna_labelToUnicode(), same behavior. + * + * @param idna UIDNA instance + * @param label Input domain name label + * @param length Label length, or -1 if NUL-terminated + * @param dest Destination string buffer + * @param capacity Destination buffer capacity + * @param pInfo Output container of IDNA processing details. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return destination string length + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +uidna_labelToUnicodeUTF8(const UIDNA *idna, + const char *label, int32_t length, + char *dest, int32_t capacity, + UIDNAInfo *pInfo, UErrorCode *pErrorCode); + +/** + * Converts a whole domain name into its ASCII form for DNS lookup. + * UTF-8 version of uidna_nameToASCII(), same behavior. + * + * @param idna UIDNA instance + * @param name Input domain name + * @param length Domain name length, or -1 if NUL-terminated + * @param dest Destination string buffer + * @param capacity Destination buffer capacity + * @param pInfo Output container of IDNA processing details. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return destination string length + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +uidna_nameToASCII_UTF8(const UIDNA *idna, + const char *name, int32_t length, + char *dest, int32_t capacity, + UIDNAInfo *pInfo, UErrorCode *pErrorCode); + +/** + * Converts a whole domain name into its Unicode form for human-readable display. + * UTF-8 version of uidna_nameToUnicode(), same behavior. + * + * @param idna UIDNA instance + * @param name Input domain name + * @param length Domain name length, or -1 if NUL-terminated + * @param dest Destination string buffer + * @param capacity Destination buffer capacity + * @param pInfo Output container of IDNA processing details. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return destination string length + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +uidna_nameToUnicodeUTF8(const UIDNA *idna, + const char *name, int32_t length, + char *dest, int32_t capacity, + UIDNAInfo *pInfo, UErrorCode *pErrorCode); + +/* + * IDNA error bit set values. + * When a domain name or label fails a processing step or does not meet the + * validity criteria, then one or more of these error bits are set. + */ +enum { + /** + * A non-final domain name label (or the whole domain name) is empty. + * @stable ICU 4.6 + */ + UIDNA_ERROR_EMPTY_LABEL=1, + /** + * A domain name label is longer than 63 bytes. + * (See STD13/RFC1034 3.1. Name space specifications and terminology.) + * This is only checked in ToASCII operations, and only if the output label is all-ASCII. + * @stable ICU 4.6 + */ + UIDNA_ERROR_LABEL_TOO_LONG=2, + /** + * A domain name is longer than 255 bytes in its storage form. + * (See STD13/RFC1034 3.1. Name space specifications and terminology.) + * This is only checked in ToASCII operations, and only if the output domain name is all-ASCII. + * @stable ICU 4.6 + */ + UIDNA_ERROR_DOMAIN_NAME_TOO_LONG=4, + /** + * A label starts with a hyphen-minus ('-'). + * @stable ICU 4.6 + */ + UIDNA_ERROR_LEADING_HYPHEN=8, + /** + * A label ends with a hyphen-minus ('-'). + * @stable ICU 4.6 + */ + UIDNA_ERROR_TRAILING_HYPHEN=0x10, + /** + * A label contains hyphen-minus ('-') in the third and fourth positions. + * @stable ICU 4.6 + */ + UIDNA_ERROR_HYPHEN_3_4=0x20, + /** + * A label starts with a combining mark. + * @stable ICU 4.6 + */ + UIDNA_ERROR_LEADING_COMBINING_MARK=0x40, + /** + * A label or domain name contains disallowed characters. + * @stable ICU 4.6 + */ + UIDNA_ERROR_DISALLOWED=0x80, + /** + * A label starts with "xn--" but does not contain valid Punycode. + * That is, an xn-- label failed Punycode decoding. + * @stable ICU 4.6 + */ + UIDNA_ERROR_PUNYCODE=0x100, + /** + * A label contains a dot=full stop. + * This can occur in an input string for a single-label function. + * @stable ICU 4.6 + */ + UIDNA_ERROR_LABEL_HAS_DOT=0x200, + /** + * An ACE label does not contain a valid label string. + * The label was successfully ACE (Punycode) decoded but the resulting + * string had severe validation errors. For example, + * it might contain characters that are not allowed in ACE labels, + * or it might not be normalized. + * @stable ICU 4.6 + */ + UIDNA_ERROR_INVALID_ACE_LABEL=0x400, + /** + * A label does not meet the IDNA BiDi requirements (for right-to-left characters). + * @stable ICU 4.6 + */ + UIDNA_ERROR_BIDI=0x800, + /** + * A label does not meet the IDNA CONTEXTJ requirements. + * @stable ICU 4.6 + */ + UIDNA_ERROR_CONTEXTJ=0x1000, + /** + * A label does not meet the IDNA CONTEXTO requirements for punctuation characters. + * Some punctuation characters "Would otherwise have been DISALLOWED" + * but are allowed in certain contexts. (RFC 5892) + * @stable ICU 49 + */ + UIDNA_ERROR_CONTEXTO_PUNCTUATION=0x2000, + /** + * A label does not meet the IDNA CONTEXTO requirements for digits. + * Arabic-Indic Digits (U+066x) must not be mixed with Extended Arabic-Indic Digits (U+06Fx). + * @stable ICU 49 + */ + UIDNA_ERROR_CONTEXTO_DIGITS=0x4000 +}; + +#ifndef U_HIDE_DEPRECATED_API + +/* IDNA2003 API ------------------------------------------------------------- */ + +/** + * IDNA2003: This function implements the ToASCII operation as defined in the IDNA RFC. + * This operation is done on <b>single labels</b> before sending it to something that expects + * ASCII names. A label is an individual part of a domain name. Labels are usually + * separated by dots; e.g. "www.example.com" is composed of 3 labels "www","example", and "com". + * + * IDNA2003 API Overview: + * + * The uidna_ API implements the IDNA protocol as defined in the IDNA RFC + * (http://www.ietf.org/rfc/rfc3490.txt). + * The RFC defines 2 operations: ToASCII and ToUnicode. Domain name labels + * containing non-ASCII code points are processed by the + * ToASCII operation before passing it to resolver libraries. Domain names + * that are obtained from resolver libraries are processed by the + * ToUnicode operation before displaying the domain name to the user. + * IDNA requires that implementations process input strings with Nameprep + * (http://www.ietf.org/rfc/rfc3491.txt), + * which is a profile of Stringprep (http://www.ietf.org/rfc/rfc3454.txt), + * and then with Punycode (http://www.ietf.org/rfc/rfc3492.txt). + * Implementations of IDNA MUST fully implement Nameprep and Punycode; + * neither Nameprep nor Punycode are optional. + * The input and output of ToASCII and ToUnicode operations are Unicode + * and are designed to be chainable, i.e., applying ToASCII or ToUnicode operations + * multiple times to an input string will yield the same result as applying the operation + * once. + * ToUnicode(ToUnicode(ToUnicode...(ToUnicode(string)))) == ToUnicode(string) + * ToASCII(ToASCII(ToASCII...(ToASCII(string))) == ToASCII(string). + * + * @param src Input UChar array containing label in Unicode. + * @param srcLength Number of UChars in src, or -1 if NUL-terminated. + * @param dest Output UChar array with ASCII (ACE encoded) label. + * @param destCapacity Size of dest. + * @param options A bit set of options: + * + * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points + * and do not use STD3 ASCII rules + * If unassigned code points are found the operation fails with + * U_UNASSIGNED_ERROR error code. + * + * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations + * If this option is set, the unassigned code points are in the input + * are treated as normal Unicode code points. + * + * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions + * If this option is set and the input does not satisfy STD3 rules, + * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR + * + * @param parseError Pointer to UParseError struct to receive information on position + * of error if an error is encountered. Can be NULL. + * @param status ICU in/out error code parameter. + * U_INVALID_CHAR_FOUND if src contains + * unmatched single surrogates. + * U_INDEX_OUTOFBOUNDS_ERROR if src contains + * too many code points. + * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. + */ +U_DEPRECATED int32_t U_EXPORT2 +uidna_toASCII(const UChar* src, int32_t srcLength, + UChar* dest, int32_t destCapacity, + int32_t options, + UParseError* parseError, + UErrorCode* status); + + +/** + * IDNA2003: This function implements the ToUnicode operation as defined in the IDNA RFC. + * This operation is done on <b>single labels</b> before sending it to something that expects + * Unicode names. A label is an individual part of a domain name. Labels are usually + * separated by dots; for e.g. "www.example.com" is composed of 3 labels "www","example", and "com". + * + * @param src Input UChar array containing ASCII (ACE encoded) label. + * @param srcLength Number of UChars in src, or -1 if NUL-terminated. + * @param dest Output Converted UChar array containing Unicode equivalent of label. + * @param destCapacity Size of dest. + * @param options A bit set of options: + * + * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points + * and do not use STD3 ASCII rules + * If unassigned code points are found the operation fails with + * U_UNASSIGNED_ERROR error code. + * + * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations + * If this option is set, the unassigned code points are in the input + * are treated as normal Unicode code points. <b> Note: </b> This option is + * required on toUnicode operation because the RFC mandates + * verification of decoded ACE input by applying toASCII and comparing + * its output with source + * + * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions + * If this option is set and the input does not satisfy STD3 rules, + * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR + * + * @param parseError Pointer to UParseError struct to receive information on position + * of error if an error is encountered. Can be NULL. + * @param status ICU in/out error code parameter. + * U_INVALID_CHAR_FOUND if src contains + * unmatched single surrogates. + * U_INDEX_OUTOFBOUNDS_ERROR if src contains + * too many code points. + * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. + */ +U_DEPRECATED int32_t U_EXPORT2 +uidna_toUnicode(const UChar* src, int32_t srcLength, + UChar* dest, int32_t destCapacity, + int32_t options, + UParseError* parseError, + UErrorCode* status); + + +/** + * IDNA2003: Convenience function that implements the IDNToASCII operation as defined in the IDNA RFC. + * This operation is done on complete domain names, e.g: "www.example.com". + * It is important to note that this operation can fail. If it fails, then the input + * domain name cannot be used as an Internationalized Domain Name and the application + * should have methods defined to deal with the failure. + * + * <b>Note:</b> IDNA RFC specifies that a conformant application should divide a domain name + * into separate labels, decide whether to apply allowUnassigned and useSTD3ASCIIRules on each, + * and then convert. This function does not offer that level of granularity. The options once + * set will apply to all labels in the domain name + * + * @param src Input UChar array containing IDN in Unicode. + * @param srcLength Number of UChars in src, or -1 if NUL-terminated. + * @param dest Output UChar array with ASCII (ACE encoded) IDN. + * @param destCapacity Size of dest. + * @param options A bit set of options: + * + * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points + * and do not use STD3 ASCII rules + * If unassigned code points are found the operation fails with + * U_UNASSIGNED_CODE_POINT_FOUND error code. + * + * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations + * If this option is set, the unassigned code points are in the input + * are treated as normal Unicode code points. + * + * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions + * If this option is set and the input does not satisfy STD3 rules, + * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR + * + * @param parseError Pointer to UParseError struct to receive information on position + * of error if an error is encountered. Can be NULL. + * @param status ICU in/out error code parameter. + * U_INVALID_CHAR_FOUND if src contains + * unmatched single surrogates. + * U_INDEX_OUTOFBOUNDS_ERROR if src contains + * too many code points. + * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. + */ +U_DEPRECATED int32_t U_EXPORT2 +uidna_IDNToASCII( const UChar* src, int32_t srcLength, + UChar* dest, int32_t destCapacity, + int32_t options, + UParseError* parseError, + UErrorCode* status); + +/** + * IDNA2003: Convenience function that implements the IDNToUnicode operation as defined in the IDNA RFC. + * This operation is done on complete domain names, e.g: "www.example.com". + * + * <b>Note:</b> IDNA RFC specifies that a conformant application should divide a domain name + * into separate labels, decide whether to apply allowUnassigned and useSTD3ASCIIRules on each, + * and then convert. This function does not offer that level of granularity. The options once + * set will apply to all labels in the domain name + * + * @param src Input UChar array containing IDN in ASCII (ACE encoded) form. + * @param srcLength Number of UChars in src, or -1 if NUL-terminated. + * @param dest Output UChar array containing Unicode equivalent of source IDN. + * @param destCapacity Size of dest. + * @param options A bit set of options: + * + * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points + * and do not use STD3 ASCII rules + * If unassigned code points are found the operation fails with + * U_UNASSIGNED_CODE_POINT_FOUND error code. + * + * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations + * If this option is set, the unassigned code points are in the input + * are treated as normal Unicode code points. + * + * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions + * If this option is set and the input does not satisfy STD3 rules, + * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR + * + * @param parseError Pointer to UParseError struct to receive information on position + * of error if an error is encountered. Can be NULL. + * @param status ICU in/out error code parameter. + * U_INVALID_CHAR_FOUND if src contains + * unmatched single surrogates. + * U_INDEX_OUTOFBOUNDS_ERROR if src contains + * too many code points. + * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough + * @return The length of the result string, if successful - or in case of a buffer overflow, + * in which case it will be greater than destCapacity. + * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. + */ +U_DEPRECATED int32_t U_EXPORT2 +uidna_IDNToUnicode( const UChar* src, int32_t srcLength, + UChar* dest, int32_t destCapacity, + int32_t options, + UParseError* parseError, + UErrorCode* status); + +/** + * IDNA2003: Compare two IDN strings for equivalence. + * This function splits the domain names into labels and compares them. + * According to IDN RFC, whenever two labels are compared, they are + * considered equal if and only if their ASCII forms (obtained by + * applying toASCII) match using an case-insensitive ASCII comparison. + * Two domain names are considered a match if and only if all labels + * match regardless of whether label separators match. + * + * @param s1 First source string. + * @param length1 Length of first source string, or -1 if NUL-terminated. + * + * @param s2 Second source string. + * @param length2 Length of second source string, or -1 if NUL-terminated. + * @param options A bit set of options: + * + * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points + * and do not use STD3 ASCII rules + * If unassigned code points are found the operation fails with + * U_UNASSIGNED_CODE_POINT_FOUND error code. + * + * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations + * If this option is set, the unassigned code points are in the input + * are treated as normal Unicode code points. + * + * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions + * If this option is set and the input does not satisfy STD3 rules, + * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR + * + * @param status ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return <0 or 0 or >0 as usual for string comparisons + * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. + */ +U_DEPRECATED int32_t U_EXPORT2 +uidna_compare( const UChar *s1, int32_t length1, + const UChar *s2, int32_t length2, + int32_t options, + UErrorCode* status); + +#endif /* U_HIDE_DEPRECATED_API */ + +#endif /* #if !UCONFIG_NO_IDNA */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/uiter.h b/thirdparty/icu4c/common/unicode/uiter.h new file mode 100644 index 0000000000..be232c774d --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uiter.h @@ -0,0 +1,709 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2002-2011 International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: uiter.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2002jan18 +* created by: Markus W. Scherer +*/ + +#ifndef __UITER_H__ +#define __UITER_H__ + +/** + * \file + * \brief C API: Unicode Character Iteration + * + * @see UCharIterator + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + U_NAMESPACE_BEGIN + + class CharacterIterator; + class Replaceable; + + U_NAMESPACE_END +#endif + +U_CDECL_BEGIN + +struct UCharIterator; +typedef struct UCharIterator UCharIterator; /**< C typedef for struct UCharIterator. @stable ICU 2.1 */ + +/** + * Origin constants for UCharIterator.getIndex() and UCharIterator.move(). + * @see UCharIteratorMove + * @see UCharIterator + * @stable ICU 2.1 + */ +typedef enum UCharIteratorOrigin { + UITER_START, UITER_CURRENT, UITER_LIMIT, UITER_ZERO, UITER_LENGTH +} UCharIteratorOrigin; + +/** Constants for UCharIterator. @stable ICU 2.6 */ +enum { + /** + * Constant value that may be returned by UCharIteratorMove + * indicating that the final UTF-16 index is not known, but that the move succeeded. + * This can occur when moving relative to limit or length, or + * when moving relative to the current index after a setState() + * when the current UTF-16 index is not known. + * + * It would be very inefficient to have to count from the beginning of the text + * just to get the current/limit/length index after moving relative to it. + * The actual index can be determined with getIndex(UITER_CURRENT) + * which will count the UChars if necessary. + * + * @stable ICU 2.6 + */ + UITER_UNKNOWN_INDEX=-2 +}; + + +/** + * Constant for UCharIterator getState() indicating an error or + * an unknown state. + * Returned by uiter_getState()/UCharIteratorGetState + * when an error occurs. + * Also, some UCharIterator implementations may not be able to return + * a valid state for each position. This will be clearly documented + * for each such iterator (none of the public ones here). + * + * @stable ICU 2.6 + */ +#define UITER_NO_STATE ((uint32_t)0xffffffff) + +/** + * Function type declaration for UCharIterator.getIndex(). + * + * Gets the current position, or the start or limit of the + * iteration range. + * + * This function may perform slowly for UITER_CURRENT after setState() was called, + * or for UITER_LENGTH, because an iterator implementation may have to count + * UChars if the underlying storage is not UTF-16. + * + * @param iter the UCharIterator structure ("this pointer") + * @param origin get the 0, start, limit, length, or current index + * @return the requested index, or U_SENTINEL in an error condition + * + * @see UCharIteratorOrigin + * @see UCharIterator + * @stable ICU 2.1 + */ +typedef int32_t U_CALLCONV +UCharIteratorGetIndex(UCharIterator *iter, UCharIteratorOrigin origin); + +/** + * Function type declaration for UCharIterator.move(). + * + * Use iter->move(iter, index, UITER_ZERO) like CharacterIterator::setIndex(index). + * + * Moves the current position relative to the start or limit of the + * iteration range, or relative to the current position itself. + * The movement is expressed in numbers of code units forward + * or backward by specifying a positive or negative delta. + * Out of bounds movement will be pinned to the start or limit. + * + * This function may perform slowly for moving relative to UITER_LENGTH + * because an iterator implementation may have to count the rest of the + * UChars if the native storage is not UTF-16. + * + * When moving relative to the limit or length, or + * relative to the current position after setState() was called, + * move() may return UITER_UNKNOWN_INDEX (-2) to avoid an inefficient + * determination of the actual UTF-16 index. + * The actual index can be determined with getIndex(UITER_CURRENT) + * which will count the UChars if necessary. + * See UITER_UNKNOWN_INDEX for details. + * + * @param iter the UCharIterator structure ("this pointer") + * @param delta can be positive, zero, or negative + * @param origin move relative to the 0, start, limit, length, or current index + * @return the new index, or U_SENTINEL on an error condition, + * or UITER_UNKNOWN_INDEX when the index is not known. + * + * @see UCharIteratorOrigin + * @see UCharIterator + * @see UITER_UNKNOWN_INDEX + * @stable ICU 2.1 + */ +typedef int32_t U_CALLCONV +UCharIteratorMove(UCharIterator *iter, int32_t delta, UCharIteratorOrigin origin); + +/** + * Function type declaration for UCharIterator.hasNext(). + * + * Check if current() and next() can still + * return another code unit. + * + * @param iter the UCharIterator structure ("this pointer") + * @return boolean value for whether current() and next() can still return another code unit + * + * @see UCharIterator + * @stable ICU 2.1 + */ +typedef UBool U_CALLCONV +UCharIteratorHasNext(UCharIterator *iter); + +/** + * Function type declaration for UCharIterator.hasPrevious(). + * + * Check if previous() can still return another code unit. + * + * @param iter the UCharIterator structure ("this pointer") + * @return boolean value for whether previous() can still return another code unit + * + * @see UCharIterator + * @stable ICU 2.1 + */ +typedef UBool U_CALLCONV +UCharIteratorHasPrevious(UCharIterator *iter); + +/** + * Function type declaration for UCharIterator.current(). + * + * Return the code unit at the current position, + * or U_SENTINEL if there is none (index is at the limit). + * + * @param iter the UCharIterator structure ("this pointer") + * @return the current code unit + * + * @see UCharIterator + * @stable ICU 2.1 + */ +typedef UChar32 U_CALLCONV +UCharIteratorCurrent(UCharIterator *iter); + +/** + * Function type declaration for UCharIterator.next(). + * + * Return the code unit at the current index and increment + * the index (post-increment, like s[i++]), + * or return U_SENTINEL if there is none (index is at the limit). + * + * @param iter the UCharIterator structure ("this pointer") + * @return the current code unit (and post-increment the current index) + * + * @see UCharIterator + * @stable ICU 2.1 + */ +typedef UChar32 U_CALLCONV +UCharIteratorNext(UCharIterator *iter); + +/** + * Function type declaration for UCharIterator.previous(). + * + * Decrement the index and return the code unit from there + * (pre-decrement, like s[--i]), + * or return U_SENTINEL if there is none (index is at the start). + * + * @param iter the UCharIterator structure ("this pointer") + * @return the previous code unit (after pre-decrementing the current index) + * + * @see UCharIterator + * @stable ICU 2.1 + */ +typedef UChar32 U_CALLCONV +UCharIteratorPrevious(UCharIterator *iter); + +/** + * Function type declaration for UCharIterator.reservedFn(). + * Reserved for future use. + * + * @param iter the UCharIterator structure ("this pointer") + * @param something some integer argument + * @return some integer + * + * @see UCharIterator + * @stable ICU 2.1 + */ +typedef int32_t U_CALLCONV +UCharIteratorReserved(UCharIterator *iter, int32_t something); + +/** + * Function type declaration for UCharIterator.getState(). + * + * Get the "state" of the iterator in the form of a single 32-bit word. + * It is recommended that the state value be calculated to be as small as + * is feasible. For strings with limited lengths, fewer than 32 bits may + * be sufficient. + * + * This is used together with setState()/UCharIteratorSetState + * to save and restore the iterator position more efficiently than with + * getIndex()/move(). + * + * The iterator state is defined as a uint32_t value because it is designed + * for use in ucol_nextSortKeyPart() which provides 32 bits to store the state + * of the character iterator. + * + * With some UCharIterator implementations (e.g., UTF-8), + * getting and setting the UTF-16 index with existing functions + * (getIndex(UITER_CURRENT) followed by move(pos, UITER_ZERO)) is possible but + * relatively slow because the iterator has to "walk" from a known index + * to the requested one. + * This takes more time the farther it needs to go. + * + * An opaque state value allows an iterator implementation to provide + * an internal index (UTF-8: the source byte array index) for + * fast, constant-time restoration. + * + * After calling setState(), a getIndex(UITER_CURRENT) may be slow because + * the UTF-16 index may not be restored as well, but the iterator can deliver + * the correct text contents and move relative to the current position + * without performance degradation. + * + * Some UCharIterator implementations may not be able to return + * a valid state for each position, in which case they return UITER_NO_STATE instead. + * This will be clearly documented for each such iterator (none of the public ones here). + * + * @param iter the UCharIterator structure ("this pointer") + * @return the state word + * + * @see UCharIterator + * @see UCharIteratorSetState + * @see UITER_NO_STATE + * @stable ICU 2.6 + */ +typedef uint32_t U_CALLCONV +UCharIteratorGetState(const UCharIterator *iter); + +/** + * Function type declaration for UCharIterator.setState(). + * + * Restore the "state" of the iterator using a state word from a getState() call. + * The iterator object need not be the same one as for which getState() was called, + * but it must be of the same type (set up using the same uiter_setXYZ function) + * and it must iterate over the same string + * (binary identical regardless of memory address). + * For more about the state word see UCharIteratorGetState. + * + * After calling setState(), a getIndex(UITER_CURRENT) may be slow because + * the UTF-16 index may not be restored as well, but the iterator can deliver + * the correct text contents and move relative to the current position + * without performance degradation. + * + * @param iter the UCharIterator structure ("this pointer") + * @param state the state word from a getState() call + * on a same-type, same-string iterator + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @see UCharIterator + * @see UCharIteratorGetState + * @stable ICU 2.6 + */ +typedef void U_CALLCONV +UCharIteratorSetState(UCharIterator *iter, uint32_t state, UErrorCode *pErrorCode); + + +/** + * C API for code unit iteration. + * This can be used as a C wrapper around + * CharacterIterator, Replaceable, or implemented using simple strings, etc. + * + * There are two roles for using UCharIterator: + * + * A "provider" sets the necessary function pointers and controls the "protected" + * fields of the UCharIterator structure. A "provider" passes a UCharIterator + * into C APIs that need a UCharIterator as an abstract, flexible string interface. + * + * Implementations of such C APIs are "callers" of UCharIterator functions; + * they only use the "public" function pointers and never access the "protected" + * fields directly. + * + * The current() and next() functions only check the current index against the + * limit, and previous() only checks the current index against the start, + * to see if the iterator already reached the end of the iteration range. + * + * The assumption - in all iterators - is that the index is moved via the API, + * which means it won't go out of bounds, or the index is modified by + * user code that knows enough about the iterator implementation to set valid + * index values. + * + * UCharIterator functions return code unit values 0..0xffff, + * or U_SENTINEL if the iteration bounds are reached. + * + * @stable ICU 2.1 + */ +struct UCharIterator { + /** + * (protected) Pointer to string or wrapped object or similar. + * Not used by caller. + * @stable ICU 2.1 + */ + const void *context; + + /** + * (protected) Length of string or similar. + * Not used by caller. + * @stable ICU 2.1 + */ + int32_t length; + + /** + * (protected) Start index or similar. + * Not used by caller. + * @stable ICU 2.1 + */ + int32_t start; + + /** + * (protected) Current index or similar. + * Not used by caller. + * @stable ICU 2.1 + */ + int32_t index; + + /** + * (protected) Limit index or similar. + * Not used by caller. + * @stable ICU 2.1 + */ + int32_t limit; + + /** + * (protected) Used by UTF-8 iterators and possibly others. + * @stable ICU 2.1 + */ + int32_t reservedField; + + /** + * (public) Returns the current position or the + * start or limit index of the iteration range. + * + * @see UCharIteratorGetIndex + * @stable ICU 2.1 + */ + UCharIteratorGetIndex *getIndex; + + /** + * (public) Moves the current position relative to the start or limit of the + * iteration range, or relative to the current position itself. + * The movement is expressed in numbers of code units forward + * or backward by specifying a positive or negative delta. + * + * @see UCharIteratorMove + * @stable ICU 2.1 + */ + UCharIteratorMove *move; + + /** + * (public) Check if current() and next() can still + * return another code unit. + * + * @see UCharIteratorHasNext + * @stable ICU 2.1 + */ + UCharIteratorHasNext *hasNext; + + /** + * (public) Check if previous() can still return another code unit. + * + * @see UCharIteratorHasPrevious + * @stable ICU 2.1 + */ + UCharIteratorHasPrevious *hasPrevious; + + /** + * (public) Return the code unit at the current position, + * or U_SENTINEL if there is none (index is at the limit). + * + * @see UCharIteratorCurrent + * @stable ICU 2.1 + */ + UCharIteratorCurrent *current; + + /** + * (public) Return the code unit at the current index and increment + * the index (post-increment, like s[i++]), + * or return U_SENTINEL if there is none (index is at the limit). + * + * @see UCharIteratorNext + * @stable ICU 2.1 + */ + UCharIteratorNext *next; + + /** + * (public) Decrement the index and return the code unit from there + * (pre-decrement, like s[--i]), + * or return U_SENTINEL if there is none (index is at the start). + * + * @see UCharIteratorPrevious + * @stable ICU 2.1 + */ + UCharIteratorPrevious *previous; + + /** + * (public) Reserved for future use. Currently NULL. + * + * @see UCharIteratorReserved + * @stable ICU 2.1 + */ + UCharIteratorReserved *reservedFn; + + /** + * (public) Return the state of the iterator, to be restored later with setState(). + * This function pointer is NULL if the iterator does not implement it. + * + * @see UCharIteratorGet + * @stable ICU 2.6 + */ + UCharIteratorGetState *getState; + + /** + * (public) Restore the iterator state from the state word from a call + * to getState(). + * This function pointer is NULL if the iterator does not implement it. + * + * @see UCharIteratorSet + * @stable ICU 2.6 + */ + UCharIteratorSetState *setState; +}; + +/** + * Helper function for UCharIterator to get the code point + * at the current index. + * + * Return the code point that includes the code unit at the current position, + * or U_SENTINEL if there is none (index is at the limit). + * If the current code unit is a lead or trail surrogate, + * then the following or preceding surrogate is used to form + * the code point value. + * + * @param iter the UCharIterator structure ("this pointer") + * @return the current code point + * + * @see UCharIterator + * @see U16_GET + * @see UnicodeString::char32At() + * @stable ICU 2.1 + */ +U_CAPI UChar32 U_EXPORT2 +uiter_current32(UCharIterator *iter); + +/** + * Helper function for UCharIterator to get the next code point. + * + * Return the code point at the current index and increment + * the index (post-increment, like s[i++]), + * or return U_SENTINEL if there is none (index is at the limit). + * + * @param iter the UCharIterator structure ("this pointer") + * @return the current code point (and post-increment the current index) + * + * @see UCharIterator + * @see U16_NEXT + * @stable ICU 2.1 + */ +U_CAPI UChar32 U_EXPORT2 +uiter_next32(UCharIterator *iter); + +/** + * Helper function for UCharIterator to get the previous code point. + * + * Decrement the index and return the code point from there + * (pre-decrement, like s[--i]), + * or return U_SENTINEL if there is none (index is at the start). + * + * @param iter the UCharIterator structure ("this pointer") + * @return the previous code point (after pre-decrementing the current index) + * + * @see UCharIterator + * @see U16_PREV + * @stable ICU 2.1 + */ +U_CAPI UChar32 U_EXPORT2 +uiter_previous32(UCharIterator *iter); + +/** + * Get the "state" of the iterator in the form of a single 32-bit word. + * This is a convenience function that calls iter->getState(iter) + * if iter->getState is not NULL; + * if it is NULL or any other error occurs, then UITER_NO_STATE is returned. + * + * Some UCharIterator implementations may not be able to return + * a valid state for each position, in which case they return UITER_NO_STATE instead. + * This will be clearly documented for each such iterator (none of the public ones here). + * + * @param iter the UCharIterator structure ("this pointer") + * @return the state word + * + * @see UCharIterator + * @see UCharIteratorGetState + * @see UITER_NO_STATE + * @stable ICU 2.6 + */ +U_CAPI uint32_t U_EXPORT2 +uiter_getState(const UCharIterator *iter); + +/** + * Restore the "state" of the iterator using a state word from a getState() call. + * This is a convenience function that calls iter->setState(iter, state, pErrorCode) + * if iter->setState is not NULL; if it is NULL, then U_UNSUPPORTED_ERROR is set. + * + * @param iter the UCharIterator structure ("this pointer") + * @param state the state word from a getState() call + * on a same-type, same-string iterator + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @see UCharIterator + * @see UCharIteratorSetState + * @stable ICU 2.6 + */ +U_CAPI void U_EXPORT2 +uiter_setState(UCharIterator *iter, uint32_t state, UErrorCode *pErrorCode); + +/** + * Set up a UCharIterator to iterate over a string. + * + * Sets the UCharIterator function pointers for iteration over the string s + * with iteration boundaries start=index=0 and length=limit=string length. + * The "provider" may set the start, index, and limit values at any time + * within the range 0..length. + * The length field will be ignored. + * + * The string pointer s is set into UCharIterator.context without copying + * or reallocating the string contents. + * + * getState() simply returns the current index. + * move() will always return the final index. + * + * @param iter UCharIterator structure to be set for iteration + * @param s String to iterate over + * @param length Length of s, or -1 if NUL-terminated + * + * @see UCharIterator + * @stable ICU 2.1 + */ +U_CAPI void U_EXPORT2 +uiter_setString(UCharIterator *iter, const UChar *s, int32_t length); + +/** + * Set up a UCharIterator to iterate over a UTF-16BE string + * (byte vector with a big-endian pair of bytes per UChar). + * + * Everything works just like with a normal UChar iterator (uiter_setString), + * except that UChars are assembled from byte pairs, + * and that the length argument here indicates an even number of bytes. + * + * getState() simply returns the current index. + * move() will always return the final index. + * + * @param iter UCharIterator structure to be set for iteration + * @param s UTF-16BE string to iterate over + * @param length Length of s as an even number of bytes, or -1 if NUL-terminated + * (NUL means pair of 0 bytes at even index from s) + * + * @see UCharIterator + * @see uiter_setString + * @stable ICU 2.6 + */ +U_CAPI void U_EXPORT2 +uiter_setUTF16BE(UCharIterator *iter, const char *s, int32_t length); + +/** + * Set up a UCharIterator to iterate over a UTF-8 string. + * + * Sets the UCharIterator function pointers for iteration over the UTF-8 string s + * with UTF-8 iteration boundaries 0 and length. + * The implementation counts the UTF-16 index on the fly and + * lazily evaluates the UTF-16 length of the text. + * + * The start field is used as the UTF-8 offset, the limit field as the UTF-8 length. + * When the reservedField is not 0, then it contains a supplementary code point + * and the UTF-16 index is between the two corresponding surrogates. + * At that point, the UTF-8 index is behind that code point. + * + * The UTF-8 string pointer s is set into UCharIterator.context without copying + * or reallocating the string contents. + * + * getState() returns a state value consisting of + * - the current UTF-8 source byte index (bits 31..1) + * - a flag (bit 0) that indicates whether the UChar position is in the middle + * of a surrogate pair + * (from a 4-byte UTF-8 sequence for the corresponding supplementary code point) + * + * getState() cannot also encode the UTF-16 index in the state value. + * move(relative to limit or length), or + * move(relative to current) after setState(), may return UITER_UNKNOWN_INDEX. + * + * @param iter UCharIterator structure to be set for iteration + * @param s UTF-8 string to iterate over + * @param length Length of s in bytes, or -1 if NUL-terminated + * + * @see UCharIterator + * @stable ICU 2.6 + */ +U_CAPI void U_EXPORT2 +uiter_setUTF8(UCharIterator *iter, const char *s, int32_t length); + +#if U_SHOW_CPLUSPLUS_API + +/** + * Set up a UCharIterator to wrap around a C++ CharacterIterator. + * + * Sets the UCharIterator function pointers for iteration using the + * CharacterIterator charIter. + * + * The CharacterIterator pointer charIter is set into UCharIterator.context + * without copying or cloning the CharacterIterator object. + * The other "protected" UCharIterator fields are set to 0 and will be ignored. + * The iteration index and boundaries are controlled by the CharacterIterator. + * + * getState() simply returns the current index. + * move() will always return the final index. + * + * @param iter UCharIterator structure to be set for iteration + * @param charIter CharacterIterator to wrap + * + * @see UCharIterator + * @stable ICU 2.1 + */ +U_CAPI void U_EXPORT2 +uiter_setCharacterIterator(UCharIterator *iter, icu::CharacterIterator *charIter); + +/** + * Set up a UCharIterator to iterate over a C++ Replaceable. + * + * Sets the UCharIterator function pointers for iteration over the + * Replaceable rep with iteration boundaries start=index=0 and + * length=limit=rep->length(). + * The "provider" may set the start, index, and limit values at any time + * within the range 0..length=rep->length(). + * The length field will be ignored. + * + * The Replaceable pointer rep is set into UCharIterator.context without copying + * or cloning/reallocating the Replaceable object. + * + * getState() simply returns the current index. + * move() will always return the final index. + * + * @param iter UCharIterator structure to be set for iteration + * @param rep Replaceable to iterate over + * + * @see UCharIterator + * @stable ICU 2.1 + */ +U_CAPI void U_EXPORT2 +uiter_setReplaceable(UCharIterator *iter, const icu::Replaceable *rep); + +#endif + +U_CDECL_END + +#endif diff --git a/thirdparty/icu4c/common/unicode/uldnames.h b/thirdparty/icu4c/common/unicode/uldnames.h new file mode 100644 index 0000000000..47b047ece9 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uldnames.h @@ -0,0 +1,307 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2010-2016, International Business Machines Corporation and +* others. All Rights Reserved. +******************************************************************************* +*/ + +#ifndef __ULDNAMES_H__ +#define __ULDNAMES_H__ + +/** + * \file + * \brief C API: Provides display names of Locale ids and their components. + */ + +#include "unicode/utypes.h" +#include "unicode/uscript.h" +#include "unicode/udisplaycontext.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * Enum used in LocaleDisplayNames::createInstance. + * @stable ICU 4.4 + */ +typedef enum { + /** + * Use standard names when generating a locale name, + * e.g. en_GB displays as 'English (United Kingdom)'. + * @stable ICU 4.4 + */ + ULDN_STANDARD_NAMES = 0, + /** + * Use dialect names, when generating a locale name, + * e.g. en_GB displays as 'British English'. + * @stable ICU 4.4 + */ + ULDN_DIALECT_NAMES +} UDialectHandling; + +/** + * Opaque C service object type for the locale display names API + * @stable ICU 4.4 + */ +struct ULocaleDisplayNames; + +/** + * C typedef for struct ULocaleDisplayNames. + * @stable ICU 4.4 + */ +typedef struct ULocaleDisplayNames ULocaleDisplayNames; + +#if !UCONFIG_NO_FORMATTING + +/** + * Returns an instance of LocaleDisplayNames that returns names + * formatted for the provided locale, using the provided + * dialectHandling. The usual value for dialectHandling is + * ULOC_STANDARD_NAMES. + * + * @param locale the display locale + * @param dialectHandling how to select names for locales + * @return a ULocaleDisplayNames instance + * @param pErrorCode the status code + * @stable ICU 4.4 + */ +U_CAPI ULocaleDisplayNames * U_EXPORT2 +uldn_open(const char * locale, + UDialectHandling dialectHandling, + UErrorCode *pErrorCode); + +/** + * Closes a ULocaleDisplayNames instance obtained from uldn_open(). + * @param ldn the ULocaleDisplayNames instance to be closed + * @stable ICU 4.4 + */ +U_CAPI void U_EXPORT2 +uldn_close(ULocaleDisplayNames *ldn); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalULocaleDisplayNamesPointer + * "Smart pointer" class, closes a ULocaleDisplayNames via uldn_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalULocaleDisplayNamesPointer, ULocaleDisplayNames, uldn_close); + +U_NAMESPACE_END + +#endif + +/* getters for state */ + +/** + * Returns the locale used to determine the display names. This is + * not necessarily the same locale passed to {@link #uldn_open}. + * @param ldn the LocaleDisplayNames instance + * @return the display locale + * @stable ICU 4.4 + */ +U_CAPI const char * U_EXPORT2 +uldn_getLocale(const ULocaleDisplayNames *ldn); + +/** + * Returns the dialect handling used in the display names. + * @param ldn the LocaleDisplayNames instance + * @return the dialect handling enum + * @stable ICU 4.4 + */ +U_CAPI UDialectHandling U_EXPORT2 +uldn_getDialectHandling(const ULocaleDisplayNames *ldn); + +/* names for entire locales */ + +/** + * Returns the display name of the provided locale. + * @param ldn the LocaleDisplayNames instance + * @param locale the locale whose display name to return + * @param result receives the display name + * @param maxResultSize the size of the result buffer + * @param pErrorCode the status code + * @return the actual buffer size needed for the display name. If it's + * greater than maxResultSize, the returned name will be truncated. + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +uldn_localeDisplayName(const ULocaleDisplayNames *ldn, + const char *locale, + UChar *result, + int32_t maxResultSize, + UErrorCode *pErrorCode); + +/* names for components of a locale */ + +/** + * Returns the display name of the provided language code. + * @param ldn the LocaleDisplayNames instance + * @param lang the language code whose display name to return + * @param result receives the display name + * @param maxResultSize the size of the result buffer + * @param pErrorCode the status code + * @return the actual buffer size needed for the display name. If it's + * greater than maxResultSize, the returned name will be truncated. + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +uldn_languageDisplayName(const ULocaleDisplayNames *ldn, + const char *lang, + UChar *result, + int32_t maxResultSize, + UErrorCode *pErrorCode); + +/** + * Returns the display name of the provided script. + * @param ldn the LocaleDisplayNames instance + * @param script the script whose display name to return + * @param result receives the display name + * @param maxResultSize the size of the result buffer + * @param pErrorCode the status code + * @return the actual buffer size needed for the display name. If it's + * greater than maxResultSize, the returned name will be truncated. + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +uldn_scriptDisplayName(const ULocaleDisplayNames *ldn, + const char *script, + UChar *result, + int32_t maxResultSize, + UErrorCode *pErrorCode); + +/** + * Returns the display name of the provided script code. + * @param ldn the LocaleDisplayNames instance + * @param scriptCode the script code whose display name to return + * @param result receives the display name + * @param maxResultSize the size of the result buffer + * @param pErrorCode the status code + * @return the actual buffer size needed for the display name. If it's + * greater than maxResultSize, the returned name will be truncated. + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +uldn_scriptCodeDisplayName(const ULocaleDisplayNames *ldn, + UScriptCode scriptCode, + UChar *result, + int32_t maxResultSize, + UErrorCode *pErrorCode); + +/** + * Returns the display name of the provided region code. + * @param ldn the LocaleDisplayNames instance + * @param region the region code whose display name to return + * @param result receives the display name + * @param maxResultSize the size of the result buffer + * @param pErrorCode the status code + * @return the actual buffer size needed for the display name. If it's + * greater than maxResultSize, the returned name will be truncated. + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +uldn_regionDisplayName(const ULocaleDisplayNames *ldn, + const char *region, + UChar *result, + int32_t maxResultSize, + UErrorCode *pErrorCode); + +/** + * Returns the display name of the provided variant + * @param ldn the LocaleDisplayNames instance + * @param variant the variant whose display name to return + * @param result receives the display name + * @param maxResultSize the size of the result buffer + * @param pErrorCode the status code + * @return the actual buffer size needed for the display name. If it's + * greater than maxResultSize, the returned name will be truncated. + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +uldn_variantDisplayName(const ULocaleDisplayNames *ldn, + const char *variant, + UChar *result, + int32_t maxResultSize, + UErrorCode *pErrorCode); + +/** + * Returns the display name of the provided locale key + * @param ldn the LocaleDisplayNames instance + * @param key the locale key whose display name to return + * @param result receives the display name + * @param maxResultSize the size of the result buffer + * @param pErrorCode the status code + * @return the actual buffer size needed for the display name. If it's + * greater than maxResultSize, the returned name will be truncated. + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +uldn_keyDisplayName(const ULocaleDisplayNames *ldn, + const char *key, + UChar *result, + int32_t maxResultSize, + UErrorCode *pErrorCode); + +/** + * Returns the display name of the provided value (used with the provided key). + * @param ldn the LocaleDisplayNames instance + * @param key the locale key + * @param value the locale key's value + * @param result receives the display name + * @param maxResultSize the size of the result buffer + * @param pErrorCode the status code + * @return the actual buffer size needed for the display name. If it's + * greater than maxResultSize, the returned name will be truncated. + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +uldn_keyValueDisplayName(const ULocaleDisplayNames *ldn, + const char *key, + const char *value, + UChar *result, + int32_t maxResultSize, + UErrorCode *pErrorCode); + +/** +* Returns an instance of LocaleDisplayNames that returns names formatted +* for the provided locale, using the provided UDisplayContext settings. +* +* @param locale The display locale +* @param contexts List of one or more context settings (e.g. for dialect +* handling, capitalization, etc. +* @param length Number of items in the contexts list +* @param pErrorCode Pointer to UErrorCode input/output status. If at entry this indicates +* a failure status, the function will do nothing; otherwise this will be +* updated with any new status from the function. +* @return a ULocaleDisplayNames instance +* @stable ICU 51 +*/ +U_CAPI ULocaleDisplayNames * U_EXPORT2 +uldn_openForContext(const char * locale, UDisplayContext *contexts, + int32_t length, UErrorCode *pErrorCode); + +/** +* Returns the UDisplayContext value for the specified UDisplayContextType. +* @param ldn the ULocaleDisplayNames instance +* @param type the UDisplayContextType whose value to return +* @param pErrorCode Pointer to UErrorCode input/output status. If at entry this indicates +* a failure status, the function will do nothing; otherwise this will be +* updated with any new status from the function. +* @return the UDisplayContextValue for the specified type. +* @stable ICU 51 +*/ +U_CAPI UDisplayContext U_EXPORT2 +uldn_getContext(const ULocaleDisplayNames *ldn, UDisplayContextType type, + UErrorCode *pErrorCode); + +#endif /* !UCONFIG_NO_FORMATTING */ +#endif /* __ULDNAMES_H__ */ diff --git a/thirdparty/icu4c/common/unicode/uloc.h b/thirdparty/icu4c/common/unicode/uloc.h new file mode 100644 index 0000000000..3addb847e7 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uloc.h @@ -0,0 +1,1393 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1997-2016, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* +* File ULOC.H +* +* Modification History: +* +* Date Name Description +* 04/01/97 aliu Creation. +* 08/22/98 stephen JDK 1.2 sync. +* 12/08/98 rtg New C API for Locale +* 03/30/99 damiba overhaul +* 03/31/99 helena Javadoc for uloc functions. +* 04/15/99 Madhu Updated Javadoc +******************************************************************************** +*/ + +#ifndef ULOC_H +#define ULOC_H + +#include "unicode/utypes.h" +#include "unicode/uenum.h" + +/** + * \file + * \brief C API: Locale + * + * <h2> ULoc C API for Locale </h2> + * A <code>Locale</code> represents a specific geographical, political, + * or cultural region. An operation that requires a <code>Locale</code> to perform + * its task is called <em>locale-sensitive</em> and uses the <code>Locale</code> + * to tailor information for the user. For example, displaying a number + * is a locale-sensitive operation--the number should be formatted + * according to the customs/conventions of the user's native country, + * region, or culture. In the C APIs, a locales is simply a const char string. + * + * <P> + * You create a <code>Locale</code> with one of the three options listed below. + * Each of the component is separated by '_' in the locale string. + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * \code + * newLanguage + * + * newLanguage + newCountry + * + * newLanguage + newCountry + newVariant + * \endcode + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * The first option is a valid <STRONG>ISO + * Language Code.</STRONG> These codes are the lower-case two-letter + * codes as defined by ISO-639. + * You can find a full list of these codes at a number of sites, such as: + * <BR><a href ="http://www.ics.uci.edu/pub/ietf/http/related/iso639.txt"> + * http://www.ics.uci.edu/pub/ietf/http/related/iso639.txt</a> + * + * <P> + * The second option includes an additional <STRONG>ISO Country + * Code.</STRONG> These codes are the upper-case two-letter codes + * as defined by ISO-3166. + * You can find a full list of these codes at a number of sites, such as: + * <BR><a href="http://www.chemie.fu-berlin.de/diverse/doc/ISO_3166.html"> + * http://www.chemie.fu-berlin.de/diverse/doc/ISO_3166.html</a> + * + * <P> + * The third option requires another additional information--the + * <STRONG>Variant.</STRONG> + * The Variant codes are vendor and browser-specific. + * For example, use WIN for Windows, MAC for Macintosh, and POSIX for POSIX. + * Where there are two variants, separate them with an underscore, and + * put the most important one first. For + * example, a Traditional Spanish collation might be referenced, with + * "ES", "ES", "Traditional_WIN". + * + * <P> + * Because a <code>Locale</code> is just an identifier for a region, + * no validity check is performed when you specify a <code>Locale</code>. + * If you want to see whether particular resources are available for the + * <code>Locale</code> you asked for, you must query those resources. For + * example, ask the <code>UNumberFormat</code> for the locales it supports + * using its <code>getAvailable</code> method. + * <BR><STRONG>Note:</STRONG> When you ask for a resource for a particular + * locale, you get back the best available match, not necessarily + * precisely what you asked for. For more information, look at + * <code>UResourceBundle</code>. + * + * <P> + * The <code>Locale</code> provides a number of convenient constants + * that you can use to specify the commonly used + * locales. For example, the following refers to a locale + * for the United States: + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * \code + * ULOC_US + * \endcode + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * + * <P> + * Once you've specified a locale you can query it for information about + * itself. Use <code>uloc_getCountry</code> to get the ISO Country Code and + * <code>uloc_getLanguage</code> to get the ISO Language Code. You can + * use <code>uloc_getDisplayCountry</code> to get the + * name of the country suitable for displaying to the user. Similarly, + * you can use <code>uloc_getDisplayLanguage</code> to get the name of + * the language suitable for displaying to the user. Interestingly, + * the <code>uloc_getDisplayXXX</code> methods are themselves locale-sensitive + * and have two versions: one that uses the default locale and one + * that takes a locale as an argument and displays the name or country in + * a language appropriate to that locale. + * + * <P> + * The ICU provides a number of services that perform locale-sensitive + * operations. For example, the <code>unum_xxx</code> functions format + * numbers, currency, or percentages in a locale-sensitive manner. + * </P> + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * \code + * UErrorCode success = U_ZERO_ERROR; + * UNumberFormat *nf; + * const char* myLocale = "fr_FR"; + * + * nf = unum_open( UNUM_DEFAULT, NULL, success ); + * unum_close(nf); + * nf = unum_open( UNUM_CURRENCY, NULL, success ); + * unum_close(nf); + * nf = unum_open( UNUM_PERCENT, NULL, success ); + * unum_close(nf); + * \endcode + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * Each of these methods has two variants; one with an explicit locale + * and one without; the latter using the default locale. + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * \code + * + * nf = unum_open( UNUM_DEFAULT, myLocale, success ); + * unum_close(nf); + * nf = unum_open( UNUM_CURRENCY, myLocale, success ); + * unum_close(nf); + * nf = unum_open( UNUM_PERCENT, myLocale, success ); + * unum_close(nf); + * \endcode + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * A <code>Locale</code> is the mechanism for identifying the kind of services + * (<code>UNumberFormat</code>) that you would like to get. The locale is + * <STRONG>just</STRONG> a mechanism for identifying these services. + * + * <P> + * Each international service that performs locale-sensitive operations + * allows you + * to get all the available objects of that type. You can sift + * through these objects by language, country, or variant, + * and use the display names to present a menu to the user. + * For example, you can create a menu of all the collation objects + * suitable for a given language. Such classes implement these + * three class methods: + * \htmlonly<blockquote>\endhtmlonly + * <pre> + * \code + * const char* uloc_getAvailable(int32_t index); + * int32_t uloc_countAvailable(); + * int32_t + * uloc_getDisplayName(const char* localeID, + * const char* inLocaleID, + * UChar* result, + * int32_t maxResultSize, + * UErrorCode* err); + * + * \endcode + * </pre> + * \htmlonly</blockquote>\endhtmlonly + * <P> + * Concerning POSIX/RFC1766 Locale IDs, + * the getLanguage/getCountry/getVariant/getName functions do understand + * the POSIX type form of language_COUNTRY.ENCODING\@VARIANT + * and if there is not an ICU-stype variant, uloc_getVariant() for example + * will return the one listed after the \@at sign. As well, the hyphen + * "-" is recognized as a country/variant separator similarly to RFC1766. + * So for example, "en-us" will be interpreted as en_US. + * As a result, uloc_getName() is far from a no-op, and will have the + * effect of converting POSIX/RFC1766 IDs into ICU form, although it does + * NOT map any of the actual codes (i.e. russian->ru) in any way. + * Applications should call uloc_getName() at the point where a locale ID + * is coming from an external source (user entry, OS, web browser) + * and pass the resulting string to other ICU functions. For example, + * don't use de-de\@EURO as an argument to resourcebundle. + * + * @see UResourceBundle + */ + +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_CHINESE "zh" +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_ENGLISH "en" +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_FRENCH "fr" +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_GERMAN "de" +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_ITALIAN "it" +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_JAPANESE "ja" +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_KOREAN "ko" +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_SIMPLIFIED_CHINESE "zh_CN" +/** Useful constant for this language. @stable ICU 2.0 */ +#define ULOC_TRADITIONAL_CHINESE "zh_TW" + +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_CANADA "en_CA" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_CANADA_FRENCH "fr_CA" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_CHINA "zh_CN" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_PRC "zh_CN" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_FRANCE "fr_FR" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_GERMANY "de_DE" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_ITALY "it_IT" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_JAPAN "ja_JP" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_KOREA "ko_KR" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_TAIWAN "zh_TW" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_UK "en_GB" +/** Useful constant for this country/region. @stable ICU 2.0 */ +#define ULOC_US "en_US" + +/** + * Useful constant for the maximum size of the language part of a locale ID. + * (including the terminating NULL). + * @stable ICU 2.0 + */ +#define ULOC_LANG_CAPACITY 12 + +/** + * Useful constant for the maximum size of the country part of a locale ID + * (including the terminating NULL). + * @stable ICU 2.0 + */ +#define ULOC_COUNTRY_CAPACITY 4 +/** + * Useful constant for the maximum size of the whole locale ID + * (including the terminating NULL and all keywords). + * @stable ICU 2.0 + */ +#define ULOC_FULLNAME_CAPACITY 157 + +/** + * Useful constant for the maximum size of the script part of a locale ID + * (including the terminating NULL). + * @stable ICU 2.8 + */ +#define ULOC_SCRIPT_CAPACITY 6 + +/** + * Useful constant for the maximum size of keywords in a locale + * @stable ICU 2.8 + */ +#define ULOC_KEYWORDS_CAPACITY 96 + +/** + * Useful constant for the maximum total size of keywords and their values in a locale + * @stable ICU 2.8 + */ +#define ULOC_KEYWORD_AND_VALUES_CAPACITY 100 + +/** + * Invariant character separating keywords from the locale string + * @stable ICU 2.8 + */ +#define ULOC_KEYWORD_SEPARATOR '@' + +/** + * Unicode code point for '@' separating keywords from the locale string. + * @see ULOC_KEYWORD_SEPARATOR + * @stable ICU 4.6 + */ +#define ULOC_KEYWORD_SEPARATOR_UNICODE 0x40 + +/** + * Invariant character for assigning value to a keyword + * @stable ICU 2.8 + */ +#define ULOC_KEYWORD_ASSIGN '=' + +/** + * Unicode code point for '=' for assigning value to a keyword. + * @see ULOC_KEYWORD_ASSIGN + * @stable ICU 4.6 + */ +#define ULOC_KEYWORD_ASSIGN_UNICODE 0x3D + +/** + * Invariant character separating keywords + * @stable ICU 2.8 + */ +#define ULOC_KEYWORD_ITEM_SEPARATOR ';' + +/** + * Unicode code point for ';' separating keywords + * @see ULOC_KEYWORD_ITEM_SEPARATOR + * @stable ICU 4.6 + */ +#define ULOC_KEYWORD_ITEM_SEPARATOR_UNICODE 0x3B + +/** + * Constants for *_getLocale() + * Allow user to select whether she wants information on + * requested, valid or actual locale. + * For example, a collator for "en_US_CALIFORNIA" was + * requested. In the current state of ICU (2.0), + * the requested locale is "en_US_CALIFORNIA", + * the valid locale is "en_US" (most specific locale supported by ICU) + * and the actual locale is "root" (the collation data comes unmodified + * from the UCA) + * The locale is considered supported by ICU if there is a core ICU bundle + * for that locale (although it may be empty). + * @stable ICU 2.1 + */ +typedef enum { + /** This is locale the data actually comes from + * @stable ICU 2.1 + */ + ULOC_ACTUAL_LOCALE = 0, + /** This is the most specific locale supported by ICU + * @stable ICU 2.1 + */ + ULOC_VALID_LOCALE = 1, + +#ifndef U_HIDE_DEPRECATED_API + /** This is the requested locale + * @deprecated ICU 2.8 + */ + ULOC_REQUESTED_LOCALE = 2, + + /** + * One more than the highest normal ULocDataLocaleType value. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + ULOC_DATA_LOCALE_TYPE_LIMIT = 3 +#endif // U_HIDE_DEPRECATED_API +} ULocDataLocaleType; + +#ifndef U_HIDE_SYSTEM_API +/** + * Gets ICU's default locale. + * The returned string is a snapshot in time, and will remain valid + * and unchanged even when uloc_setDefault() is called. + * The returned storage is owned by ICU, and must not be altered or deleted + * by the caller. + * + * @return the ICU default locale + * @system + * @stable ICU 2.0 + */ +U_CAPI const char* U_EXPORT2 +uloc_getDefault(void); + +/** + * Sets ICU's default locale. + * By default (without calling this function), ICU's default locale will be based + * on information obtained from the underlying system environment. + * <p> + * Changes to ICU's default locale do not propagate back to the + * system environment. + * <p> + * Changes to ICU's default locale to not affect any ICU services that + * may already be open based on the previous default locale value. + * + * @param localeID the new ICU default locale. A value of NULL will try to get + * the system's default locale. + * @param status the error information if the setting of default locale fails + * @system + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +uloc_setDefault(const char* localeID, + UErrorCode* status); +#endif /* U_HIDE_SYSTEM_API */ + +/** + * Gets the language code for the specified locale. + * + * @param localeID the locale to get the ISO language code with + * @param language the language code for localeID + * @param languageCapacity the size of the language buffer to store the + * language code with + * @param err error information if retrieving the language code failed + * @return the actual buffer size needed for the language code. If it's greater + * than languageCapacity, the returned language code will be truncated. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getLanguage(const char* localeID, + char* language, + int32_t languageCapacity, + UErrorCode* err); + +/** + * Gets the script code for the specified locale. + * + * @param localeID the locale to get the ISO language code with + * @param script the language code for localeID + * @param scriptCapacity the size of the language buffer to store the + * language code with + * @param err error information if retrieving the language code failed + * @return the actual buffer size needed for the language code. If it's greater + * than scriptCapacity, the returned language code will be truncated. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getScript(const char* localeID, + char* script, + int32_t scriptCapacity, + UErrorCode* err); + +/** + * Gets the country code for the specified locale. + * + * @param localeID the locale to get the country code with + * @param country the country code for localeID + * @param countryCapacity the size of the country buffer to store the + * country code with + * @param err error information if retrieving the country code failed + * @return the actual buffer size needed for the country code. If it's greater + * than countryCapacity, the returned country code will be truncated. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getCountry(const char* localeID, + char* country, + int32_t countryCapacity, + UErrorCode* err); + +/** + * Gets the variant code for the specified locale. + * + * @param localeID the locale to get the variant code with + * @param variant the variant code for localeID + * @param variantCapacity the size of the variant buffer to store the + * variant code with + * @param err error information if retrieving the variant code failed + * @return the actual buffer size needed for the variant code. If it's greater + * than variantCapacity, the returned variant code will be truncated. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getVariant(const char* localeID, + char* variant, + int32_t variantCapacity, + UErrorCode* err); + + +/** + * Gets the full name for the specified locale. + * Note: This has the effect of 'canonicalizing' the ICU locale ID to + * a certain extent. Upper and lower case are set as needed. + * It does NOT map aliased names in any way. + * See the top of this header file. + * This API supports preflighting. + * + * @param localeID the locale to get the full name with + * @param name fill in buffer for the name without keywords. + * @param nameCapacity capacity of the fill in buffer. + * @param err error information if retrieving the full name failed + * @return the actual buffer size needed for the full name. If it's greater + * than nameCapacity, the returned full name will be truncated. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getName(const char* localeID, + char* name, + int32_t nameCapacity, + UErrorCode* err); + +/** + * Gets the full name for the specified locale. + * Note: This has the effect of 'canonicalizing' the string to + * a certain extent. Upper and lower case are set as needed, + * and if the components were in 'POSIX' format they are changed to + * ICU format. It does NOT map aliased names in any way. + * See the top of this header file. + * + * @param localeID the locale to get the full name with + * @param name the full name for localeID + * @param nameCapacity the size of the name buffer to store the + * full name with + * @param err error information if retrieving the full name failed + * @return the actual buffer size needed for the full name. If it's greater + * than nameCapacity, the returned full name will be truncated. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +uloc_canonicalize(const char* localeID, + char* name, + int32_t nameCapacity, + UErrorCode* err); + +/** + * Gets the ISO language code for the specified locale. + * + * @param localeID the locale to get the ISO language code with + * @return language the ISO language code for localeID + * @stable ICU 2.0 + */ +U_CAPI const char* U_EXPORT2 +uloc_getISO3Language(const char* localeID); + + +/** + * Gets the ISO country code for the specified locale. + * + * @param localeID the locale to get the ISO country code with + * @return country the ISO country code for localeID + * @stable ICU 2.0 + */ +U_CAPI const char* U_EXPORT2 +uloc_getISO3Country(const char* localeID); + +/** + * Gets the Win32 LCID value for the specified locale. + * If the ICU locale is not recognized by Windows, 0 will be returned. + * + * LCIDs were deprecated with Windows Vista and Microsoft recommends + * that developers use BCP47 style tags instead (uloc_toLanguageTag). + * + * @param localeID the locale to get the Win32 LCID value with + * @return country the Win32 LCID for localeID + * @stable ICU 2.0 + */ +U_CAPI uint32_t U_EXPORT2 +uloc_getLCID(const char* localeID); + +/** + * Gets the language name suitable for display for the specified locale. + * + * @param locale the locale to get the ISO language code with + * @param displayLocale Specifies the locale to be used to display the name. In + * other words, if the locale's language code is "en", passing + * Locale::getFrench() for inLocale would result in "Anglais", + * while passing Locale::getGerman() for inLocale would result + * in "Englisch". + * @param language the displayable language code for localeID + * @param languageCapacity the size of the language buffer to store the + * displayable language code with. + * @param status error information if retrieving the displayable language code + * failed. U_USING_DEFAULT_WARNING indicates that no data was + * found from the locale resources and a case canonicalized + * language code is placed into language as fallback. + * @return the actual buffer size needed for the displayable language code. If + * it's greater than languageCapacity, the returned language + * code will be truncated. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getDisplayLanguage(const char* locale, + const char* displayLocale, + UChar* language, + int32_t languageCapacity, + UErrorCode* status); + +/** + * Gets the script name suitable for display for the specified locale. + * + * @param locale the locale to get the displayable script code with. NULL may be + * used to specify the default. + * @param displayLocale Specifies the locale to be used to display the name. In + * other words, if the locale's language code is "en", passing + * Locale::getFrench() for inLocale would result in "", while + * passing Locale::getGerman() for inLocale would result in "". + * NULL may be used to specify the default. + * @param script the displayable script for the localeID. + * @param scriptCapacity the size of the script buffer to store the displayable + * script code with. + * @param status error information if retrieving the displayable script code + * failed. U_USING_DEFAULT_WARNING indicates that no data was + * found from the locale resources and a case canonicalized + * script code is placed into script as fallback. + * @return the actual buffer size needed for the displayable script code. If + * it's greater than scriptCapacity, the returned displayable + * script code will be truncated. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getDisplayScript(const char* locale, + const char* displayLocale, + UChar* script, + int32_t scriptCapacity, + UErrorCode* status); + +/** + * Gets the country name suitable for display for the specified locale. + * Warning: this is for the region part of a valid locale ID; it cannot just be + * the region code (like "FR"). To get the display name for a region alone, or + * for other options, use ULocaleDisplayNames instead. + * + * @param locale the locale to get the displayable country code with. NULL may + * be used to specify the default. + * @param displayLocale Specifies the locale to be used to display the name. In + * other words, if the locale's language code is "en", passing + * Locale::getFrench() for inLocale would result in "Anglais", + * while passing Locale::getGerman() for inLocale would result + * in "Englisch". NULL may be used to specify the default. + * @param country the displayable country code for localeID. + * @param countryCapacity the size of the country buffer to store the + * displayable country code with. + * @param status error information if retrieving the displayable country code + * failed. U_USING_DEFAULT_WARNING indicates that no data was + * found from the locale resources and a case canonicalized + * country code is placed into country as fallback. + * @return the actual buffer size needed for the displayable country code. If + * it's greater than countryCapacity, the returned displayable + * country code will be truncated. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getDisplayCountry(const char* locale, + const char* displayLocale, + UChar* country, + int32_t countryCapacity, + UErrorCode* status); + + +/** + * Gets the variant name suitable for display for the specified locale. + * + * @param locale the locale to get the displayable variant code with. NULL may + * be used to specify the default. + * @param displayLocale Specifies the locale to be used to display the name. In + * other words, if the locale's language code is "en", passing + * Locale::getFrench() for inLocale would result in "Anglais", + * while passing Locale::getGerman() for inLocale would result + * in "Englisch". NULL may be used to specify the default. + * @param variant the displayable variant code for localeID. + * @param variantCapacity the size of the variant buffer to store the + * displayable variant code with. + * @param status error information if retrieving the displayable variant code + * failed. U_USING_DEFAULT_WARNING indicates that no data was + * found from the locale resources and a case canonicalized + * variant code is placed into variant as fallback. + * @return the actual buffer size needed for the displayable variant code. If + * it's greater than variantCapacity, the returned displayable + * variant code will be truncated. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getDisplayVariant(const char* locale, + const char* displayLocale, + UChar* variant, + int32_t variantCapacity, + UErrorCode* status); + +/** + * Gets the keyword name suitable for display for the specified locale. E.g: + * for the locale string de_DE\@collation=PHONEBOOK, this API gets the display + * string for the keyword collation. + * Usage: + * <code> + * UErrorCode status = U_ZERO_ERROR; + * const char* keyword =NULL; + * int32_t keywordLen = 0; + * int32_t keywordCount = 0; + * UChar displayKeyword[256]; + * int32_t displayKeywordLen = 0; + * UEnumeration* keywordEnum = uloc_openKeywords("de_DE@collation=PHONEBOOK;calendar=TRADITIONAL", &status); + * for(keywordCount = uenum_count(keywordEnum, &status); keywordCount > 0 ; keywordCount--){ + * if(U_FAILURE(status)){ + * ...something went wrong so handle the error... + * break; + * } + * // the uenum_next returns NUL terminated string + * keyword = uenum_next(keywordEnum, &keywordLen, &status); + * displayKeywordLen = uloc_getDisplayKeyword(keyword, "en_US", displayKeyword, 256); + * ... do something interesting ..... + * } + * uenum_close(keywordEnum); + * </code> + * @param keyword The keyword whose display string needs to be returned. + * @param displayLocale Specifies the locale to be used to display the name. In other words, + * if the locale's language code is "en", passing Locale::getFrench() for + * inLocale would result in "Anglais", while passing Locale::getGerman() + * for inLocale would result in "Englisch". NULL may be used to specify the default. + * @param dest the buffer to which the displayable keyword should be written. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param status error information if retrieving the displayable string failed. + * Should not be NULL and should not indicate failure on entry. + * U_USING_DEFAULT_WARNING indicates that no data was found from the locale + * resources and the keyword is placed into dest as fallback. + * @return the actual buffer size needed for the displayable variant code. + * @see #uloc_openKeywords + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getDisplayKeyword(const char* keyword, + const char* displayLocale, + UChar* dest, + int32_t destCapacity, + UErrorCode* status); +/** + * Gets the value of the keyword suitable for display for the specified locale. + * E.g: for the locale string de_DE\@collation=PHONEBOOK, this API gets the display + * string for PHONEBOOK, in the display locale, when "collation" is specified as the keyword. + * + * @param locale The locale to get the displayable variant code with. NULL may be used to specify the default. + * @param keyword The keyword for whose value should be used. + * @param displayLocale Specifies the locale to be used to display the name. In other words, + * if the locale's language code is "en", passing Locale::getFrench() for + * inLocale would result in "Anglais", while passing Locale::getGerman() + * for inLocale would result in "Englisch". NULL may be used to specify the default. + * @param dest the buffer to which the displayable keyword should be written. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param status error information if retrieving the displayable string failed. + * Should not be NULL and must not indicate failure on entry. + * U_USING_DEFAULT_WARNING indicates that no data was found from the locale + * resources and the value of the keyword is placed into dest as fallback. + * @return the actual buffer size needed for the displayable variant code. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getDisplayKeywordValue( const char* locale, + const char* keyword, + const char* displayLocale, + UChar* dest, + int32_t destCapacity, + UErrorCode* status); +/** + * Gets the full name suitable for display for the specified locale. + * + * @param localeID the locale to get the displayable name with. NULL may be used to specify the default. + * @param inLocaleID Specifies the locale to be used to display the name. In other words, + * if the locale's language code is "en", passing Locale::getFrench() for + * inLocale would result in "Anglais", while passing Locale::getGerman() + * for inLocale would result in "Englisch". NULL may be used to specify the default. + * @param result the displayable name for localeID + * @param maxResultSize the size of the name buffer to store the + * displayable full name with + * @param err error information if retrieving the displayable name failed + * @return the actual buffer size needed for the displayable name. If it's greater + * than maxResultSize, the returned displayable name will be truncated. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getDisplayName(const char* localeID, + const char* inLocaleID, + UChar* result, + int32_t maxResultSize, + UErrorCode* err); + + +/** + * Gets the specified locale from a list of available locales. + * + * This method corresponds to uloc_openAvailableByType called with the + * ULOC_AVAILABLE_DEFAULT type argument. + * + * The return value is a pointer to an item of a locale name array. Both this + * array and the pointers it contains are owned by ICU and should not be + * deleted or written through by the caller. The locale name is terminated by + * a null pointer. + * + * @param n the specific locale name index of the available locale list; + * should not exceed the number returned by uloc_countAvailable. + * @return a specified locale name of all available locales + * @stable ICU 2.0 + */ +U_CAPI const char* U_EXPORT2 +uloc_getAvailable(int32_t n); + +/** + * Gets the size of the all available locale list. + * + * @return the size of the locale list + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 uloc_countAvailable(void); + +/** + * Types for uloc_getAvailableByType and uloc_countAvailableByType. + * + * @stable ICU 65 + */ +typedef enum ULocAvailableType { + /** + * Locales that return data when passed to ICU APIs, + * but not including legacy or alias locales. + * + * @stable ICU 65 + */ + ULOC_AVAILABLE_DEFAULT, + + /** + * Legacy or alias locales that return data when passed to ICU APIs. + * Examples of supported legacy or alias locales: + * + * - iw (alias to he) + * - mo (alias to ro) + * - zh_CN (alias to zh_Hans_CN) + * - sr_BA (alias to sr_Cyrl_BA) + * - ars (alias to ar_SA) + * + * The locales in this set are disjoint from the ones in + * ULOC_AVAILABLE_DEFAULT. To get both sets at the same time, use + * ULOC_AVAILABLE_WITH_LEGACY_ALIASES. + * + * @stable ICU 65 + */ + ULOC_AVAILABLE_ONLY_LEGACY_ALIASES, + + /** + * The union of the locales in ULOC_AVAILABLE_DEFAULT and + * ULOC_AVAILABLE_ONLY_LEGACY_ALIAS. + * + * @stable ICU 65 + */ + ULOC_AVAILABLE_WITH_LEGACY_ALIASES, + +#ifndef U_HIDE_INTERNAL_API + /** + * @internal + */ + ULOC_AVAILABLE_COUNT +#endif +} ULocAvailableType; + +/** + * Gets a list of available locales according to the type argument, allowing + * the user to access different sets of supported locales in ICU. + * + * The returned UEnumeration must be closed by the caller. + * + * @param type Type choice from ULocAvailableType. + * @param status Set if an error occurred. + * @return a UEnumeration owned by the caller, or nullptr on failure. + * @stable ICU 65 + */ +U_CAPI UEnumeration* U_EXPORT2 +uloc_openAvailableByType(ULocAvailableType type, UErrorCode* status); + +/** + * + * Gets a list of all available 2-letter language codes defined in ISO 639, + * plus additional 3-letter codes determined to be useful for locale generation as + * defined by Unicode CLDR. This is a pointer + * to an array of pointers to arrays of char. All of these pointers are owned + * by ICU-- do not delete them, and do not write through them. The array is + * terminated with a null pointer. + * @return a list of all available language codes + * @stable ICU 2.0 + */ +U_CAPI const char* const* U_EXPORT2 +uloc_getISOLanguages(void); + +/** + * + * Gets a list of all available 2-letter country codes defined in ISO 639. This is a + * pointer to an array of pointers to arrays of char. All of these pointers are + * owned by ICU-- do not delete them, and do not write through them. The array is + * terminated with a null pointer. + * @return a list of all available country codes + * @stable ICU 2.0 + */ +U_CAPI const char* const* U_EXPORT2 +uloc_getISOCountries(void); + +/** + * Truncate the locale ID string to get the parent locale ID. + * Copies the part of the string before the last underscore. + * The parent locale ID will be an empty string if there is no + * underscore, or if there is only one underscore at localeID[0]. + * + * @param localeID Input locale ID string. + * @param parent Output string buffer for the parent locale ID. + * @param parentCapacity Size of the output buffer. + * @param err A UErrorCode value. + * @return The length of the parent locale ID. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getParent(const char* localeID, + char* parent, + int32_t parentCapacity, + UErrorCode* err); + + + + +/** + * Gets the full name for the specified locale, like uloc_getName(), + * but without keywords. + * + * Note: This has the effect of 'canonicalizing' the string to + * a certain extent. Upper and lower case are set as needed, + * and if the components were in 'POSIX' format they are changed to + * ICU format. It does NOT map aliased names in any way. + * See the top of this header file. + * + * This API strips off the keyword part, so "de_DE\@collation=phonebook" + * will become "de_DE". + * This API supports preflighting. + * + * @param localeID the locale to get the full name with + * @param name fill in buffer for the name without keywords. + * @param nameCapacity capacity of the fill in buffer. + * @param err error information if retrieving the full name failed + * @return the actual buffer size needed for the full name. If it's greater + * than nameCapacity, the returned full name will be truncated. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getBaseName(const char* localeID, + char* name, + int32_t nameCapacity, + UErrorCode* err); + +/** + * Gets an enumeration of keywords for the specified locale. Enumeration + * must get disposed of by the client using uenum_close function. + * + * @param localeID the locale to get the variant code with + * @param status error information if retrieving the keywords failed + * @return enumeration of keywords or NULL if there are no keywords. + * @stable ICU 2.8 + */ +U_CAPI UEnumeration* U_EXPORT2 +uloc_openKeywords(const char* localeID, + UErrorCode* status); + +/** + * Get the value for a keyword. Locale name does not need to be normalized. + * + * @param localeID locale name containing the keyword ("de_DE@currency=EURO;collation=PHONEBOOK") + * @param keywordName name of the keyword for which we want the value; must not be + * NULL or empty, and must consist only of [A-Za-z0-9]. Case insensitive. + * @param buffer receiving buffer + * @param bufferCapacity capacity of receiving buffer + * @param status containing error code: e.g. buffer not big enough or ill-formed localeID + * or keywordName parameters. + * @return the length of keyword value + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getKeywordValue(const char* localeID, + const char* keywordName, + char* buffer, int32_t bufferCapacity, + UErrorCode* status); + + +/** + * Sets or removes the value of the specified keyword. + * + * For removing all keywords, use uloc_getBaseName(). + * + * NOTE: Unlike almost every other ICU function which takes a + * buffer, this function will NOT truncate the output text, and will + * not update the buffer with unterminated text setting a status of + * U_STRING_NOT_TERMINATED_WARNING. If a BUFFER_OVERFLOW_ERROR is received, + * it means a terminated version of the updated locale ID would not fit + * in the buffer, and the original buffer is untouched. This is done to + * prevent incorrect or possibly even malformed locales from being generated + * and used. + * + * @param keywordName name of the keyword to be set; must not be + * NULL or empty, and must consist only of [A-Za-z0-9]. Case insensitive. + * @param keywordValue value of the keyword to be set. If 0-length or + * NULL, will result in the keyword being removed; no error is given if + * that keyword does not exist. Otherwise, must consist only of + * [A-Za-z0-9] and [/_+-]. + * @param buffer input buffer containing well-formed locale ID to be + * modified. + * @param bufferCapacity capacity of receiving buffer + * @param status containing error code: e.g. buffer not big enough + * or ill-formed keywordName or keywordValue parameters, or ill-formed + * locale ID in buffer on input. + * @return the length needed for the buffer + * @see uloc_getKeywordValue + * @stable ICU 3.2 + */ +U_CAPI int32_t U_EXPORT2 +uloc_setKeywordValue(const char* keywordName, + const char* keywordValue, + char* buffer, int32_t bufferCapacity, + UErrorCode* status); + +/** + * Returns whether the locale's script is written right-to-left. + * If there is no script subtag, then the likely script is used, see uloc_addLikelySubtags(). + * If no likely script is known, then false is returned. + * + * A script is right-to-left according to the CLDR script metadata + * which corresponds to whether the script's letters have Bidi_Class=R or AL. + * + * Returns true for "ar" and "en-Hebr", false for "zh" and "fa-Cyrl". + * + * @param locale input locale ID + * @return true if the locale's script is written right-to-left + * @stable ICU 54 + */ +U_CAPI UBool U_EXPORT2 +uloc_isRightToLeft(const char *locale); + +/** + * enums for the return value for the character and line orientation + * functions. + * @stable ICU 4.0 + */ +typedef enum { + ULOC_LAYOUT_LTR = 0, /* left-to-right. */ + ULOC_LAYOUT_RTL = 1, /* right-to-left. */ + ULOC_LAYOUT_TTB = 2, /* top-to-bottom. */ + ULOC_LAYOUT_BTT = 3, /* bottom-to-top. */ + ULOC_LAYOUT_UNKNOWN +} ULayoutType; + +/** + * Get the layout character orientation for the specified locale. + * + * @param localeId locale name + * @param status Error status + * @return an enum indicating the layout orientation for characters. + * @stable ICU 4.0 + */ +U_CAPI ULayoutType U_EXPORT2 +uloc_getCharacterOrientation(const char* localeId, + UErrorCode *status); + +/** + * Get the layout line orientation for the specified locale. + * + * @param localeId locale name + * @param status Error status + * @return an enum indicating the layout orientation for lines. + * @stable ICU 4.0 + */ +U_CAPI ULayoutType U_EXPORT2 +uloc_getLineOrientation(const char* localeId, + UErrorCode *status); + +/** + * Output values which uloc_acceptLanguage() writes to the 'outResult' parameter. + * + * @see uloc_acceptLanguageFromHTTP + * @see uloc_acceptLanguage + * @stable ICU 3.2 + */ +typedef enum { + /** + * No exact match was found. + * @stable ICU 3.2 + */ + ULOC_ACCEPT_FAILED = 0, + /** + * An exact match was found. + * @stable ICU 3.2 + */ + ULOC_ACCEPT_VALID = 1, + /** + * A fallback was found. For example, the Accept-Language list includes 'ja_JP' + * and is matched with available locale 'ja'. + * @stable ICU 3.2 + */ + ULOC_ACCEPT_FALLBACK = 2 /* */ +} UAcceptResult; + +/** + * Based on a HTTP header from a web browser and a list of available locales, + * determine an acceptable locale for the user. + * + * This is a thin wrapper over C++ class LocaleMatcher. + * + * @param result - buffer to accept the result locale + * @param resultAvailable the size of the result buffer. + * @param outResult - An out parameter that contains the fallback status + * @param httpAcceptLanguage - "Accept-Language:" header as per HTTP. + * @param availableLocales - list of available locales to match + * @param status ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return length needed for the locale. + * @stable ICU 3.2 + */ +U_CAPI int32_t U_EXPORT2 +uloc_acceptLanguageFromHTTP(char *result, int32_t resultAvailable, + UAcceptResult *outResult, + const char *httpAcceptLanguage, + UEnumeration* availableLocales, + UErrorCode *status); + +/** + * Based on a list of available locales, + * determine an acceptable locale for the user. + * + * This is a thin wrapper over C++ class LocaleMatcher. + * + * @param result - buffer to accept the result locale + * @param resultAvailable the size of the result buffer. + * @param outResult - An out parameter that contains the fallback status + * @param acceptList - list of acceptable languages + * @param acceptListCount - count of acceptList items + * @param availableLocales - list of available locales to match + * @param status ICU error code. Its input value must pass the U_SUCCESS() test, + * or else the function returns immediately. Check for U_FAILURE() + * on output or use with function chaining. (See User Guide for details.) + * @return length needed for the locale. + * @stable ICU 3.2 + */ +U_CAPI int32_t U_EXPORT2 +uloc_acceptLanguage(char *result, int32_t resultAvailable, + UAcceptResult *outResult, const char **acceptList, + int32_t acceptListCount, + UEnumeration* availableLocales, + UErrorCode *status); + + +/** + * Gets the ICU locale ID for the specified Win32 LCID value. + * + * @param hostID the Win32 LCID to translate + * @param locale the output buffer for the ICU locale ID, which will be NUL-terminated + * if there is room. + * @param localeCapacity the size of the output buffer + * @param status an error is returned if the LCID is unrecognized or the output buffer + * is too small + * @return actual the actual size of the locale ID, not including NUL-termination + * @stable ICU 3.8 + */ +U_CAPI int32_t U_EXPORT2 +uloc_getLocaleForLCID(uint32_t hostID, char *locale, int32_t localeCapacity, + UErrorCode *status); + + +/** + * Add the likely subtags for a provided locale ID, per the algorithm described + * in the following CLDR technical report: + * + * http://www.unicode.org/reports/tr35/#Likely_Subtags + * + * If localeID is already in the maximal form, or there is no data available + * for maximization, it will be copied to the output buffer. For example, + * "und-Zzzz" cannot be maximized, since there is no reasonable maximization. + * + * Examples: + * + * "en" maximizes to "en_Latn_US" + * + * "de" maximizes to "de_Latn_US" + * + * "sr" maximizes to "sr_Cyrl_RS" + * + * "sh" maximizes to "sr_Latn_RS" (Note this will not reverse.) + * + * "zh_Hani" maximizes to "zh_Hans_CN" (Note this will not reverse.) + * + * @param localeID The locale to maximize + * @param maximizedLocaleID The maximized locale + * @param maximizedLocaleIDCapacity The capacity of the maximizedLocaleID buffer + * @param err Error information if maximizing the locale failed. If the length + * of the localeID and the null-terminator is greater than the maximum allowed size, + * or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR. + * @return The actual buffer size needed for the maximized locale. If it's + * greater than maximizedLocaleIDCapacity, the returned ID will be truncated. + * On error, the return value is -1. + * @stable ICU 4.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_addLikelySubtags(const char* localeID, + char* maximizedLocaleID, + int32_t maximizedLocaleIDCapacity, + UErrorCode* err); + + +/** + * Minimize the subtags for a provided locale ID, per the algorithm described + * in the following CLDR technical report: + * + * http://www.unicode.org/reports/tr35/#Likely_Subtags + * + * If localeID is already in the minimal form, or there is no data available + * for minimization, it will be copied to the output buffer. Since the + * minimization algorithm relies on proper maximization, see the comments + * for uloc_addLikelySubtags for reasons why there might not be any data. + * + * Examples: + * + * "en_Latn_US" minimizes to "en" + * + * "de_Latn_US" minimizes to "de" + * + * "sr_Cyrl_RS" minimizes to "sr" + * + * "zh_Hant_TW" minimizes to "zh_TW" (The region is preferred to the + * script, and minimizing to "zh" would imply "zh_Hans_CN".) + * + * @param localeID The locale to minimize + * @param minimizedLocaleID The minimized locale + * @param minimizedLocaleIDCapacity The capacity of the minimizedLocaleID buffer + * @param err Error information if minimizing the locale failed. If the length + * of the localeID and the null-terminator is greater than the maximum allowed size, + * or the localeId is not well-formed, the error code is U_ILLEGAL_ARGUMENT_ERROR. + * @return The actual buffer size needed for the minimized locale. If it's + * greater than minimizedLocaleIDCapacity, the returned ID will be truncated. + * On error, the return value is -1. + * @stable ICU 4.0 + */ +U_CAPI int32_t U_EXPORT2 +uloc_minimizeSubtags(const char* localeID, + char* minimizedLocaleID, + int32_t minimizedLocaleIDCapacity, + UErrorCode* err); + +/** + * Returns a locale ID for the specified BCP47 language tag string. + * If the specified language tag contains any ill-formed subtags, + * the first such subtag and all following subtags are ignored. + * <p> + * This implements the 'Language-Tag' production of BCP 47, and so + * supports legacy language tags (marked as “Type: grandfathered” in BCP 47) + * (regular and irregular) as well as private use language tags. + * + * Private use tags are represented as 'x-whatever', + * and legacy tags are converted to their canonical replacements where they exist. + * + * Note that a few legacy tags have no modern replacement; + * these will be converted using the fallback described in + * the first paragraph, so some information might be lost. + * + * @param langtag the input BCP47 language tag. + * @param localeID the output buffer receiving a locale ID for the + * specified BCP47 language tag. + * @param localeIDCapacity the size of the locale ID output buffer. + * @param parsedLength if not NULL, successfully parsed length + * for the input language tag is set. + * @param err error information if receiving the locald ID + * failed. + * @return the length of the locale ID. + * @stable ICU 4.2 + */ +U_CAPI int32_t U_EXPORT2 +uloc_forLanguageTag(const char* langtag, + char* localeID, + int32_t localeIDCapacity, + int32_t* parsedLength, + UErrorCode* err); + +/** + * Returns a well-formed language tag for this locale ID. + * <p> + * <b>Note</b>: When <code>strict</code> is false, any locale + * fields which do not satisfy the BCP47 syntax requirement will + * be omitted from the result. When <code>strict</code> is + * true, this function sets U_ILLEGAL_ARGUMENT_ERROR to the + * <code>err</code> if any locale fields do not satisfy the + * BCP47 syntax requirement. + * @param localeID the input locale ID + * @param langtag the output buffer receiving BCP47 language + * tag for the locale ID. + * @param langtagCapacity the size of the BCP47 language tag + * output buffer. + * @param strict boolean value indicating if the function returns + * an error for an ill-formed input locale ID. + * @param err error information if receiving the language + * tag failed. + * @return The length of the BCP47 language tag. + * @stable ICU 4.2 + */ +U_CAPI int32_t U_EXPORT2 +uloc_toLanguageTag(const char* localeID, + char* langtag, + int32_t langtagCapacity, + UBool strict, + UErrorCode* err); + +/** + * Converts the specified keyword (legacy key, or BCP 47 Unicode locale + * extension key) to the equivalent BCP 47 Unicode locale extension key. + * For example, BCP 47 Unicode locale extension key "co" is returned for + * the input keyword "collation". + * <p> + * When the specified keyword is unknown, but satisfies the BCP syntax, + * then the pointer to the input keyword itself will be returned. + * For example, + * <code>uloc_toUnicodeLocaleKey("ZZ")</code> returns "ZZ". + * + * @param keyword the input locale keyword (either legacy key + * such as "collation" or BCP 47 Unicode locale extension + * key such as "co"). + * @return the well-formed BCP 47 Unicode locale extension key, + * or NULL if the specified locale keyword cannot be + * mapped to a well-formed BCP 47 Unicode locale extension + * key. + * @see uloc_toLegacyKey + * @stable ICU 54 + */ +U_CAPI const char* U_EXPORT2 +uloc_toUnicodeLocaleKey(const char* keyword); + +/** + * Converts the specified keyword value (legacy type, or BCP 47 + * Unicode locale extension type) to the well-formed BCP 47 Unicode locale + * extension type for the specified keyword (category). For example, BCP 47 + * Unicode locale extension type "phonebk" is returned for the input + * keyword value "phonebook", with the keyword "collation" (or "co"). + * <p> + * When the specified keyword is not recognized, but the specified value + * satisfies the syntax of the BCP 47 Unicode locale extension type, + * or when the specified keyword allows 'variable' type and the specified + * value satisfies the syntax, then the pointer to the input type value itself + * will be returned. + * For example, + * <code>uloc_toUnicodeLocaleType("Foo", "Bar")</code> returns "Bar", + * <code>uloc_toUnicodeLocaleType("variableTop", "00A4")</code> returns "00A4". + * + * @param keyword the locale keyword (either legacy key such as + * "collation" or BCP 47 Unicode locale extension + * key such as "co"). + * @param value the locale keyword value (either legacy type + * such as "phonebook" or BCP 47 Unicode locale extension + * type such as "phonebk"). + * @return the well-formed BCP47 Unicode locale extension type, + * or NULL if the locale keyword value cannot be mapped to + * a well-formed BCP 47 Unicode locale extension type. + * @see uloc_toLegacyType + * @stable ICU 54 + */ +U_CAPI const char* U_EXPORT2 +uloc_toUnicodeLocaleType(const char* keyword, const char* value); + +/** + * Converts the specified keyword (BCP 47 Unicode locale extension key, or + * legacy key) to the legacy key. For example, legacy key "collation" is + * returned for the input BCP 47 Unicode locale extension key "co". + * + * @param keyword the input locale keyword (either BCP 47 Unicode locale + * extension key or legacy key). + * @return the well-formed legacy key, or NULL if the specified + * keyword cannot be mapped to a well-formed legacy key. + * @see toUnicodeLocaleKey + * @stable ICU 54 + */ +U_CAPI const char* U_EXPORT2 +uloc_toLegacyKey(const char* keyword); + +/** + * Converts the specified keyword value (BCP 47 Unicode locale extension type, + * or legacy type or type alias) to the canonical legacy type. For example, + * the legacy type "phonebook" is returned for the input BCP 47 Unicode + * locale extension type "phonebk" with the keyword "collation" (or "co"). + * <p> + * When the specified keyword is not recognized, but the specified value + * satisfies the syntax of legacy key, or when the specified keyword + * allows 'variable' type and the specified value satisfies the syntax, + * then the pointer to the input type value itself will be returned. + * For example, + * <code>uloc_toLegacyType("Foo", "Bar")</code> returns "Bar", + * <code>uloc_toLegacyType("vt", "00A4")</code> returns "00A4". + * + * @param keyword the locale keyword (either legacy keyword such as + * "collation" or BCP 47 Unicode locale extension + * key such as "co"). + * @param value the locale keyword value (either BCP 47 Unicode locale + * extension type such as "phonebk" or legacy keyword value + * such as "phonebook"). + * @return the well-formed legacy type, or NULL if the specified + * keyword value cannot be mapped to a well-formed legacy + * type. + * @see toUnicodeLocaleType + * @stable ICU 54 + */ +U_CAPI const char* U_EXPORT2 +uloc_toLegacyType(const char* keyword, const char* value); + +#endif /*_ULOC*/ diff --git a/thirdparty/icu4c/common/unicode/umachine.h b/thirdparty/icu4c/common/unicode/umachine.h new file mode 100644 index 0000000000..09c887c80e --- /dev/null +++ b/thirdparty/icu4c/common/unicode/umachine.h @@ -0,0 +1,491 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1999-2015, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* file name: umachine.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999sep13 +* created by: Markus W. Scherer +* +* This file defines basic types and constants for ICU to be +* platform-independent. umachine.h and utf.h are included into +* utypes.h to provide all the general definitions for ICU. +* All of these definitions used to be in utypes.h before +* the UTF-handling macros made this unmaintainable. +*/ + +#ifndef __UMACHINE_H__ +#define __UMACHINE_H__ + + +/** + * \file + * \brief Basic types and constants for UTF + * + * <h2> Basic types and constants for UTF </h2> + * This file defines basic types and constants for utf.h to be + * platform-independent. umachine.h and utf.h are included into + * utypes.h to provide all the general definitions for ICU. + * All of these definitions used to be in utypes.h before + * the UTF-handling macros made this unmaintainable. + * + */ +/*==========================================================================*/ +/* Include platform-dependent definitions */ +/* which are contained in the platform-specific file platform.h */ +/*==========================================================================*/ + +#include "unicode/ptypes.h" /* platform.h is included in ptypes.h */ + +/* + * ANSI C headers: + * stddef.h defines wchar_t + */ +#include <stdbool.h> +#include <stddef.h> + +/*==========================================================================*/ +/* For C wrappers, we use the symbol U_CAPI. */ +/* This works properly if the includer is C or C++. */ +/* Functions are declared U_CAPI return-type U_EXPORT2 function-name()... */ +/*==========================================================================*/ + +/** + * \def U_CFUNC + * This is used in a declaration of a library private ICU C function. + * @stable ICU 2.4 + */ + +/** + * \def U_CDECL_BEGIN + * This is used to begin a declaration of a library private ICU C API. + * @stable ICU 2.4 + */ + +/** + * \def U_CDECL_END + * This is used to end a declaration of a library private ICU C API + * @stable ICU 2.4 + */ + +#ifdef __cplusplus +# define U_CFUNC extern "C" +# define U_CDECL_BEGIN extern "C" { +# define U_CDECL_END } +#else +# define U_CFUNC extern +# define U_CDECL_BEGIN +# define U_CDECL_END +#endif + +#ifndef U_ATTRIBUTE_DEPRECATED +/** + * \def U_ATTRIBUTE_DEPRECATED + * This is used for GCC specific attributes + * @internal + */ +#if U_GCC_MAJOR_MINOR >= 302 +# define U_ATTRIBUTE_DEPRECATED __attribute__ ((deprecated)) +/** + * \def U_ATTRIBUTE_DEPRECATED + * This is used for Visual C++ specific attributes + * @internal + */ +#elif defined(_MSC_VER) && (_MSC_VER >= 1400) +# define U_ATTRIBUTE_DEPRECATED __declspec(deprecated) +#else +# define U_ATTRIBUTE_DEPRECATED +#endif +#endif + +/** This is used to declare a function as a public ICU C API @stable ICU 2.0*/ +#define U_CAPI U_CFUNC U_EXPORT +/** Obsolete/same as U_CAPI; was used to declare a function as a stable public ICU C API*/ +#define U_STABLE U_CAPI +/** Obsolete/same as U_CAPI; was used to declare a function as a draft public ICU C API */ +#define U_DRAFT U_CAPI +/** This is used to declare a function as a deprecated public ICU C API */ +#define U_DEPRECATED U_CAPI U_ATTRIBUTE_DEPRECATED +/** Obsolete/same as U_CAPI; was used to declare a function as an obsolete public ICU C API */ +#define U_OBSOLETE U_CAPI +/** Obsolete/same as U_CAPI; was used to declare a function as an internal ICU C API */ +#define U_INTERNAL U_CAPI + +/** + * \def U_OVERRIDE + * Defined to the C++11 "override" keyword if available. + * Denotes a class or member which is an override of the base class. + * May result in an error if it applied to something not an override. + * @internal + */ +#ifndef U_OVERRIDE +#define U_OVERRIDE override +#endif + +/** + * \def U_FINAL + * Defined to the C++11 "final" keyword if available. + * Denotes a class or member which may not be overridden in subclasses. + * May result in an error if subclasses attempt to override. + * @internal + */ +#if !defined(U_FINAL) || defined(U_IN_DOXYGEN) +#define U_FINAL final +#endif + +// Before ICU 65, function-like, multi-statement ICU macros were just defined as +// series of statements wrapped in { } blocks and the caller could choose to +// either treat them as if they were actual functions and end the invocation +// with a trailing ; creating an empty statement after the block or else omit +// this trailing ; using the knowledge that the macro would expand to { }. +// +// But doing so doesn't work well with macros that look like functions and +// compiler warnings about empty statements (ICU-20601) and ICU 65 therefore +// switches to the standard solution of wrapping such macros in do { } while. +// +// This will however break existing code that depends on being able to invoke +// these macros without a trailing ; so to be able to remain compatible with +// such code the wrapper is itself defined as macros so that it's possible to +// build ICU 65 and later with the old macro behaviour, like this: +// +// export CPPFLAGS='-DUPRV_BLOCK_MACRO_BEGIN="" -DUPRV_BLOCK_MACRO_END=""' +// runConfigureICU ... +// + +/** + * \def UPRV_BLOCK_MACRO_BEGIN + * Defined as the "do" keyword by default. + * @internal + */ +#ifndef UPRV_BLOCK_MACRO_BEGIN +#define UPRV_BLOCK_MACRO_BEGIN do +#endif + +/** + * \def UPRV_BLOCK_MACRO_END + * Defined as "while (false)" by default. + * @internal + */ +#ifndef UPRV_BLOCK_MACRO_END +#define UPRV_BLOCK_MACRO_END while (false) +#endif + +/*==========================================================================*/ +/* limits for int32_t etc., like in POSIX inttypes.h */ +/*==========================================================================*/ + +#ifndef INT8_MIN +/** The smallest value an 8 bit signed integer can hold @stable ICU 2.0 */ +# define INT8_MIN ((int8_t)(-128)) +#endif +#ifndef INT16_MIN +/** The smallest value a 16 bit signed integer can hold @stable ICU 2.0 */ +# define INT16_MIN ((int16_t)(-32767-1)) +#endif +#ifndef INT32_MIN +/** The smallest value a 32 bit signed integer can hold @stable ICU 2.0 */ +# define INT32_MIN ((int32_t)(-2147483647-1)) +#endif + +#ifndef INT8_MAX +/** The largest value an 8 bit signed integer can hold @stable ICU 2.0 */ +# define INT8_MAX ((int8_t)(127)) +#endif +#ifndef INT16_MAX +/** The largest value a 16 bit signed integer can hold @stable ICU 2.0 */ +# define INT16_MAX ((int16_t)(32767)) +#endif +#ifndef INT32_MAX +/** The largest value a 32 bit signed integer can hold @stable ICU 2.0 */ +# define INT32_MAX ((int32_t)(2147483647)) +#endif + +#ifndef UINT8_MAX +/** The largest value an 8 bit unsigned integer can hold @stable ICU 2.0 */ +# define UINT8_MAX ((uint8_t)(255U)) +#endif +#ifndef UINT16_MAX +/** The largest value a 16 bit unsigned integer can hold @stable ICU 2.0 */ +# define UINT16_MAX ((uint16_t)(65535U)) +#endif +#ifndef UINT32_MAX +/** The largest value a 32 bit unsigned integer can hold @stable ICU 2.0 */ +# define UINT32_MAX ((uint32_t)(4294967295U)) +#endif + +#if defined(U_INT64_T_UNAVAILABLE) +# error int64_t is required for decimal format and rule-based number format. +#else +# ifndef INT64_C +/** + * Provides a platform independent way to specify a signed 64-bit integer constant. + * note: may be wrong for some 64 bit platforms - ensure your compiler provides INT64_C + * @stable ICU 2.8 + */ +# define INT64_C(c) c ## LL +# endif +# ifndef UINT64_C +/** + * Provides a platform independent way to specify an unsigned 64-bit integer constant. + * note: may be wrong for some 64 bit platforms - ensure your compiler provides UINT64_C + * @stable ICU 2.8 + */ +# define UINT64_C(c) c ## ULL +# endif +# ifndef U_INT64_MIN +/** The smallest value a 64 bit signed integer can hold @stable ICU 2.8 */ +# define U_INT64_MIN ((int64_t)(INT64_C(-9223372036854775807)-1)) +# endif +# ifndef U_INT64_MAX +/** The largest value a 64 bit signed integer can hold @stable ICU 2.8 */ +# define U_INT64_MAX ((int64_t)(INT64_C(9223372036854775807))) +# endif +# ifndef U_UINT64_MAX +/** The largest value a 64 bit unsigned integer can hold @stable ICU 2.8 */ +# define U_UINT64_MAX ((uint64_t)(UINT64_C(18446744073709551615))) +# endif +#endif + +/*==========================================================================*/ +/* Boolean data type */ +/*==========================================================================*/ + +/** + * The ICU boolean type, a signed-byte integer. + * ICU-specific for historical reasons: The C and C++ standards used to not define type bool. + * Also provides a fixed type definition, as opposed to + * type bool whose details (e.g., sizeof) may vary by compiler and between C and C++. + * + * @stable ICU 2.0 + */ +typedef int8_t UBool; + +/** + * \def U_DEFINE_FALSE_AND_TRUE + * Normally turns off defining macros FALSE=0 & TRUE=1 in public ICU headers. + * These obsolete macros sometimes break compilation of other code that + * defines enum constants or similar with these names. + * C++ has long defined bool/false/true. + * C99 also added definitions for these, although as macros; see stdbool.h. + * + * You may transitionally define U_DEFINE_FALSE_AND_TRUE=1 if you need time to migrate code. + * + * @internal ICU 68 + */ +#ifdef U_DEFINE_FALSE_AND_TRUE + // Use the predefined value. +#elif defined(U_COMBINED_IMPLEMENTATION) || \ + defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || \ + defined(U_IO_IMPLEMENTATION) || defined(U_LAYOUTEX_IMPLEMENTATION) || \ + defined(U_TOOLUTIL_IMPLEMENTATION) + // Inside ICU: Keep FALSE & TRUE available. +# define U_DEFINE_FALSE_AND_TRUE 1 +#else + // Outside ICU: Avoid collision with non-macro definitions of FALSE & TRUE. +# define U_DEFINE_FALSE_AND_TRUE 0 +#endif + +#if U_DEFINE_FALSE_AND_TRUE || defined(U_IN_DOXYGEN) +#ifndef TRUE +/** + * The TRUE value of a UBool. + * + * @deprecated ICU 68 Use standard "true" instead. + */ +# define TRUE 1 +#endif +#ifndef FALSE +/** + * The FALSE value of a UBool. + * + * @deprecated ICU 68 Use standard "false" instead. + */ +# define FALSE 0 +#endif +#endif // U_DEFINE_FALSE_AND_TRUE + +/*==========================================================================*/ +/* Unicode data types */ +/*==========================================================================*/ + +/* wchar_t-related definitions -------------------------------------------- */ + +/* + * \def U_WCHAR_IS_UTF16 + * Defined if wchar_t uses UTF-16. + * + * @stable ICU 2.0 + */ +/* + * \def U_WCHAR_IS_UTF32 + * Defined if wchar_t uses UTF-32. + * + * @stable ICU 2.0 + */ +#if !defined(U_WCHAR_IS_UTF16) && !defined(U_WCHAR_IS_UTF32) +# ifdef __STDC_ISO_10646__ +# if (U_SIZEOF_WCHAR_T==2) +# define U_WCHAR_IS_UTF16 +# elif (U_SIZEOF_WCHAR_T==4) +# define U_WCHAR_IS_UTF32 +# endif +# elif defined __UCS2__ +# if (U_PF_OS390 <= U_PLATFORM && U_PLATFORM <= U_PF_OS400) && (U_SIZEOF_WCHAR_T==2) +# define U_WCHAR_IS_UTF16 +# endif +# elif defined(__UCS4__) || (U_PLATFORM == U_PF_OS400 && defined(__UTF32__)) +# if (U_SIZEOF_WCHAR_T==4) +# define U_WCHAR_IS_UTF32 +# endif +# elif U_PLATFORM_IS_DARWIN_BASED || (U_SIZEOF_WCHAR_T==4 && U_PLATFORM_IS_LINUX_BASED) +# define U_WCHAR_IS_UTF32 +# elif U_PLATFORM_HAS_WIN32_API +# define U_WCHAR_IS_UTF16 +# endif +#endif + +/* UChar and UChar32 definitions -------------------------------------------- */ + +/** Number of bytes in a UChar. @stable ICU 2.0 */ +#define U_SIZEOF_UCHAR 2 + +/** + * \def U_CHAR16_IS_TYPEDEF + * If 1, then char16_t is a typedef and not a real type (yet) + * @internal + */ +#if (U_PLATFORM == U_PF_AIX) && defined(__cplusplus) &&(U_CPLUSPLUS_VERSION < 11) +// for AIX, uchar.h needs to be included +# include <uchar.h> +# define U_CHAR16_IS_TYPEDEF 1 +#elif defined(_MSC_VER) && (_MSC_VER < 1900) +// Versions of Visual Studio/MSVC below 2015 do not support char16_t as a real type, +// and instead use a typedef. https://msdn.microsoft.com/library/bb531344.aspx +# define U_CHAR16_IS_TYPEDEF 1 +#else +# define U_CHAR16_IS_TYPEDEF 0 +#endif + + +/** + * \var UChar + * + * The base type for UTF-16 code units and pointers. + * Unsigned 16-bit integer. + * Starting with ICU 59, C++ API uses char16_t directly, while C API continues to use UChar. + * + * UChar is configurable by defining the macro UCHAR_TYPE + * on the preprocessor or compiler command line: + * -DUCHAR_TYPE=uint16_t or -DUCHAR_TYPE=wchar_t (if U_SIZEOF_WCHAR_T==2) etc. + * (The UCHAR_TYPE can also be \#defined earlier in this file, for outside the ICU library code.) + * This is for transitional use from application code that uses uint16_t or wchar_t for UTF-16. + * + * The default is UChar=char16_t. + * + * C++11 defines char16_t as bit-compatible with uint16_t, but as a distinct type. + * + * In C, char16_t is a simple typedef of uint_least16_t. + * ICU requires uint_least16_t=uint16_t for data memory mapping. + * On macOS, char16_t is not available because the uchar.h standard header is missing. + * + * @stable ICU 4.4 + */ + +#if 1 + // #if 1 is normal. UChar defaults to char16_t in C++. + // For configuration testing of UChar=uint16_t temporarily change this to #if 0. + // The intltest Makefile #defines UCHAR_TYPE=char16_t, + // so we only #define it to uint16_t if it is undefined so far. +#elif !defined(UCHAR_TYPE) +# define UCHAR_TYPE uint16_t +#endif + +#if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || \ + defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) + // Inside the ICU library code, never configurable. + typedef char16_t UChar; +#elif defined(UCHAR_TYPE) + typedef UCHAR_TYPE UChar; +#elif (U_CPLUSPLUS_VERSION >= 11) + typedef char16_t UChar; +#else + typedef uint16_t UChar; +#endif + +/** + * \var OldUChar + * Default ICU 58 definition of UChar. + * A base type for UTF-16 code units and pointers. + * Unsigned 16-bit integer. + * + * Define OldUChar to be wchar_t if that is 16 bits wide. + * If wchar_t is not 16 bits wide, then define UChar to be uint16_t. + * + * This makes the definition of OldUChar platform-dependent + * but allows direct string type compatibility with platforms with + * 16-bit wchar_t types. + * + * This is how UChar was defined in ICU 58, for transition convenience. + * Exception: ICU 58 UChar was defined to UCHAR_TYPE if that macro was defined. + * The current UChar responds to UCHAR_TYPE but OldUChar does not. + * + * @stable ICU 59 + */ +#if U_SIZEOF_WCHAR_T==2 + typedef wchar_t OldUChar; +#elif defined(__CHAR16_TYPE__) + typedef __CHAR16_TYPE__ OldUChar; +#else + typedef uint16_t OldUChar; +#endif + +/** + * Define UChar32 as a type for single Unicode code points. + * UChar32 is a signed 32-bit integer (same as int32_t). + * + * The Unicode code point range is 0..0x10ffff. + * All other values (negative or >=0x110000) are illegal as Unicode code points. + * They may be used as sentinel values to indicate "done", "error" + * or similar non-code point conditions. + * + * Before ICU 2.4 (Jitterbug 2146), UChar32 was defined + * to be wchar_t if that is 32 bits wide (wchar_t may be signed or unsigned) + * or else to be uint32_t. + * That is, the definition of UChar32 was platform-dependent. + * + * @see U_SENTINEL + * @stable ICU 2.4 + */ +typedef int32_t UChar32; + +/** + * This value is intended for sentinel values for APIs that + * (take or) return single code points (UChar32). + * It is outside of the Unicode code point range 0..0x10ffff. + * + * For example, a "done" or "error" value in a new API + * could be indicated with U_SENTINEL. + * + * ICU APIs designed before ICU 2.4 usually define service-specific "done" + * values, mostly 0xffff. + * Those may need to be distinguished from + * actual U+ffff text contents by calling functions like + * CharacterIterator::hasNext() or UnicodeString::length(). + * + * @return -1 + * @see UChar32 + * @stable ICU 2.4 + */ +#define U_SENTINEL (-1) + +#include "unicode/urename.h" + +#endif diff --git a/thirdparty/icu4c/common/unicode/umisc.h b/thirdparty/icu4c/common/unicode/umisc.h new file mode 100644 index 0000000000..213290b9af --- /dev/null +++ b/thirdparty/icu4c/common/unicode/umisc.h @@ -0,0 +1,62 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1999-2006, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* file name: umisc.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999oct15 +* created by: Markus W. Scherer +*/ + +#ifndef UMISC_H +#define UMISC_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C API:misc definitions + * + * This file contains miscellaneous definitions for the C APIs. + */ + +U_CDECL_BEGIN + +/** A struct representing a range of text containing a specific field + * @stable ICU 2.0 + */ +typedef struct UFieldPosition { + /** + * The field + * @stable ICU 2.0 + */ + int32_t field; + /** + * The start of the text range containing field + * @stable ICU 2.0 + */ + int32_t beginIndex; + /** + * The limit of the text range containing field + * @stable ICU 2.0 + */ + int32_t endIndex; +} UFieldPosition; + +#if !UCONFIG_NO_SERVICE +/** + * Opaque type returned by registerInstance, registerFactory and unregister for service registration. + * @stable ICU 2.6 + */ +typedef const void* URegistryKey; +#endif + +U_CDECL_END + +#endif diff --git a/thirdparty/icu4c/common/unicode/umutablecptrie.h b/thirdparty/icu4c/common/unicode/umutablecptrie.h new file mode 100644 index 0000000000..5325d58147 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/umutablecptrie.h @@ -0,0 +1,241 @@ +// © 2017 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html + +// umutablecptrie.h (split out of ucptrie.h) +// created: 2018jan24 Markus W. Scherer + +#ifndef __UMUTABLECPTRIE_H__ +#define __UMUTABLECPTRIE_H__ + +#include "unicode/utypes.h" + +#include "unicode/ucpmap.h" +#include "unicode/ucptrie.h" +#include "unicode/utf8.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +U_CDECL_BEGIN + +/** + * \file + * + * This file defines a mutable Unicode code point trie. + * + * @see UCPTrie + * @see UMutableCPTrie + */ + +/** + * Mutable Unicode code point trie. + * Fast map from Unicode code points (U+0000..U+10FFFF) to 32-bit integer values. + * For details see http://site.icu-project.org/design/struct/utrie + * + * Setting values (especially ranges) and lookup is fast. + * The mutable trie is only somewhat space-efficient. + * It builds a compacted, immutable UCPTrie. + * + * This trie can be modified while iterating over its contents. + * For example, it is possible to merge its values with those from another + * set of ranges (e.g., another mutable or immutable trie): + * Iterate over those source ranges; for each of them iterate over this trie; + * add the source value into the value of each trie range. + * + * @see UCPTrie + * @see umutablecptrie_buildImmutable + * @stable ICU 63 + */ +typedef struct UMutableCPTrie UMutableCPTrie; + +/** + * Creates a mutable trie that initially maps each Unicode code point to the same value. + * It uses 32-bit data values until umutablecptrie_buildImmutable() is called. + * umutablecptrie_buildImmutable() takes a valueWidth parameter which + * determines the number of bits in the data value in the resulting UCPTrie. + * You must umutablecptrie_close() the trie once you are done using it. + * + * @param initialValue the initial value that is set for all code points + * @param errorValue the value for out-of-range code points and ill-formed UTF-8/16 + * @param pErrorCode an in/out ICU UErrorCode + * @return the trie + * @stable ICU 63 + */ +U_CAPI UMutableCPTrie * U_EXPORT2 +umutablecptrie_open(uint32_t initialValue, uint32_t errorValue, UErrorCode *pErrorCode); + +/** + * Clones a mutable trie. + * You must umutablecptrie_close() the clone once you are done using it. + * + * @param other the trie to clone + * @param pErrorCode an in/out ICU UErrorCode + * @return the trie clone + * @stable ICU 63 + */ +U_CAPI UMutableCPTrie * U_EXPORT2 +umutablecptrie_clone(const UMutableCPTrie *other, UErrorCode *pErrorCode); + +/** + * Closes a mutable trie and releases associated memory. + * + * @param trie the trie + * @stable ICU 63 + */ +U_CAPI void U_EXPORT2 +umutablecptrie_close(UMutableCPTrie *trie); + +/** + * Creates a mutable trie with the same contents as the UCPMap. + * You must umutablecptrie_close() the mutable trie once you are done using it. + * + * @param map the source map + * @param pErrorCode an in/out ICU UErrorCode + * @return the mutable trie + * @stable ICU 63 + */ +U_CAPI UMutableCPTrie * U_EXPORT2 +umutablecptrie_fromUCPMap(const UCPMap *map, UErrorCode *pErrorCode); + +/** + * Creates a mutable trie with the same contents as the immutable one. + * You must umutablecptrie_close() the mutable trie once you are done using it. + * + * @param trie the immutable trie + * @param pErrorCode an in/out ICU UErrorCode + * @return the mutable trie + * @stable ICU 63 + */ +U_CAPI UMutableCPTrie * U_EXPORT2 +umutablecptrie_fromUCPTrie(const UCPTrie *trie, UErrorCode *pErrorCode); + +/** + * Returns the value for a code point as stored in the trie. + * + * @param trie the trie + * @param c the code point + * @return the value + * @stable ICU 63 + */ +U_CAPI uint32_t U_EXPORT2 +umutablecptrie_get(const UMutableCPTrie *trie, UChar32 c); + +/** + * Returns the last code point such that all those from start to there have the same value. + * Can be used to efficiently iterate over all same-value ranges in a trie. + * (This is normally faster than iterating over code points and get()ting each value, + * but much slower than a data structure that stores ranges directly.) + * + * The trie can be modified between calls to this function. + * + * If the UCPMapValueFilter function pointer is not NULL, then + * the value to be delivered is passed through that function, and the return value is the end + * of the range where all values are modified to the same actual value. + * The value is unchanged if that function pointer is NULL. + * + * See the same-signature ucptrie_getRange() for a code sample. + * + * @param trie the trie + * @param start range start + * @param option defines whether surrogates are treated normally, + * or as having the surrogateValue; usually UCPMAP_RANGE_NORMAL + * @param surrogateValue value for surrogates; ignored if option==UCPMAP_RANGE_NORMAL + * @param filter a pointer to a function that may modify the trie data value, + * or NULL if the values from the trie are to be used unmodified + * @param context an opaque pointer that is passed on to the filter function + * @param pValue if not NULL, receives the value that every code point start..end has; + * may have been modified by filter(context, trie value) + * if that function pointer is not NULL + * @return the range end code point, or -1 if start is not a valid code point + * @stable ICU 63 + */ +U_CAPI UChar32 U_EXPORT2 +umutablecptrie_getRange(const UMutableCPTrie *trie, UChar32 start, + UCPMapRangeOption option, uint32_t surrogateValue, + UCPMapValueFilter *filter, const void *context, uint32_t *pValue); + +/** + * Sets a value for a code point. + * + * @param trie the trie + * @param c the code point + * @param value the value + * @param pErrorCode an in/out ICU UErrorCode + * @stable ICU 63 + */ +U_CAPI void U_EXPORT2 +umutablecptrie_set(UMutableCPTrie *trie, UChar32 c, uint32_t value, UErrorCode *pErrorCode); + +/** + * Sets a value for each code point [start..end]. + * Faster and more space-efficient than setting the value for each code point separately. + * + * @param trie the trie + * @param start the first code point to get the value + * @param end the last code point to get the value (inclusive) + * @param value the value + * @param pErrorCode an in/out ICU UErrorCode + * @stable ICU 63 + */ +U_CAPI void U_EXPORT2 +umutablecptrie_setRange(UMutableCPTrie *trie, + UChar32 start, UChar32 end, + uint32_t value, UErrorCode *pErrorCode); + +/** + * Compacts the data and builds an immutable UCPTrie according to the parameters. + * After this, the mutable trie will be empty. + * + * The mutable trie stores 32-bit values until buildImmutable() is called. + * If values shorter than 32 bits are to be stored in the immutable trie, + * then the upper bits are discarded. + * For example, when the mutable trie contains values 0x81, -0x7f, and 0xa581, + * and the value width is 8 bits, then each of these is stored as 0x81 + * and the immutable trie will return that as an unsigned value. + * (Some implementations may want to make productive temporary use of the upper bits + * until buildImmutable() discards them.) + * + * Not every possible set of mappings can be built into a UCPTrie, + * because of limitations resulting from speed and space optimizations. + * Every Unicode assigned character can be mapped to a unique value. + * Typical data yields data structures far smaller than the limitations. + * + * It is possible to construct extremely unusual mappings that exceed the data structure limits. + * In such a case this function will fail with a U_INDEX_OUTOFBOUNDS_ERROR. + * + * @param trie the trie trie + * @param type selects the trie type + * @param valueWidth selects the number of bits in a trie data value; if smaller than 32 bits, + * then the values stored in the trie will be truncated first + * @param pErrorCode an in/out ICU UErrorCode + * + * @see umutablecptrie_fromUCPTrie + * @stable ICU 63 + */ +U_CAPI UCPTrie * U_EXPORT2 +umutablecptrie_buildImmutable(UMutableCPTrie *trie, UCPTrieType type, UCPTrieValueWidth valueWidth, + UErrorCode *pErrorCode); + +U_CDECL_END + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUMutableCPTriePointer + * "Smart pointer" class, closes a UMutableCPTrie via umutablecptrie_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 63 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUMutableCPTriePointer, UMutableCPTrie, umutablecptrie_close); + +U_NAMESPACE_END + +#endif + +#endif diff --git a/thirdparty/icu4c/common/unicode/unifilt.h b/thirdparty/icu4c/common/unicode/unifilt.h new file mode 100644 index 0000000000..420e1a1905 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/unifilt.h @@ -0,0 +1,136 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1999-2010, International Business Machines Corporation and others. +* All Rights Reserved. +********************************************************************** +* Date Name Description +* 11/17/99 aliu Creation. +********************************************************************** +*/ +#ifndef UNIFILT_H +#define UNIFILT_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/unifunct.h" +#include "unicode/unimatch.h" + +/** + * \file + * \brief C++ API: Unicode Filter + */ + +U_NAMESPACE_BEGIN + +/** + * U_ETHER is used to represent character values for positions outside + * a range. For example, transliterator uses this to represent + * characters outside the range contextStart..contextLimit-1. This + * allows explicit matching by rules and UnicodeSets of text outside a + * defined range. + * @stable ICU 3.0 + */ +#define U_ETHER ((char16_t)0xFFFF) + +/** + * + * <code>UnicodeFilter</code> defines a protocol for selecting a + * subset of the full range (U+0000 to U+10FFFF) of Unicode characters. + * Currently, filters are used in conjunction with classes like {@link + * Transliterator} to only process selected characters through a + * transformation. + * + * <p>Note: UnicodeFilter currently stubs out two pure virtual methods + * of its base class, UnicodeMatcher. These methods are toPattern() + * and matchesIndexValue(). This is done so that filter classes that + * are not actually used as matchers -- specifically, those in the + * UnicodeFilterLogic component, and those in tests -- can continue to + * work without defining these methods. As long as a filter is not + * used in an RBT during real transliteration, these methods will not + * be called. However, this breaks the UnicodeMatcher base class + * protocol, and it is not a correct solution. + * + * <p>In the future we may revisit the UnicodeMatcher / UnicodeFilter + * hierarchy and either redesign it, or simply remove the stubs in + * UnicodeFilter and force subclasses to implement the full + * UnicodeMatcher protocol. + * + * @see UnicodeFilterLogic + * @stable ICU 2.0 + */ +class U_COMMON_API UnicodeFilter : public UnicodeFunctor, public UnicodeMatcher { + +public: + /** + * Destructor + * @stable ICU 2.0 + */ + virtual ~UnicodeFilter(); + + /** + * Clones this object polymorphically. + * The caller owns the result and should delete it when done. + * @return clone, or nullptr if an error occurred + * @stable ICU 2.4 + */ + virtual UnicodeFilter* clone() const = 0; + + /** + * Returns <tt>true</tt> for characters that are in the selected + * subset. In other words, if a character is <b>to be + * filtered</b>, then <tt>contains()</tt> returns + * <b><tt>false</tt></b>. + * @stable ICU 2.0 + */ + virtual UBool contains(UChar32 c) const = 0; + + /** + * UnicodeFunctor API. Cast 'this' to a UnicodeMatcher* pointer + * and return the pointer. + * @stable ICU 2.4 + */ + virtual UnicodeMatcher* toMatcher() const; + + /** + * Implement UnicodeMatcher API. + * @stable ICU 2.4 + */ + virtual UMatchDegree matches(const Replaceable& text, + int32_t& offset, + int32_t limit, + UBool incremental); + + /** + * UnicodeFunctor API. Nothing to do. + * @stable ICU 2.4 + */ + virtual void setData(const TransliterationRuleData*); + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + +protected: + + /* + * Since this class has pure virtual functions, + * a constructor can't be used. + * @stable ICU 2.0 + */ +/* UnicodeFilter();*/ +}; + +/*inline UnicodeFilter::UnicodeFilter() {}*/ + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/unifunct.h b/thirdparty/icu4c/common/unicode/unifunct.h new file mode 100644 index 0000000000..7d31af7daf --- /dev/null +++ b/thirdparty/icu4c/common/unicode/unifunct.h @@ -0,0 +1,132 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (c) 2002-2005, International Business Machines Corporation +* and others. All Rights Reserved. +********************************************************************** +* Date Name Description +* 01/14/2002 aliu Creation. +********************************************************************** +*/ +#ifndef UNIFUNCT_H +#define UNIFUNCT_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" + +/** + * \file + * \brief C++ API: Unicode Functor + */ + +U_NAMESPACE_BEGIN + +class UnicodeMatcher; +class UnicodeReplacer; +class TransliterationRuleData; + +/** + * <code>UnicodeFunctor</code> is an abstract base class for objects + * that perform match and/or replace operations on Unicode strings. + * @author Alan Liu + * @stable ICU 2.4 + */ +class U_COMMON_API UnicodeFunctor : public UObject { + +public: + + /** + * Destructor + * @stable ICU 2.4 + */ + virtual ~UnicodeFunctor(); + + /** + * Return a copy of this object. All UnicodeFunctor objects + * have to support cloning in order to allow classes using + * UnicodeFunctor to implement cloning. + * @stable ICU 2.4 + */ + virtual UnicodeFunctor* clone() const = 0; + + /** + * Cast 'this' to a UnicodeMatcher* pointer and return the + * pointer, or null if this is not a UnicodeMatcher*. Subclasses + * that mix in UnicodeMatcher as a base class must override this. + * This protocol is required because a pointer to a UnicodeFunctor + * cannot be cast to a pointer to a UnicodeMatcher, since + * UnicodeMatcher is a mixin that does not derive from + * UnicodeFunctor. + * @stable ICU 2.4 + */ + virtual UnicodeMatcher* toMatcher() const; + + /** + * Cast 'this' to a UnicodeReplacer* pointer and return the + * pointer, or null if this is not a UnicodeReplacer*. Subclasses + * that mix in UnicodeReplacer as a base class must override this. + * This protocol is required because a pointer to a UnicodeFunctor + * cannot be cast to a pointer to a UnicodeReplacer, since + * UnicodeReplacer is a mixin that does not derive from + * UnicodeFunctor. + * @stable ICU 2.4 + */ + virtual UnicodeReplacer* toReplacer() const; + + /** + * Return the class ID for this class. This is useful only for + * comparing to a return value from getDynamicClassID(). + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Returns a unique class ID <b>polymorphically</b>. This method + * is to implement a simple version of RTTI, since not all C++ + * compilers support genuine RTTI. Polymorphic operator==() and + * clone() methods call this method. + * + * <p>Concrete subclasses of UnicodeFunctor should use the macro + * UOBJECT_DEFINE_RTTI_IMPLEMENTATION from uobject.h to + * provide definitios getStaticClassID and getDynamicClassID. + * + * @return The class ID for this object. All objects of a given + * class have the same class ID. Objects of other classes have + * different class IDs. + * @stable ICU 2.4 + */ + virtual UClassID getDynamicClassID(void) const = 0; + + /** + * Set the data object associated with this functor. The data + * object provides context for functor-to-standin mapping. This + * method is required when assigning a functor to a different data + * object. This function MAY GO AWAY later if the architecture is + * changed to pass data object pointers through the API. + * @internal ICU 2.1 + */ + virtual void setData(const TransliterationRuleData*) = 0; + +protected: + + /** + * Since this class has pure virtual functions, + * a constructor can't be used. + * @stable ICU 2.0 + */ + /*UnicodeFunctor();*/ + +}; + +/*inline UnicodeFunctor::UnicodeFunctor() {}*/ + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/unimatch.h b/thirdparty/icu4c/common/unicode/unimatch.h new file mode 100644 index 0000000000..302332f455 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/unimatch.h @@ -0,0 +1,168 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +* Copyright (C) 2001-2005, International Business Machines Corporation and others. All Rights Reserved. +********************************************************************** +* Date Name Description +* 07/18/01 aliu Creation. +********************************************************************** +*/ +#ifndef UNIMATCH_H +#define UNIMATCH_H + +#include "unicode/utypes.h" + +/** + * \file + * \brief C++ API: Unicode Matcher + */ + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +class Replaceable; +class UnicodeString; +class UnicodeSet; + +/** + * Constants returned by <code>UnicodeMatcher::matches()</code> + * indicating the degree of match. + * @stable ICU 2.4 + */ +enum UMatchDegree { + /** + * Constant returned by <code>matches()</code> indicating a + * mismatch between the text and this matcher. The text contains + * a character which does not match, or the text does not contain + * all desired characters for a non-incremental match. + * @stable ICU 2.4 + */ + U_MISMATCH, + + /** + * Constant returned by <code>matches()</code> indicating a + * partial match between the text and this matcher. This value is + * only returned for incremental match operations. All characters + * of the text match, but more characters are required for a + * complete match. Alternatively, for variable-length matchers, + * all characters of the text match, and if more characters were + * supplied at limit, they might also match. + * @stable ICU 2.4 + */ + U_PARTIAL_MATCH, + + /** + * Constant returned by <code>matches()</code> indicating a + * complete match between the text and this matcher. For an + * incremental variable-length match, this value is returned if + * the given text matches, and it is known that additional + * characters would not alter the extent of the match. + * @stable ICU 2.4 + */ + U_MATCH +}; + +/** + * <code>UnicodeMatcher</code> defines a protocol for objects that can + * match a range of characters in a Replaceable string. + * @stable ICU 2.4 + */ +class U_COMMON_API UnicodeMatcher /* not : public UObject because this is an interface/mixin class */ { + +public: + /** + * Destructor. + * @stable ICU 2.4 + */ + virtual ~UnicodeMatcher(); + + /** + * Return a UMatchDegree value indicating the degree of match for + * the given text at the given offset. Zero, one, or more + * characters may be matched. + * + * Matching in the forward direction is indicated by limit > + * offset. Characters from offset forwards to limit-1 will be + * considered for matching. + * + * Matching in the reverse direction is indicated by limit < + * offset. Characters from offset backwards to limit+1 will be + * considered for matching. + * + * If limit == offset then the only match possible is a zero + * character match (which subclasses may implement if desired). + * + * As a side effect, advance the offset parameter to the limit of + * the matched substring. In the forward direction, this will be + * the index of the last matched character plus one. In the + * reverse direction, this will be the index of the last matched + * character minus one. + * + * <p>Note: This method is not const because some classes may + * modify their state as the result of a match. + * + * @param text the text to be matched + * @param offset on input, the index into text at which to begin + * matching. On output, the limit of the matched text. The + * number of matched characters is the output value of offset + * minus the input value. Offset should always point to the + * HIGH SURROGATE (leading code unit) of a pair of surrogates, + * both on entry and upon return. + * @param limit the limit index of text to be matched. Greater + * than offset for a forward direction match, less than offset for + * a backward direction match. The last character to be + * considered for matching will be text.charAt(limit-1) in the + * forward direction or text.charAt(limit+1) in the backward + * direction. + * @param incremental if true, then assume further characters may + * be inserted at limit and check for partial matching. Otherwise + * assume the text as given is complete. + * @return a match degree value indicating a full match, a partial + * match, or a mismatch. If incremental is false then + * U_PARTIAL_MATCH should never be returned. + * @stable ICU 2.4 + */ + virtual UMatchDegree matches(const Replaceable& text, + int32_t& offset, + int32_t limit, + UBool incremental) = 0; + + /** + * Returns a string representation of this matcher. If the result of + * calling this function is passed to the appropriate parser, it + * will produce another matcher that is equal to this one. + * @param result the string to receive the pattern. Previous + * contents will be deleted. + * @param escapeUnprintable if true then convert unprintable + * character to their hex escape representations, \\uxxxx or + * \\Uxxxxxxxx. Unprintable characters are those other than + * U+000A, U+0020..U+007E. + * @stable ICU 2.4 + */ + virtual UnicodeString& toPattern(UnicodeString& result, + UBool escapeUnprintable = false) const = 0; + + /** + * Returns true if this matcher will match a character c, where c + * & 0xFF == v, at offset, in the forward direction (with limit > + * offset). This is used by <tt>RuleBasedTransliterator</tt> for + * indexing. + * @stable ICU 2.4 + */ + virtual UBool matchesIndexValue(uint8_t v) const = 0; + + /** + * Union the set of all characters that may be matched by this object + * into the given set. + * @param toUnionTo the set into which to union the source characters + * @stable ICU 2.4 + */ + virtual void addMatchSetTo(UnicodeSet& toUnionTo) const = 0; +}; + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/uniset.h b/thirdparty/icu4c/common/unicode/uniset.h new file mode 100644 index 0000000000..50b6360f3a --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uniset.h @@ -0,0 +1,1744 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +*************************************************************************** +* Copyright (C) 1999-2016, International Business Machines Corporation +* and others. All Rights Reserved. +*************************************************************************** +* Date Name Description +* 10/20/99 alan Creation. +*************************************************************************** +*/ + +#ifndef UNICODESET_H +#define UNICODESET_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/ucpmap.h" +#include "unicode/unifilt.h" +#include "unicode/unistr.h" +#include "unicode/uset.h" + +/** + * \file + * \brief C++ API: Unicode Set + */ + +U_NAMESPACE_BEGIN + +// Forward Declarations. +class BMPSet; +class ParsePosition; +class RBBIRuleScanner; +class SymbolTable; +class UnicodeSetStringSpan; +class UVector; +class RuleCharacterIterator; + +/** + * A mutable set of Unicode characters and multicharacter strings. Objects of this class + * represent <em>character classes</em> used in regular expressions. + * A character specifies a subset of Unicode code points. Legal + * code points are U+0000 to U+10FFFF, inclusive. + * + * <p>The UnicodeSet class is not designed to be subclassed. + * + * <p><code>UnicodeSet</code> supports two APIs. The first is the + * <em>operand</em> API that allows the caller to modify the value of + * a <code>UnicodeSet</code> object. It conforms to Java 2's + * <code>java.util.Set</code> interface, although + * <code>UnicodeSet</code> does not actually implement that + * interface. All methods of <code>Set</code> are supported, with the + * modification that they take a character range or single character + * instead of an <code>Object</code>, and they take a + * <code>UnicodeSet</code> instead of a <code>Collection</code>. The + * operand API may be thought of in terms of boolean logic: a boolean + * OR is implemented by <code>add</code>, a boolean AND is implemented + * by <code>retain</code>, a boolean XOR is implemented by + * <code>complement</code> taking an argument, and a boolean NOT is + * implemented by <code>complement</code> with no argument. In terms + * of traditional set theory function names, <code>add</code> is a + * union, <code>retain</code> is an intersection, <code>remove</code> + * is an asymmetric difference, and <code>complement</code> with no + * argument is a set complement with respect to the superset range + * <code>MIN_VALUE-MAX_VALUE</code> + * + * <p>The second API is the + * <code>applyPattern()</code>/<code>toPattern()</code> API from the + * <code>java.text.Format</code>-derived classes. Unlike the + * methods that add characters, add categories, and control the logic + * of the set, the method <code>applyPattern()</code> sets all + * attributes of a <code>UnicodeSet</code> at once, based on a + * string pattern. + * + * <p><b>Pattern syntax</b></p> + * + * Patterns are accepted by the constructors and the + * <code>applyPattern()</code> methods and returned by the + * <code>toPattern()</code> method. These patterns follow a syntax + * similar to that employed by version 8 regular expression character + * classes. Here are some simple examples: + * + * \htmlonly<blockquote>\endhtmlonly + * <table> + * <tr align="top"> + * <td nowrap valign="top" align="left"><code>[]</code></td> + * <td valign="top">No characters</td> + * </tr><tr align="top"> + * <td nowrap valign="top" align="left"><code>[a]</code></td> + * <td valign="top">The character 'a'</td> + * </tr><tr align="top"> + * <td nowrap valign="top" align="left"><code>[ae]</code></td> + * <td valign="top">The characters 'a' and 'e'</td> + * </tr> + * <tr> + * <td nowrap valign="top" align="left"><code>[a-e]</code></td> + * <td valign="top">The characters 'a' through 'e' inclusive, in Unicode code + * point order</td> + * </tr> + * <tr> + * <td nowrap valign="top" align="left"><code>[\\u4E01]</code></td> + * <td valign="top">The character U+4E01</td> + * </tr> + * <tr> + * <td nowrap valign="top" align="left"><code>[a{ab}{ac}]</code></td> + * <td valign="top">The character 'a' and the multicharacter strings "ab" and + * "ac"</td> + * </tr> + * <tr> + * <td nowrap valign="top" align="left"><code>[\\p{Lu}]</code></td> + * <td valign="top">All characters in the general category Uppercase Letter</td> + * </tr> + * </table> + * \htmlonly</blockquote>\endhtmlonly + * + * Any character may be preceded by a backslash in order to remove any special + * meaning. White space characters, as defined by UCharacter.isWhitespace(), are + * ignored, unless they are escaped. + * + * <p>Property patterns specify a set of characters having a certain + * property as defined by the Unicode standard. Both the POSIX-like + * "[:Lu:]" and the Perl-like syntax "\\p{Lu}" are recognized. For a + * complete list of supported property patterns, see the User's Guide + * for UnicodeSet at + * <a href="http://icu-project.org/userguide/unicodeSet.html"> + * http://icu-project.org/userguide/unicodeSet.html</a>. + * Actual determination of property data is defined by the underlying + * Unicode database as implemented by UCharacter. + * + * <p>Patterns specify individual characters, ranges of characters, and + * Unicode property sets. When elements are concatenated, they + * specify their union. To complement a set, place a '^' immediately + * after the opening '['. Property patterns are inverted by modifying + * their delimiters; "[:^foo]" and "\\P{foo}". In any other location, + * '^' has no special meaning. + * + * <p>Ranges are indicated by placing two a '-' between two + * characters, as in "a-z". This specifies the range of all + * characters from the left to the right, in Unicode order. If the + * left character is greater than or equal to the + * right character it is a syntax error. If a '-' occurs as the first + * character after the opening '[' or '[^', or if it occurs as the + * last character before the closing ']', then it is taken as a + * literal. Thus "[a\-b]", "[-ab]", and "[ab-]" all indicate the same + * set of three characters, 'a', 'b', and '-'. + * + * <p>Sets may be intersected using the '&' operator or the asymmetric + * set difference may be taken using the '-' operator, for example, + * "[[:L:]&[\\u0000-\\u0FFF]]" indicates the set of all Unicode letters + * with values less than 4096. Operators ('&' and '|') have equal + * precedence and bind left-to-right. Thus + * "[[:L:]-[a-z]-[\\u0100-\\u01FF]]" is equivalent to + * "[[[:L:]-[a-z]]-[\\u0100-\\u01FF]]". This only really matters for + * difference; intersection is commutative. + * + * <table> + * <tr valign=top><td nowrap><code>[a]</code><td>The set containing 'a' + * <tr valign=top><td nowrap><code>[a-z]</code><td>The set containing 'a' + * through 'z' and all letters in between, in Unicode order + * <tr valign=top><td nowrap><code>[^a-z]</code><td>The set containing + * all characters but 'a' through 'z', + * that is, U+0000 through 'a'-1 and 'z'+1 through U+10FFFF + * <tr valign=top><td nowrap><code>[[<em>pat1</em>][<em>pat2</em>]]</code> + * <td>The union of sets specified by <em>pat1</em> and <em>pat2</em> + * <tr valign=top><td nowrap><code>[[<em>pat1</em>]&[<em>pat2</em>]]</code> + * <td>The intersection of sets specified by <em>pat1</em> and <em>pat2</em> + * <tr valign=top><td nowrap><code>[[<em>pat1</em>]-[<em>pat2</em>]]</code> + * <td>The asymmetric difference of sets specified by <em>pat1</em> and + * <em>pat2</em> + * <tr valign=top><td nowrap><code>[:Lu:] or \\p{Lu}</code> + * <td>The set of characters having the specified + * Unicode property; in + * this case, Unicode uppercase letters + * <tr valign=top><td nowrap><code>[:^Lu:] or \\P{Lu}</code> + * <td>The set of characters <em>not</em> having the given + * Unicode property + * </table> + * + * <p><b>Warning</b>: you cannot add an empty string ("") to a UnicodeSet.</p> + * + * <p><b>Formal syntax</b></p> + * + * \htmlonly<blockquote>\endhtmlonly + * <table> + * <tr align="top"> + * <td nowrap valign="top" align="right"><code>pattern := </code></td> + * <td valign="top"><code>('[' '^'? item* ']') | + * property</code></td> + * </tr> + * <tr align="top"> + * <td nowrap valign="top" align="right"><code>item := </code></td> + * <td valign="top"><code>char | (char '-' char) | pattern-expr<br> + * </code></td> + * </tr> + * <tr align="top"> + * <td nowrap valign="top" align="right"><code>pattern-expr := </code></td> + * <td valign="top"><code>pattern | pattern-expr pattern | + * pattern-expr op pattern<br> + * </code></td> + * </tr> + * <tr align="top"> + * <td nowrap valign="top" align="right"><code>op := </code></td> + * <td valign="top"><code>'&' | '-'<br> + * </code></td> + * </tr> + * <tr align="top"> + * <td nowrap valign="top" align="right"><code>special := </code></td> + * <td valign="top"><code>'[' | ']' | '-'<br> + * </code></td> + * </tr> + * <tr align="top"> + * <td nowrap valign="top" align="right"><code>char := </code></td> + * <td valign="top"><em>any character that is not</em><code> special<br> + * | ('\' </code><em>any character</em><code>)<br> + * | ('\\u' hex hex hex hex)<br> + * </code></td> + * </tr> + * <tr align="top"> + * <td nowrap valign="top" align="right"><code>hex := </code></td> + * <td valign="top"><em>any character for which + * </em><code>Character.digit(c, 16)</code><em> + * returns a non-negative result</em></td> + * </tr> + * <tr> + * <td nowrap valign="top" align="right"><code>property := </code></td> + * <td valign="top"><em>a Unicode property set pattern</em></td> + * </tr> + * </table> + * <br> + * <table border="1"> + * <tr> + * <td>Legend: <table> + * <tr> + * <td nowrap valign="top"><code>a := b</code></td> + * <td width="20" valign="top"> </td> + * <td valign="top"><code>a</code> may be replaced by <code>b</code> </td> + * </tr> + * <tr> + * <td nowrap valign="top"><code>a?</code></td> + * <td valign="top"></td> + * <td valign="top">zero or one instance of <code>a</code><br> + * </td> + * </tr> + * <tr> + * <td nowrap valign="top"><code>a*</code></td> + * <td valign="top"></td> + * <td valign="top">one or more instances of <code>a</code><br> + * </td> + * </tr> + * <tr> + * <td nowrap valign="top"><code>a | b</code></td> + * <td valign="top"></td> + * <td valign="top">either <code>a</code> or <code>b</code><br> + * </td> + * </tr> + * <tr> + * <td nowrap valign="top"><code>'a'</code></td> + * <td valign="top"></td> + * <td valign="top">the literal string between the quotes </td> + * </tr> + * </table> + * </td> + * </tr> + * </table> + * \htmlonly</blockquote>\endhtmlonly + * + * <p>Note: + * - Most UnicodeSet methods do not take a UErrorCode parameter because + * there are usually very few opportunities for failure other than a shortage + * of memory, error codes in low-level C++ string methods would be inconvenient, + * and the error code as the last parameter (ICU convention) would prevent + * the use of default parameter values. + * Instead, such methods set the UnicodeSet into a "bogus" state + * (see isBogus()) if an error occurs. + * + * @author Alan Liu + * @stable ICU 2.0 + */ +class U_COMMON_API UnicodeSet U_FINAL : public UnicodeFilter { +private: + /** + * Enough for sets with few ranges. + * For example, White_Space has 10 ranges, list length 21. + */ + static constexpr int32_t INITIAL_CAPACITY = 25; + // fFlags constant + static constexpr uint8_t kIsBogus = 1; // This set is bogus (i.e. not valid) + + UChar32* list = stackList; // MUST be terminated with HIGH + int32_t capacity = INITIAL_CAPACITY; // capacity of list + int32_t len = 1; // length of list used; 1 <= len <= capacity + uint8_t fFlags = 0; // Bit flag (see constants above) + + BMPSet *bmpSet = nullptr; // The set is frozen iff either bmpSet or stringSpan is not NULL. + UChar32* buffer = nullptr; // internal buffer, may be NULL + int32_t bufferCapacity = 0; // capacity of buffer + + /** + * The pattern representation of this set. This may not be the + * most economical pattern. It is the pattern supplied to + * applyPattern(), with variables substituted and whitespace + * removed. For sets constructed without applyPattern(), or + * modified using the non-pattern API, this string will be empty, + * indicating that toPattern() must generate a pattern + * representation from the inversion list. + */ + char16_t *pat = nullptr; + int32_t patLen = 0; + + UVector* strings = nullptr; // maintained in sorted order + UnicodeSetStringSpan *stringSpan = nullptr; + + /** + * Initial list array. + * Avoids some heap allocations, and list is never nullptr. + * Increases the object size a bit. + */ + UChar32 stackList[INITIAL_CAPACITY]; + +public: + /** + * Determine if this object contains a valid set. + * A bogus set has no value. It is different from an empty set. + * It can be used to indicate that no set value is available. + * + * @return true if the set is bogus/invalid, false otherwise + * @see setToBogus() + * @stable ICU 4.0 + */ + inline UBool isBogus(void) const; + + /** + * Make this UnicodeSet object invalid. + * The string will test true with isBogus(). + * + * A bogus set has no value. It is different from an empty set. + * It can be used to indicate that no set value is available. + * + * This utility function is used throughout the UnicodeSet + * implementation to indicate that a UnicodeSet operation failed, + * and may be used in other functions, + * especially but not exclusively when such functions do not + * take a UErrorCode for simplicity. + * + * @see isBogus() + * @stable ICU 4.0 + */ + void setToBogus(); + +public: + + enum { + /** + * Minimum value that can be stored in a UnicodeSet. + * @stable ICU 2.4 + */ + MIN_VALUE = 0, + + /** + * Maximum value that can be stored in a UnicodeSet. + * @stable ICU 2.4 + */ + MAX_VALUE = 0x10ffff + }; + + //---------------------------------------------------------------- + // Constructors &c + //---------------------------------------------------------------- + +public: + + /** + * Constructs an empty set. + * @stable ICU 2.0 + */ + UnicodeSet(); + + /** + * Constructs a set containing the given range. If <code>end < + * start</code> then an empty set is created. + * + * @param start first character, inclusive, of range + * @param end last character, inclusive, of range + * @stable ICU 2.4 + */ + UnicodeSet(UChar32 start, UChar32 end); + +#ifndef U_HIDE_INTERNAL_API + /** + * @internal + */ + enum ESerialization { + kSerialized /* result of serialize() */ + }; + + /** + * Constructs a set from the output of serialize(). + * + * @param buffer the 16 bit array + * @param bufferLen the original length returned from serialize() + * @param serialization the value 'kSerialized' + * @param status error code + * + * @internal + */ + UnicodeSet(const uint16_t buffer[], int32_t bufferLen, + ESerialization serialization, UErrorCode &status); +#endif /* U_HIDE_INTERNAL_API */ + + /** + * Constructs a set from the given pattern. See the class + * description for the syntax of the pattern language. + * @param pattern a string specifying what characters are in the set + * @param status returns <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern + * contains a syntax error. + * @stable ICU 2.0 + */ + UnicodeSet(const UnicodeString& pattern, + UErrorCode& status); + +#ifndef U_HIDE_INTERNAL_API + /** + * Constructs a set from the given pattern. See the class + * description for the syntax of the pattern language. + * @param pattern a string specifying what characters are in the set + * @param options bitmask for options to apply to the pattern. + * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE. + * @param symbols a symbol table mapping variable names to values + * and stand-in characters to UnicodeSets; may be NULL + * @param status returns <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern + * contains a syntax error. + * @internal + */ + UnicodeSet(const UnicodeString& pattern, + uint32_t options, + const SymbolTable* symbols, + UErrorCode& status); +#endif /* U_HIDE_INTERNAL_API */ + + /** + * Constructs a set from the given pattern. See the class description + * for the syntax of the pattern language. + * @param pattern a string specifying what characters are in the set + * @param pos on input, the position in pattern at which to start parsing. + * On output, the position after the last character parsed. + * @param options bitmask for options to apply to the pattern. + * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE. + * @param symbols a symbol table mapping variable names to values + * and stand-in characters to UnicodeSets; may be NULL + * @param status input-output error code + * @stable ICU 2.8 + */ + UnicodeSet(const UnicodeString& pattern, ParsePosition& pos, + uint32_t options, + const SymbolTable* symbols, + UErrorCode& status); + + /** + * Constructs a set that is identical to the given UnicodeSet. + * @stable ICU 2.0 + */ + UnicodeSet(const UnicodeSet& o); + + /** + * Destructs the set. + * @stable ICU 2.0 + */ + virtual ~UnicodeSet(); + + /** + * Assigns this object to be a copy of another. + * A frozen set will not be modified. + * @stable ICU 2.0 + */ + UnicodeSet& operator=(const UnicodeSet& o); + + /** + * Compares the specified object with this set for equality. Returns + * <tt>true</tt> if the two sets + * have the same size, and every member of the specified set is + * contained in this set (or equivalently, every member of this set is + * contained in the specified set). + * + * @param o set to be compared for equality with this set. + * @return <tt>true</tt> if the specified set is equal to this set. + * @stable ICU 2.0 + */ + virtual UBool operator==(const UnicodeSet& o) const; + + /** + * Compares the specified object with this set for equality. Returns + * <tt>true</tt> if the specified set is not equal to this set. + * @stable ICU 2.0 + */ + inline UBool operator!=(const UnicodeSet& o) const; + + /** + * Returns a copy of this object. All UnicodeFunctor objects have + * to support cloning in order to allow classes using + * UnicodeFunctors, such as Transliterator, to implement cloning. + * If this set is frozen, then the clone will be frozen as well. + * Use cloneAsThawed() for a mutable clone of a frozen set. + * @see cloneAsThawed + * @stable ICU 2.0 + */ + virtual UnicodeSet* clone() const; + + /** + * Returns the hash code value for this set. + * + * @return the hash code value for this set. + * @see Object#hashCode() + * @stable ICU 2.0 + */ + virtual int32_t hashCode(void) const; + + /** + * Get a UnicodeSet pointer from a USet + * + * @param uset a USet (the ICU plain C type for UnicodeSet) + * @return the corresponding UnicodeSet pointer. + * + * @stable ICU 4.2 + */ + inline static UnicodeSet *fromUSet(USet *uset); + + /** + * Get a UnicodeSet pointer from a const USet + * + * @param uset a const USet (the ICU plain C type for UnicodeSet) + * @return the corresponding UnicodeSet pointer. + * + * @stable ICU 4.2 + */ + inline static const UnicodeSet *fromUSet(const USet *uset); + + /** + * Produce a USet * pointer for this UnicodeSet. + * USet is the plain C type for UnicodeSet + * + * @return a USet pointer for this UnicodeSet + * @stable ICU 4.2 + */ + inline USet *toUSet(); + + + /** + * Produce a const USet * pointer for this UnicodeSet. + * USet is the plain C type for UnicodeSet + * + * @return a const USet pointer for this UnicodeSet + * @stable ICU 4.2 + */ + inline const USet * toUSet() const; + + + //---------------------------------------------------------------- + // Freezable API + //---------------------------------------------------------------- + + /** + * Determines whether the set has been frozen (made immutable) or not. + * See the ICU4J Freezable interface for details. + * @return true/false for whether the set has been frozen + * @see freeze + * @see cloneAsThawed + * @stable ICU 3.8 + */ + inline UBool isFrozen() const; + + /** + * Freeze the set (make it immutable). + * Once frozen, it cannot be unfrozen and is therefore thread-safe + * until it is deleted. + * See the ICU4J Freezable interface for details. + * Freezing the set may also make some operations faster, for example + * contains() and span(). + * A frozen set will not be modified. (It remains frozen.) + * @return this set. + * @see isFrozen + * @see cloneAsThawed + * @stable ICU 3.8 + */ + UnicodeSet *freeze(); + + /** + * Clone the set and make the clone mutable. + * See the ICU4J Freezable interface for details. + * @return the mutable clone + * @see freeze + * @see isFrozen + * @stable ICU 3.8 + */ + UnicodeSet *cloneAsThawed() const; + + //---------------------------------------------------------------- + // Public API + //---------------------------------------------------------------- + + /** + * Make this object represent the range `start - end`. + * If `end > start` then this object is set to an empty range. + * A frozen set will not be modified. + * + * @param start first character in the set, inclusive + * @param end last character in the set, inclusive + * @stable ICU 2.4 + */ + UnicodeSet& set(UChar32 start, UChar32 end); + + /** + * Return true if the given position, in the given pattern, appears + * to be the start of a UnicodeSet pattern. + * @stable ICU 2.4 + */ + static UBool resemblesPattern(const UnicodeString& pattern, + int32_t pos); + + /** + * Modifies this set to represent the set specified by the given + * pattern, ignoring Unicode Pattern_White_Space characters. + * See the class description for the syntax of the pattern language. + * A frozen set will not be modified. + * @param pattern a string specifying what characters are in the set + * @param status returns <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern + * contains a syntax error. + * <em> Empties the set passed before applying the pattern.</em> + * @return a reference to this + * @stable ICU 2.0 + */ + UnicodeSet& applyPattern(const UnicodeString& pattern, + UErrorCode& status); + +#ifndef U_HIDE_INTERNAL_API + /** + * Modifies this set to represent the set specified by the given + * pattern, optionally ignoring Unicode Pattern_White_Space characters. + * See the class description for the syntax of the pattern language. + * A frozen set will not be modified. + * @param pattern a string specifying what characters are in the set + * @param options bitmask for options to apply to the pattern. + * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE. + * @param symbols a symbol table mapping variable names to + * values and stand-ins to UnicodeSets; may be NULL + * @param status returns <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern + * contains a syntax error. + *<em> Empties the set passed before applying the pattern.</em> + * @return a reference to this + * @internal + */ + UnicodeSet& applyPattern(const UnicodeString& pattern, + uint32_t options, + const SymbolTable* symbols, + UErrorCode& status); +#endif /* U_HIDE_INTERNAL_API */ + + /** + * Parses the given pattern, starting at the given position. The + * character at pattern.charAt(pos.getIndex()) must be '[', or the + * parse fails. Parsing continues until the corresponding closing + * ']'. If a syntax error is encountered between the opening and + * closing brace, the parse fails. Upon return from a successful + * parse, the ParsePosition is updated to point to the character + * following the closing ']', and a StringBuffer containing a + * pairs list for the parsed pattern is returned. This method calls + * itself recursively to parse embedded subpatterns. + *<em> Empties the set passed before applying the pattern.</em> + * A frozen set will not be modified. + * + * @param pattern the string containing the pattern to be parsed. + * The portion of the string from pos.getIndex(), which must be a + * '[', to the corresponding closing ']', is parsed. + * @param pos upon entry, the position at which to being parsing. + * The character at pattern.charAt(pos.getIndex()) must be a '['. + * Upon return from a successful parse, pos.getIndex() is either + * the character after the closing ']' of the parsed pattern, or + * pattern.length() if the closing ']' is the last character of + * the pattern string. + * @param options bitmask for options to apply to the pattern. + * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE. + * @param symbols a symbol table mapping variable names to + * values and stand-ins to UnicodeSets; may be NULL + * @param status returns <code>U_ILLEGAL_ARGUMENT_ERROR</code> if the pattern + * contains a syntax error. + * @return a reference to this + * @stable ICU 2.8 + */ + UnicodeSet& applyPattern(const UnicodeString& pattern, + ParsePosition& pos, + uint32_t options, + const SymbolTable* symbols, + UErrorCode& status); + + /** + * Returns a string representation of this set. If the result of + * calling this function is passed to a UnicodeSet constructor, it + * will produce another set that is equal to this one. + * A frozen set will not be modified. + * @param result the string to receive the rules. Previous + * contents will be deleted. + * @param escapeUnprintable if true then convert unprintable + * character to their hex escape representations, \\uxxxx or + * \\Uxxxxxxxx. Unprintable characters are those other than + * U+000A, U+0020..U+007E. + * @stable ICU 2.0 + */ + virtual UnicodeString& toPattern(UnicodeString& result, + UBool escapeUnprintable = false) const; + + /** + * Modifies this set to contain those code points which have the given value + * for the given binary or enumerated property, as returned by + * u_getIntPropertyValue. Prior contents of this set are lost. + * A frozen set will not be modified. + * + * @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1 + * or UCHAR_INT_START..UCHAR_INT_LIMIT-1 + * or UCHAR_MASK_START..UCHAR_MASK_LIMIT-1. + * + * @param value a value in the range u_getIntPropertyMinValue(prop).. + * u_getIntPropertyMaxValue(prop), with one exception. If prop is + * UCHAR_GENERAL_CATEGORY_MASK, then value should not be a UCharCategory, but + * rather a mask value produced by U_GET_GC_MASK(). This allows grouped + * categories such as [:L:] to be represented. + * + * @param ec error code input/output parameter + * + * @return a reference to this set + * + * @stable ICU 2.4 + */ + UnicodeSet& applyIntPropertyValue(UProperty prop, + int32_t value, + UErrorCode& ec); + + /** + * Modifies this set to contain those code points which have the + * given value for the given property. Prior contents of this + * set are lost. + * A frozen set will not be modified. + * + * @param prop a property alias, either short or long. The name is matched + * loosely. See PropertyAliases.txt for names and a description of loose + * matching. If the value string is empty, then this string is interpreted + * as either a General_Category value alias, a Script value alias, a binary + * property alias, or a special ID. Special IDs are matched loosely and + * correspond to the following sets: + * + * "ANY" = [\\u0000-\\U0010FFFF], + * "ASCII" = [\\u0000-\\u007F], + * "Assigned" = [:^Cn:]. + * + * @param value a value alias, either short or long. The name is matched + * loosely. See PropertyValueAliases.txt for names and a description of + * loose matching. In addition to aliases listed, numeric values and + * canonical combining classes may be expressed numerically, e.g., ("nv", + * "0.5") or ("ccc", "220"). The value string may also be empty. + * + * @param ec error code input/output parameter + * + * @return a reference to this set + * + * @stable ICU 2.4 + */ + UnicodeSet& applyPropertyAlias(const UnicodeString& prop, + const UnicodeString& value, + UErrorCode& ec); + + /** + * Returns the number of elements in this set (its cardinality). + * Note than the elements of a set may include both individual + * codepoints and strings. + * + * @return the number of elements in this set (its cardinality). + * @stable ICU 2.0 + */ + virtual int32_t size(void) const; + + /** + * Returns <tt>true</tt> if this set contains no elements. + * + * @return <tt>true</tt> if this set contains no elements. + * @stable ICU 2.0 + */ + virtual UBool isEmpty(void) const; + + /** + * Returns true if this set contains the given character. + * This function works faster with a frozen set. + * @param c character to be checked for containment + * @return true if the test condition is met + * @stable ICU 2.0 + */ + virtual UBool contains(UChar32 c) const; + + /** + * Returns true if this set contains every character + * of the given range. + * @param start first character, inclusive, of the range + * @param end last character, inclusive, of the range + * @return true if the test condition is met + * @stable ICU 2.0 + */ + virtual UBool contains(UChar32 start, UChar32 end) const; + + /** + * Returns <tt>true</tt> if this set contains the given + * multicharacter string. + * @param s string to be checked for containment + * @return <tt>true</tt> if this set contains the specified string + * @stable ICU 2.4 + */ + UBool contains(const UnicodeString& s) const; + + /** + * Returns true if this set contains all the characters and strings + * of the given set. + * @param c set to be checked for containment + * @return true if the test condition is met + * @stable ICU 2.4 + */ + virtual UBool containsAll(const UnicodeSet& c) const; + + /** + * Returns true if this set contains all the characters + * of the given string. + * @param s string containing characters to be checked for containment + * @return true if the test condition is met + * @stable ICU 2.4 + */ + UBool containsAll(const UnicodeString& s) const; + + /** + * Returns true if this set contains none of the characters + * of the given range. + * @param start first character, inclusive, of the range + * @param end last character, inclusive, of the range + * @return true if the test condition is met + * @stable ICU 2.4 + */ + UBool containsNone(UChar32 start, UChar32 end) const; + + /** + * Returns true if this set contains none of the characters and strings + * of the given set. + * @param c set to be checked for containment + * @return true if the test condition is met + * @stable ICU 2.4 + */ + UBool containsNone(const UnicodeSet& c) const; + + /** + * Returns true if this set contains none of the characters + * of the given string. + * @param s string containing characters to be checked for containment + * @return true if the test condition is met + * @stable ICU 2.4 + */ + UBool containsNone(const UnicodeString& s) const; + + /** + * Returns true if this set contains one or more of the characters + * in the given range. + * @param start first character, inclusive, of the range + * @param end last character, inclusive, of the range + * @return true if the condition is met + * @stable ICU 2.4 + */ + inline UBool containsSome(UChar32 start, UChar32 end) const; + + /** + * Returns true if this set contains one or more of the characters + * and strings of the given set. + * @param s The set to be checked for containment + * @return true if the condition is met + * @stable ICU 2.4 + */ + inline UBool containsSome(const UnicodeSet& s) const; + + /** + * Returns true if this set contains one or more of the characters + * of the given string. + * @param s string containing characters to be checked for containment + * @return true if the condition is met + * @stable ICU 2.4 + */ + inline UBool containsSome(const UnicodeString& s) const; + + /** + * Returns the length of the initial substring of the input string which + * consists only of characters and strings that are contained in this set + * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), + * or only of characters and strings that are not contained + * in this set (USET_SPAN_NOT_CONTAINED). + * See USetSpanCondition for details. + * Similar to the strspn() C library function. + * Unpaired surrogates are treated according to contains() of their surrogate code points. + * This function works faster with a frozen set and with a non-negative string length argument. + * @param s start of the string + * @param length of the string; can be -1 for NUL-terminated + * @param spanCondition specifies the containment condition + * @return the length of the initial substring according to the spanCondition; + * 0 if the start of the string does not fit the spanCondition + * @stable ICU 3.8 + * @see USetSpanCondition + */ + int32_t span(const char16_t *s, int32_t length, USetSpanCondition spanCondition) const; + + /** + * Returns the end of the substring of the input string according to the USetSpanCondition. + * Same as <code>start+span(s.getBuffer()+start, s.length()-start, spanCondition)</code> + * after pinning start to 0<=start<=s.length(). + * @param s the string + * @param start the start index in the string for the span operation + * @param spanCondition specifies the containment condition + * @return the exclusive end of the substring according to the spanCondition; + * the substring s.tempSubStringBetween(start, end) fulfills the spanCondition + * @stable ICU 4.4 + * @see USetSpanCondition + */ + inline int32_t span(const UnicodeString &s, int32_t start, USetSpanCondition spanCondition) const; + + /** + * Returns the start of the trailing substring of the input string which + * consists only of characters and strings that are contained in this set + * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), + * or only of characters and strings that are not contained + * in this set (USET_SPAN_NOT_CONTAINED). + * See USetSpanCondition for details. + * Unpaired surrogates are treated according to contains() of their surrogate code points. + * This function works faster with a frozen set and with a non-negative string length argument. + * @param s start of the string + * @param length of the string; can be -1 for NUL-terminated + * @param spanCondition specifies the containment condition + * @return the start of the trailing substring according to the spanCondition; + * the string length if the end of the string does not fit the spanCondition + * @stable ICU 3.8 + * @see USetSpanCondition + */ + int32_t spanBack(const char16_t *s, int32_t length, USetSpanCondition spanCondition) const; + + /** + * Returns the start of the substring of the input string according to the USetSpanCondition. + * Same as <code>spanBack(s.getBuffer(), limit, spanCondition)</code> + * after pinning limit to 0<=end<=s.length(). + * @param s the string + * @param limit the exclusive-end index in the string for the span operation + * (use s.length() or INT32_MAX for spanning back from the end of the string) + * @param spanCondition specifies the containment condition + * @return the start of the substring according to the spanCondition; + * the substring s.tempSubStringBetween(start, limit) fulfills the spanCondition + * @stable ICU 4.4 + * @see USetSpanCondition + */ + inline int32_t spanBack(const UnicodeString &s, int32_t limit, USetSpanCondition spanCondition) const; + + /** + * Returns the length of the initial substring of the input string which + * consists only of characters and strings that are contained in this set + * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), + * or only of characters and strings that are not contained + * in this set (USET_SPAN_NOT_CONTAINED). + * See USetSpanCondition for details. + * Similar to the strspn() C library function. + * Malformed byte sequences are treated according to contains(0xfffd). + * This function works faster with a frozen set and with a non-negative string length argument. + * @param s start of the string (UTF-8) + * @param length of the string; can be -1 for NUL-terminated + * @param spanCondition specifies the containment condition + * @return the length of the initial substring according to the spanCondition; + * 0 if the start of the string does not fit the spanCondition + * @stable ICU 3.8 + * @see USetSpanCondition + */ + int32_t spanUTF8(const char *s, int32_t length, USetSpanCondition spanCondition) const; + + /** + * Returns the start of the trailing substring of the input string which + * consists only of characters and strings that are contained in this set + * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), + * or only of characters and strings that are not contained + * in this set (USET_SPAN_NOT_CONTAINED). + * See USetSpanCondition for details. + * Malformed byte sequences are treated according to contains(0xfffd). + * This function works faster with a frozen set and with a non-negative string length argument. + * @param s start of the string (UTF-8) + * @param length of the string; can be -1 for NUL-terminated + * @param spanCondition specifies the containment condition + * @return the start of the trailing substring according to the spanCondition; + * the string length if the end of the string does not fit the spanCondition + * @stable ICU 3.8 + * @see USetSpanCondition + */ + int32_t spanBackUTF8(const char *s, int32_t length, USetSpanCondition spanCondition) const; + + /** + * Implement UnicodeMatcher::matches() + * @stable ICU 2.4 + */ + virtual UMatchDegree matches(const Replaceable& text, + int32_t& offset, + int32_t limit, + UBool incremental); + +private: + /** + * Returns the longest match for s in text at the given position. + * If limit > start then match forward from start+1 to limit + * matching all characters except s.charAt(0). If limit < start, + * go backward starting from start-1 matching all characters + * except s.charAt(s.length()-1). This method assumes that the + * first character, text.charAt(start), matches s, so it does not + * check it. + * @param text the text to match + * @param start the first character to match. In the forward + * direction, text.charAt(start) is matched against s.charAt(0). + * In the reverse direction, it is matched against + * s.charAt(s.length()-1). + * @param limit the limit offset for matching, either last+1 in + * the forward direction, or last-1 in the reverse direction, + * where last is the index of the last character to match. + * @param s + * @return If part of s matches up to the limit, return |limit - + * start|. If all of s matches before reaching the limit, return + * s.length(). If there is a mismatch between s and text, return + * 0 + */ + static int32_t matchRest(const Replaceable& text, + int32_t start, int32_t limit, + const UnicodeString& s); + + /** + * Returns the smallest value i such that c < list[i]. Caller + * must ensure that c is a legal value or this method will enter + * an infinite loop. This method performs a binary search. + * @param c a character in the range MIN_VALUE..MAX_VALUE + * inclusive + * @return the smallest integer i in the range 0..len-1, + * inclusive, such that c < list[i] + */ + int32_t findCodePoint(UChar32 c) const; + +public: + + /** + * Implementation of UnicodeMatcher API. Union the set of all + * characters that may be matched by this object into the given + * set. + * @param toUnionTo the set into which to union the source characters + * @stable ICU 2.4 + */ + virtual void addMatchSetTo(UnicodeSet& toUnionTo) const; + + /** + * Returns the index of the given character within this set, where + * the set is ordered by ascending code point. If the character + * is not in this set, return -1. The inverse of this method is + * <code>charAt()</code>. + * @return an index from 0..size()-1, or -1 + * @stable ICU 2.4 + */ + int32_t indexOf(UChar32 c) const; + + /** + * Returns the character at the given index within this set, where + * the set is ordered by ascending code point. If the index is + * out of range, return (UChar32)-1. The inverse of this method is + * <code>indexOf()</code>. + * @param index an index from 0..size()-1 + * @return the character at the given index, or (UChar32)-1. + * @stable ICU 2.4 + */ + UChar32 charAt(int32_t index) const; + + /** + * Adds the specified range to this set if it is not already + * present. If this set already contains the specified range, + * the call leaves this set unchanged. If <code>end > start</code> + * then an empty range is added, leaving the set unchanged. + * This is equivalent to a boolean logic OR, or a set UNION. + * A frozen set will not be modified. + * + * @param start first character, inclusive, of range to be added + * to this set. + * @param end last character, inclusive, of range to be added + * to this set. + * @stable ICU 2.0 + */ + virtual UnicodeSet& add(UChar32 start, UChar32 end); + + /** + * Adds the specified character to this set if it is not already + * present. If this set already contains the specified character, + * the call leaves this set unchanged. + * A frozen set will not be modified. + * @stable ICU 2.0 + */ + UnicodeSet& add(UChar32 c); + + /** + * Adds the specified multicharacter to this set if it is not already + * present. If this set already contains the multicharacter, + * the call leaves this set unchanged. + * Thus "ch" => {"ch"} + * <br><b>Warning: you cannot add an empty string ("") to a UnicodeSet.</b> + * A frozen set will not be modified. + * @param s the source string + * @return this object, for chaining + * @stable ICU 2.4 + */ + UnicodeSet& add(const UnicodeString& s); + + private: + /** + * @return a code point IF the string consists of a single one. + * otherwise returns -1. + * @param s string to test + */ + static int32_t getSingleCP(const UnicodeString& s); + + void _add(const UnicodeString& s); + + public: + /** + * Adds each of the characters in this string to the set. Thus "ch" => {"c", "h"} + * If this set already any particular character, it has no effect on that character. + * A frozen set will not be modified. + * @param s the source string + * @return this object, for chaining + * @stable ICU 2.4 + */ + UnicodeSet& addAll(const UnicodeString& s); + + /** + * Retains EACH of the characters in this string. Note: "ch" == {"c", "h"} + * If this set already any particular character, it has no effect on that character. + * A frozen set will not be modified. + * @param s the source string + * @return this object, for chaining + * @stable ICU 2.4 + */ + UnicodeSet& retainAll(const UnicodeString& s); + + /** + * Complement EACH of the characters in this string. Note: "ch" == {"c", "h"} + * If this set already any particular character, it has no effect on that character. + * A frozen set will not be modified. + * @param s the source string + * @return this object, for chaining + * @stable ICU 2.4 + */ + UnicodeSet& complementAll(const UnicodeString& s); + + /** + * Remove EACH of the characters in this string. Note: "ch" == {"c", "h"} + * If this set already any particular character, it has no effect on that character. + * A frozen set will not be modified. + * @param s the source string + * @return this object, for chaining + * @stable ICU 2.4 + */ + UnicodeSet& removeAll(const UnicodeString& s); + + /** + * Makes a set from a multicharacter string. Thus "ch" => {"ch"} + * <br><b>Warning: you cannot add an empty string ("") to a UnicodeSet.</b> + * @param s the source string + * @return a newly created set containing the given string. + * The caller owns the return object and is responsible for deleting it. + * @stable ICU 2.4 + */ + static UnicodeSet* U_EXPORT2 createFrom(const UnicodeString& s); + + + /** + * Makes a set from each of the characters in the string. Thus "ch" => {"c", "h"} + * @param s the source string + * @return a newly created set containing the given characters + * The caller owns the return object and is responsible for deleting it. + * @stable ICU 2.4 + */ + static UnicodeSet* U_EXPORT2 createFromAll(const UnicodeString& s); + + /** + * Retain only the elements in this set that are contained in the + * specified range. If <code>end > start</code> then an empty range is + * retained, leaving the set empty. This is equivalent to + * a boolean logic AND, or a set INTERSECTION. + * A frozen set will not be modified. + * + * @param start first character, inclusive, of range to be retained + * to this set. + * @param end last character, inclusive, of range to be retained + * to this set. + * @stable ICU 2.0 + */ + virtual UnicodeSet& retain(UChar32 start, UChar32 end); + + + /** + * Retain the specified character from this set if it is present. + * A frozen set will not be modified. + * @stable ICU 2.0 + */ + UnicodeSet& retain(UChar32 c); + + /** + * Removes the specified range from this set if it is present. + * The set will not contain the specified range once the call + * returns. If <code>end > start</code> then an empty range is + * removed, leaving the set unchanged. + * A frozen set will not be modified. + * + * @param start first character, inclusive, of range to be removed + * from this set. + * @param end last character, inclusive, of range to be removed + * from this set. + * @stable ICU 2.0 + */ + virtual UnicodeSet& remove(UChar32 start, UChar32 end); + + /** + * Removes the specified character from this set if it is present. + * The set will not contain the specified range once the call + * returns. + * A frozen set will not be modified. + * @stable ICU 2.0 + */ + UnicodeSet& remove(UChar32 c); + + /** + * Removes the specified string from this set if it is present. + * The set will not contain the specified character once the call + * returns. + * A frozen set will not be modified. + * @param s the source string + * @return this object, for chaining + * @stable ICU 2.4 + */ + UnicodeSet& remove(const UnicodeString& s); + + /** + * Inverts this set. This operation modifies this set so that + * its value is its complement. This is equivalent to + * <code>complement(MIN_VALUE, MAX_VALUE)</code>. + * A frozen set will not be modified. + * @stable ICU 2.0 + */ + virtual UnicodeSet& complement(void); + + /** + * Complements the specified range in this set. Any character in + * the range will be removed if it is in this set, or will be + * added if it is not in this set. If <code>end > start</code> + * then an empty range is complemented, leaving the set unchanged. + * This is equivalent to a boolean logic XOR. + * A frozen set will not be modified. + * + * @param start first character, inclusive, of range to be removed + * from this set. + * @param end last character, inclusive, of range to be removed + * from this set. + * @stable ICU 2.0 + */ + virtual UnicodeSet& complement(UChar32 start, UChar32 end); + + /** + * Complements the specified character in this set. The character + * will be removed if it is in this set, or will be added if it is + * not in this set. + * A frozen set will not be modified. + * @stable ICU 2.0 + */ + UnicodeSet& complement(UChar32 c); + + /** + * Complement the specified string in this set. + * The set will not contain the specified string once the call + * returns. + * <br><b>Warning: you cannot add an empty string ("") to a UnicodeSet.</b> + * A frozen set will not be modified. + * @param s the string to complement + * @return this object, for chaining + * @stable ICU 2.4 + */ + UnicodeSet& complement(const UnicodeString& s); + + /** + * Adds all of the elements in the specified set to this set if + * they're not already present. This operation effectively + * modifies this set so that its value is the <i>union</i> of the two + * sets. The behavior of this operation is unspecified if the specified + * collection is modified while the operation is in progress. + * A frozen set will not be modified. + * + * @param c set whose elements are to be added to this set. + * @see #add(UChar32, UChar32) + * @stable ICU 2.0 + */ + virtual UnicodeSet& addAll(const UnicodeSet& c); + + /** + * Retains only the elements in this set that are contained in the + * specified set. In other words, removes from this set all of + * its elements that are not contained in the specified set. This + * operation effectively modifies this set so that its value is + * the <i>intersection</i> of the two sets. + * A frozen set will not be modified. + * + * @param c set that defines which elements this set will retain. + * @stable ICU 2.0 + */ + virtual UnicodeSet& retainAll(const UnicodeSet& c); + + /** + * Removes from this set all of its elements that are contained in the + * specified set. This operation effectively modifies this + * set so that its value is the <i>asymmetric set difference</i> of + * the two sets. + * A frozen set will not be modified. + * + * @param c set that defines which elements will be removed from + * this set. + * @stable ICU 2.0 + */ + virtual UnicodeSet& removeAll(const UnicodeSet& c); + + /** + * Complements in this set all elements contained in the specified + * set. Any character in the other set will be removed if it is + * in this set, or will be added if it is not in this set. + * A frozen set will not be modified. + * + * @param c set that defines which elements will be xor'ed from + * this set. + * @stable ICU 2.4 + */ + virtual UnicodeSet& complementAll(const UnicodeSet& c); + + /** + * Removes all of the elements from this set. This set will be + * empty after this call returns. + * A frozen set will not be modified. + * @stable ICU 2.0 + */ + virtual UnicodeSet& clear(void); + + /** + * Close this set over the given attribute. For the attribute + * USET_CASE, the result is to modify this set so that: + * + * 1. For each character or string 'a' in this set, all strings or + * characters 'b' such that foldCase(a) == foldCase(b) are added + * to this set. + * + * 2. For each string 'e' in the resulting set, if e != + * foldCase(e), 'e' will be removed. + * + * Example: [aq\\u00DF{Bc}{bC}{Fi}] => [aAqQ\\u00DF\\uFB01{ss}{bc}{fi}] + * + * (Here foldCase(x) refers to the operation u_strFoldCase, and a + * == b denotes that the contents are the same, not pointer + * comparison.) + * + * A frozen set will not be modified. + * + * @param attribute bitmask for attributes to close over. + * Currently only the USET_CASE bit is supported. Any undefined bits + * are ignored. + * @return a reference to this set. + * @stable ICU 4.2 + */ + UnicodeSet& closeOver(int32_t attribute); + + /** + * Remove all strings from this set. + * + * @return a reference to this set. + * @stable ICU 4.2 + */ + virtual UnicodeSet &removeAllStrings(); + + /** + * Iteration method that returns the number of ranges contained in + * this set. + * @see #getRangeStart + * @see #getRangeEnd + * @stable ICU 2.4 + */ + virtual int32_t getRangeCount(void) const; + + /** + * Iteration method that returns the first character in the + * specified range of this set. + * @see #getRangeCount + * @see #getRangeEnd + * @stable ICU 2.4 + */ + virtual UChar32 getRangeStart(int32_t index) const; + + /** + * Iteration method that returns the last character in the + * specified range of this set. + * @see #getRangeStart + * @see #getRangeEnd + * @stable ICU 2.4 + */ + virtual UChar32 getRangeEnd(int32_t index) const; + + /** + * Serializes this set into an array of 16-bit integers. Serialization + * (currently) only records the characters in the set; multicharacter + * strings are ignored. + * + * The array has following format (each line is one 16-bit + * integer): + * + * length = (n+2*m) | (m!=0?0x8000:0) + * bmpLength = n; present if m!=0 + * bmp[0] + * bmp[1] + * ... + * bmp[n-1] + * supp-high[0] + * supp-low[0] + * supp-high[1] + * supp-low[1] + * ... + * supp-high[m-1] + * supp-low[m-1] + * + * The array starts with a header. After the header are n bmp + * code points, then m supplementary code points. Either n or m + * or both may be zero. n+2*m is always <= 0x7FFF. + * + * If there are no supplementary characters (if m==0) then the + * header is one 16-bit integer, 'length', with value n. + * + * If there are supplementary characters (if m!=0) then the header + * is two 16-bit integers. The first, 'length', has value + * (n+2*m)|0x8000. The second, 'bmpLength', has value n. + * + * After the header the code points are stored in ascending order. + * Supplementary code points are stored as most significant 16 + * bits followed by least significant 16 bits. + * + * @param dest pointer to buffer of destCapacity 16-bit integers. + * May be NULL only if destCapacity is zero. + * @param destCapacity size of dest, or zero. Must not be negative. + * @param ec error code. Will be set to U_INDEX_OUTOFBOUNDS_ERROR + * if n+2*m > 0x7FFF. Will be set to U_BUFFER_OVERFLOW_ERROR if + * n+2*m+(m!=0?2:1) > destCapacity. + * @return the total length of the serialized format, including + * the header, that is, n+2*m+(m!=0?2:1), or 0 on error other + * than U_BUFFER_OVERFLOW_ERROR. + * @stable ICU 2.4 + */ + int32_t serialize(uint16_t *dest, int32_t destCapacity, UErrorCode& ec) const; + + /** + * Reallocate this objects internal structures to take up the least + * possible space, without changing this object's value. + * A frozen set will not be modified. + * @stable ICU 2.4 + */ + virtual UnicodeSet& compact(); + + /** + * Return the class ID for this class. This is useful only for + * comparing to a return value from getDynamicClassID(). For example: + * <pre> + * . Base* polymorphic_pointer = createPolymorphicObject(); + * . if (polymorphic_pointer->getDynamicClassID() == + * . Derived::getStaticClassID()) ... + * </pre> + * @return The class ID for all objects of this class. + * @stable ICU 2.0 + */ + static UClassID U_EXPORT2 getStaticClassID(void); + + /** + * Implement UnicodeFunctor API. + * + * @return The class ID for this object. All objects of a given + * class have the same class ID. Objects of other classes have + * different class IDs. + * @stable ICU 2.4 + */ + virtual UClassID getDynamicClassID(void) const; + +private: + + // Private API for the USet API + + friend class USetAccess; + + const UnicodeString* getString(int32_t index) const; + + //---------------------------------------------------------------- + // RuleBasedTransliterator support + //---------------------------------------------------------------- + +private: + + /** + * Returns <tt>true</tt> if this set contains any character whose low byte + * is the given value. This is used by <tt>RuleBasedTransliterator</tt> for + * indexing. + */ + virtual UBool matchesIndexValue(uint8_t v) const; + +private: + friend class RBBIRuleScanner; + + //---------------------------------------------------------------- + // Implementation: Clone as thawed (see ICU4J Freezable) + //---------------------------------------------------------------- + + UnicodeSet(const UnicodeSet& o, UBool /* asThawed */); + UnicodeSet& copyFrom(const UnicodeSet& o, UBool asThawed); + + //---------------------------------------------------------------- + // Implementation: Pattern parsing + //---------------------------------------------------------------- + + void applyPatternIgnoreSpace(const UnicodeString& pattern, + ParsePosition& pos, + const SymbolTable* symbols, + UErrorCode& status); + + void applyPattern(RuleCharacterIterator& chars, + const SymbolTable* symbols, + UnicodeString& rebuiltPat, + uint32_t options, + UnicodeSet& (UnicodeSet::*caseClosure)(int32_t attribute), + int32_t depth, + UErrorCode& ec); + + //---------------------------------------------------------------- + // Implementation: Utility methods + //---------------------------------------------------------------- + + static int32_t nextCapacity(int32_t minCapacity); + + bool ensureCapacity(int32_t newLen); + + bool ensureBufferCapacity(int32_t newLen); + + void swapBuffers(void); + + UBool allocateStrings(UErrorCode &status); + UBool hasStrings() const; + int32_t stringsSize() const; + UBool stringsContains(const UnicodeString &s) const; + + UnicodeString& _toPattern(UnicodeString& result, + UBool escapeUnprintable) const; + + UnicodeString& _generatePattern(UnicodeString& result, + UBool escapeUnprintable) const; + + static void _appendToPat(UnicodeString& buf, const UnicodeString& s, UBool escapeUnprintable); + + static void _appendToPat(UnicodeString& buf, UChar32 c, UBool escapeUnprintable); + + //---------------------------------------------------------------- + // Implementation: Fundamental operators + //---------------------------------------------------------------- + + void exclusiveOr(const UChar32* other, int32_t otherLen, int8_t polarity); + + void add(const UChar32* other, int32_t otherLen, int8_t polarity); + + void retain(const UChar32* other, int32_t otherLen, int8_t polarity); + + /** + * Return true if the given position, in the given pattern, appears + * to be the start of a property set pattern [:foo:], \\p{foo}, or + * \\P{foo}, or \\N{name}. + */ + static UBool resemblesPropertyPattern(const UnicodeString& pattern, + int32_t pos); + + static UBool resemblesPropertyPattern(RuleCharacterIterator& chars, + int32_t iterOpts); + + /** + * Parse the given property pattern at the given parse position + * and set this UnicodeSet to the result. + * + * The original design document is out of date, but still useful. + * Ignore the property and value names: + * http://source.icu-project.org/repos/icu/icuhtml/trunk/design/unicodeset_properties.html + * + * Recognized syntax: + * + * [:foo:] [:^foo:] - white space not allowed within "[:" or ":]" + * \\p{foo} \\P{foo} - white space not allowed within "\\p" or "\\P" + * \\N{name} - white space not allowed within "\\N" + * + * Other than the above restrictions, Unicode Pattern_White_Space characters are ignored. + * Case is ignored except in "\\p" and "\\P" and "\\N". In 'name' leading + * and trailing space is deleted, and internal runs of whitespace + * are collapsed to a single space. + * + * We support binary properties, enumerated properties, and the + * following non-enumerated properties: + * + * Numeric_Value + * Name + * Unicode_1_Name + * + * @param pattern the pattern string + * @param ppos on entry, the position at which to begin parsing. + * This should be one of the locations marked '^': + * + * [:blah:] \\p{blah} \\P{blah} \\N{name} + * ^ % ^ % ^ % ^ % + * + * On return, the position after the last character parsed, that is, + * the locations marked '%'. If the parse fails, ppos is returned + * unchanged. + * @param ec status + * @return a reference to this. + */ + UnicodeSet& applyPropertyPattern(const UnicodeString& pattern, + ParsePosition& ppos, + UErrorCode &ec); + + void applyPropertyPattern(RuleCharacterIterator& chars, + UnicodeString& rebuiltPat, + UErrorCode& ec); + + static const UnicodeSet* getInclusions(int32_t src, UErrorCode &status); + + /** + * A filter that returns true if the given code point should be + * included in the UnicodeSet being constructed. + */ + typedef UBool (*Filter)(UChar32 codePoint, void* context); + + /** + * Given a filter, set this UnicodeSet to the code points + * contained by that filter. The filter MUST be + * property-conformant. That is, if it returns value v for one + * code point, then it must return v for all affiliated code + * points, as defined by the inclusions list. See + * getInclusions(). + * src is a UPropertySource value. + */ + void applyFilter(Filter filter, + void* context, + const UnicodeSet* inclusions, + UErrorCode &status); + + // UCPMap is now stable ICU 63 + void applyIntPropertyValue(const UCPMap *map, + UCPMapValueFilter *filter, const void *context, + UErrorCode &errorCode); + + /** + * Set the new pattern to cache. + */ + void setPattern(const UnicodeString& newPat) { + setPattern(newPat.getBuffer(), newPat.length()); + } + void setPattern(const char16_t *newPat, int32_t newPatLen); + /** + * Release existing cached pattern. + */ + void releasePattern(); + + friend class UnicodeSetIterator; +}; + + + +inline UBool UnicodeSet::operator!=(const UnicodeSet& o) const { + return !operator==(o); +} + +inline UBool UnicodeSet::isFrozen() const { + return (UBool)(bmpSet!=NULL || stringSpan!=NULL); +} + +inline UBool UnicodeSet::containsSome(UChar32 start, UChar32 end) const { + return !containsNone(start, end); +} + +inline UBool UnicodeSet::containsSome(const UnicodeSet& s) const { + return !containsNone(s); +} + +inline UBool UnicodeSet::containsSome(const UnicodeString& s) const { + return !containsNone(s); +} + +inline UBool UnicodeSet::isBogus() const { + return (UBool)(fFlags & kIsBogus); +} + +inline UnicodeSet *UnicodeSet::fromUSet(USet *uset) { + return reinterpret_cast<UnicodeSet *>(uset); +} + +inline const UnicodeSet *UnicodeSet::fromUSet(const USet *uset) { + return reinterpret_cast<const UnicodeSet *>(uset); +} + +inline USet *UnicodeSet::toUSet() { + return reinterpret_cast<USet *>(this); +} + +inline const USet *UnicodeSet::toUSet() const { + return reinterpret_cast<const USet *>(this); +} + +inline int32_t UnicodeSet::span(const UnicodeString &s, int32_t start, USetSpanCondition spanCondition) const { + int32_t sLength=s.length(); + if(start<0) { + start=0; + } else if(start>sLength) { + start=sLength; + } + return start+span(s.getBuffer()+start, sLength-start, spanCondition); +} + +inline int32_t UnicodeSet::spanBack(const UnicodeString &s, int32_t limit, USetSpanCondition spanCondition) const { + int32_t sLength=s.length(); + if(limit<0) { + limit=0; + } else if(limit>sLength) { + limit=sLength; + } + return spanBack(s.getBuffer(), limit, spanCondition); +} + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/unistr.h b/thirdparty/icu4c/common/unicode/unistr.h new file mode 100644 index 0000000000..456389f265 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/unistr.h @@ -0,0 +1,4757 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1998-2016, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* +* File unistr.h +* +* Modification History: +* +* Date Name Description +* 09/25/98 stephen Creation. +* 11/11/98 stephen Changed per 11/9 code review. +* 04/20/99 stephen Overhauled per 4/16 code review. +* 11/18/99 aliu Made to inherit from Replaceable. Added method +* handleReplaceBetween(); other methods unchanged. +* 06/25/01 grhoten Remove dependency on iostream. +****************************************************************************** +*/ + +#ifndef UNISTR_H +#define UNISTR_H + +/** + * \file + * \brief C++ API: Unicode String + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include <cstddef> +#include "unicode/char16ptr.h" +#include "unicode/rep.h" +#include "unicode/std_string.h" +#include "unicode/stringpiece.h" +#include "unicode/bytestream.h" + +struct UConverter; // unicode/ucnv.h + +#ifndef USTRING_H +/** + * \ingroup ustring_ustrlen + */ +U_CAPI int32_t U_EXPORT2 +u_strlen(const UChar *s); +#endif + +U_NAMESPACE_BEGIN + +#if !UCONFIG_NO_BREAK_ITERATION +class BreakIterator; // unicode/brkiter.h +#endif +class Edits; + +U_NAMESPACE_END + +// Not #ifndef U_HIDE_INTERNAL_API because UnicodeString needs the UStringCaseMapper. +/** + * Internal string case mapping function type. + * All error checking must be done. + * src and dest must not overlap. + * @internal + */ +typedef int32_t U_CALLCONV +UStringCaseMapper(int32_t caseLocale, uint32_t options, +#if !UCONFIG_NO_BREAK_ITERATION + icu::BreakIterator *iter, +#endif + char16_t *dest, int32_t destCapacity, + const char16_t *src, int32_t srcLength, + icu::Edits *edits, + UErrorCode &errorCode); + +U_NAMESPACE_BEGIN + +class Locale; // unicode/locid.h +class StringCharacterIterator; +class UnicodeStringAppendable; // unicode/appendable.h + +/* The <iostream> include has been moved to unicode/ustream.h */ + +/** + * Constant to be used in the UnicodeString(char *, int32_t, EInvariant) constructor + * which constructs a Unicode string from an invariant-character char * string. + * About invariant characters see utypes.h. + * This constructor has no runtime dependency on conversion code and is + * therefore recommended over ones taking a charset name string + * (where the empty string "" indicates invariant-character conversion). + * + * @stable ICU 3.2 + */ +#define US_INV icu::UnicodeString::kInvariant + +/** + * Unicode String literals in C++. + * + * Note: these macros are not recommended for new code. + * Prior to the availability of C++11 and u"unicode string literals", + * these macros were provided for portability and efficiency when + * initializing UnicodeStrings from literals. + * + * They work only for strings that contain "invariant characters", i.e., + * only latin letters, digits, and some punctuation. + * See utypes.h for details. + * + * The string parameter must be a C string literal. + * The length of the string, not including the terminating + * `NUL`, must be specified as a constant. + * @stable ICU 2.0 + */ +#if !U_CHAR16_IS_TYPEDEF +# define UNICODE_STRING(cs, _length) icu::UnicodeString(true, u ## cs, _length) +#else +# define UNICODE_STRING(cs, _length) icu::UnicodeString(true, (const char16_t*)u ## cs, _length) +#endif + +/** + * Unicode String literals in C++. + * Dependent on the platform properties, different UnicodeString + * constructors should be used to create a UnicodeString object from + * a string literal. + * The macros are defined for improved performance. + * They work only for strings that contain "invariant characters", i.e., + * only latin letters, digits, and some punctuation. + * See utypes.h for details. + * + * The string parameter must be a C string literal. + * @stable ICU 2.0 + */ +#define UNICODE_STRING_SIMPLE(cs) UNICODE_STRING(cs, -1) + +/** + * \def UNISTR_FROM_CHAR_EXPLICIT + * This can be defined to be empty or "explicit". + * If explicit, then the UnicodeString(char16_t) and UnicodeString(UChar32) + * constructors are marked as explicit, preventing their inadvertent use. + * @stable ICU 49 + */ +#ifndef UNISTR_FROM_CHAR_EXPLICIT +# if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) + // Auto-"explicit" in ICU library code. +# define UNISTR_FROM_CHAR_EXPLICIT explicit +# else + // Empty by default for source code compatibility. +# define UNISTR_FROM_CHAR_EXPLICIT +# endif +#endif + +/** + * \def UNISTR_FROM_STRING_EXPLICIT + * This can be defined to be empty or "explicit". + * If explicit, then the UnicodeString(const char *) and UnicodeString(const char16_t *) + * constructors are marked as explicit, preventing their inadvertent use. + * + * In particular, this helps prevent accidentally depending on ICU conversion code + * by passing a string literal into an API with a const UnicodeString & parameter. + * @stable ICU 49 + */ +#ifndef UNISTR_FROM_STRING_EXPLICIT +# if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) + // Auto-"explicit" in ICU library code. +# define UNISTR_FROM_STRING_EXPLICIT explicit +# else + // Empty by default for source code compatibility. +# define UNISTR_FROM_STRING_EXPLICIT +# endif +#endif + +/** + * \def UNISTR_OBJECT_SIZE + * Desired sizeof(UnicodeString) in bytes. + * It should be a multiple of sizeof(pointer) to avoid unusable space for padding. + * The object size may want to be a multiple of 16 bytes, + * which is a common granularity for heap allocation. + * + * Any space inside the object beyond sizeof(vtable pointer) + 2 + * is available for storing short strings inside the object. + * The bigger the object, the longer a string that can be stored inside the object, + * without additional heap allocation. + * + * Depending on a platform's pointer size, pointer alignment requirements, + * and struct padding, the compiler will usually round up sizeof(UnicodeString) + * to 4 * sizeof(pointer) (or 3 * sizeof(pointer) for P128 data models), + * to hold the fields for heap-allocated strings. + * Such a minimum size also ensures that the object is easily large enough + * to hold at least 2 char16_ts, for one supplementary code point (U16_MAX_LENGTH). + * + * sizeof(UnicodeString) >= 48 should work for all known platforms. + * + * For example, on a 64-bit machine where sizeof(vtable pointer) is 8, + * sizeof(UnicodeString) = 64 would leave space for + * (64 - sizeof(vtable pointer) - 2) / U_SIZEOF_UCHAR = (64 - 8 - 2) / 2 = 27 + * char16_ts stored inside the object. + * + * The minimum object size on a 64-bit machine would be + * 4 * sizeof(pointer) = 4 * 8 = 32 bytes, + * and the internal buffer would hold up to 11 char16_ts in that case. + * + * @see U16_MAX_LENGTH + * @stable ICU 56 + */ +#ifndef UNISTR_OBJECT_SIZE +# define UNISTR_OBJECT_SIZE 64 +#endif + +/** + * UnicodeString is a string class that stores Unicode characters directly and provides + * similar functionality as the Java String and StringBuffer/StringBuilder classes. + * It is a concrete implementation of the abstract class Replaceable (for transliteration). + * + * The UnicodeString equivalent of std::string’s clear() is remove(). + * + * A UnicodeString may "alias" an external array of characters + * (that is, point to it, rather than own the array) + * whose lifetime must then at least match the lifetime of the aliasing object. + * This aliasing may be preserved when returning a UnicodeString by value, + * depending on the compiler and the function implementation, + * via Return Value Optimization (RVO) or the move assignment operator. + * (However, the copy assignment operator does not preserve aliasing.) + * For details see the description of storage models at the end of the class API docs + * and in the User Guide chapter linked from there. + * + * The UnicodeString class is not suitable for subclassing. + * + * For an overview of Unicode strings in C and C++ see the + * [User Guide Strings chapter](https://unicode-org.github.io/icu/userguide/strings#strings-in-cc). + * + * In ICU, a Unicode string consists of 16-bit Unicode *code units*. + * A Unicode character may be stored with either one code unit + * (the most common case) or with a matched pair of special code units + * ("surrogates"). The data type for code units is char16_t. + * For single-character handling, a Unicode character code *point* is a value + * in the range 0..0x10ffff. ICU uses the UChar32 type for code points. + * + * Indexes and offsets into and lengths of strings always count code units, not code points. + * This is the same as with multi-byte char* strings in traditional string handling. + * Operations on partial strings typically do not test for code point boundaries. + * If necessary, the user needs to take care of such boundaries by testing for the code unit + * values or by using functions like + * UnicodeString::getChar32Start() and UnicodeString::getChar32Limit() + * (or, in C, the equivalent macros U16_SET_CP_START() and U16_SET_CP_LIMIT(), see utf.h). + * + * UnicodeString methods are more lenient with regard to input parameter values + * than other ICU APIs. In particular: + * - If indexes are out of bounds for a UnicodeString object + * (< 0 or > length()) then they are "pinned" to the nearest boundary. + * - If the buffer passed to an insert/append/replace operation is owned by the + * target object, e.g., calling str.append(str), an extra copy may take place + * to ensure safety. + * - If primitive string pointer values (e.g., const char16_t * or char *) + * for input strings are NULL, then those input string parameters are treated + * as if they pointed to an empty string. + * However, this is *not* the case for char * parameters for charset names + * or other IDs. + * - Most UnicodeString methods do not take a UErrorCode parameter because + * there are usually very few opportunities for failure other than a shortage + * of memory, error codes in low-level C++ string methods would be inconvenient, + * and the error code as the last parameter (ICU convention) would prevent + * the use of default parameter values. + * Instead, such methods set the UnicodeString into a "bogus" state + * (see isBogus()) if an error occurs. + * + * In string comparisons, two UnicodeString objects that are both "bogus" + * compare equal (to be transitive and prevent endless loops in sorting), + * and a "bogus" string compares less than any non-"bogus" one. + * + * Const UnicodeString methods are thread-safe. Multiple threads can use + * const methods on the same UnicodeString object simultaneously, + * but non-const methods must not be called concurrently (in multiple threads) + * with any other (const or non-const) methods. + * + * Similarly, const UnicodeString & parameters are thread-safe. + * One object may be passed in as such a parameter concurrently in multiple threads. + * This includes the const UnicodeString & parameters for + * copy construction, assignment, and cloning. + * + * UnicodeString uses several storage methods. + * String contents can be stored inside the UnicodeString object itself, + * in an allocated and shared buffer, or in an outside buffer that is "aliased". + * Most of this is done transparently, but careful aliasing in particular provides + * significant performance improvements. + * Also, the internal buffer is accessible via special functions. + * For details see the + * [User Guide Strings chapter](https://unicode-org.github.io/icu/userguide/strings#maximizing-performance-with-the-unicodestring-storage-model). + * + * @see utf.h + * @see CharacterIterator + * @stable ICU 2.0 + */ +class U_COMMON_API UnicodeString : public Replaceable +{ +public: + + /** + * Constant to be used in the UnicodeString(char *, int32_t, EInvariant) constructor + * which constructs a Unicode string from an invariant-character char * string. + * Use the macro US_INV instead of the full qualification for this value. + * + * @see US_INV + * @stable ICU 3.2 + */ + enum EInvariant { + /** + * @see EInvariant + * @stable ICU 3.2 + */ + kInvariant + }; + + //======================================== + // Read-only operations + //======================================== + + /* Comparison - bitwise only - for international comparison use collation */ + + /** + * Equality operator. Performs only bitwise comparison. + * @param text The UnicodeString to compare to this one. + * @return true if `text` contains the same characters as this one, + * false otherwise. + * @stable ICU 2.0 + */ + inline UBool operator== (const UnicodeString& text) const; + + /** + * Inequality operator. Performs only bitwise comparison. + * @param text The UnicodeString to compare to this one. + * @return false if `text` contains the same characters as this one, + * true otherwise. + * @stable ICU 2.0 + */ + inline UBool operator!= (const UnicodeString& text) const; + + /** + * Greater than operator. Performs only bitwise comparison. + * @param text The UnicodeString to compare to this one. + * @return true if the characters in this are bitwise + * greater than the characters in `text`, false otherwise + * @stable ICU 2.0 + */ + inline UBool operator> (const UnicodeString& text) const; + + /** + * Less than operator. Performs only bitwise comparison. + * @param text The UnicodeString to compare to this one. + * @return true if the characters in this are bitwise + * less than the characters in `text`, false otherwise + * @stable ICU 2.0 + */ + inline UBool operator< (const UnicodeString& text) const; + + /** + * Greater than or equal operator. Performs only bitwise comparison. + * @param text The UnicodeString to compare to this one. + * @return true if the characters in this are bitwise + * greater than or equal to the characters in `text`, false otherwise + * @stable ICU 2.0 + */ + inline UBool operator>= (const UnicodeString& text) const; + + /** + * Less than or equal operator. Performs only bitwise comparison. + * @param text The UnicodeString to compare to this one. + * @return true if the characters in this are bitwise + * less than or equal to the characters in `text`, false otherwise + * @stable ICU 2.0 + */ + inline UBool operator<= (const UnicodeString& text) const; + + /** + * Compare the characters bitwise in this UnicodeString to + * the characters in `text`. + * @param text The UnicodeString to compare to this one. + * @return The result of bitwise character comparison: 0 if this + * contains the same characters as `text`, -1 if the characters in + * this are bitwise less than the characters in `text`, +1 if the + * characters in this are bitwise greater than the characters + * in `text`. + * @stable ICU 2.0 + */ + inline int8_t compare(const UnicodeString& text) const; + + /** + * Compare the characters bitwise in the range + * [`start`, `start + length`) with the characters + * in the **entire string** `text`. + * (The parameters "start" and "length" are not applied to the other text "text".) + * @param start the offset at which the compare operation begins + * @param length the number of characters of text to compare. + * @param text the other text to be compared against this string. + * @return The result of bitwise character comparison: 0 if this + * contains the same characters as `text`, -1 if the characters in + * this are bitwise less than the characters in `text`, +1 if the + * characters in this are bitwise greater than the characters + * in `text`. + * @stable ICU 2.0 + */ + inline int8_t compare(int32_t start, + int32_t length, + const UnicodeString& text) const; + + /** + * Compare the characters bitwise in the range + * [`start`, `start + length`) with the characters + * in `srcText` in the range + * [`srcStart`, `srcStart + srcLength`). + * @param start the offset at which the compare operation begins + * @param length the number of characters in this to compare. + * @param srcText the text to be compared + * @param srcStart the offset into `srcText` to start comparison + * @param srcLength the number of characters in `src` to compare + * @return The result of bitwise character comparison: 0 if this + * contains the same characters as `srcText`, -1 if the characters in + * this are bitwise less than the characters in `srcText`, +1 if the + * characters in this are bitwise greater than the characters + * in `srcText`. + * @stable ICU 2.0 + */ + inline int8_t compare(int32_t start, + int32_t length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const; + + /** + * Compare the characters bitwise in this UnicodeString with the first + * `srcLength` characters in `srcChars`. + * @param srcChars The characters to compare to this UnicodeString. + * @param srcLength the number of characters in `srcChars` to compare + * @return The result of bitwise character comparison: 0 if this + * contains the same characters as `srcChars`, -1 if the characters in + * this are bitwise less than the characters in `srcChars`, +1 if the + * characters in this are bitwise greater than the characters + * in `srcChars`. + * @stable ICU 2.0 + */ + inline int8_t compare(ConstChar16Ptr srcChars, + int32_t srcLength) const; + + /** + * Compare the characters bitwise in the range + * [`start`, `start + length`) with the first + * `length` characters in `srcChars` + * @param start the offset at which the compare operation begins + * @param length the number of characters to compare. + * @param srcChars the characters to be compared + * @return The result of bitwise character comparison: 0 if this + * contains the same characters as `srcChars`, -1 if the characters in + * this are bitwise less than the characters in `srcChars`, +1 if the + * characters in this are bitwise greater than the characters + * in `srcChars`. + * @stable ICU 2.0 + */ + inline int8_t compare(int32_t start, + int32_t length, + const char16_t *srcChars) const; + + /** + * Compare the characters bitwise in the range + * [`start`, `start + length`) with the characters + * in `srcChars` in the range + * [`srcStart`, `srcStart + srcLength`). + * @param start the offset at which the compare operation begins + * @param length the number of characters in this to compare + * @param srcChars the characters to be compared + * @param srcStart the offset into `srcChars` to start comparison + * @param srcLength the number of characters in `srcChars` to compare + * @return The result of bitwise character comparison: 0 if this + * contains the same characters as `srcChars`, -1 if the characters in + * this are bitwise less than the characters in `srcChars`, +1 if the + * characters in this are bitwise greater than the characters + * in `srcChars`. + * @stable ICU 2.0 + */ + inline int8_t compare(int32_t start, + int32_t length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const; + + /** + * Compare the characters bitwise in the range + * [`start`, `limit`) with the characters + * in `srcText` in the range + * [`srcStart`, `srcLimit`). + * @param start the offset at which the compare operation begins + * @param limit the offset immediately following the compare operation + * @param srcText the text to be compared + * @param srcStart the offset into `srcText` to start comparison + * @param srcLimit the offset into `srcText` to limit comparison + * @return The result of bitwise character comparison: 0 if this + * contains the same characters as `srcText`, -1 if the characters in + * this are bitwise less than the characters in `srcText`, +1 if the + * characters in this are bitwise greater than the characters + * in `srcText`. + * @stable ICU 2.0 + */ + inline int8_t compareBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLimit) const; + + /** + * Compare two Unicode strings in code point order. + * The result may be different from the results of compare(), operator<, etc. + * if supplementary characters are present: + * + * In UTF-16, supplementary characters (with code points U+10000 and above) are + * stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, + * which means that they compare as less than some other BMP characters like U+feff. + * This function compares Unicode strings in code point order. + * If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined. + * + * @param text Another string to compare this one to. + * @return a negative/zero/positive integer corresponding to whether + * this string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ + inline int8_t compareCodePointOrder(const UnicodeString& text) const; + + /** + * Compare two Unicode strings in code point order. + * The result may be different from the results of compare(), operator<, etc. + * if supplementary characters are present: + * + * In UTF-16, supplementary characters (with code points U+10000 and above) are + * stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, + * which means that they compare as less than some other BMP characters like U+feff. + * This function compares Unicode strings in code point order. + * If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined. + * + * @param start The start offset in this string at which the compare operation begins. + * @param length The number of code units from this string to compare. + * @param srcText Another string to compare this one to. + * @return a negative/zero/positive integer corresponding to whether + * this string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ + inline int8_t compareCodePointOrder(int32_t start, + int32_t length, + const UnicodeString& srcText) const; + + /** + * Compare two Unicode strings in code point order. + * The result may be different from the results of compare(), operator<, etc. + * if supplementary characters are present: + * + * In UTF-16, supplementary characters (with code points U+10000 and above) are + * stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, + * which means that they compare as less than some other BMP characters like U+feff. + * This function compares Unicode strings in code point order. + * If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined. + * + * @param start The start offset in this string at which the compare operation begins. + * @param length The number of code units from this string to compare. + * @param srcText Another string to compare this one to. + * @param srcStart The start offset in that string at which the compare operation begins. + * @param srcLength The number of code units from that string to compare. + * @return a negative/zero/positive integer corresponding to whether + * this string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ + inline int8_t compareCodePointOrder(int32_t start, + int32_t length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const; + + /** + * Compare two Unicode strings in code point order. + * The result may be different from the results of compare(), operator<, etc. + * if supplementary characters are present: + * + * In UTF-16, supplementary characters (with code points U+10000 and above) are + * stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, + * which means that they compare as less than some other BMP characters like U+feff. + * This function compares Unicode strings in code point order. + * If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined. + * + * @param srcChars A pointer to another string to compare this one to. + * @param srcLength The number of code units from that string to compare. + * @return a negative/zero/positive integer corresponding to whether + * this string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ + inline int8_t compareCodePointOrder(ConstChar16Ptr srcChars, + int32_t srcLength) const; + + /** + * Compare two Unicode strings in code point order. + * The result may be different from the results of compare(), operator<, etc. + * if supplementary characters are present: + * + * In UTF-16, supplementary characters (with code points U+10000 and above) are + * stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, + * which means that they compare as less than some other BMP characters like U+feff. + * This function compares Unicode strings in code point order. + * If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined. + * + * @param start The start offset in this string at which the compare operation begins. + * @param length The number of code units from this string to compare. + * @param srcChars A pointer to another string to compare this one to. + * @return a negative/zero/positive integer corresponding to whether + * this string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ + inline int8_t compareCodePointOrder(int32_t start, + int32_t length, + const char16_t *srcChars) const; + + /** + * Compare two Unicode strings in code point order. + * The result may be different from the results of compare(), operator<, etc. + * if supplementary characters are present: + * + * In UTF-16, supplementary characters (with code points U+10000 and above) are + * stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, + * which means that they compare as less than some other BMP characters like U+feff. + * This function compares Unicode strings in code point order. + * If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined. + * + * @param start The start offset in this string at which the compare operation begins. + * @param length The number of code units from this string to compare. + * @param srcChars A pointer to another string to compare this one to. + * @param srcStart The start offset in that string at which the compare operation begins. + * @param srcLength The number of code units from that string to compare. + * @return a negative/zero/positive integer corresponding to whether + * this string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ + inline int8_t compareCodePointOrder(int32_t start, + int32_t length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const; + + /** + * Compare two Unicode strings in code point order. + * The result may be different from the results of compare(), operator<, etc. + * if supplementary characters are present: + * + * In UTF-16, supplementary characters (with code points U+10000 and above) are + * stored with pairs of surrogate code units. These have values from 0xd800 to 0xdfff, + * which means that they compare as less than some other BMP characters like U+feff. + * This function compares Unicode strings in code point order. + * If either of the UTF-16 strings is malformed (i.e., it contains unpaired surrogates), then the result is not defined. + * + * @param start The start offset in this string at which the compare operation begins. + * @param limit The offset after the last code unit from this string to compare. + * @param srcText Another string to compare this one to. + * @param srcStart The start offset in that string at which the compare operation begins. + * @param srcLimit The offset after the last code unit from that string to compare. + * @return a negative/zero/positive integer corresponding to whether + * this string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ + inline int8_t compareCodePointOrderBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLimit) const; + + /** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to this->foldCase(options).compare(text.foldCase(options)). + * + * @param text Another string to compare this one to. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ + inline int8_t caseCompare(const UnicodeString& text, uint32_t options) const; + + /** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to this->foldCase(options).compare(srcText.foldCase(options)). + * + * @param start The start offset in this string at which the compare operation begins. + * @param length The number of code units from this string to compare. + * @param srcText Another string to compare this one to. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ + inline int8_t caseCompare(int32_t start, + int32_t length, + const UnicodeString& srcText, + uint32_t options) const; + + /** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to this->foldCase(options).compare(srcText.foldCase(options)). + * + * @param start The start offset in this string at which the compare operation begins. + * @param length The number of code units from this string to compare. + * @param srcText Another string to compare this one to. + * @param srcStart The start offset in that string at which the compare operation begins. + * @param srcLength The number of code units from that string to compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ + inline int8_t caseCompare(int32_t start, + int32_t length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength, + uint32_t options) const; + + /** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to this->foldCase(options).compare(srcChars.foldCase(options)). + * + * @param srcChars A pointer to another string to compare this one to. + * @param srcLength The number of code units from that string to compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ + inline int8_t caseCompare(ConstChar16Ptr srcChars, + int32_t srcLength, + uint32_t options) const; + + /** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to this->foldCase(options).compare(srcChars.foldCase(options)). + * + * @param start The start offset in this string at which the compare operation begins. + * @param length The number of code units from this string to compare. + * @param srcChars A pointer to another string to compare this one to. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ + inline int8_t caseCompare(int32_t start, + int32_t length, + const char16_t *srcChars, + uint32_t options) const; + + /** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to this->foldCase(options).compare(srcChars.foldCase(options)). + * + * @param start The start offset in this string at which the compare operation begins. + * @param length The number of code units from this string to compare. + * @param srcChars A pointer to another string to compare this one to. + * @param srcStart The start offset in that string at which the compare operation begins. + * @param srcLength The number of code units from that string to compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ + inline int8_t caseCompare(int32_t start, + int32_t length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength, + uint32_t options) const; + + /** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to this->foldCase(options).compareBetween(text.foldCase(options)). + * + * @param start The start offset in this string at which the compare operation begins. + * @param limit The offset after the last code unit from this string to compare. + * @param srcText Another string to compare this one to. + * @param srcStart The start offset in that string at which the compare operation begins. + * @param srcLimit The offset after the last code unit from that string to compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ + inline int8_t caseCompareBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLimit, + uint32_t options) const; + + /** + * Determine if this starts with the characters in `text` + * @param text The text to match. + * @return true if this starts with the characters in `text`, + * false otherwise + * @stable ICU 2.0 + */ + inline UBool startsWith(const UnicodeString& text) const; + + /** + * Determine if this starts with the characters in `srcText` + * in the range [`srcStart`, `srcStart + srcLength`). + * @param srcText The text to match. + * @param srcStart the offset into `srcText` to start matching + * @param srcLength the number of characters in `srcText` to match + * @return true if this starts with the characters in `text`, + * false otherwise + * @stable ICU 2.0 + */ + inline UBool startsWith(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const; + + /** + * Determine if this starts with the characters in `srcChars` + * @param srcChars The characters to match. + * @param srcLength the number of characters in `srcChars` + * @return true if this starts with the characters in `srcChars`, + * false otherwise + * @stable ICU 2.0 + */ + inline UBool startsWith(ConstChar16Ptr srcChars, + int32_t srcLength) const; + + /** + * Determine if this ends with the characters in `srcChars` + * in the range [`srcStart`, `srcStart + srcLength`). + * @param srcChars The characters to match. + * @param srcStart the offset into `srcText` to start matching + * @param srcLength the number of characters in `srcChars` to match + * @return true if this ends with the characters in `srcChars`, false otherwise + * @stable ICU 2.0 + */ + inline UBool startsWith(const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const; + + /** + * Determine if this ends with the characters in `text` + * @param text The text to match. + * @return true if this ends with the characters in `text`, + * false otherwise + * @stable ICU 2.0 + */ + inline UBool endsWith(const UnicodeString& text) const; + + /** + * Determine if this ends with the characters in `srcText` + * in the range [`srcStart`, `srcStart + srcLength`). + * @param srcText The text to match. + * @param srcStart the offset into `srcText` to start matching + * @param srcLength the number of characters in `srcText` to match + * @return true if this ends with the characters in `text`, + * false otherwise + * @stable ICU 2.0 + */ + inline UBool endsWith(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const; + + /** + * Determine if this ends with the characters in `srcChars` + * @param srcChars The characters to match. + * @param srcLength the number of characters in `srcChars` + * @return true if this ends with the characters in `srcChars`, + * false otherwise + * @stable ICU 2.0 + */ + inline UBool endsWith(ConstChar16Ptr srcChars, + int32_t srcLength) const; + + /** + * Determine if this ends with the characters in `srcChars` + * in the range [`srcStart`, `srcStart + srcLength`). + * @param srcChars The characters to match. + * @param srcStart the offset into `srcText` to start matching + * @param srcLength the number of characters in `srcChars` to match + * @return true if this ends with the characters in `srcChars`, + * false otherwise + * @stable ICU 2.0 + */ + inline UBool endsWith(const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const; + + + /* Searching - bitwise only */ + + /** + * Locate in this the first occurrence of the characters in `text`, + * using bitwise comparison. + * @param text The text to search for. + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(const UnicodeString& text) const; + + /** + * Locate in this the first occurrence of the characters in `text` + * starting at offset `start`, using bitwise comparison. + * @param text The text to search for. + * @param start The offset at which searching will start. + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(const UnicodeString& text, + int32_t start) const; + + /** + * Locate in this the first occurrence in the range + * [`start`, `start + length`) of the characters + * in `text`, using bitwise comparison. + * @param text The text to search for. + * @param start The offset at which searching will start. + * @param length The number of characters to search + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(const UnicodeString& text, + int32_t start, + int32_t length) const; + + /** + * Locate in this the first occurrence in the range + * [`start`, `start + length`) of the characters + * in `srcText` in the range + * [`srcStart`, `srcStart + srcLength`), + * using bitwise comparison. + * @param srcText The text to search for. + * @param srcStart the offset into `srcText` at which + * to start matching + * @param srcLength the number of characters in `srcText` to match + * @param start the offset into this at which to start matching + * @param length the number of characters in this to search + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength, + int32_t start, + int32_t length) const; + + /** + * Locate in this the first occurrence of the characters in + * `srcChars` + * starting at offset `start`, using bitwise comparison. + * @param srcChars The text to search for. + * @param srcLength the number of characters in `srcChars` to match + * @param start the offset into this at which to start matching + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(const char16_t *srcChars, + int32_t srcLength, + int32_t start) const; + + /** + * Locate in this the first occurrence in the range + * [`start`, `start + length`) of the characters + * in `srcChars`, using bitwise comparison. + * @param srcChars The text to search for. + * @param srcLength the number of characters in `srcChars` + * @param start The offset at which searching will start. + * @param length The number of characters to search + * @return The offset into this of the start of `srcChars`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(ConstChar16Ptr srcChars, + int32_t srcLength, + int32_t start, + int32_t length) const; + + /** + * Locate in this the first occurrence in the range + * [`start`, `start + length`) of the characters + * in `srcChars` in the range + * [`srcStart`, `srcStart + srcLength`), + * using bitwise comparison. + * @param srcChars The text to search for. + * @param srcStart the offset into `srcChars` at which + * to start matching + * @param srcLength the number of characters in `srcChars` to match + * @param start the offset into this at which to start matching + * @param length the number of characters in this to search + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + int32_t indexOf(const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength, + int32_t start, + int32_t length) const; + + /** + * Locate in this the first occurrence of the BMP code point `c`, + * using bitwise comparison. + * @param c The code unit to search for. + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(char16_t c) const; + + /** + * Locate in this the first occurrence of the code point `c`, + * using bitwise comparison. + * + * @param c The code point to search for. + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(UChar32 c) const; + + /** + * Locate in this the first occurrence of the BMP code point `c`, + * starting at offset `start`, using bitwise comparison. + * @param c The code unit to search for. + * @param start The offset at which searching will start. + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(char16_t c, + int32_t start) const; + + /** + * Locate in this the first occurrence of the code point `c` + * starting at offset `start`, using bitwise comparison. + * + * @param c The code point to search for. + * @param start The offset at which searching will start. + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(UChar32 c, + int32_t start) const; + + /** + * Locate in this the first occurrence of the BMP code point `c` + * in the range [`start`, `start + length`), + * using bitwise comparison. + * @param c The code unit to search for. + * @param start the offset into this at which to start matching + * @param length the number of characters in this to search + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(char16_t c, + int32_t start, + int32_t length) const; + + /** + * Locate in this the first occurrence of the code point `c` + * in the range [`start`, `start + length`), + * using bitwise comparison. + * + * @param c The code point to search for. + * @param start the offset into this at which to start matching + * @param length the number of characters in this to search + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t indexOf(UChar32 c, + int32_t start, + int32_t length) const; + + /** + * Locate in this the last occurrence of the characters in `text`, + * using bitwise comparison. + * @param text The text to search for. + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(const UnicodeString& text) const; + + /** + * Locate in this the last occurrence of the characters in `text` + * starting at offset `start`, using bitwise comparison. + * @param text The text to search for. + * @param start The offset at which searching will start. + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(const UnicodeString& text, + int32_t start) const; + + /** + * Locate in this the last occurrence in the range + * [`start`, `start + length`) of the characters + * in `text`, using bitwise comparison. + * @param text The text to search for. + * @param start The offset at which searching will start. + * @param length The number of characters to search + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(const UnicodeString& text, + int32_t start, + int32_t length) const; + + /** + * Locate in this the last occurrence in the range + * [`start`, `start + length`) of the characters + * in `srcText` in the range + * [`srcStart`, `srcStart + srcLength`), + * using bitwise comparison. + * @param srcText The text to search for. + * @param srcStart the offset into `srcText` at which + * to start matching + * @param srcLength the number of characters in `srcText` to match + * @param start the offset into this at which to start matching + * @param length the number of characters in this to search + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength, + int32_t start, + int32_t length) const; + + /** + * Locate in this the last occurrence of the characters in `srcChars` + * starting at offset `start`, using bitwise comparison. + * @param srcChars The text to search for. + * @param srcLength the number of characters in `srcChars` to match + * @param start the offset into this at which to start matching + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(const char16_t *srcChars, + int32_t srcLength, + int32_t start) const; + + /** + * Locate in this the last occurrence in the range + * [`start`, `start + length`) of the characters + * in `srcChars`, using bitwise comparison. + * @param srcChars The text to search for. + * @param srcLength the number of characters in `srcChars` + * @param start The offset at which searching will start. + * @param length The number of characters to search + * @return The offset into this of the start of `srcChars`, + * or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(ConstChar16Ptr srcChars, + int32_t srcLength, + int32_t start, + int32_t length) const; + + /** + * Locate in this the last occurrence in the range + * [`start`, `start + length`) of the characters + * in `srcChars` in the range + * [`srcStart`, `srcStart + srcLength`), + * using bitwise comparison. + * @param srcChars The text to search for. + * @param srcStart the offset into `srcChars` at which + * to start matching + * @param srcLength the number of characters in `srcChars` to match + * @param start the offset into this at which to start matching + * @param length the number of characters in this to search + * @return The offset into this of the start of `text`, + * or -1 if not found. + * @stable ICU 2.0 + */ + int32_t lastIndexOf(const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength, + int32_t start, + int32_t length) const; + + /** + * Locate in this the last occurrence of the BMP code point `c`, + * using bitwise comparison. + * @param c The code unit to search for. + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(char16_t c) const; + + /** + * Locate in this the last occurrence of the code point `c`, + * using bitwise comparison. + * + * @param c The code point to search for. + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(UChar32 c) const; + + /** + * Locate in this the last occurrence of the BMP code point `c` + * starting at offset `start`, using bitwise comparison. + * @param c The code unit to search for. + * @param start The offset at which searching will start. + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(char16_t c, + int32_t start) const; + + /** + * Locate in this the last occurrence of the code point `c` + * starting at offset `start`, using bitwise comparison. + * + * @param c The code point to search for. + * @param start The offset at which searching will start. + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(UChar32 c, + int32_t start) const; + + /** + * Locate in this the last occurrence of the BMP code point `c` + * in the range [`start`, `start + length`), + * using bitwise comparison. + * @param c The code unit to search for. + * @param start the offset into this at which to start matching + * @param length the number of characters in this to search + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(char16_t c, + int32_t start, + int32_t length) const; + + /** + * Locate in this the last occurrence of the code point `c` + * in the range [`start`, `start + length`), + * using bitwise comparison. + * + * @param c The code point to search for. + * @param start the offset into this at which to start matching + * @param length the number of characters in this to search + * @return The offset into this of `c`, or -1 if not found. + * @stable ICU 2.0 + */ + inline int32_t lastIndexOf(UChar32 c, + int32_t start, + int32_t length) const; + + + /* Character access */ + + /** + * Return the code unit at offset `offset`. + * If the offset is not valid (0..length()-1) then U+ffff is returned. + * @param offset a valid offset into the text + * @return the code unit at offset `offset` + * or 0xffff if the offset is not valid for this string + * @stable ICU 2.0 + */ + inline char16_t charAt(int32_t offset) const; + + /** + * Return the code unit at offset `offset`. + * If the offset is not valid (0..length()-1) then U+ffff is returned. + * @param offset a valid offset into the text + * @return the code unit at offset `offset` + * @stable ICU 2.0 + */ + inline char16_t operator[] (int32_t offset) const; + + /** + * Return the code point that contains the code unit + * at offset `offset`. + * If the offset is not valid (0..length()-1) then U+ffff is returned. + * @param offset a valid offset into the text + * that indicates the text offset of any of the code units + * that will be assembled into a code point (21-bit value) and returned + * @return the code point of text at `offset` + * or 0xffff if the offset is not valid for this string + * @stable ICU 2.0 + */ + UChar32 char32At(int32_t offset) const; + + /** + * Adjust a random-access offset so that + * it points to the beginning of a Unicode character. + * The offset that is passed in points to + * any code unit of a code point, + * while the returned offset will point to the first code unit + * of the same code point. + * In UTF-16, if the input offset points to a second surrogate + * of a surrogate pair, then the returned offset will point + * to the first surrogate. + * @param offset a valid offset into one code point of the text + * @return offset of the first code unit of the same code point + * @see U16_SET_CP_START + * @stable ICU 2.0 + */ + int32_t getChar32Start(int32_t offset) const; + + /** + * Adjust a random-access offset so that + * it points behind a Unicode character. + * The offset that is passed in points behind + * any code unit of a code point, + * while the returned offset will point behind the last code unit + * of the same code point. + * In UTF-16, if the input offset points behind the first surrogate + * (i.e., to the second surrogate) + * of a surrogate pair, then the returned offset will point + * behind the second surrogate (i.e., to the first surrogate). + * @param offset a valid offset after any code unit of a code point of the text + * @return offset of the first code unit after the same code point + * @see U16_SET_CP_LIMIT + * @stable ICU 2.0 + */ + int32_t getChar32Limit(int32_t offset) const; + + /** + * Move the code unit index along the string by delta code points. + * Interpret the input index as a code unit-based offset into the string, + * move the index forward or backward by delta code points, and + * return the resulting index. + * The input index should point to the first code unit of a code point, + * if there is more than one. + * + * Both input and output indexes are code unit-based as for all + * string indexes/offsets in ICU (and other libraries, like MBCS char*). + * If delta<0 then the index is moved backward (toward the start of the string). + * If delta>0 then the index is moved forward (toward the end of the string). + * + * This behaves like CharacterIterator::move32(delta, kCurrent). + * + * Behavior for out-of-bounds indexes: + * `moveIndex32` pins the input index to 0..length(), i.e., + * if the input index<0 then it is pinned to 0; + * if it is index>length() then it is pinned to length(). + * Afterwards, the index is moved by `delta` code points + * forward or backward, + * but no further backward than to 0 and no further forward than to length(). + * The resulting index return value will be in between 0 and length(), inclusively. + * + * Examples: + * \code + * // s has code points 'a' U+10000 'b' U+10ffff U+2029 + * UnicodeString s(u"a\U00010000b\U0010ffff\u2029"); + * + * // initial index: position of U+10000 + * int32_t index=1; + * + * // the following examples will all result in index==4, position of U+10ffff + * + * // skip 2 code points from some position in the string + * index=s.moveIndex32(index, 2); // skips U+10000 and 'b' + * + * // go to the 3rd code point from the start of s (0-based) + * index=s.moveIndex32(0, 3); // skips 'a', U+10000, and 'b' + * + * // go to the next-to-last code point of s + * index=s.moveIndex32(s.length(), -2); // backward-skips U+2029 and U+10ffff + * \endcode + * + * @param index input code unit index + * @param delta (signed) code point count to move the index forward or backward + * in the string + * @return the resulting code unit index + * @stable ICU 2.0 + */ + int32_t moveIndex32(int32_t index, int32_t delta) const; + + /* Substring extraction */ + + /** + * Copy the characters in the range + * [`start`, `start + length`) into the array `dst`, + * beginning at `dstStart`. + * If the string aliases to `dst` itself as an external buffer, + * then extract() will not copy the contents. + * + * @param start offset of first character which will be copied into the array + * @param length the number of characters to extract + * @param dst array in which to copy characters. The length of `dst` + * must be at least (`dstStart + length`). + * @param dstStart the offset in `dst` where the first character + * will be extracted + * @stable ICU 2.0 + */ + inline void extract(int32_t start, + int32_t length, + Char16Ptr dst, + int32_t dstStart = 0) const; + + /** + * Copy the contents of the string into dest. + * This is a convenience function that + * checks if there is enough space in dest, + * extracts the entire string if possible, + * and NUL-terminates dest if possible. + * + * If the string fits into dest but cannot be NUL-terminated + * (length()==destCapacity) then the error code is set to U_STRING_NOT_TERMINATED_WARNING. + * If the string itself does not fit into dest + * (length()>destCapacity) then the error code is set to U_BUFFER_OVERFLOW_ERROR. + * + * If the string aliases to `dest` itself as an external buffer, + * then extract() will not copy the contents. + * + * @param dest Destination string buffer. + * @param destCapacity Number of char16_ts available at dest. + * @param errorCode ICU error code. + * @return length() + * @stable ICU 2.0 + */ + int32_t + extract(Char16Ptr dest, int32_t destCapacity, + UErrorCode &errorCode) const; + + /** + * Copy the characters in the range + * [`start`, `start + length`) into the UnicodeString + * `target`. + * @param start offset of first character which will be copied + * @param length the number of characters to extract + * @param target UnicodeString into which to copy characters. + * @stable ICU 2.0 + */ + inline void extract(int32_t start, + int32_t length, + UnicodeString& target) const; + + /** + * Copy the characters in the range [`start`, `limit`) + * into the array `dst`, beginning at `dstStart`. + * @param start offset of first character which will be copied into the array + * @param limit offset immediately following the last character to be copied + * @param dst array in which to copy characters. The length of `dst` + * must be at least (`dstStart + (limit - start)`). + * @param dstStart the offset in `dst` where the first character + * will be extracted + * @stable ICU 2.0 + */ + inline void extractBetween(int32_t start, + int32_t limit, + char16_t *dst, + int32_t dstStart = 0) const; + + /** + * Copy the characters in the range [`start`, `limit`) + * into the UnicodeString `target`. Replaceable API. + * @param start offset of first character which will be copied + * @param limit offset immediately following the last character to be copied + * @param target UnicodeString into which to copy characters. + * @stable ICU 2.0 + */ + virtual void extractBetween(int32_t start, + int32_t limit, + UnicodeString& target) const; + + /** + * Copy the characters in the range + * [`start`, `start + startLength`) into an array of characters. + * All characters must be invariant (see utypes.h). + * Use US_INV as the last, signature-distinguishing parameter. + * + * This function does not write any more than `targetCapacity` + * characters but returns the length of the entire output string + * so that one can allocate a larger buffer and call the function again + * if necessary. + * The output string is NUL-terminated if possible. + * + * @param start offset of first character which will be copied + * @param startLength the number of characters to extract + * @param target the target buffer for extraction, can be NULL + * if targetLength is 0 + * @param targetCapacity the length of the target buffer + * @param inv Signature-distinguishing paramater, use US_INV. + * @return the output string length, not including the terminating NUL + * @stable ICU 3.2 + */ + int32_t extract(int32_t start, + int32_t startLength, + char *target, + int32_t targetCapacity, + enum EInvariant inv) const; + +#if U_CHARSET_IS_UTF8 || !UCONFIG_NO_CONVERSION + + /** + * Copy the characters in the range + * [`start`, `start + length`) into an array of characters + * in the platform's default codepage. + * This function does not write any more than `targetLength` + * characters but returns the length of the entire output string + * so that one can allocate a larger buffer and call the function again + * if necessary. + * The output string is NUL-terminated if possible. + * + * @param start offset of first character which will be copied + * @param startLength the number of characters to extract + * @param target the target buffer for extraction + * @param targetLength the length of the target buffer + * If `target` is NULL, then the number of bytes required for + * `target` is returned. + * @return the output string length, not including the terminating NUL + * @stable ICU 2.0 + */ + int32_t extract(int32_t start, + int32_t startLength, + char *target, + uint32_t targetLength) const; + +#endif + +#if !UCONFIG_NO_CONVERSION + + /** + * Copy the characters in the range + * [`start`, `start + length`) into an array of characters + * in a specified codepage. + * The output string is NUL-terminated. + * + * Recommendation: For invariant-character strings use + * extract(int32_t start, int32_t length, char *target, int32_t targetCapacity, enum EInvariant inv) const + * because it avoids object code dependencies of UnicodeString on + * the conversion code. + * + * @param start offset of first character which will be copied + * @param startLength the number of characters to extract + * @param target the target buffer for extraction + * @param codepage the desired codepage for the characters. 0 has + * the special meaning of the default codepage + * If `codepage` is an empty string (`""`), + * then a simple conversion is performed on the codepage-invariant + * subset ("invariant characters") of the platform encoding. See utypes.h. + * If `target` is NULL, then the number of bytes required for + * `target` is returned. It is assumed that the target is big enough + * to fit all of the characters. + * @return the output string length, not including the terminating NUL + * @stable ICU 2.0 + */ + inline int32_t extract(int32_t start, + int32_t startLength, + char *target, + const char *codepage = 0) const; + + /** + * Copy the characters in the range + * [`start`, `start + length`) into an array of characters + * in a specified codepage. + * This function does not write any more than `targetLength` + * characters but returns the length of the entire output string + * so that one can allocate a larger buffer and call the function again + * if necessary. + * The output string is NUL-terminated if possible. + * + * Recommendation: For invariant-character strings use + * extract(int32_t start, int32_t length, char *target, int32_t targetCapacity, enum EInvariant inv) const + * because it avoids object code dependencies of UnicodeString on + * the conversion code. + * + * @param start offset of first character which will be copied + * @param startLength the number of characters to extract + * @param target the target buffer for extraction + * @param targetLength the length of the target buffer + * @param codepage the desired codepage for the characters. 0 has + * the special meaning of the default codepage + * If `codepage` is an empty string (`""`), + * then a simple conversion is performed on the codepage-invariant + * subset ("invariant characters") of the platform encoding. See utypes.h. + * If `target` is NULL, then the number of bytes required for + * `target` is returned. + * @return the output string length, not including the terminating NUL + * @stable ICU 2.0 + */ + int32_t extract(int32_t start, + int32_t startLength, + char *target, + uint32_t targetLength, + const char *codepage) const; + + /** + * Convert the UnicodeString into a codepage string using an existing UConverter. + * The output string is NUL-terminated if possible. + * + * This function avoids the overhead of opening and closing a converter if + * multiple strings are extracted. + * + * @param dest destination string buffer, can be NULL if destCapacity==0 + * @param destCapacity the number of chars available at dest + * @param cnv the converter object to be used (ucnv_resetFromUnicode() will be called), + * or NULL for the default converter + * @param errorCode normal ICU error code + * @return the length of the output string, not counting the terminating NUL; + * if the length is greater than destCapacity, then the string will not fit + * and a buffer of the indicated length would need to be passed in + * @stable ICU 2.0 + */ + int32_t extract(char *dest, int32_t destCapacity, + UConverter *cnv, + UErrorCode &errorCode) const; + +#endif + + /** + * Create a temporary substring for the specified range. + * Unlike the substring constructor and setTo() functions, + * the object returned here will be a read-only alias (using getBuffer()) + * rather than copying the text. + * As a result, this substring operation is much faster but requires + * that the original string not be modified or deleted during the lifetime + * of the returned substring object. + * @param start offset of the first character visible in the substring + * @param length length of the substring + * @return a read-only alias UnicodeString object for the substring + * @stable ICU 4.4 + */ + UnicodeString tempSubString(int32_t start=0, int32_t length=INT32_MAX) const; + + /** + * Create a temporary substring for the specified range. + * Same as tempSubString(start, length) except that the substring range + * is specified as a (start, limit) pair (with an exclusive limit index) + * rather than a (start, length) pair. + * @param start offset of the first character visible in the substring + * @param limit offset immediately following the last character visible in the substring + * @return a read-only alias UnicodeString object for the substring + * @stable ICU 4.4 + */ + inline UnicodeString tempSubStringBetween(int32_t start, int32_t limit=INT32_MAX) const; + + /** + * Convert the UnicodeString to UTF-8 and write the result + * to a ByteSink. This is called by toUTF8String(). + * Unpaired surrogates are replaced with U+FFFD. + * Calls u_strToUTF8WithSub(). + * + * @param sink A ByteSink to which the UTF-8 version of the string is written. + * sink.Flush() is called at the end. + * @stable ICU 4.2 + * @see toUTF8String + */ + void toUTF8(ByteSink &sink) const; + + /** + * Convert the UnicodeString to UTF-8 and append the result + * to a standard string. + * Unpaired surrogates are replaced with U+FFFD. + * Calls toUTF8(). + * + * @param result A standard string (or a compatible object) + * to which the UTF-8 version of the string is appended. + * @return The string object. + * @stable ICU 4.2 + * @see toUTF8 + */ + template<typename StringClass> + StringClass &toUTF8String(StringClass &result) const { + StringByteSink<StringClass> sbs(&result, length()); + toUTF8(sbs); + return result; + } + + /** + * Convert the UnicodeString to UTF-32. + * Unpaired surrogates are replaced with U+FFFD. + * Calls u_strToUTF32WithSub(). + * + * @param utf32 destination string buffer, can be NULL if capacity==0 + * @param capacity the number of UChar32s available at utf32 + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The length of the UTF-32 string. + * @see fromUTF32 + * @stable ICU 4.2 + */ + int32_t toUTF32(UChar32 *utf32, int32_t capacity, UErrorCode &errorCode) const; + + /* Length operations */ + + /** + * Return the length of the UnicodeString object. + * The length is the number of char16_t code units are in the UnicodeString. + * If you want the number of code points, please use countChar32(). + * @return the length of the UnicodeString object + * @see countChar32 + * @stable ICU 2.0 + */ + inline int32_t length(void) const; + + /** + * Count Unicode code points in the length char16_t code units of the string. + * A code point may occupy either one or two char16_t code units. + * Counting code points involves reading all code units. + * + * This functions is basically the inverse of moveIndex32(). + * + * @param start the index of the first code unit to check + * @param length the number of char16_t code units to check + * @return the number of code points in the specified code units + * @see length + * @stable ICU 2.0 + */ + int32_t + countChar32(int32_t start=0, int32_t length=INT32_MAX) const; + + /** + * Check if the length char16_t code units of the string + * contain more Unicode code points than a certain number. + * This is more efficient than counting all code points in this part of the string + * and comparing that number with a threshold. + * This function may not need to scan the string at all if the length + * falls within a certain range, and + * never needs to count more than 'number+1' code points. + * Logically equivalent to (countChar32(start, length)>number). + * A Unicode code point may occupy either one or two char16_t code units. + * + * @param start the index of the first code unit to check (0 for the entire string) + * @param length the number of char16_t code units to check + * (use INT32_MAX for the entire string; remember that start/length + * values are pinned) + * @param number The number of code points in the (sub)string is compared against + * the 'number' parameter. + * @return Boolean value for whether the string contains more Unicode code points + * than 'number'. Same as (u_countChar32(s, length)>number). + * @see countChar32 + * @see u_strHasMoreChar32Than + * @stable ICU 2.4 + */ + UBool + hasMoreChar32Than(int32_t start, int32_t length, int32_t number) const; + + /** + * Determine if this string is empty. + * @return true if this string contains 0 characters, false otherwise. + * @stable ICU 2.0 + */ + inline UBool isEmpty(void) const; + + /** + * Return the capacity of the internal buffer of the UnicodeString object. + * This is useful together with the getBuffer functions. + * See there for details. + * + * @return the number of char16_ts available in the internal buffer + * @see getBuffer + * @stable ICU 2.0 + */ + inline int32_t getCapacity(void) const; + + /* Other operations */ + + /** + * Generate a hash code for this object. + * @return The hash code of this UnicodeString. + * @stable ICU 2.0 + */ + inline int32_t hashCode(void) const; + + /** + * Determine if this object contains a valid string. + * A bogus string has no value. It is different from an empty string, + * although in both cases isEmpty() returns true and length() returns 0. + * setToBogus() and isBogus() can be used to indicate that no string value is available. + * For a bogus string, getBuffer() and getTerminatedBuffer() return NULL, and + * length() returns 0. + * + * @return true if the string is bogus/invalid, false otherwise + * @see setToBogus() + * @stable ICU 2.0 + */ + inline UBool isBogus(void) const; + + + //======================================== + // Write operations + //======================================== + + /* Assignment operations */ + + /** + * Assignment operator. Replace the characters in this UnicodeString + * with the characters from `srcText`. + * + * Starting with ICU 2.4, the assignment operator and the copy constructor + * allocate a new buffer and copy the buffer contents even for readonly aliases. + * By contrast, the fastCopyFrom() function implements the old, + * more efficient but less safe behavior + * of making this string also a readonly alias to the same buffer. + * + * If the source object has an "open" buffer from getBuffer(minCapacity), + * then the copy is an empty string. + * + * @param srcText The text containing the characters to replace + * @return a reference to this + * @stable ICU 2.0 + * @see fastCopyFrom + */ + UnicodeString &operator=(const UnicodeString &srcText); + + /** + * Almost the same as the assignment operator. + * Replace the characters in this UnicodeString + * with the characters from `srcText`. + * + * This function works the same as the assignment operator + * for all strings except for ones that are readonly aliases. + * + * Starting with ICU 2.4, the assignment operator and the copy constructor + * allocate a new buffer and copy the buffer contents even for readonly aliases. + * This function implements the old, more efficient but less safe behavior + * of making this string also a readonly alias to the same buffer. + * + * The fastCopyFrom function must be used only if it is known that the lifetime of + * this UnicodeString does not exceed the lifetime of the aliased buffer + * including its contents, for example for strings from resource bundles + * or aliases to string constants. + * + * If the source object has an "open" buffer from getBuffer(minCapacity), + * then the copy is an empty string. + * + * @param src The text containing the characters to replace. + * @return a reference to this + * @stable ICU 2.4 + */ + UnicodeString &fastCopyFrom(const UnicodeString &src); + + /** + * Move assignment operator; might leave src in bogus state. + * This string will have the same contents and state that the source string had. + * The behavior is undefined if *this and src are the same object. + * @param src source string + * @return *this + * @stable ICU 56 + */ + UnicodeString &operator=(UnicodeString &&src) U_NOEXCEPT; + + /** + * Swap strings. + * @param other other string + * @stable ICU 56 + */ + void swap(UnicodeString &other) U_NOEXCEPT; + + /** + * Non-member UnicodeString swap function. + * @param s1 will get s2's contents and state + * @param s2 will get s1's contents and state + * @stable ICU 56 + */ + friend inline void U_EXPORT2 + swap(UnicodeString &s1, UnicodeString &s2) U_NOEXCEPT { + s1.swap(s2); + } + + /** + * Assignment operator. Replace the characters in this UnicodeString + * with the code unit `ch`. + * @param ch the code unit to replace + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& operator= (char16_t ch); + + /** + * Assignment operator. Replace the characters in this UnicodeString + * with the code point `ch`. + * @param ch the code point to replace + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& operator= (UChar32 ch); + + /** + * Set the text in the UnicodeString object to the characters + * in `srcText` in the range + * [`srcStart`, `srcText.length()`). + * `srcText` is not modified. + * @param srcText the source for the new characters + * @param srcStart the offset into `srcText` where new characters + * will be obtained + * @return a reference to this + * @stable ICU 2.2 + */ + inline UnicodeString& setTo(const UnicodeString& srcText, + int32_t srcStart); + + /** + * Set the text in the UnicodeString object to the characters + * in `srcText` in the range + * [`srcStart`, `srcStart + srcLength`). + * `srcText` is not modified. + * @param srcText the source for the new characters + * @param srcStart the offset into `srcText` where new characters + * will be obtained + * @param srcLength the number of characters in `srcText` in the + * replace string. + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& setTo(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength); + + /** + * Set the text in the UnicodeString object to the characters in + * `srcText`. + * `srcText` is not modified. + * @param srcText the source for the new characters + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& setTo(const UnicodeString& srcText); + + /** + * Set the characters in the UnicodeString object to the characters + * in `srcChars`. `srcChars` is not modified. + * @param srcChars the source for the new characters + * @param srcLength the number of Unicode characters in srcChars. + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& setTo(const char16_t *srcChars, + int32_t srcLength); + + /** + * Set the characters in the UnicodeString object to the code unit + * `srcChar`. + * @param srcChar the code unit which becomes the UnicodeString's character + * content + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& setTo(char16_t srcChar); + + /** + * Set the characters in the UnicodeString object to the code point + * `srcChar`. + * @param srcChar the code point which becomes the UnicodeString's character + * content + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& setTo(UChar32 srcChar); + + /** + * Aliasing setTo() function, analogous to the readonly-aliasing char16_t* constructor. + * The text will be used for the UnicodeString object, but + * it will not be released when the UnicodeString is destroyed. + * This has copy-on-write semantics: + * When the string is modified, then the buffer is first copied into + * newly allocated memory. + * The aliased buffer is never modified. + * + * In an assignment to another UnicodeString, when using the copy constructor + * or the assignment operator, the text will be copied. + * When using fastCopyFrom(), the text will be aliased again, + * so that both strings then alias the same readonly-text. + * + * @param isTerminated specifies if `text` is `NUL`-terminated. + * This must be true if `textLength==-1`. + * @param text The characters to alias for the UnicodeString. + * @param textLength The number of Unicode characters in `text` to alias. + * If -1, then this constructor will determine the length + * by calling `u_strlen()`. + * @return a reference to this + * @stable ICU 2.0 + */ + UnicodeString &setTo(UBool isTerminated, + ConstChar16Ptr text, + int32_t textLength); + + /** + * Aliasing setTo() function, analogous to the writable-aliasing char16_t* constructor. + * The text will be used for the UnicodeString object, but + * it will not be released when the UnicodeString is destroyed. + * This has write-through semantics: + * For as long as the capacity of the buffer is sufficient, write operations + * will directly affect the buffer. When more capacity is necessary, then + * a new buffer will be allocated and the contents copied as with regularly + * constructed strings. + * In an assignment to another UnicodeString, the buffer will be copied. + * The extract(Char16Ptr dst) function detects whether the dst pointer is the same + * as the string buffer itself and will in this case not copy the contents. + * + * @param buffer The characters to alias for the UnicodeString. + * @param buffLength The number of Unicode characters in `buffer` to alias. + * @param buffCapacity The size of `buffer` in char16_ts. + * @return a reference to this + * @stable ICU 2.0 + */ + UnicodeString &setTo(char16_t *buffer, + int32_t buffLength, + int32_t buffCapacity); + + /** + * Make this UnicodeString object invalid. + * The string will test true with isBogus(). + * + * A bogus string has no value. It is different from an empty string. + * It can be used to indicate that no string value is available. + * getBuffer() and getTerminatedBuffer() return NULL, and + * length() returns 0. + * + * This utility function is used throughout the UnicodeString + * implementation to indicate that a UnicodeString operation failed, + * and may be used in other functions, + * especially but not exclusively when such functions do not + * take a UErrorCode for simplicity. + * + * The following methods, and no others, will clear a string object's bogus flag: + * - remove() + * - remove(0, INT32_MAX) + * - truncate(0) + * - operator=() (assignment operator) + * - setTo(...) + * + * The simplest ways to turn a bogus string into an empty one + * is to use the remove() function. + * Examples for other functions that are equivalent to "set to empty string": + * \code + * if(s.isBogus()) { + * s.remove(); // set to an empty string (remove all), or + * s.remove(0, INT32_MAX); // set to an empty string (remove all), or + * s.truncate(0); // set to an empty string (complete truncation), or + * s=UnicodeString(); // assign an empty string, or + * s.setTo((UChar32)-1); // set to a pseudo code point that is out of range, or + * s.setTo(u"", 0); // set to an empty C Unicode string + * } + * \endcode + * + * @see isBogus() + * @stable ICU 2.0 + */ + void setToBogus(); + + /** + * Set the character at the specified offset to the specified character. + * @param offset A valid offset into the text of the character to set + * @param ch The new character + * @return A reference to this + * @stable ICU 2.0 + */ + UnicodeString& setCharAt(int32_t offset, + char16_t ch); + + + /* Append operations */ + + /** + * Append operator. Append the code unit `ch` to the UnicodeString + * object. + * @param ch the code unit to be appended + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& operator+= (char16_t ch); + + /** + * Append operator. Append the code point `ch` to the UnicodeString + * object. + * @param ch the code point to be appended + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& operator+= (UChar32 ch); + + /** + * Append operator. Append the characters in `srcText` to the + * UnicodeString object. `srcText` is not modified. + * @param srcText the source for the new characters + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& operator+= (const UnicodeString& srcText); + + /** + * Append the characters + * in `srcText` in the range + * [`srcStart`, `srcStart + srcLength`) to the + * UnicodeString object at offset `start`. `srcText` + * is not modified. + * @param srcText the source for the new characters + * @param srcStart the offset into `srcText` where new characters + * will be obtained + * @param srcLength the number of characters in `srcText` in + * the append string + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& append(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength); + + /** + * Append the characters in `srcText` to the UnicodeString object. + * `srcText` is not modified. + * @param srcText the source for the new characters + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& append(const UnicodeString& srcText); + + /** + * Append the characters in `srcChars` in the range + * [`srcStart`, `srcStart + srcLength`) to the UnicodeString + * object at offset + * `start`. `srcChars` is not modified. + * @param srcChars the source for the new characters + * @param srcStart the offset into `srcChars` where new characters + * will be obtained + * @param srcLength the number of characters in `srcChars` in + * the append string; can be -1 if `srcChars` is NUL-terminated + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& append(const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength); + + /** + * Append the characters in `srcChars` to the UnicodeString object + * at offset `start`. `srcChars` is not modified. + * @param srcChars the source for the new characters + * @param srcLength the number of Unicode characters in `srcChars`; + * can be -1 if `srcChars` is NUL-terminated + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& append(ConstChar16Ptr srcChars, + int32_t srcLength); + + /** + * Append the code unit `srcChar` to the UnicodeString object. + * @param srcChar the code unit to append + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& append(char16_t srcChar); + + /** + * Append the code point `srcChar` to the UnicodeString object. + * @param srcChar the code point to append + * @return a reference to this + * @stable ICU 2.0 + */ + UnicodeString& append(UChar32 srcChar); + + + /* Insert operations */ + + /** + * Insert the characters in `srcText` in the range + * [`srcStart`, `srcStart + srcLength`) into the UnicodeString + * object at offset `start`. `srcText` is not modified. + * @param start the offset where the insertion begins + * @param srcText the source for the new characters + * @param srcStart the offset into `srcText` where new characters + * will be obtained + * @param srcLength the number of characters in `srcText` in + * the insert string + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& insert(int32_t start, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength); + + /** + * Insert the characters in `srcText` into the UnicodeString object + * at offset `start`. `srcText` is not modified. + * @param start the offset where the insertion begins + * @param srcText the source for the new characters + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& insert(int32_t start, + const UnicodeString& srcText); + + /** + * Insert the characters in `srcChars` in the range + * [`srcStart`, `srcStart + srcLength`) into the UnicodeString + * object at offset `start`. `srcChars` is not modified. + * @param start the offset at which the insertion begins + * @param srcChars the source for the new characters + * @param srcStart the offset into `srcChars` where new characters + * will be obtained + * @param srcLength the number of characters in `srcChars` + * in the insert string + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& insert(int32_t start, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength); + + /** + * Insert the characters in `srcChars` into the UnicodeString object + * at offset `start`. `srcChars` is not modified. + * @param start the offset where the insertion begins + * @param srcChars the source for the new characters + * @param srcLength the number of Unicode characters in srcChars. + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& insert(int32_t start, + ConstChar16Ptr srcChars, + int32_t srcLength); + + /** + * Insert the code unit `srcChar` into the UnicodeString object at + * offset `start`. + * @param start the offset at which the insertion occurs + * @param srcChar the code unit to insert + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& insert(int32_t start, + char16_t srcChar); + + /** + * Insert the code point `srcChar` into the UnicodeString object at + * offset `start`. + * @param start the offset at which the insertion occurs + * @param srcChar the code point to insert + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& insert(int32_t start, + UChar32 srcChar); + + + /* Replace operations */ + + /** + * Replace the characters in the range + * [`start`, `start + length`) with the characters in + * `srcText` in the range + * [`srcStart`, `srcStart + srcLength`). + * `srcText` is not modified. + * @param start the offset at which the replace operation begins + * @param length the number of characters to replace. The character at + * `start + length` is not modified. + * @param srcText the source for the new characters + * @param srcStart the offset into `srcText` where new characters + * will be obtained + * @param srcLength the number of characters in `srcText` in + * the replace string + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& replace(int32_t start, + int32_t length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength); + + /** + * Replace the characters in the range + * [`start`, `start + length`) + * with the characters in `srcText`. `srcText` is + * not modified. + * @param start the offset at which the replace operation begins + * @param length the number of characters to replace. The character at + * `start + length` is not modified. + * @param srcText the source for the new characters + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& replace(int32_t start, + int32_t length, + const UnicodeString& srcText); + + /** + * Replace the characters in the range + * [`start`, `start + length`) with the characters in + * `srcChars` in the range + * [`srcStart`, `srcStart + srcLength`). `srcChars` + * is not modified. + * @param start the offset at which the replace operation begins + * @param length the number of characters to replace. The character at + * `start + length` is not modified. + * @param srcChars the source for the new characters + * @param srcStart the offset into `srcChars` where new characters + * will be obtained + * @param srcLength the number of characters in `srcChars` + * in the replace string + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& replace(int32_t start, + int32_t length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength); + + /** + * Replace the characters in the range + * [`start`, `start + length`) with the characters in + * `srcChars`. `srcChars` is not modified. + * @param start the offset at which the replace operation begins + * @param length number of characters to replace. The character at + * `start + length` is not modified. + * @param srcChars the source for the new characters + * @param srcLength the number of Unicode characters in srcChars + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& replace(int32_t start, + int32_t length, + ConstChar16Ptr srcChars, + int32_t srcLength); + + /** + * Replace the characters in the range + * [`start`, `start + length`) with the code unit + * `srcChar`. + * @param start the offset at which the replace operation begins + * @param length the number of characters to replace. The character at + * `start + length` is not modified. + * @param srcChar the new code unit + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& replace(int32_t start, + int32_t length, + char16_t srcChar); + + /** + * Replace the characters in the range + * [`start`, `start + length`) with the code point + * `srcChar`. + * @param start the offset at which the replace operation begins + * @param length the number of characters to replace. The character at + * `start + length` is not modified. + * @param srcChar the new code point + * @return a reference to this + * @stable ICU 2.0 + */ + UnicodeString& replace(int32_t start, int32_t length, UChar32 srcChar); + + /** + * Replace the characters in the range [`start`, `limit`) + * with the characters in `srcText`. `srcText` is not modified. + * @param start the offset at which the replace operation begins + * @param limit the offset immediately following the replace range + * @param srcText the source for the new characters + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& replaceBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText); + + /** + * Replace the characters in the range [`start`, `limit`) + * with the characters in `srcText` in the range + * [`srcStart`, `srcLimit`). `srcText` is not modified. + * @param start the offset at which the replace operation begins + * @param limit the offset immediately following the replace range + * @param srcText the source for the new characters + * @param srcStart the offset into `srcChars` where new characters + * will be obtained + * @param srcLimit the offset immediately following the range to copy + * in `srcText` + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& replaceBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLimit); + + /** + * Replace a substring of this object with the given text. + * @param start the beginning index, inclusive; `0 <= start <= limit`. + * @param limit the ending index, exclusive; `start <= limit <= length()`. + * @param text the text to replace characters `start` to `limit - 1` + * @stable ICU 2.0 + */ + virtual void handleReplaceBetween(int32_t start, + int32_t limit, + const UnicodeString& text); + + /** + * Replaceable API + * @return true if it has MetaData + * @stable ICU 2.4 + */ + virtual UBool hasMetaData() const; + + /** + * Copy a substring of this object, retaining attribute (out-of-band) + * information. This method is used to duplicate or reorder substrings. + * The destination index must not overlap the source range. + * + * @param start the beginning index, inclusive; `0 <= start <= limit`. + * @param limit the ending index, exclusive; `start <= limit <= length()`. + * @param dest the destination index. The characters from + * `start..limit-1` will be copied to `dest`. + * Implementations of this method may assume that `dest <= start || + * dest >= limit`. + * @stable ICU 2.0 + */ + virtual void copy(int32_t start, int32_t limit, int32_t dest); + + /* Search and replace operations */ + + /** + * Replace all occurrences of characters in oldText with the characters + * in newText + * @param oldText the text containing the search text + * @param newText the text containing the replacement text + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& findAndReplace(const UnicodeString& oldText, + const UnicodeString& newText); + + /** + * Replace all occurrences of characters in oldText with characters + * in newText + * in the range [`start`, `start + length`). + * @param start the start of the range in which replace will performed + * @param length the length of the range in which replace will be performed + * @param oldText the text containing the search text + * @param newText the text containing the replacement text + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& findAndReplace(int32_t start, + int32_t length, + const UnicodeString& oldText, + const UnicodeString& newText); + + /** + * Replace all occurrences of characters in oldText in the range + * [`oldStart`, `oldStart + oldLength`) with the characters + * in newText in the range + * [`newStart`, `newStart + newLength`) + * in the range [`start`, `start + length`). + * @param start the start of the range in which replace will performed + * @param length the length of the range in which replace will be performed + * @param oldText the text containing the search text + * @param oldStart the start of the search range in `oldText` + * @param oldLength the length of the search range in `oldText` + * @param newText the text containing the replacement text + * @param newStart the start of the replacement range in `newText` + * @param newLength the length of the replacement range in `newText` + * @return a reference to this + * @stable ICU 2.0 + */ + UnicodeString& findAndReplace(int32_t start, + int32_t length, + const UnicodeString& oldText, + int32_t oldStart, + int32_t oldLength, + const UnicodeString& newText, + int32_t newStart, + int32_t newLength); + + + /* Remove operations */ + + /** + * Removes all characters from the UnicodeString object and clears the bogus flag. + * This is the UnicodeString equivalent of std::string’s clear(). + * + * @return a reference to this + * @see setToBogus + * @stable ICU 2.0 + */ + inline UnicodeString& remove(); + + /** + * Remove the characters in the range + * [`start`, `start + length`) from the UnicodeString object. + * @param start the offset of the first character to remove + * @param length the number of characters to remove + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& remove(int32_t start, + int32_t length = (int32_t)INT32_MAX); + + /** + * Remove the characters in the range + * [`start`, `limit`) from the UnicodeString object. + * @param start the offset of the first character to remove + * @param limit the offset immediately following the range to remove + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& removeBetween(int32_t start, + int32_t limit = (int32_t)INT32_MAX); + + /** + * Retain only the characters in the range + * [`start`, `limit`) from the UnicodeString object. + * Removes characters before `start` and at and after `limit`. + * @param start the offset of the first character to retain + * @param limit the offset immediately following the range to retain + * @return a reference to this + * @stable ICU 4.4 + */ + inline UnicodeString &retainBetween(int32_t start, int32_t limit = INT32_MAX); + + /* Length operations */ + + /** + * Pad the start of this UnicodeString with the character `padChar`. + * If the length of this UnicodeString is less than targetLength, + * length() - targetLength copies of padChar will be added to the + * beginning of this UnicodeString. + * @param targetLength the desired length of the string + * @param padChar the character to use for padding. Defaults to + * space (U+0020) + * @return true if the text was padded, false otherwise. + * @stable ICU 2.0 + */ + UBool padLeading(int32_t targetLength, + char16_t padChar = 0x0020); + + /** + * Pad the end of this UnicodeString with the character `padChar`. + * If the length of this UnicodeString is less than targetLength, + * length() - targetLength copies of padChar will be added to the + * end of this UnicodeString. + * @param targetLength the desired length of the string + * @param padChar the character to use for padding. Defaults to + * space (U+0020) + * @return true if the text was padded, false otherwise. + * @stable ICU 2.0 + */ + UBool padTrailing(int32_t targetLength, + char16_t padChar = 0x0020); + + /** + * Truncate this UnicodeString to the `targetLength`. + * @param targetLength the desired length of this UnicodeString. + * @return true if the text was truncated, false otherwise + * @stable ICU 2.0 + */ + inline UBool truncate(int32_t targetLength); + + /** + * Trims leading and trailing whitespace from this UnicodeString. + * @return a reference to this + * @stable ICU 2.0 + */ + UnicodeString& trim(void); + + + /* Miscellaneous operations */ + + /** + * Reverse this UnicodeString in place. + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& reverse(void); + + /** + * Reverse the range [`start`, `start + length`) in + * this UnicodeString. + * @param start the start of the range to reverse + * @param length the number of characters to to reverse + * @return a reference to this + * @stable ICU 2.0 + */ + inline UnicodeString& reverse(int32_t start, + int32_t length); + + /** + * Convert the characters in this to UPPER CASE following the conventions of + * the default locale. + * @return A reference to this. + * @stable ICU 2.0 + */ + UnicodeString& toUpper(void); + + /** + * Convert the characters in this to UPPER CASE following the conventions of + * a specific locale. + * @param locale The locale containing the conventions to use. + * @return A reference to this. + * @stable ICU 2.0 + */ + UnicodeString& toUpper(const Locale& locale); + + /** + * Convert the characters in this to lower case following the conventions of + * the default locale. + * @return A reference to this. + * @stable ICU 2.0 + */ + UnicodeString& toLower(void); + + /** + * Convert the characters in this to lower case following the conventions of + * a specific locale. + * @param locale The locale containing the conventions to use. + * @return A reference to this. + * @stable ICU 2.0 + */ + UnicodeString& toLower(const Locale& locale); + +#if !UCONFIG_NO_BREAK_ITERATION + + /** + * Titlecase this string, convenience function using the default locale. + * + * Casing is locale-dependent and context-sensitive. + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. + * + * The titlecase break iterator can be provided to customize for arbitrary + * styles, using rules and dictionaries beyond the standard iterators. + * It may be more efficient to always provide an iterator to avoid + * opening and closing one for each string. + * The standard titlecase iterator for the root locale implements the + * algorithm of Unicode TR 21. + * + * This function uses only the setText(), first() and next() methods of the + * provided break iterator. + * + * @param titleIter A break iterator to find the first characters of words + * that are to be titlecased. + * If none is provided (0), then a standard titlecase + * break iterator is opened. + * Otherwise the provided iterator is set to the string's text. + * @return A reference to this. + * @stable ICU 2.1 + */ + UnicodeString &toTitle(BreakIterator *titleIter); + + /** + * Titlecase this string. + * + * Casing is locale-dependent and context-sensitive. + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. + * + * The titlecase break iterator can be provided to customize for arbitrary + * styles, using rules and dictionaries beyond the standard iterators. + * It may be more efficient to always provide an iterator to avoid + * opening and closing one for each string. + * The standard titlecase iterator for the root locale implements the + * algorithm of Unicode TR 21. + * + * This function uses only the setText(), first() and next() methods of the + * provided break iterator. + * + * @param titleIter A break iterator to find the first characters of words + * that are to be titlecased. + * If none is provided (0), then a standard titlecase + * break iterator is opened. + * Otherwise the provided iterator is set to the string's text. + * @param locale The locale to consider. + * @return A reference to this. + * @stable ICU 2.1 + */ + UnicodeString &toTitle(BreakIterator *titleIter, const Locale &locale); + + /** + * Titlecase this string, with options. + * + * Casing is locale-dependent and context-sensitive. + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. (This can be modified with options.) + * + * The titlecase break iterator can be provided to customize for arbitrary + * styles, using rules and dictionaries beyond the standard iterators. + * It may be more efficient to always provide an iterator to avoid + * opening and closing one for each string. + * The standard titlecase iterator for the root locale implements the + * algorithm of Unicode TR 21. + * + * This function uses only the setText(), first() and next() methods of the + * provided break iterator. + * + * @param titleIter A break iterator to find the first characters of words + * that are to be titlecased. + * If none is provided (0), then a standard titlecase + * break iterator is opened. + * Otherwise the provided iterator is set to the string's text. + * @param locale The locale to consider. + * @param options Options bit set, usually 0. See U_TITLECASE_NO_LOWERCASE, + * U_TITLECASE_NO_BREAK_ADJUSTMENT, U_TITLECASE_ADJUST_TO_CASED, + * U_TITLECASE_WHOLE_STRING, U_TITLECASE_SENTENCES. + * @param options Options bit set, see ucasemap_open(). + * @return A reference to this. + * @stable ICU 3.8 + */ + UnicodeString &toTitle(BreakIterator *titleIter, const Locale &locale, uint32_t options); + +#endif + + /** + * Case-folds the characters in this string. + * + * Case-folding is locale-independent and not context-sensitive, + * but there is an option for whether to include or exclude mappings for dotted I + * and dotless i that are marked with 'T' in CaseFolding.txt. + * + * The result may be longer or shorter than the original. + * + * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I + * @return A reference to this. + * @stable ICU 2.0 + */ + UnicodeString &foldCase(uint32_t options=0 /*U_FOLD_CASE_DEFAULT*/); + + //======================================== + // Access to the internal buffer + //======================================== + + /** + * Get a read/write pointer to the internal buffer. + * The buffer is guaranteed to be large enough for at least minCapacity char16_ts, + * writable, and is still owned by the UnicodeString object. + * Calls to getBuffer(minCapacity) must not be nested, and + * must be matched with calls to releaseBuffer(newLength). + * If the string buffer was read-only or shared, + * then it will be reallocated and copied. + * + * An attempted nested call will return 0, and will not further modify the + * state of the UnicodeString object. + * It also returns 0 if the string is bogus. + * + * The actual capacity of the string buffer may be larger than minCapacity. + * getCapacity() returns the actual capacity. + * For many operations, the full capacity should be used to avoid reallocations. + * + * While the buffer is "open" between getBuffer(minCapacity) + * and releaseBuffer(newLength), the following applies: + * - The string length is set to 0. + * - Any read API call on the UnicodeString object will behave like on a 0-length string. + * - Any write API call on the UnicodeString object is disallowed and will have no effect. + * - You can read from and write to the returned buffer. + * - The previous string contents will still be in the buffer; + * if you want to use it, then you need to call length() before getBuffer(minCapacity). + * If the length() was greater than minCapacity, then any contents after minCapacity + * may be lost. + * The buffer contents is not NUL-terminated by getBuffer(). + * If length() < getCapacity() then you can terminate it by writing a NUL + * at index length(). + * - You must call releaseBuffer(newLength) before and in order to + * return to normal UnicodeString operation. + * + * @param minCapacity the minimum number of char16_ts that are to be available + * in the buffer, starting at the returned pointer; + * default to the current string capacity if minCapacity==-1 + * @return a writable pointer to the internal string buffer, + * or nullptr if an error occurs (nested calls, out of memory) + * + * @see releaseBuffer + * @see getTerminatedBuffer() + * @stable ICU 2.0 + */ + char16_t *getBuffer(int32_t minCapacity); + + /** + * Release a read/write buffer on a UnicodeString object with an + * "open" getBuffer(minCapacity). + * This function must be called in a matched pair with getBuffer(minCapacity). + * releaseBuffer(newLength) must be called if and only if a getBuffer(minCapacity) is "open". + * + * It will set the string length to newLength, at most to the current capacity. + * If newLength==-1 then it will set the length according to the + * first NUL in the buffer, or to the capacity if there is no NUL. + * + * After calling releaseBuffer(newLength) the UnicodeString is back to normal operation. + * + * @param newLength the new length of the UnicodeString object; + * defaults to the current capacity if newLength is greater than that; + * if newLength==-1, it defaults to u_strlen(buffer) but not more than + * the current capacity of the string + * + * @see getBuffer(int32_t minCapacity) + * @stable ICU 2.0 + */ + void releaseBuffer(int32_t newLength=-1); + + /** + * Get a read-only pointer to the internal buffer. + * This can be called at any time on a valid UnicodeString. + * + * It returns 0 if the string is bogus, or + * during an "open" getBuffer(minCapacity). + * + * It can be called as many times as desired. + * The pointer that it returns will remain valid until the UnicodeString object is modified, + * at which time the pointer is semantically invalidated and must not be used any more. + * + * The capacity of the buffer can be determined with getCapacity(). + * The part after length() may or may not be initialized and valid, + * depending on the history of the UnicodeString object. + * + * The buffer contents is (probably) not NUL-terminated. + * You can check if it is with + * `(s.length() < s.getCapacity() && buffer[s.length()]==0)`. + * (See getTerminatedBuffer().) + * + * The buffer may reside in read-only memory. Its contents must not + * be modified. + * + * @return a read-only pointer to the internal string buffer, + * or nullptr if the string is empty or bogus + * + * @see getBuffer(int32_t minCapacity) + * @see getTerminatedBuffer() + * @stable ICU 2.0 + */ + inline const char16_t *getBuffer() const; + + /** + * Get a read-only pointer to the internal buffer, + * making sure that it is NUL-terminated. + * This can be called at any time on a valid UnicodeString. + * + * It returns 0 if the string is bogus, or + * during an "open" getBuffer(minCapacity), or if the buffer cannot + * be NUL-terminated (because memory allocation failed). + * + * It can be called as many times as desired. + * The pointer that it returns will remain valid until the UnicodeString object is modified, + * at which time the pointer is semantically invalidated and must not be used any more. + * + * The capacity of the buffer can be determined with getCapacity(). + * The part after length()+1 may or may not be initialized and valid, + * depending on the history of the UnicodeString object. + * + * The buffer contents is guaranteed to be NUL-terminated. + * getTerminatedBuffer() may reallocate the buffer if a terminating NUL + * is written. + * For this reason, this function is not const, unlike getBuffer(). + * Note that a UnicodeString may also contain NUL characters as part of its contents. + * + * The buffer may reside in read-only memory. Its contents must not + * be modified. + * + * @return a read-only pointer to the internal string buffer, + * or 0 if the string is empty or bogus + * + * @see getBuffer(int32_t minCapacity) + * @see getBuffer() + * @stable ICU 2.2 + */ + const char16_t *getTerminatedBuffer(); + + //======================================== + // Constructors + //======================================== + + /** Construct an empty UnicodeString. + * @stable ICU 2.0 + */ + inline UnicodeString(); + + /** + * Construct a UnicodeString with capacity to hold `capacity` char16_ts + * @param capacity the number of char16_ts this UnicodeString should hold + * before a resize is necessary; if count is greater than 0 and count + * code points c take up more space than capacity, then capacity is adjusted + * accordingly. + * @param c is used to initially fill the string + * @param count specifies how many code points c are to be written in the + * string + * @stable ICU 2.0 + */ + UnicodeString(int32_t capacity, UChar32 c, int32_t count); + + /** + * Single char16_t (code unit) constructor. + * + * It is recommended to mark this constructor "explicit" by + * `-DUNISTR_FROM_CHAR_EXPLICIT=explicit` + * on the compiler command line or similar. + * @param ch the character to place in the UnicodeString + * @stable ICU 2.0 + */ + UNISTR_FROM_CHAR_EXPLICIT UnicodeString(char16_t ch); + + /** + * Single UChar32 (code point) constructor. + * + * It is recommended to mark this constructor "explicit" by + * `-DUNISTR_FROM_CHAR_EXPLICIT=explicit` + * on the compiler command line or similar. + * @param ch the character to place in the UnicodeString + * @stable ICU 2.0 + */ + UNISTR_FROM_CHAR_EXPLICIT UnicodeString(UChar32 ch); + + /** + * char16_t* constructor. + * + * It is recommended to mark this constructor "explicit" by + * `-DUNISTR_FROM_STRING_EXPLICIT=explicit` + * on the compiler command line or similar. + * @param text The characters to place in the UnicodeString. `text` + * must be NULL (U+0000) terminated. + * @stable ICU 2.0 + */ + UNISTR_FROM_STRING_EXPLICIT UnicodeString(const char16_t *text); + +#if !U_CHAR16_IS_TYPEDEF + /** + * uint16_t * constructor. + * Delegates to UnicodeString(const char16_t *). + * + * It is recommended to mark this constructor "explicit" by + * `-DUNISTR_FROM_STRING_EXPLICIT=explicit` + * on the compiler command line or similar. + * @param text NUL-terminated UTF-16 string + * @stable ICU 59 + */ + UNISTR_FROM_STRING_EXPLICIT UnicodeString(const uint16_t *text) : + UnicodeString(ConstChar16Ptr(text)) {} +#endif + +#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN) + /** + * wchar_t * constructor. + * (Only defined if U_SIZEOF_WCHAR_T==2.) + * Delegates to UnicodeString(const char16_t *). + * + * It is recommended to mark this constructor "explicit" by + * `-DUNISTR_FROM_STRING_EXPLICIT=explicit` + * on the compiler command line or similar. + * @param text NUL-terminated UTF-16 string + * @stable ICU 59 + */ + UNISTR_FROM_STRING_EXPLICIT UnicodeString(const wchar_t *text) : + UnicodeString(ConstChar16Ptr(text)) {} +#endif + + /** + * nullptr_t constructor. + * Effectively the same as the default constructor, makes an empty string object. + * + * It is recommended to mark this constructor "explicit" by + * `-DUNISTR_FROM_STRING_EXPLICIT=explicit` + * on the compiler command line or similar. + * @param text nullptr + * @stable ICU 59 + */ + UNISTR_FROM_STRING_EXPLICIT inline UnicodeString(const std::nullptr_t text); + + /** + * char16_t* constructor. + * @param text The characters to place in the UnicodeString. + * @param textLength The number of Unicode characters in `text` + * to copy. + * @stable ICU 2.0 + */ + UnicodeString(const char16_t *text, + int32_t textLength); + +#if !U_CHAR16_IS_TYPEDEF + /** + * uint16_t * constructor. + * Delegates to UnicodeString(const char16_t *, int32_t). + * @param text UTF-16 string + * @param textLength string length + * @stable ICU 59 + */ + UnicodeString(const uint16_t *text, int32_t textLength) : + UnicodeString(ConstChar16Ptr(text), textLength) {} +#endif + +#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN) + /** + * wchar_t * constructor. + * (Only defined if U_SIZEOF_WCHAR_T==2.) + * Delegates to UnicodeString(const char16_t *, int32_t). + * @param text NUL-terminated UTF-16 string + * @param textLength string length + * @stable ICU 59 + */ + UnicodeString(const wchar_t *text, int32_t textLength) : + UnicodeString(ConstChar16Ptr(text), textLength) {} +#endif + + /** + * nullptr_t constructor. + * Effectively the same as the default constructor, makes an empty string object. + * @param text nullptr + * @param textLength ignored + * @stable ICU 59 + */ + inline UnicodeString(const std::nullptr_t text, int32_t textLength); + + /** + * Readonly-aliasing char16_t* constructor. + * The text will be used for the UnicodeString object, but + * it will not be released when the UnicodeString is destroyed. + * This has copy-on-write semantics: + * When the string is modified, then the buffer is first copied into + * newly allocated memory. + * The aliased buffer is never modified. + * + * In an assignment to another UnicodeString, when using the copy constructor + * or the assignment operator, the text will be copied. + * When using fastCopyFrom(), the text will be aliased again, + * so that both strings then alias the same readonly-text. + * + * @param isTerminated specifies if `text` is `NUL`-terminated. + * This must be true if `textLength==-1`. + * @param text The characters to alias for the UnicodeString. + * @param textLength The number of Unicode characters in `text` to alias. + * If -1, then this constructor will determine the length + * by calling `u_strlen()`. + * @stable ICU 2.0 + */ + UnicodeString(UBool isTerminated, + ConstChar16Ptr text, + int32_t textLength); + + /** + * Writable-aliasing char16_t* constructor. + * The text will be used for the UnicodeString object, but + * it will not be released when the UnicodeString is destroyed. + * This has write-through semantics: + * For as long as the capacity of the buffer is sufficient, write operations + * will directly affect the buffer. When more capacity is necessary, then + * a new buffer will be allocated and the contents copied as with regularly + * constructed strings. + * In an assignment to another UnicodeString, the buffer will be copied. + * The extract(Char16Ptr dst) function detects whether the dst pointer is the same + * as the string buffer itself and will in this case not copy the contents. + * + * @param buffer The characters to alias for the UnicodeString. + * @param buffLength The number of Unicode characters in `buffer` to alias. + * @param buffCapacity The size of `buffer` in char16_ts. + * @stable ICU 2.0 + */ + UnicodeString(char16_t *buffer, int32_t buffLength, int32_t buffCapacity); + +#if !U_CHAR16_IS_TYPEDEF + /** + * Writable-aliasing uint16_t * constructor. + * Delegates to UnicodeString(const char16_t *, int32_t, int32_t). + * @param buffer writable buffer of/for UTF-16 text + * @param buffLength length of the current buffer contents + * @param buffCapacity buffer capacity + * @stable ICU 59 + */ + UnicodeString(uint16_t *buffer, int32_t buffLength, int32_t buffCapacity) : + UnicodeString(Char16Ptr(buffer), buffLength, buffCapacity) {} +#endif + +#if U_SIZEOF_WCHAR_T==2 || defined(U_IN_DOXYGEN) + /** + * Writable-aliasing wchar_t * constructor. + * (Only defined if U_SIZEOF_WCHAR_T==2.) + * Delegates to UnicodeString(const char16_t *, int32_t, int32_t). + * @param buffer writable buffer of/for UTF-16 text + * @param buffLength length of the current buffer contents + * @param buffCapacity buffer capacity + * @stable ICU 59 + */ + UnicodeString(wchar_t *buffer, int32_t buffLength, int32_t buffCapacity) : + UnicodeString(Char16Ptr(buffer), buffLength, buffCapacity) {} +#endif + + /** + * Writable-aliasing nullptr_t constructor. + * Effectively the same as the default constructor, makes an empty string object. + * @param buffer nullptr + * @param buffLength ignored + * @param buffCapacity ignored + * @stable ICU 59 + */ + inline UnicodeString(std::nullptr_t buffer, int32_t buffLength, int32_t buffCapacity); + +#if U_CHARSET_IS_UTF8 || !UCONFIG_NO_CONVERSION + + /** + * char* constructor. + * Uses the default converter (and thus depends on the ICU conversion code) + * unless U_CHARSET_IS_UTF8 is set to 1. + * + * For ASCII (really "invariant character") strings it is more efficient to use + * the constructor that takes a US_INV (for its enum EInvariant). + * For ASCII (invariant-character) string literals, see UNICODE_STRING and + * UNICODE_STRING_SIMPLE. + * + * It is recommended to mark this constructor "explicit" by + * `-DUNISTR_FROM_STRING_EXPLICIT=explicit` + * on the compiler command line or similar. + * @param codepageData an array of bytes, null-terminated, + * in the platform's default codepage. + * @stable ICU 2.0 + * @see UNICODE_STRING + * @see UNICODE_STRING_SIMPLE + */ + UNISTR_FROM_STRING_EXPLICIT UnicodeString(const char *codepageData); + + /** + * char* constructor. + * Uses the default converter (and thus depends on the ICU conversion code) + * unless U_CHARSET_IS_UTF8 is set to 1. + * @param codepageData an array of bytes in the platform's default codepage. + * @param dataLength The number of bytes in `codepageData`. + * @stable ICU 2.0 + */ + UnicodeString(const char *codepageData, int32_t dataLength); + +#endif + +#if !UCONFIG_NO_CONVERSION + + /** + * char* constructor. + * @param codepageData an array of bytes, null-terminated + * @param codepage the encoding of `codepageData`. The special + * value 0 for `codepage` indicates that the text is in the + * platform's default codepage. + * + * If `codepage` is an empty string (`""`), + * then a simple conversion is performed on the codepage-invariant + * subset ("invariant characters") of the platform encoding. See utypes.h. + * Recommendation: For invariant-character strings use the constructor + * UnicodeString(const char *src, int32_t length, enum EInvariant inv) + * because it avoids object code dependencies of UnicodeString on + * the conversion code. + * + * @stable ICU 2.0 + */ + UnicodeString(const char *codepageData, const char *codepage); + + /** + * char* constructor. + * @param codepageData an array of bytes. + * @param dataLength The number of bytes in `codepageData`. + * @param codepage the encoding of `codepageData`. The special + * value 0 for `codepage` indicates that the text is in the + * platform's default codepage. + * If `codepage` is an empty string (`""`), + * then a simple conversion is performed on the codepage-invariant + * subset ("invariant characters") of the platform encoding. See utypes.h. + * Recommendation: For invariant-character strings use the constructor + * UnicodeString(const char *src, int32_t length, enum EInvariant inv) + * because it avoids object code dependencies of UnicodeString on + * the conversion code. + * + * @stable ICU 2.0 + */ + UnicodeString(const char *codepageData, int32_t dataLength, const char *codepage); + + /** + * char * / UConverter constructor. + * This constructor uses an existing UConverter object to + * convert the codepage string to Unicode and construct a UnicodeString + * from that. + * + * The converter is reset at first. + * If the error code indicates a failure before this constructor is called, + * or if an error occurs during conversion or construction, + * then the string will be bogus. + * + * This function avoids the overhead of opening and closing a converter if + * multiple strings are constructed. + * + * @param src input codepage string + * @param srcLength length of the input string, can be -1 for NUL-terminated strings + * @param cnv converter object (ucnv_resetToUnicode() will be called), + * can be NULL for the default converter + * @param errorCode normal ICU error code + * @stable ICU 2.0 + */ + UnicodeString( + const char *src, int32_t srcLength, + UConverter *cnv, + UErrorCode &errorCode); + +#endif + + /** + * Constructs a Unicode string from an invariant-character char * string. + * About invariant characters see utypes.h. + * This constructor has no runtime dependency on conversion code and is + * therefore recommended over ones taking a charset name string + * (where the empty string "" indicates invariant-character conversion). + * + * Use the macro US_INV as the third, signature-distinguishing parameter. + * + * For example: + * \code + * void fn(const char *s) { + * UnicodeString ustr(s, -1, US_INV); + * // use ustr ... + * } + * \endcode + * @param src String using only invariant characters. + * @param textLength Length of src, or -1 if NUL-terminated. + * @param inv Signature-distinguishing paramater, use US_INV. + * + * @see US_INV + * @stable ICU 3.2 + */ + UnicodeString(const char *src, int32_t textLength, enum EInvariant inv); + + + /** + * Copy constructor. + * + * Starting with ICU 2.4, the assignment operator and the copy constructor + * allocate a new buffer and copy the buffer contents even for readonly aliases. + * By contrast, the fastCopyFrom() function implements the old, + * more efficient but less safe behavior + * of making this string also a readonly alias to the same buffer. + * + * If the source object has an "open" buffer from getBuffer(minCapacity), + * then the copy is an empty string. + * + * @param that The UnicodeString object to copy. + * @stable ICU 2.0 + * @see fastCopyFrom + */ + UnicodeString(const UnicodeString& that); + + /** + * Move constructor; might leave src in bogus state. + * This string will have the same contents and state that the source string had. + * @param src source string + * @stable ICU 56 + */ + UnicodeString(UnicodeString &&src) U_NOEXCEPT; + + /** + * 'Substring' constructor from tail of source string. + * @param src The UnicodeString object to copy. + * @param srcStart The offset into `src` at which to start copying. + * @stable ICU 2.2 + */ + UnicodeString(const UnicodeString& src, int32_t srcStart); + + /** + * 'Substring' constructor from subrange of source string. + * @param src The UnicodeString object to copy. + * @param srcStart The offset into `src` at which to start copying. + * @param srcLength The number of characters from `src` to copy. + * @stable ICU 2.2 + */ + UnicodeString(const UnicodeString& src, int32_t srcStart, int32_t srcLength); + + /** + * Clone this object, an instance of a subclass of Replaceable. + * Clones can be used concurrently in multiple threads. + * If a subclass does not implement clone(), or if an error occurs, + * then NULL is returned. + * The caller must delete the clone. + * + * @return a clone of this object + * + * @see Replaceable::clone + * @see getDynamicClassID + * @stable ICU 2.6 + */ + virtual UnicodeString *clone() const; + + /** Destructor. + * @stable ICU 2.0 + */ + virtual ~UnicodeString(); + + /** + * Create a UnicodeString from a UTF-8 string. + * Illegal input is replaced with U+FFFD. Otherwise, errors result in a bogus string. + * Calls u_strFromUTF8WithSub(). + * + * @param utf8 UTF-8 input string. + * Note that a StringPiece can be implicitly constructed + * from a std::string or a NUL-terminated const char * string. + * @return A UnicodeString with equivalent UTF-16 contents. + * @see toUTF8 + * @see toUTF8String + * @stable ICU 4.2 + */ + static UnicodeString fromUTF8(StringPiece utf8); + + /** + * Create a UnicodeString from a UTF-32 string. + * Illegal input is replaced with U+FFFD. Otherwise, errors result in a bogus string. + * Calls u_strFromUTF32WithSub(). + * + * @param utf32 UTF-32 input string. Must not be NULL. + * @param length Length of the input string, or -1 if NUL-terminated. + * @return A UnicodeString with equivalent UTF-16 contents. + * @see toUTF32 + * @stable ICU 4.2 + */ + static UnicodeString fromUTF32(const UChar32 *utf32, int32_t length); + + /* Miscellaneous operations */ + + /** + * Unescape a string of characters and return a string containing + * the result. The following escape sequences are recognized: + * + * \\uhhhh 4 hex digits; h in [0-9A-Fa-f] + * \\Uhhhhhhhh 8 hex digits + * \\xhh 1-2 hex digits + * \\ooo 1-3 octal digits; o in [0-7] + * \\cX control-X; X is masked with 0x1F + * + * as well as the standard ANSI C escapes: + * + * \\a => U+0007, \\b => U+0008, \\t => U+0009, \\n => U+000A, + * \\v => U+000B, \\f => U+000C, \\r => U+000D, \\e => U+001B, + * \\" => U+0022, \\' => U+0027, \\? => U+003F, \\\\ => U+005C + * + * Anything else following a backslash is generically escaped. For + * example, "[a\\-z]" returns "[a-z]". + * + * If an escape sequence is ill-formed, this method returns an empty + * string. An example of an ill-formed sequence is "\\u" followed by + * fewer than 4 hex digits. + * + * This function is similar to u_unescape() but not identical to it. + * The latter takes a source char*, so it does escape recognition + * and also invariant conversion. + * + * @return a string with backslash escapes interpreted, or an + * empty string on error. + * @see UnicodeString#unescapeAt() + * @see u_unescape() + * @see u_unescapeAt() + * @stable ICU 2.0 + */ + UnicodeString unescape() const; + + /** + * Unescape a single escape sequence and return the represented + * character. See unescape() for a listing of the recognized escape + * sequences. The character at offset-1 is assumed (without + * checking) to be a backslash. If the escape sequence is + * ill-formed, or the offset is out of range, U_SENTINEL=-1 is + * returned. + * + * @param offset an input output parameter. On input, it is the + * offset into this string where the escape sequence is located, + * after the initial backslash. On output, it is advanced after the + * last character parsed. On error, it is not advanced at all. + * @return the character represented by the escape sequence at + * offset, or U_SENTINEL=-1 on error. + * @see UnicodeString#unescape() + * @see u_unescape() + * @see u_unescapeAt() + * @stable ICU 2.0 + */ + UChar32 unescapeAt(int32_t &offset) const; + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.2 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + + //======================================== + // Implementation methods + //======================================== + +protected: + /** + * Implement Replaceable::getLength() (see jitterbug 1027). + * @stable ICU 2.4 + */ + virtual int32_t getLength() const; + + /** + * The change in Replaceable to use virtual getCharAt() allows + * UnicodeString::charAt() to be inline again (see jitterbug 709). + * @stable ICU 2.4 + */ + virtual char16_t getCharAt(int32_t offset) const; + + /** + * The change in Replaceable to use virtual getChar32At() allows + * UnicodeString::char32At() to be inline again (see jitterbug 709). + * @stable ICU 2.4 + */ + virtual UChar32 getChar32At(int32_t offset) const; + +private: + // For char* constructors. Could be made public. + UnicodeString &setToUTF8(StringPiece utf8); + // For extract(char*). + // We could make a toUTF8(target, capacity, errorCode) public but not + // this version: New API will be cleaner if we make callers create substrings + // rather than having start+length on every method, + // and it should take a UErrorCode&. + int32_t + toUTF8(int32_t start, int32_t len, + char *target, int32_t capacity) const; + + /** + * Internal string contents comparison, called by operator==. + * Requires: this & text not bogus and have same lengths. + */ + UBool doEquals(const UnicodeString &text, int32_t len) const; + + inline int8_t + doCompare(int32_t start, + int32_t length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const; + + int8_t doCompare(int32_t start, + int32_t length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const; + + inline int8_t + doCompareCodePointOrder(int32_t start, + int32_t length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const; + + int8_t doCompareCodePointOrder(int32_t start, + int32_t length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const; + + inline int8_t + doCaseCompare(int32_t start, + int32_t length, + const UnicodeString &srcText, + int32_t srcStart, + int32_t srcLength, + uint32_t options) const; + + int8_t + doCaseCompare(int32_t start, + int32_t length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength, + uint32_t options) const; + + int32_t doIndexOf(char16_t c, + int32_t start, + int32_t length) const; + + int32_t doIndexOf(UChar32 c, + int32_t start, + int32_t length) const; + + int32_t doLastIndexOf(char16_t c, + int32_t start, + int32_t length) const; + + int32_t doLastIndexOf(UChar32 c, + int32_t start, + int32_t length) const; + + void doExtract(int32_t start, + int32_t length, + char16_t *dst, + int32_t dstStart) const; + + inline void doExtract(int32_t start, + int32_t length, + UnicodeString& target) const; + + inline char16_t doCharAt(int32_t offset) const; + + UnicodeString& doReplace(int32_t start, + int32_t length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength); + + UnicodeString& doReplace(int32_t start, + int32_t length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength); + + UnicodeString& doAppend(const UnicodeString& src, int32_t srcStart, int32_t srcLength); + UnicodeString& doAppend(const char16_t *srcChars, int32_t srcStart, int32_t srcLength); + + UnicodeString& doReverse(int32_t start, + int32_t length); + + // calculate hash code + int32_t doHashCode(void) const; + + // get pointer to start of array + // these do not check for kOpenGetBuffer, unlike the public getBuffer() function + inline char16_t* getArrayStart(void); + inline const char16_t* getArrayStart(void) const; + + inline UBool hasShortLength() const; + inline int32_t getShortLength() const; + + // A UnicodeString object (not necessarily its current buffer) + // is writable unless it isBogus() or it has an "open" getBuffer(minCapacity). + inline UBool isWritable() const; + + // Is the current buffer writable? + inline UBool isBufferWritable() const; + + // None of the following does releaseArray(). + inline void setZeroLength(); + inline void setShortLength(int32_t len); + inline void setLength(int32_t len); + inline void setToEmpty(); + inline void setArray(char16_t *array, int32_t len, int32_t capacity); // sets length but not flags + + // allocate the array; result may be the stack buffer + // sets refCount to 1 if appropriate + // sets fArray, fCapacity, and flags + // sets length to 0 + // returns boolean for success or failure + UBool allocate(int32_t capacity); + + // release the array if owned + void releaseArray(void); + + // turn a bogus string into an empty one + void unBogus(); + + // implements assigment operator, copy constructor, and fastCopyFrom() + UnicodeString ©From(const UnicodeString &src, UBool fastCopy=false); + + // Copies just the fields without memory management. + void copyFieldsFrom(UnicodeString &src, UBool setSrcToBogus) U_NOEXCEPT; + + // Pin start and limit to acceptable values. + inline void pinIndex(int32_t& start) const; + inline void pinIndices(int32_t& start, + int32_t& length) const; + +#if !UCONFIG_NO_CONVERSION + + /* Internal extract() using UConverter. */ + int32_t doExtract(int32_t start, int32_t length, + char *dest, int32_t destCapacity, + UConverter *cnv, + UErrorCode &errorCode) const; + + /* + * Real constructor for converting from codepage data. + * It assumes that it is called with !fRefCounted. + * + * If `codepage==0`, then the default converter + * is used for the platform encoding. + * If `codepage` is an empty string (`""`), + * then a simple conversion is performed on the codepage-invariant + * subset ("invariant characters") of the platform encoding. See utypes.h. + */ + void doCodepageCreate(const char *codepageData, + int32_t dataLength, + const char *codepage); + + /* + * Worker function for creating a UnicodeString from + * a codepage string using a UConverter. + */ + void + doCodepageCreate(const char *codepageData, + int32_t dataLength, + UConverter *converter, + UErrorCode &status); + +#endif + + /* + * This function is called when write access to the array + * is necessary. + * + * We need to make a copy of the array if + * the buffer is read-only, or + * the buffer is refCounted (shared), and refCount>1, or + * the buffer is too small. + * + * Return false if memory could not be allocated. + */ + UBool cloneArrayIfNeeded(int32_t newCapacity = -1, + int32_t growCapacity = -1, + UBool doCopyArray = true, + int32_t **pBufferToDelete = 0, + UBool forceClone = false); + + /** + * Common function for UnicodeString case mappings. + * The stringCaseMapper has the same type UStringCaseMapper + * as in ustr_imp.h for ustrcase_map(). + */ + UnicodeString & + caseMap(int32_t caseLocale, uint32_t options, +#if !UCONFIG_NO_BREAK_ITERATION + BreakIterator *iter, +#endif + UStringCaseMapper *stringCaseMapper); + + // ref counting + void addRef(void); + int32_t removeRef(void); + int32_t refCount(void) const; + + // constants + enum { + /** + * Size of stack buffer for short strings. + * Must be at least U16_MAX_LENGTH for the single-code point constructor to work. + * @see UNISTR_OBJECT_SIZE + */ + US_STACKBUF_SIZE=(int32_t)(UNISTR_OBJECT_SIZE-sizeof(void *)-2)/U_SIZEOF_UCHAR, + kInvalidUChar=0xffff, // U+FFFF returned by charAt(invalid index) + kInvalidHashCode=0, // invalid hash code + kEmptyHashCode=1, // hash code for empty string + + // bit flag values for fLengthAndFlags + kIsBogus=1, // this string is bogus, i.e., not valid or NULL + kUsingStackBuffer=2,// using fUnion.fStackFields instead of fUnion.fFields + kRefCounted=4, // there is a refCount field before the characters in fArray + kBufferIsReadonly=8,// do not write to this buffer + kOpenGetBuffer=16, // getBuffer(minCapacity) was called (is "open"), + // and releaseBuffer(newLength) must be called + kAllStorageFlags=0x1f, + + kLengthShift=5, // remaining 11 bits for non-negative short length, or negative if long + kLength1=1<<kLengthShift, + kMaxShortLength=0x3ff, // max non-negative short length (leaves top bit 0) + kLengthIsLarge=0xffe0, // short length < 0, real length is in fUnion.fFields.fLength + + // combined values for convenience + kShortString=kUsingStackBuffer, + kLongString=kRefCounted, + kReadonlyAlias=kBufferIsReadonly, + kWritableAlias=0 + }; + + friend class UnicodeStringAppendable; + + union StackBufferOrFields; // forward declaration necessary before friend declaration + friend union StackBufferOrFields; // make US_STACKBUF_SIZE visible inside fUnion + + /* + * The following are all the class fields that are stored + * in each UnicodeString object. + * Note that UnicodeString has virtual functions, + * therefore there is an implicit vtable pointer + * as the first real field. + * The fields should be aligned such that no padding is necessary. + * On 32-bit machines, the size should be 32 bytes, + * on 64-bit machines (8-byte pointers), it should be 40 bytes. + * + * We use a hack to achieve this. + * + * With at least some compilers, each of the following is forced to + * a multiple of sizeof(pointer) [the largest field base unit here is a data pointer], + * rounded up with additional padding if the fields do not already fit that requirement: + * - sizeof(class UnicodeString) + * - offsetof(UnicodeString, fUnion) + * - sizeof(fUnion) + * - sizeof(fStackFields) + * + * We optimize for the longest possible internal buffer for short strings. + * fUnion.fStackFields begins with 2 bytes for storage flags + * and the length of relatively short strings, + * followed by the buffer for short string contents. + * There is no padding inside fStackFields. + * + * Heap-allocated and aliased strings use fUnion.fFields. + * Both fStackFields and fFields must begin with the same fields for flags and short length, + * that is, those must have the same memory offsets inside the object, + * because the flags must be inspected in order to decide which half of fUnion is being used. + * We assume that the compiler does not reorder the fields. + * + * (Padding at the end of fFields is ok: + * As long as it is no larger than fStackFields, it is not wasted space.) + * + * For some of the history of the UnicodeString class fields layout, see + * - ICU ticket #11551 "longer UnicodeString contents in stack buffer" + * - ICU ticket #11336 "UnicodeString: recombine stack buffer arrays" + * - ICU ticket #8322 "why is sizeof(UnicodeString)==48?" + */ + // (implicit) *vtable; + union StackBufferOrFields { + // fStackFields is used iff (fLengthAndFlags&kUsingStackBuffer) else fFields is used. + // Each struct of the union must begin with fLengthAndFlags. + struct { + int16_t fLengthAndFlags; // bit fields: see constants above + char16_t fBuffer[US_STACKBUF_SIZE]; // buffer for short strings + } fStackFields; + struct { + int16_t fLengthAndFlags; // bit fields: see constants above + int32_t fLength; // number of characters in fArray if >127; else undefined + int32_t fCapacity; // capacity of fArray (in char16_ts) + // array pointer last to minimize padding for machines with P128 data model + // or pointer sizes that are not a power of 2 + char16_t *fArray; // the Unicode data + } fFields; + } fUnion; +}; + +/** + * Create a new UnicodeString with the concatenation of two others. + * + * @param s1 The first string to be copied to the new one. + * @param s2 The second string to be copied to the new one, after s1. + * @return UnicodeString(s1).append(s2) + * @stable ICU 2.8 + */ +U_COMMON_API UnicodeString U_EXPORT2 +operator+ (const UnicodeString &s1, const UnicodeString &s2); + +//======================================== +// Inline members +//======================================== + +//======================================== +// Privates +//======================================== + +inline void +UnicodeString::pinIndex(int32_t& start) const +{ + // pin index + if(start < 0) { + start = 0; + } else if(start > length()) { + start = length(); + } +} + +inline void +UnicodeString::pinIndices(int32_t& start, + int32_t& _length) const +{ + // pin indices + int32_t len = length(); + if(start < 0) { + start = 0; + } else if(start > len) { + start = len; + } + if(_length < 0) { + _length = 0; + } else if(_length > (len - start)) { + _length = (len - start); + } +} + +inline char16_t* +UnicodeString::getArrayStart() { + return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ? + fUnion.fStackFields.fBuffer : fUnion.fFields.fArray; +} + +inline const char16_t* +UnicodeString::getArrayStart() const { + return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ? + fUnion.fStackFields.fBuffer : fUnion.fFields.fArray; +} + +//======================================== +// Default constructor +//======================================== + +inline +UnicodeString::UnicodeString() { + fUnion.fStackFields.fLengthAndFlags=kShortString; +} + +inline UnicodeString::UnicodeString(const std::nullptr_t /*text*/) { + fUnion.fStackFields.fLengthAndFlags=kShortString; +} + +inline UnicodeString::UnicodeString(const std::nullptr_t /*text*/, int32_t /*length*/) { + fUnion.fStackFields.fLengthAndFlags=kShortString; +} + +inline UnicodeString::UnicodeString(std::nullptr_t /*buffer*/, int32_t /*buffLength*/, int32_t /*buffCapacity*/) { + fUnion.fStackFields.fLengthAndFlags=kShortString; +} + +//======================================== +// Read-only implementation methods +//======================================== +inline UBool +UnicodeString::hasShortLength() const { + return fUnion.fFields.fLengthAndFlags>=0; +} + +inline int32_t +UnicodeString::getShortLength() const { + // fLengthAndFlags must be non-negative -> short length >= 0 + // and arithmetic or logical shift does not matter. + return fUnion.fFields.fLengthAndFlags>>kLengthShift; +} + +inline int32_t +UnicodeString::length() const { + return hasShortLength() ? getShortLength() : fUnion.fFields.fLength; +} + +inline int32_t +UnicodeString::getCapacity() const { + return (fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) ? + US_STACKBUF_SIZE : fUnion.fFields.fCapacity; +} + +inline int32_t +UnicodeString::hashCode() const +{ return doHashCode(); } + +inline UBool +UnicodeString::isBogus() const +{ return (UBool)(fUnion.fFields.fLengthAndFlags & kIsBogus); } + +inline UBool +UnicodeString::isWritable() const +{ return (UBool)!(fUnion.fFields.fLengthAndFlags&(kOpenGetBuffer|kIsBogus)); } + +inline UBool +UnicodeString::isBufferWritable() const +{ + return (UBool)( + !(fUnion.fFields.fLengthAndFlags&(kOpenGetBuffer|kIsBogus|kBufferIsReadonly)) && + (!(fUnion.fFields.fLengthAndFlags&kRefCounted) || refCount()==1)); +} + +inline const char16_t * +UnicodeString::getBuffer() const { + if(fUnion.fFields.fLengthAndFlags&(kIsBogus|kOpenGetBuffer)) { + return nullptr; + } else if(fUnion.fFields.fLengthAndFlags&kUsingStackBuffer) { + return fUnion.fStackFields.fBuffer; + } else { + return fUnion.fFields.fArray; + } +} + +//======================================== +// Read-only alias methods +//======================================== +inline int8_t +UnicodeString::doCompare(int32_t start, + int32_t thisLength, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const +{ + if(srcText.isBogus()) { + return (int8_t)!isBogus(); // 0 if both are bogus, 1 otherwise + } else { + srcText.pinIndices(srcStart, srcLength); + return doCompare(start, thisLength, srcText.getArrayStart(), srcStart, srcLength); + } +} + +inline UBool +UnicodeString::operator== (const UnicodeString& text) const +{ + if(isBogus()) { + return text.isBogus(); + } else { + int32_t len = length(), textLength = text.length(); + return !text.isBogus() && len == textLength && doEquals(text, len); + } +} + +inline UBool +UnicodeString::operator!= (const UnicodeString& text) const +{ return (! operator==(text)); } + +inline UBool +UnicodeString::operator> (const UnicodeString& text) const +{ return doCompare(0, length(), text, 0, text.length()) == 1; } + +inline UBool +UnicodeString::operator< (const UnicodeString& text) const +{ return doCompare(0, length(), text, 0, text.length()) == -1; } + +inline UBool +UnicodeString::operator>= (const UnicodeString& text) const +{ return doCompare(0, length(), text, 0, text.length()) != -1; } + +inline UBool +UnicodeString::operator<= (const UnicodeString& text) const +{ return doCompare(0, length(), text, 0, text.length()) != 1; } + +inline int8_t +UnicodeString::compare(const UnicodeString& text) const +{ return doCompare(0, length(), text, 0, text.length()); } + +inline int8_t +UnicodeString::compare(int32_t start, + int32_t _length, + const UnicodeString& srcText) const +{ return doCompare(start, _length, srcText, 0, srcText.length()); } + +inline int8_t +UnicodeString::compare(ConstChar16Ptr srcChars, + int32_t srcLength) const +{ return doCompare(0, length(), srcChars, 0, srcLength); } + +inline int8_t +UnicodeString::compare(int32_t start, + int32_t _length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const +{ return doCompare(start, _length, srcText, srcStart, srcLength); } + +inline int8_t +UnicodeString::compare(int32_t start, + int32_t _length, + const char16_t *srcChars) const +{ return doCompare(start, _length, srcChars, 0, _length); } + +inline int8_t +UnicodeString::compare(int32_t start, + int32_t _length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const +{ return doCompare(start, _length, srcChars, srcStart, srcLength); } + +inline int8_t +UnicodeString::compareBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLimit) const +{ return doCompare(start, limit - start, + srcText, srcStart, srcLimit - srcStart); } + +inline int8_t +UnicodeString::doCompareCodePointOrder(int32_t start, + int32_t thisLength, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const +{ + if(srcText.isBogus()) { + return (int8_t)!isBogus(); // 0 if both are bogus, 1 otherwise + } else { + srcText.pinIndices(srcStart, srcLength); + return doCompareCodePointOrder(start, thisLength, srcText.getArrayStart(), srcStart, srcLength); + } +} + +inline int8_t +UnicodeString::compareCodePointOrder(const UnicodeString& text) const +{ return doCompareCodePointOrder(0, length(), text, 0, text.length()); } + +inline int8_t +UnicodeString::compareCodePointOrder(int32_t start, + int32_t _length, + const UnicodeString& srcText) const +{ return doCompareCodePointOrder(start, _length, srcText, 0, srcText.length()); } + +inline int8_t +UnicodeString::compareCodePointOrder(ConstChar16Ptr srcChars, + int32_t srcLength) const +{ return doCompareCodePointOrder(0, length(), srcChars, 0, srcLength); } + +inline int8_t +UnicodeString::compareCodePointOrder(int32_t start, + int32_t _length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const +{ return doCompareCodePointOrder(start, _length, srcText, srcStart, srcLength); } + +inline int8_t +UnicodeString::compareCodePointOrder(int32_t start, + int32_t _length, + const char16_t *srcChars) const +{ return doCompareCodePointOrder(start, _length, srcChars, 0, _length); } + +inline int8_t +UnicodeString::compareCodePointOrder(int32_t start, + int32_t _length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const +{ return doCompareCodePointOrder(start, _length, srcChars, srcStart, srcLength); } + +inline int8_t +UnicodeString::compareCodePointOrderBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLimit) const +{ return doCompareCodePointOrder(start, limit - start, + srcText, srcStart, srcLimit - srcStart); } + +inline int8_t +UnicodeString::doCaseCompare(int32_t start, + int32_t thisLength, + const UnicodeString &srcText, + int32_t srcStart, + int32_t srcLength, + uint32_t options) const +{ + if(srcText.isBogus()) { + return (int8_t)!isBogus(); // 0 if both are bogus, 1 otherwise + } else { + srcText.pinIndices(srcStart, srcLength); + return doCaseCompare(start, thisLength, srcText.getArrayStart(), srcStart, srcLength, options); + } +} + +inline int8_t +UnicodeString::caseCompare(const UnicodeString &text, uint32_t options) const { + return doCaseCompare(0, length(), text, 0, text.length(), options); +} + +inline int8_t +UnicodeString::caseCompare(int32_t start, + int32_t _length, + const UnicodeString &srcText, + uint32_t options) const { + return doCaseCompare(start, _length, srcText, 0, srcText.length(), options); +} + +inline int8_t +UnicodeString::caseCompare(ConstChar16Ptr srcChars, + int32_t srcLength, + uint32_t options) const { + return doCaseCompare(0, length(), srcChars, 0, srcLength, options); +} + +inline int8_t +UnicodeString::caseCompare(int32_t start, + int32_t _length, + const UnicodeString &srcText, + int32_t srcStart, + int32_t srcLength, + uint32_t options) const { + return doCaseCompare(start, _length, srcText, srcStart, srcLength, options); +} + +inline int8_t +UnicodeString::caseCompare(int32_t start, + int32_t _length, + const char16_t *srcChars, + uint32_t options) const { + return doCaseCompare(start, _length, srcChars, 0, _length, options); +} + +inline int8_t +UnicodeString::caseCompare(int32_t start, + int32_t _length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength, + uint32_t options) const { + return doCaseCompare(start, _length, srcChars, srcStart, srcLength, options); +} + +inline int8_t +UnicodeString::caseCompareBetween(int32_t start, + int32_t limit, + const UnicodeString &srcText, + int32_t srcStart, + int32_t srcLimit, + uint32_t options) const { + return doCaseCompare(start, limit - start, srcText, srcStart, srcLimit - srcStart, options); +} + +inline int32_t +UnicodeString::indexOf(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength, + int32_t start, + int32_t _length) const +{ + if(!srcText.isBogus()) { + srcText.pinIndices(srcStart, srcLength); + if(srcLength > 0) { + return indexOf(srcText.getArrayStart(), srcStart, srcLength, start, _length); + } + } + return -1; +} + +inline int32_t +UnicodeString::indexOf(const UnicodeString& text) const +{ return indexOf(text, 0, text.length(), 0, length()); } + +inline int32_t +UnicodeString::indexOf(const UnicodeString& text, + int32_t start) const { + pinIndex(start); + return indexOf(text, 0, text.length(), start, length() - start); +} + +inline int32_t +UnicodeString::indexOf(const UnicodeString& text, + int32_t start, + int32_t _length) const +{ return indexOf(text, 0, text.length(), start, _length); } + +inline int32_t +UnicodeString::indexOf(const char16_t *srcChars, + int32_t srcLength, + int32_t start) const { + pinIndex(start); + return indexOf(srcChars, 0, srcLength, start, length() - start); +} + +inline int32_t +UnicodeString::indexOf(ConstChar16Ptr srcChars, + int32_t srcLength, + int32_t start, + int32_t _length) const +{ return indexOf(srcChars, 0, srcLength, start, _length); } + +inline int32_t +UnicodeString::indexOf(char16_t c, + int32_t start, + int32_t _length) const +{ return doIndexOf(c, start, _length); } + +inline int32_t +UnicodeString::indexOf(UChar32 c, + int32_t start, + int32_t _length) const +{ return doIndexOf(c, start, _length); } + +inline int32_t +UnicodeString::indexOf(char16_t c) const +{ return doIndexOf(c, 0, length()); } + +inline int32_t +UnicodeString::indexOf(UChar32 c) const +{ return indexOf(c, 0, length()); } + +inline int32_t +UnicodeString::indexOf(char16_t c, + int32_t start) const { + pinIndex(start); + return doIndexOf(c, start, length() - start); +} + +inline int32_t +UnicodeString::indexOf(UChar32 c, + int32_t start) const { + pinIndex(start); + return indexOf(c, start, length() - start); +} + +inline int32_t +UnicodeString::lastIndexOf(ConstChar16Ptr srcChars, + int32_t srcLength, + int32_t start, + int32_t _length) const +{ return lastIndexOf(srcChars, 0, srcLength, start, _length); } + +inline int32_t +UnicodeString::lastIndexOf(const char16_t *srcChars, + int32_t srcLength, + int32_t start) const { + pinIndex(start); + return lastIndexOf(srcChars, 0, srcLength, start, length() - start); +} + +inline int32_t +UnicodeString::lastIndexOf(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength, + int32_t start, + int32_t _length) const +{ + if(!srcText.isBogus()) { + srcText.pinIndices(srcStart, srcLength); + if(srcLength > 0) { + return lastIndexOf(srcText.getArrayStart(), srcStart, srcLength, start, _length); + } + } + return -1; +} + +inline int32_t +UnicodeString::lastIndexOf(const UnicodeString& text, + int32_t start, + int32_t _length) const +{ return lastIndexOf(text, 0, text.length(), start, _length); } + +inline int32_t +UnicodeString::lastIndexOf(const UnicodeString& text, + int32_t start) const { + pinIndex(start); + return lastIndexOf(text, 0, text.length(), start, length() - start); +} + +inline int32_t +UnicodeString::lastIndexOf(const UnicodeString& text) const +{ return lastIndexOf(text, 0, text.length(), 0, length()); } + +inline int32_t +UnicodeString::lastIndexOf(char16_t c, + int32_t start, + int32_t _length) const +{ return doLastIndexOf(c, start, _length); } + +inline int32_t +UnicodeString::lastIndexOf(UChar32 c, + int32_t start, + int32_t _length) const { + return doLastIndexOf(c, start, _length); +} + +inline int32_t +UnicodeString::lastIndexOf(char16_t c) const +{ return doLastIndexOf(c, 0, length()); } + +inline int32_t +UnicodeString::lastIndexOf(UChar32 c) const { + return lastIndexOf(c, 0, length()); +} + +inline int32_t +UnicodeString::lastIndexOf(char16_t c, + int32_t start) const { + pinIndex(start); + return doLastIndexOf(c, start, length() - start); +} + +inline int32_t +UnicodeString::lastIndexOf(UChar32 c, + int32_t start) const { + pinIndex(start); + return lastIndexOf(c, start, length() - start); +} + +inline UBool +UnicodeString::startsWith(const UnicodeString& text) const +{ return compare(0, text.length(), text, 0, text.length()) == 0; } + +inline UBool +UnicodeString::startsWith(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const +{ return doCompare(0, srcLength, srcText, srcStart, srcLength) == 0; } + +inline UBool +UnicodeString::startsWith(ConstChar16Ptr srcChars, int32_t srcLength) const { + if(srcLength < 0) { + srcLength = u_strlen(toUCharPtr(srcChars)); + } + return doCompare(0, srcLength, srcChars, 0, srcLength) == 0; +} + +inline UBool +UnicodeString::startsWith(const char16_t *srcChars, int32_t srcStart, int32_t srcLength) const { + if(srcLength < 0) { + srcLength = u_strlen(toUCharPtr(srcChars)); + } + return doCompare(0, srcLength, srcChars, srcStart, srcLength) == 0; +} + +inline UBool +UnicodeString::endsWith(const UnicodeString& text) const +{ return doCompare(length() - text.length(), text.length(), + text, 0, text.length()) == 0; } + +inline UBool +UnicodeString::endsWith(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) const { + srcText.pinIndices(srcStart, srcLength); + return doCompare(length() - srcLength, srcLength, + srcText, srcStart, srcLength) == 0; +} + +inline UBool +UnicodeString::endsWith(ConstChar16Ptr srcChars, + int32_t srcLength) const { + if(srcLength < 0) { + srcLength = u_strlen(toUCharPtr(srcChars)); + } + return doCompare(length() - srcLength, srcLength, + srcChars, 0, srcLength) == 0; +} + +inline UBool +UnicodeString::endsWith(const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) const { + if(srcLength < 0) { + srcLength = u_strlen(toUCharPtr(srcChars + srcStart)); + } + return doCompare(length() - srcLength, srcLength, + srcChars, srcStart, srcLength) == 0; +} + +//======================================== +// replace +//======================================== +inline UnicodeString& +UnicodeString::replace(int32_t start, + int32_t _length, + const UnicodeString& srcText) +{ return doReplace(start, _length, srcText, 0, srcText.length()); } + +inline UnicodeString& +UnicodeString::replace(int32_t start, + int32_t _length, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) +{ return doReplace(start, _length, srcText, srcStart, srcLength); } + +inline UnicodeString& +UnicodeString::replace(int32_t start, + int32_t _length, + ConstChar16Ptr srcChars, + int32_t srcLength) +{ return doReplace(start, _length, srcChars, 0, srcLength); } + +inline UnicodeString& +UnicodeString::replace(int32_t start, + int32_t _length, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) +{ return doReplace(start, _length, srcChars, srcStart, srcLength); } + +inline UnicodeString& +UnicodeString::replace(int32_t start, + int32_t _length, + char16_t srcChar) +{ return doReplace(start, _length, &srcChar, 0, 1); } + +inline UnicodeString& +UnicodeString::replaceBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText) +{ return doReplace(start, limit - start, srcText, 0, srcText.length()); } + +inline UnicodeString& +UnicodeString::replaceBetween(int32_t start, + int32_t limit, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLimit) +{ return doReplace(start, limit - start, srcText, srcStart, srcLimit - srcStart); } + +inline UnicodeString& +UnicodeString::findAndReplace(const UnicodeString& oldText, + const UnicodeString& newText) +{ return findAndReplace(0, length(), oldText, 0, oldText.length(), + newText, 0, newText.length()); } + +inline UnicodeString& +UnicodeString::findAndReplace(int32_t start, + int32_t _length, + const UnicodeString& oldText, + const UnicodeString& newText) +{ return findAndReplace(start, _length, oldText, 0, oldText.length(), + newText, 0, newText.length()); } + +// ============================ +// extract +// ============================ +inline void +UnicodeString::doExtract(int32_t start, + int32_t _length, + UnicodeString& target) const +{ target.replace(0, target.length(), *this, start, _length); } + +inline void +UnicodeString::extract(int32_t start, + int32_t _length, + Char16Ptr target, + int32_t targetStart) const +{ doExtract(start, _length, target, targetStart); } + +inline void +UnicodeString::extract(int32_t start, + int32_t _length, + UnicodeString& target) const +{ doExtract(start, _length, target); } + +#if !UCONFIG_NO_CONVERSION + +inline int32_t +UnicodeString::extract(int32_t start, + int32_t _length, + char *dst, + const char *codepage) const + +{ + // This dstSize value will be checked explicitly + return extract(start, _length, dst, dst!=0 ? 0xffffffff : 0, codepage); +} + +#endif + +inline void +UnicodeString::extractBetween(int32_t start, + int32_t limit, + char16_t *dst, + int32_t dstStart) const { + pinIndex(start); + pinIndex(limit); + doExtract(start, limit - start, dst, dstStart); +} + +inline UnicodeString +UnicodeString::tempSubStringBetween(int32_t start, int32_t limit) const { + return tempSubString(start, limit - start); +} + +inline char16_t +UnicodeString::doCharAt(int32_t offset) const +{ + if((uint32_t)offset < (uint32_t)length()) { + return getArrayStart()[offset]; + } else { + return kInvalidUChar; + } +} + +inline char16_t +UnicodeString::charAt(int32_t offset) const +{ return doCharAt(offset); } + +inline char16_t +UnicodeString::operator[] (int32_t offset) const +{ return doCharAt(offset); } + +inline UBool +UnicodeString::isEmpty() const { + // Arithmetic or logical right shift does not matter: only testing for 0. + return (fUnion.fFields.fLengthAndFlags>>kLengthShift) == 0; +} + +//======================================== +// Write implementation methods +//======================================== +inline void +UnicodeString::setZeroLength() { + fUnion.fFields.fLengthAndFlags &= kAllStorageFlags; +} + +inline void +UnicodeString::setShortLength(int32_t len) { + // requires 0 <= len <= kMaxShortLength + fUnion.fFields.fLengthAndFlags = + (int16_t)((fUnion.fFields.fLengthAndFlags & kAllStorageFlags) | (len << kLengthShift)); +} + +inline void +UnicodeString::setLength(int32_t len) { + if(len <= kMaxShortLength) { + setShortLength(len); + } else { + fUnion.fFields.fLengthAndFlags |= kLengthIsLarge; + fUnion.fFields.fLength = len; + } +} + +inline void +UnicodeString::setToEmpty() { + fUnion.fFields.fLengthAndFlags = kShortString; +} + +inline void +UnicodeString::setArray(char16_t *array, int32_t len, int32_t capacity) { + setLength(len); + fUnion.fFields.fArray = array; + fUnion.fFields.fCapacity = capacity; +} + +inline UnicodeString& +UnicodeString::operator= (char16_t ch) +{ return doReplace(0, length(), &ch, 0, 1); } + +inline UnicodeString& +UnicodeString::operator= (UChar32 ch) +{ return replace(0, length(), ch); } + +inline UnicodeString& +UnicodeString::setTo(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) +{ + unBogus(); + return doReplace(0, length(), srcText, srcStart, srcLength); +} + +inline UnicodeString& +UnicodeString::setTo(const UnicodeString& srcText, + int32_t srcStart) +{ + unBogus(); + srcText.pinIndex(srcStart); + return doReplace(0, length(), srcText, srcStart, srcText.length() - srcStart); +} + +inline UnicodeString& +UnicodeString::setTo(const UnicodeString& srcText) +{ + return copyFrom(srcText); +} + +inline UnicodeString& +UnicodeString::setTo(const char16_t *srcChars, + int32_t srcLength) +{ + unBogus(); + return doReplace(0, length(), srcChars, 0, srcLength); +} + +inline UnicodeString& +UnicodeString::setTo(char16_t srcChar) +{ + unBogus(); + return doReplace(0, length(), &srcChar, 0, 1); +} + +inline UnicodeString& +UnicodeString::setTo(UChar32 srcChar) +{ + unBogus(); + return replace(0, length(), srcChar); +} + +inline UnicodeString& +UnicodeString::append(const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) +{ return doAppend(srcText, srcStart, srcLength); } + +inline UnicodeString& +UnicodeString::append(const UnicodeString& srcText) +{ return doAppend(srcText, 0, srcText.length()); } + +inline UnicodeString& +UnicodeString::append(const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) +{ return doAppend(srcChars, srcStart, srcLength); } + +inline UnicodeString& +UnicodeString::append(ConstChar16Ptr srcChars, + int32_t srcLength) +{ return doAppend(srcChars, 0, srcLength); } + +inline UnicodeString& +UnicodeString::append(char16_t srcChar) +{ return doAppend(&srcChar, 0, 1); } + +inline UnicodeString& +UnicodeString::operator+= (char16_t ch) +{ return doAppend(&ch, 0, 1); } + +inline UnicodeString& +UnicodeString::operator+= (UChar32 ch) { + return append(ch); +} + +inline UnicodeString& +UnicodeString::operator+= (const UnicodeString& srcText) +{ return doAppend(srcText, 0, srcText.length()); } + +inline UnicodeString& +UnicodeString::insert(int32_t start, + const UnicodeString& srcText, + int32_t srcStart, + int32_t srcLength) +{ return doReplace(start, 0, srcText, srcStart, srcLength); } + +inline UnicodeString& +UnicodeString::insert(int32_t start, + const UnicodeString& srcText) +{ return doReplace(start, 0, srcText, 0, srcText.length()); } + +inline UnicodeString& +UnicodeString::insert(int32_t start, + const char16_t *srcChars, + int32_t srcStart, + int32_t srcLength) +{ return doReplace(start, 0, srcChars, srcStart, srcLength); } + +inline UnicodeString& +UnicodeString::insert(int32_t start, + ConstChar16Ptr srcChars, + int32_t srcLength) +{ return doReplace(start, 0, srcChars, 0, srcLength); } + +inline UnicodeString& +UnicodeString::insert(int32_t start, + char16_t srcChar) +{ return doReplace(start, 0, &srcChar, 0, 1); } + +inline UnicodeString& +UnicodeString::insert(int32_t start, + UChar32 srcChar) +{ return replace(start, 0, srcChar); } + + +inline UnicodeString& +UnicodeString::remove() +{ + // remove() of a bogus string makes the string empty and non-bogus + if(isBogus()) { + setToEmpty(); + } else { + setZeroLength(); + } + return *this; +} + +inline UnicodeString& +UnicodeString::remove(int32_t start, + int32_t _length) +{ + if(start <= 0 && _length == INT32_MAX) { + // remove(guaranteed everything) of a bogus string makes the string empty and non-bogus + return remove(); + } + return doReplace(start, _length, NULL, 0, 0); +} + +inline UnicodeString& +UnicodeString::removeBetween(int32_t start, + int32_t limit) +{ return doReplace(start, limit - start, NULL, 0, 0); } + +inline UnicodeString & +UnicodeString::retainBetween(int32_t start, int32_t limit) { + truncate(limit); + return doReplace(0, start, NULL, 0, 0); +} + +inline UBool +UnicodeString::truncate(int32_t targetLength) +{ + if(isBogus() && targetLength == 0) { + // truncate(0) of a bogus string makes the string empty and non-bogus + unBogus(); + return false; + } else if((uint32_t)targetLength < (uint32_t)length()) { + setLength(targetLength); + return true; + } else { + return false; + } +} + +inline UnicodeString& +UnicodeString::reverse() +{ return doReverse(0, length()); } + +inline UnicodeString& +UnicodeString::reverse(int32_t start, + int32_t _length) +{ return doReverse(start, _length); } + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/unorm.h b/thirdparty/icu4c/common/unicode/unorm.h new file mode 100644 index 0000000000..c3c57582d4 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/unorm.h @@ -0,0 +1,476 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (c) 1996-2016, International Business Machines Corporation +* and others. All Rights Reserved. +******************************************************************************* +* File unorm.h +* +* Created by: Vladimir Weinstein 12052000 +* +* Modification history : +* +* Date Name Description +* 02/01/01 synwee Added normalization quickcheck enum and method. +*/ +#ifndef UNORM_H +#define UNORM_H + +#include "unicode/utypes.h" + +#if !UCONFIG_NO_NORMALIZATION + +#include "unicode/uiter.h" +#include "unicode/unorm2.h" + +/** + * \file + * \brief C API: Unicode Normalization + * + * Old Unicode normalization API. + * + * This API has been replaced by the unorm2.h API and is only available + * for backward compatibility. The functions here simply delegate to the + * unorm2.h functions, for example unorm2_getInstance() and unorm2_normalize(). + * There is one exception: The new API does not provide a replacement for unorm_compare(). + * Its declaration has been moved to unorm2.h. + * + * <code>unorm_normalize</code> transforms Unicode text into an equivalent composed or + * decomposed form, allowing for easier sorting and searching of text. + * <code>unorm_normalize</code> supports the standard normalization forms described in + * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> + * Unicode Standard Annex #15: Unicode Normalization Forms</a>. + * + * Characters with accents or other adornments can be encoded in + * several different ways in Unicode. For example, take the character A-acute. + * In Unicode, this can be encoded as a single character (the + * "composed" form): + * + * \code + * 00C1 LATIN CAPITAL LETTER A WITH ACUTE + * \endcode + * + * or as two separate characters (the "decomposed" form): + * + * \code + * 0041 LATIN CAPITAL LETTER A + * 0301 COMBINING ACUTE ACCENT + * \endcode + * + * To a user of your program, however, both of these sequences should be + * treated as the same "user-level" character "A with acute accent". When you are searching or + * comparing text, you must ensure that these two sequences are treated + * equivalently. In addition, you must handle characters with more than one + * accent. Sometimes the order of a character's combining accents is + * significant, while in other cases accent sequences in different orders are + * really equivalent. + * + * Similarly, the string "ffi" can be encoded as three separate letters: + * + * \code + * 0066 LATIN SMALL LETTER F + * 0066 LATIN SMALL LETTER F + * 0069 LATIN SMALL LETTER I + * \endcode + * + * or as the single character + * + * \code + * FB03 LATIN SMALL LIGATURE FFI + * \endcode + * + * The ffi ligature is not a distinct semantic character, and strictly speaking + * it shouldn't be in Unicode at all, but it was included for compatibility + * with existing character sets that already provided it. The Unicode standard + * identifies such characters by giving them "compatibility" decompositions + * into the corresponding semantic characters. When sorting and searching, you + * will often want to use these mappings. + * + * <code>unorm_normalize</code> helps solve these problems by transforming text into the + * canonical composed and decomposed forms as shown in the first example above. + * In addition, you can have it perform compatibility decompositions so that + * you can treat compatibility characters the same as their equivalents. + * Finally, <code>unorm_normalize</code> rearranges accents into the proper canonical + * order, so that you do not have to worry about accent rearrangement on your + * own. + * + * Form FCD, "Fast C or D", is also designed for collation. + * It allows to work on strings that are not necessarily normalized + * with an algorithm (like in collation) that works under "canonical closure", i.e., it treats precomposed + * characters and their decomposed equivalents the same. + * + * It is not a normalization form because it does not provide for uniqueness of representation. Multiple strings + * may be canonically equivalent (their NFDs are identical) and may all conform to FCD without being identical + * themselves. + * + * The form is defined such that the "raw decomposition", the recursive canonical decomposition of each character, + * results in a string that is canonically ordered. This means that precomposed characters are allowed for as long + * as their decompositions do not need canonical reordering. + * + * Its advantage for a process like collation is that all NFD and most NFC texts - and many unnormalized texts - + * already conform to FCD and do not need to be normalized (NFD) for such a process. The FCD quick check will + * return UNORM_YES for most strings in practice. + * + * unorm_normalize(UNORM_FCD) may be implemented with UNORM_NFD. + * + * For more details on FCD see the collation design document: + * http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm + * + * ICU collation performs either NFD or FCD normalization automatically if normalization + * is turned on for the collator object. + * Beyond collation and string search, normalized strings may be useful for string equivalence comparisons, + * transliteration/transcription, unique representations, etc. + * + * The W3C generally recommends to exchange texts in NFC. + * Note also that most legacy character encodings use only precomposed forms and often do not + * encode any combining marks by themselves. For conversion to such character encodings the + * Unicode text needs to be normalized to NFC. + * For more usage examples, see the Unicode Standard Annex. + */ + +// Do not conditionalize the following enum with #ifndef U_HIDE_DEPRECATED_API, +// it is needed for layout of Normalizer object. +#ifndef U_FORCE_HIDE_DEPRECATED_API + +/** + * Constants for normalization modes. + * @deprecated ICU 56 Use unorm2.h instead. + */ +typedef enum { + /** No decomposition/composition. @deprecated ICU 56 Use unorm2.h instead. */ + UNORM_NONE = 1, + /** Canonical decomposition. @deprecated ICU 56 Use unorm2.h instead. */ + UNORM_NFD = 2, + /** Compatibility decomposition. @deprecated ICU 56 Use unorm2.h instead. */ + UNORM_NFKD = 3, + /** Canonical decomposition followed by canonical composition. @deprecated ICU 56 Use unorm2.h instead. */ + UNORM_NFC = 4, + /** Default normalization. @deprecated ICU 56 Use unorm2.h instead. */ + UNORM_DEFAULT = UNORM_NFC, + /** Compatibility decomposition followed by canonical composition. @deprecated ICU 56 Use unorm2.h instead. */ + UNORM_NFKC =5, + /** "Fast C or D" form. @deprecated ICU 56 Use unorm2.h instead. */ + UNORM_FCD = 6, + + /** One more than the highest normalization mode constant. @deprecated ICU 56 Use unorm2.h instead. */ + UNORM_MODE_COUNT +} UNormalizationMode; + +#endif // U_FORCE_HIDE_DEPRECATED_API + +#ifndef U_HIDE_DEPRECATED_API + +/** + * Constants for options flags for normalization. + * Use 0 for default options, + * including normalization according to the Unicode version + * that is currently supported by ICU (see u_getUnicodeVersion). + * @deprecated ICU 56 Use unorm2.h instead. + */ +enum { + /** + * Options bit set value to select Unicode 3.2 normalization + * (except NormalizationCorrections). + * At most one Unicode version can be selected at a time. + * @deprecated ICU 56 Use unorm2.h instead. + */ + UNORM_UNICODE_3_2=0x20 +}; + +/** + * Lowest-order bit number of unorm_compare() options bits corresponding to + * normalization options bits. + * + * The options parameter for unorm_compare() uses most bits for + * itself and for various comparison and folding flags. + * The most significant bits, however, are shifted down and passed on + * to the normalization implementation. + * (That is, from unorm_compare(..., options, ...), + * options>>UNORM_COMPARE_NORM_OPTIONS_SHIFT will be passed on to the + * internal normalization functions.) + * + * @see unorm_compare + * @deprecated ICU 56 Use unorm2.h instead. + */ +#define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20 + +/** + * Normalize a string. + * The string will be normalized according the specified normalization mode + * and options. + * The source and result buffers must not be the same, nor overlap. + * + * @param source The string to normalize. + * @param sourceLength The length of source, or -1 if NUL-terminated. + * @param mode The normalization mode; one of UNORM_NONE, + * UNORM_NFD, UNORM_NFC, UNORM_NFKC, UNORM_NFKD, UNORM_DEFAULT. + * @param options The normalization options, ORed together (0 for no options). + * @param result A pointer to a buffer to receive the result string. + * The result string is NUL-terminated if possible. + * @param resultLength The maximum size of result. + * @param status A pointer to a UErrorCode to receive any errors. + * @return The total buffer size needed; if greater than resultLength, + * the output was truncated, and the error code is set to U_BUFFER_OVERFLOW_ERROR. + * @deprecated ICU 56 Use unorm2.h instead. + */ +U_DEPRECATED int32_t U_EXPORT2 +unorm_normalize(const UChar *source, int32_t sourceLength, + UNormalizationMode mode, int32_t options, + UChar *result, int32_t resultLength, + UErrorCode *status); + +/** + * Performing quick check on a string, to quickly determine if the string is + * in a particular normalization format. + * Three types of result can be returned UNORM_YES, UNORM_NO or + * UNORM_MAYBE. Result UNORM_YES indicates that the argument + * string is in the desired normalized format, UNORM_NO determines that + * argument string is not in the desired normalized format. A + * UNORM_MAYBE result indicates that a more thorough check is required, + * the user may have to put the string in its normalized form and compare the + * results. + * + * @param source string for determining if it is in a normalized format + * @param sourcelength length of source to test, or -1 if NUL-terminated + * @param mode which normalization form to test for + * @param status a pointer to a UErrorCode to receive any errors + * @return UNORM_YES, UNORM_NO or UNORM_MAYBE + * + * @see unorm_isNormalized + * @deprecated ICU 56 Use unorm2.h instead. + */ +U_DEPRECATED UNormalizationCheckResult U_EXPORT2 +unorm_quickCheck(const UChar *source, int32_t sourcelength, + UNormalizationMode mode, + UErrorCode *status); + +/** + * Performing quick check on a string; same as unorm_quickCheck but + * takes an extra options parameter like most normalization functions. + * + * @param src String that is to be tested if it is in a normalization format. + * @param srcLength Length of source to test, or -1 if NUL-terminated. + * @param mode Which normalization form to test for. + * @param options The normalization options, ORed together (0 for no options). + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return UNORM_YES, UNORM_NO or UNORM_MAYBE + * + * @see unorm_quickCheck + * @see unorm_isNormalized + * @deprecated ICU 56 Use unorm2.h instead. + */ +U_DEPRECATED UNormalizationCheckResult U_EXPORT2 +unorm_quickCheckWithOptions(const UChar *src, int32_t srcLength, + UNormalizationMode mode, int32_t options, + UErrorCode *pErrorCode); + +/** + * Test if a string is in a given normalization form. + * This is semantically equivalent to source.equals(normalize(source, mode)) . + * + * Unlike unorm_quickCheck(), this function returns a definitive result, + * never a "maybe". + * For NFD, NFKD, and FCD, both functions work exactly the same. + * For NFC and NFKC where quickCheck may return "maybe", this function will + * perform further tests to arrive at a true/false result. + * + * @param src String that is to be tested if it is in a normalization format. + * @param srcLength Length of source to test, or -1 if NUL-terminated. + * @param mode Which normalization form to test for. + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Boolean value indicating whether the source string is in the + * "mode" normalization form. + * + * @see unorm_quickCheck + * @deprecated ICU 56 Use unorm2.h instead. + */ +U_DEPRECATED UBool U_EXPORT2 +unorm_isNormalized(const UChar *src, int32_t srcLength, + UNormalizationMode mode, + UErrorCode *pErrorCode); + +/** + * Test if a string is in a given normalization form; same as unorm_isNormalized but + * takes an extra options parameter like most normalization functions. + * + * @param src String that is to be tested if it is in a normalization format. + * @param srcLength Length of source to test, or -1 if NUL-terminated. + * @param mode Which normalization form to test for. + * @param options The normalization options, ORed together (0 for no options). + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Boolean value indicating whether the source string is in the + * "mode/options" normalization form. + * + * @see unorm_quickCheck + * @see unorm_isNormalized + * @deprecated ICU 56 Use unorm2.h instead. + */ +U_DEPRECATED UBool U_EXPORT2 +unorm_isNormalizedWithOptions(const UChar *src, int32_t srcLength, + UNormalizationMode mode, int32_t options, + UErrorCode *pErrorCode); + +/** + * Iterative normalization forward. + * This function (together with unorm_previous) is somewhat + * similar to the C++ Normalizer class (see its non-static functions). + * + * Iterative normalization is useful when only a small portion of a longer + * string/text needs to be processed. + * + * For example, the likelihood may be high that processing the first 10% of some + * text will be sufficient to find certain data. + * Another example: When one wants to concatenate two normalized strings and get a + * normalized result, it is much more efficient to normalize just a small part of + * the result around the concatenation place instead of re-normalizing everything. + * + * The input text is an instance of the C character iteration API UCharIterator. + * It may wrap around a simple string, a CharacterIterator, a Replaceable, or any + * other kind of text object. + * + * If a buffer overflow occurs, then the caller needs to reset the iterator to the + * old index and call the function again with a larger buffer - if the caller cares + * for the actual output. + * Regardless of the output buffer, the iterator will always be moved to the next + * normalization boundary. + * + * This function (like unorm_previous) serves two purposes: + * + * 1) To find the next boundary so that the normalization of the part of the text + * from the current position to that boundary does not affect and is not affected + * by the part of the text beyond that boundary. + * + * 2) To normalize the text up to the boundary. + * + * The second step is optional, per the doNormalize parameter. + * It is omitted for operations like string concatenation, where the two adjacent + * string ends need to be normalized together. + * In such a case, the output buffer will just contain a copy of the text up to the + * boundary. + * + * pNeededToNormalize is an output-only parameter. Its output value is only defined + * if normalization was requested (doNormalize) and successful (especially, no + * buffer overflow). + * It is useful for operations like a normalizing transliterator, where one would + * not want to replace a piece of text if it is not modified. + * + * If doNormalize==true and pNeededToNormalize!=NULL then *pNeeded... is set true + * if the normalization was necessary. + * + * If doNormalize==false then *pNeededToNormalize will be set to false. + * + * If the buffer overflows, then *pNeededToNormalize will be undefined; + * essentially, whenever U_FAILURE is true (like in buffer overflows), this result + * will be undefined. + * + * @param src The input text in the form of a C character iterator. + * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. + * @param destCapacity The number of UChars that fit into dest. + * @param mode The normalization mode. + * @param options The normalization options, ORed together (0 for no options). + * @param doNormalize Indicates if the source text up to the next boundary + * is to be normalized (true) or just copied (false). + * @param pNeededToNormalize Output flag indicating if the normalization resulted in + * different text from the input. + * Not defined if an error occurs including buffer overflow. + * Always false if !doNormalize. + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Length of output (number of UChars) when successful or buffer overflow. + * + * @see unorm_previous + * @see unorm_normalize + * + * @deprecated ICU 56 Use unorm2.h instead. + */ +U_DEPRECATED int32_t U_EXPORT2 +unorm_next(UCharIterator *src, + UChar *dest, int32_t destCapacity, + UNormalizationMode mode, int32_t options, + UBool doNormalize, UBool *pNeededToNormalize, + UErrorCode *pErrorCode); + +/** + * Iterative normalization backward. + * This function (together with unorm_next) is somewhat + * similar to the C++ Normalizer class (see its non-static functions). + * For all details see unorm_next. + * + * @param src The input text in the form of a C character iterator. + * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. + * @param destCapacity The number of UChars that fit into dest. + * @param mode The normalization mode. + * @param options The normalization options, ORed together (0 for no options). + * @param doNormalize Indicates if the source text up to the next boundary + * is to be normalized (true) or just copied (false). + * @param pNeededToNormalize Output flag indicating if the normalization resulted in + * different text from the input. + * Not defined if an error occurs including buffer overflow. + * Always false if !doNormalize. + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Length of output (number of UChars) when successful or buffer overflow. + * + * @see unorm_next + * @see unorm_normalize + * + * @deprecated ICU 56 Use unorm2.h instead. + */ +U_DEPRECATED int32_t U_EXPORT2 +unorm_previous(UCharIterator *src, + UChar *dest, int32_t destCapacity, + UNormalizationMode mode, int32_t options, + UBool doNormalize, UBool *pNeededToNormalize, + UErrorCode *pErrorCode); + +/** + * Concatenate normalized strings, making sure that the result is normalized as well. + * + * If both the left and the right strings are in + * the normalization form according to "mode/options", + * then the result will be + * + * \code + * dest=normalize(left+right, mode, options) + * \endcode + * + * With the input strings already being normalized, + * this function will use unorm_next() and unorm_previous() + * to find the adjacent end pieces of the input strings. + * Only the concatenation of these end pieces will be normalized and + * then concatenated with the remaining parts of the input strings. + * + * It is allowed to have dest==left to avoid copying the entire left string. + * + * @param left Left source string, may be same as dest. + * @param leftLength Length of left source string, or -1 if NUL-terminated. + * @param right Right source string. Must not be the same as dest, nor overlap. + * @param rightLength Length of right source string, or -1 if NUL-terminated. + * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. + * @param destCapacity The number of UChars that fit into dest. + * @param mode The normalization mode. + * @param options The normalization options, ORed together (0 for no options). + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return Length of output (number of UChars) when successful or buffer overflow. + * + * @see unorm_normalize + * @see unorm_next + * @see unorm_previous + * + * @deprecated ICU 56 Use unorm2.h instead. + */ +U_DEPRECATED int32_t U_EXPORT2 +unorm_concatenate(const UChar *left, int32_t leftLength, + const UChar *right, int32_t rightLength, + UChar *dest, int32_t destCapacity, + UNormalizationMode mode, int32_t options, + UErrorCode *pErrorCode); + +#endif /* U_HIDE_DEPRECATED_API */ +#endif /* #if !UCONFIG_NO_NORMALIZATION */ +#endif diff --git a/thirdparty/icu4c/common/unicode/unorm2.h b/thirdparty/icu4c/common/unicode/unorm2.h new file mode 100644 index 0000000000..24417b7103 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/unorm2.h @@ -0,0 +1,606 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2009-2015, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: unorm2.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2009dec15 +* created by: Markus W. Scherer +*/ + +#ifndef __UNORM2_H__ +#define __UNORM2_H__ + +/** + * \file + * \brief C API: New API for Unicode Normalization. + * + * Unicode normalization functionality for standard Unicode normalization or + * for using custom mapping tables. + * All instances of UNormalizer2 are unmodifiable/immutable. + * Instances returned by unorm2_getInstance() are singletons that must not be deleted by the caller. + * For more details see the Normalizer2 C++ class. + */ + +#include "unicode/utypes.h" +#include "unicode/stringoptions.h" +#include "unicode/uset.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * Constants for normalization modes. + * For details about standard Unicode normalization forms + * and about the algorithms which are also used with custom mapping tables + * see http://www.unicode.org/unicode/reports/tr15/ + * @stable ICU 4.4 + */ +typedef enum { + /** + * Decomposition followed by composition. + * Same as standard NFC when using an "nfc" instance. + * Same as standard NFKC when using an "nfkc" instance. + * For details about standard Unicode normalization forms + * see http://www.unicode.org/unicode/reports/tr15/ + * @stable ICU 4.4 + */ + UNORM2_COMPOSE, + /** + * Map, and reorder canonically. + * Same as standard NFD when using an "nfc" instance. + * Same as standard NFKD when using an "nfkc" instance. + * For details about standard Unicode normalization forms + * see http://www.unicode.org/unicode/reports/tr15/ + * @stable ICU 4.4 + */ + UNORM2_DECOMPOSE, + /** + * "Fast C or D" form. + * If a string is in this form, then further decomposition <i>without reordering</i> + * would yield the same form as DECOMPOSE. + * Text in "Fast C or D" form can be processed efficiently with data tables + * that are "canonically closed", that is, that provide equivalent data for + * equivalent text, without having to be fully normalized. + * Not a standard Unicode normalization form. + * Not a unique form: Different FCD strings can be canonically equivalent. + * For details see http://www.unicode.org/notes/tn5/#FCD + * @stable ICU 4.4 + */ + UNORM2_FCD, + /** + * Compose only contiguously. + * Also known as "FCC" or "Fast C Contiguous". + * The result will often but not always be in NFC. + * The result will conform to FCD which is useful for processing. + * Not a standard Unicode normalization form. + * For details see http://www.unicode.org/notes/tn5/#FCC + * @stable ICU 4.4 + */ + UNORM2_COMPOSE_CONTIGUOUS +} UNormalization2Mode; + +/** + * Result values for normalization quick check functions. + * For details see http://www.unicode.org/reports/tr15/#Detecting_Normalization_Forms + * @stable ICU 2.0 + */ +typedef enum UNormalizationCheckResult { + /** + * The input string is not in the normalization form. + * @stable ICU 2.0 + */ + UNORM_NO, + /** + * The input string is in the normalization form. + * @stable ICU 2.0 + */ + UNORM_YES, + /** + * The input string may or may not be in the normalization form. + * This value is only returned for composition forms like NFC and FCC, + * when a backward-combining character is found for which the surrounding text + * would have to be analyzed further. + * @stable ICU 2.0 + */ + UNORM_MAYBE +} UNormalizationCheckResult; + +/** + * Opaque C service object type for the new normalization API. + * @stable ICU 4.4 + */ +struct UNormalizer2; +typedef struct UNormalizer2 UNormalizer2; /**< C typedef for struct UNormalizer2. @stable ICU 4.4 */ + +#if !UCONFIG_NO_NORMALIZATION + +/** + * Returns a UNormalizer2 instance for Unicode NFC normalization. + * Same as unorm2_getInstance(NULL, "nfc", UNORM2_COMPOSE, pErrorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ +U_CAPI const UNormalizer2 * U_EXPORT2 +unorm2_getNFCInstance(UErrorCode *pErrorCode); + +/** + * Returns a UNormalizer2 instance for Unicode NFD normalization. + * Same as unorm2_getInstance(NULL, "nfc", UNORM2_DECOMPOSE, pErrorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ +U_CAPI const UNormalizer2 * U_EXPORT2 +unorm2_getNFDInstance(UErrorCode *pErrorCode); + +/** + * Returns a UNormalizer2 instance for Unicode NFKC normalization. + * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_COMPOSE, pErrorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ +U_CAPI const UNormalizer2 * U_EXPORT2 +unorm2_getNFKCInstance(UErrorCode *pErrorCode); + +/** + * Returns a UNormalizer2 instance for Unicode NFKD normalization. + * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, pErrorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ +U_CAPI const UNormalizer2 * U_EXPORT2 +unorm2_getNFKDInstance(UErrorCode *pErrorCode); + +/** + * Returns a UNormalizer2 instance for Unicode NFKC_Casefold normalization. + * Same as unorm2_getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, pErrorCode). + * Returns an unmodifiable singleton instance. Do not delete it. + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested Normalizer2, if successful + * @stable ICU 49 + */ +U_CAPI const UNormalizer2 * U_EXPORT2 +unorm2_getNFKCCasefoldInstance(UErrorCode *pErrorCode); + +/** + * Returns a UNormalizer2 instance which uses the specified data file + * (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle) + * and which composes or decomposes text according to the specified mode. + * Returns an unmodifiable singleton instance. Do not delete it. + * + * Use packageName=NULL for data files that are part of ICU's own data. + * Use name="nfc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFC/NFD. + * Use name="nfkc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFKC/NFKD. + * Use name="nfkc_cf" and UNORM2_COMPOSE for Unicode standard NFKC_CF=NFKC_Casefold. + * + * @param packageName NULL for ICU built-in data, otherwise application data package name + * @param name "nfc" or "nfkc" or "nfkc_cf" or name of custom data file + * @param mode normalization mode (compose or decompose etc.) + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested UNormalizer2, if successful + * @stable ICU 4.4 + */ +U_CAPI const UNormalizer2 * U_EXPORT2 +unorm2_getInstance(const char *packageName, + const char *name, + UNormalization2Mode mode, + UErrorCode *pErrorCode); + +/** + * Constructs a filtered normalizer wrapping any UNormalizer2 instance + * and a filter set. + * Both are aliased and must not be modified or deleted while this object + * is used. + * The filter set should be frozen; otherwise the performance will suffer greatly. + * @param norm2 wrapped UNormalizer2 instance + * @param filterSet USet which determines the characters to be normalized + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the requested UNormalizer2, if successful + * @stable ICU 4.4 + */ +U_CAPI UNormalizer2 * U_EXPORT2 +unorm2_openFiltered(const UNormalizer2 *norm2, const USet *filterSet, UErrorCode *pErrorCode); + +/** + * Closes a UNormalizer2 instance from unorm2_openFiltered(). + * Do not close instances from unorm2_getInstance()! + * @param norm2 UNormalizer2 instance to be closed + * @stable ICU 4.4 + */ +U_CAPI void U_EXPORT2 +unorm2_close(UNormalizer2 *norm2); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUNormalizer2Pointer + * "Smart pointer" class, closes a UNormalizer2 via unorm2_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUNormalizer2Pointer, UNormalizer2, unorm2_close); + +U_NAMESPACE_END + +#endif + +/** + * Writes the normalized form of the source string to the destination string + * (replacing its contents) and returns the length of the destination string. + * The source and destination strings must be different buffers. + * @param norm2 UNormalizer2 instance + * @param src source string + * @param length length of the source string, or -1 if NUL-terminated + * @param dest destination string; its contents is replaced with normalized src + * @param capacity number of UChars that can be written to dest + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return dest + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +unorm2_normalize(const UNormalizer2 *norm2, + const UChar *src, int32_t length, + UChar *dest, int32_t capacity, + UErrorCode *pErrorCode); +/** + * Appends the normalized form of the second string to the first string + * (merging them at the boundary) and returns the length of the first string. + * The result is normalized if the first string was normalized. + * The first and second strings must be different buffers. + * @param norm2 UNormalizer2 instance + * @param first string, should be normalized + * @param firstLength length of the first string, or -1 if NUL-terminated + * @param firstCapacity number of UChars that can be written to first + * @param second string, will be normalized + * @param secondLength length of the source string, or -1 if NUL-terminated + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return first + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +unorm2_normalizeSecondAndAppend(const UNormalizer2 *norm2, + UChar *first, int32_t firstLength, int32_t firstCapacity, + const UChar *second, int32_t secondLength, + UErrorCode *pErrorCode); +/** + * Appends the second string to the first string + * (merging them at the boundary) and returns the length of the first string. + * The result is normalized if both the strings were normalized. + * The first and second strings must be different buffers. + * @param norm2 UNormalizer2 instance + * @param first string, should be normalized + * @param firstLength length of the first string, or -1 if NUL-terminated + * @param firstCapacity number of UChars that can be written to first + * @param second string, should be normalized + * @param secondLength length of the source string, or -1 if NUL-terminated + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return first + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +unorm2_append(const UNormalizer2 *norm2, + UChar *first, int32_t firstLength, int32_t firstCapacity, + const UChar *second, int32_t secondLength, + UErrorCode *pErrorCode); + +/** + * Gets the decomposition mapping of c. + * Roughly equivalent to normalizing the String form of c + * on a UNORM2_DECOMPOSE UNormalizer2 instance, but much faster, and except that this function + * returns a negative value and does not write a string + * if c does not have a decomposition mapping in this instance's data. + * This function is independent of the mode of the UNormalizer2. + * @param norm2 UNormalizer2 instance + * @param c code point + * @param decomposition String buffer which will be set to c's + * decomposition mapping, if there is one. + * @param capacity number of UChars that can be written to decomposition + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the non-negative length of c's decomposition, if there is one; otherwise a negative value + * @stable ICU 4.6 + */ +U_CAPI int32_t U_EXPORT2 +unorm2_getDecomposition(const UNormalizer2 *norm2, + UChar32 c, UChar *decomposition, int32_t capacity, + UErrorCode *pErrorCode); + +/** + * Gets the raw decomposition mapping of c. + * + * This is similar to the unorm2_getDecomposition() function but returns the + * raw decomposition mapping as specified in UnicodeData.txt or + * (for custom data) in the mapping files processed by the gennorm2 tool. + * By contrast, unorm2_getDecomposition() returns the processed, + * recursively-decomposed version of this mapping. + * + * When used on a standard NFKC Normalizer2 instance, + * unorm2_getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property. + * + * When used on a standard NFC Normalizer2 instance, + * it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can); + * in this case, the result contains either one or two code points (=1..4 UChars). + * + * This function is independent of the mode of the UNormalizer2. + * @param norm2 UNormalizer2 instance + * @param c code point + * @param decomposition String buffer which will be set to c's + * raw decomposition mapping, if there is one. + * @param capacity number of UChars that can be written to decomposition + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return the non-negative length of c's raw decomposition, if there is one; otherwise a negative value + * @stable ICU 49 + */ +U_CAPI int32_t U_EXPORT2 +unorm2_getRawDecomposition(const UNormalizer2 *norm2, + UChar32 c, UChar *decomposition, int32_t capacity, + UErrorCode *pErrorCode); + +/** + * Performs pairwise composition of a & b and returns the composite if there is one. + * + * Returns a composite code point c only if c has a two-way mapping to a+b. + * In standard Unicode normalization, this means that + * c has a canonical decomposition to a+b + * and c does not have the Full_Composition_Exclusion property. + * + * This function is independent of the mode of the UNormalizer2. + * @param norm2 UNormalizer2 instance + * @param a A (normalization starter) code point. + * @param b Another code point. + * @return The non-negative composite code point if there is one; otherwise a negative value. + * @stable ICU 49 + */ +U_CAPI UChar32 U_EXPORT2 +unorm2_composePair(const UNormalizer2 *norm2, UChar32 a, UChar32 b); + +/** + * Gets the combining class of c. + * The default implementation returns 0 + * but all standard implementations return the Unicode Canonical_Combining_Class value. + * @param norm2 UNormalizer2 instance + * @param c code point + * @return c's combining class + * @stable ICU 49 + */ +U_CAPI uint8_t U_EXPORT2 +unorm2_getCombiningClass(const UNormalizer2 *norm2, UChar32 c); + +/** + * Tests if the string is normalized. + * Internally, in cases where the quickCheck() method would return "maybe" + * (which is only possible for the two COMPOSE modes) this method + * resolves to "yes" or "no" to provide a definitive result, + * at the cost of doing more work in those cases. + * @param norm2 UNormalizer2 instance + * @param s input string + * @param length length of the string, or -1 if NUL-terminated + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return true if s is normalized + * @stable ICU 4.4 + */ +U_CAPI UBool U_EXPORT2 +unorm2_isNormalized(const UNormalizer2 *norm2, + const UChar *s, int32_t length, + UErrorCode *pErrorCode); + +/** + * Tests if the string is normalized. + * For the two COMPOSE modes, the result could be "maybe" in cases that + * would take a little more work to resolve definitively. + * Use spanQuickCheckYes() and normalizeSecondAndAppend() for a faster + * combination of quick check + normalization, to avoid + * re-checking the "yes" prefix. + * @param norm2 UNormalizer2 instance + * @param s input string + * @param length length of the string, or -1 if NUL-terminated + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return UNormalizationCheckResult + * @stable ICU 4.4 + */ +U_CAPI UNormalizationCheckResult U_EXPORT2 +unorm2_quickCheck(const UNormalizer2 *norm2, + const UChar *s, int32_t length, + UErrorCode *pErrorCode); + +/** + * Returns the end of the normalized substring of the input string. + * In other words, with <code>end=spanQuickCheckYes(s, ec);</code> + * the substring <code>UnicodeString(s, 0, end)</code> + * will pass the quick check with a "yes" result. + * + * The returned end index is usually one or more characters before the + * "no" or "maybe" character: The end index is at a normalization boundary. + * (See the class documentation for more about normalization boundaries.) + * + * When the goal is a normalized string and most input strings are expected + * to be normalized already, then call this method, + * and if it returns a prefix shorter than the input string, + * copy that prefix and use normalizeSecondAndAppend() for the remainder. + * @param norm2 UNormalizer2 instance + * @param s input string + * @param length length of the string, or -1 if NUL-terminated + * @param pErrorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return "yes" span end index + * @stable ICU 4.4 + */ +U_CAPI int32_t U_EXPORT2 +unorm2_spanQuickCheckYes(const UNormalizer2 *norm2, + const UChar *s, int32_t length, + UErrorCode *pErrorCode); + +/** + * Tests if the character always has a normalization boundary before it, + * regardless of context. + * For details see the Normalizer2 base class documentation. + * @param norm2 UNormalizer2 instance + * @param c character to test + * @return true if c has a normalization boundary before it + * @stable ICU 4.4 + */ +U_CAPI UBool U_EXPORT2 +unorm2_hasBoundaryBefore(const UNormalizer2 *norm2, UChar32 c); + +/** + * Tests if the character always has a normalization boundary after it, + * regardless of context. + * For details see the Normalizer2 base class documentation. + * @param norm2 UNormalizer2 instance + * @param c character to test + * @return true if c has a normalization boundary after it + * @stable ICU 4.4 + */ +U_CAPI UBool U_EXPORT2 +unorm2_hasBoundaryAfter(const UNormalizer2 *norm2, UChar32 c); + +/** + * Tests if the character is normalization-inert. + * For details see the Normalizer2 base class documentation. + * @param norm2 UNormalizer2 instance + * @param c character to test + * @return true if c is normalization-inert + * @stable ICU 4.4 + */ +U_CAPI UBool U_EXPORT2 +unorm2_isInert(const UNormalizer2 *norm2, UChar32 c); + +/** + * Compares two strings for canonical equivalence. + * Further options include case-insensitive comparison and + * code point order (as opposed to code unit order). + * + * Canonical equivalence between two strings is defined as their normalized + * forms (NFD or NFC) being identical. + * This function compares strings incrementally instead of normalizing + * (and optionally case-folding) both strings entirely, + * improving performance significantly. + * + * Bulk normalization is only necessary if the strings do not fulfill the FCD + * conditions. Only in this case, and only if the strings are relatively long, + * is memory allocated temporarily. + * For FCD strings and short non-FCD strings there is no memory allocation. + * + * Semantically, this is equivalent to + * strcmp[CodePointOrder](NFD(foldCase(NFD(s1))), NFD(foldCase(NFD(s2)))) + * where code point order and foldCase are all optional. + * + * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match + * the case folding must be performed first, then the normalization. + * + * @param s1 First source string. + * @param length1 Length of first source string, or -1 if NUL-terminated. + * + * @param s2 Second source string. + * @param length2 Length of second source string, or -1 if NUL-terminated. + * + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Case-sensitive comparison in code unit order, and the input strings + * are quick-checked for FCD. + * + * - UNORM_INPUT_IS_FCD + * Set if the caller knows that both s1 and s2 fulfill the FCD conditions. + * If not set, the function will quickCheck for FCD + * and normalize if necessary. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_COMPARE_IGNORE_CASE + * Set to compare strings case-insensitively using case folding, + * instead of case-sensitively. + * If set, then the following case folding options are used. + * + * - Options as used with case-insensitive comparisons, currently: + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * (see u_strCaseCompare for details) + * + * - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT + * + * @param pErrorCode ICU error code in/out parameter. + * Must fulfill U_SUCCESS before the function call. + * @return <0 or 0 or >0 as usual for string comparisons + * + * @see unorm_normalize + * @see UNORM_FCD + * @see u_strCompare + * @see u_strCaseCompare + * + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +unorm_compare(const UChar *s1, int32_t length1, + const UChar *s2, int32_t length2, + uint32_t options, + UErrorCode *pErrorCode); + +#endif /* !UCONFIG_NO_NORMALIZATION */ +#endif /* __UNORM2_H__ */ diff --git a/thirdparty/icu4c/common/unicode/uobject.h b/thirdparty/icu4c/common/unicode/uobject.h new file mode 100644 index 0000000000..eeb331ce97 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uobject.h @@ -0,0 +1,324 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 2002-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* file name: uobject.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2002jun26 +* created by: Markus W. Scherer +*/ + +#ifndef __UOBJECT_H__ +#define __UOBJECT_H__ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/platform.h" + +/** + * \file + * \brief C++ API: Common ICU base class UObject. + */ + +/** + * \def U_NO_THROW + * Since ICU 64, use U_NOEXCEPT instead. + * + * Previously, define this to define the throw() specification so + * certain functions do not throw any exceptions + * + * UMemory operator new methods should have the throw() specification + * appended to them, so that the compiler adds the additional NULL check + * before calling constructors. Without, if <code>operator new</code> returns NULL the + * constructor is still called, and if the constructor references member + * data, (which it typically does), the result is a segmentation violation. + * + * @stable ICU 4.2. Since ICU 64, Use U_NOEXCEPT instead. See ICU-20422. + */ +#ifndef U_NO_THROW +#define U_NO_THROW U_NOEXCEPT +#endif + +/*===========================================================================*/ +/* UClassID-based RTTI */ +/*===========================================================================*/ + +/** + * UClassID is used to identify classes without using the compiler's RTTI. + * This was used before C++ compilers consistently supported RTTI. + * ICU 4.6 requires compiler RTTI to be turned on. + * + * Each class hierarchy which needs + * to implement polymorphic clone() or operator==() defines two methods, + * described in detail below. UClassID values can be compared using + * operator==(). Nothing else should be done with them. + * + * \par + * In class hierarchies that implement "poor man's RTTI", + * each concrete subclass implements getDynamicClassID() in the same way: + * + * \code + * class Derived { + * public: + * virtual UClassID getDynamicClassID() const + * { return Derived::getStaticClassID(); } + * } + * \endcode + * + * Each concrete class implements getStaticClassID() as well, which allows + * clients to test for a specific type. + * + * \code + * class Derived { + * public: + * static UClassID U_EXPORT2 getStaticClassID(); + * private: + * static char fgClassID; + * } + * + * // In Derived.cpp: + * UClassID Derived::getStaticClassID() + * { return (UClassID)&Derived::fgClassID; } + * char Derived::fgClassID = 0; // Value is irrelevant + * \endcode + * @stable ICU 2.0 + */ +typedef void* UClassID; + +U_NAMESPACE_BEGIN + +/** + * UMemory is the common ICU base class. + * All other ICU C++ classes are derived from UMemory (starting with ICU 2.4). + * + * This is primarily to make it possible and simple to override the + * C++ memory management by adding new/delete operators to this base class. + * + * To override ALL ICU memory management, including that from plain C code, + * replace the allocation functions declared in cmemory.h + * + * UMemory does not contain any virtual functions. + * Common "boilerplate" functions are defined in UObject. + * + * @stable ICU 2.4 + */ +class U_COMMON_API UMemory { +public: + +/* test versions for debugging shaper heap memory problems */ +#ifdef SHAPER_MEMORY_DEBUG + static void * NewArray(int size, int count); + static void * GrowArray(void * array, int newSize ); + static void FreeArray(void * array ); +#endif + +#if U_OVERRIDE_CXX_ALLOCATION + /** + * Override for ICU4C C++ memory management. + * simple, non-class types are allocated using the macros in common/cmemory.h + * (uprv_malloc(), uprv_free(), uprv_realloc()); + * they or something else could be used here to implement C++ new/delete + * for ICU4C C++ classes + * @stable ICU 2.4 + */ + static void * U_EXPORT2 operator new(size_t size) U_NOEXCEPT; + + /** + * Override for ICU4C C++ memory management. + * See new(). + * @stable ICU 2.4 + */ + static void * U_EXPORT2 operator new[](size_t size) U_NOEXCEPT; + + /** + * Override for ICU4C C++ memory management. + * simple, non-class types are allocated using the macros in common/cmemory.h + * (uprv_malloc(), uprv_free(), uprv_realloc()); + * they or something else could be used here to implement C++ new/delete + * for ICU4C C++ classes + * @stable ICU 2.4 + */ + static void U_EXPORT2 operator delete(void *p) U_NOEXCEPT; + + /** + * Override for ICU4C C++ memory management. + * See delete(). + * @stable ICU 2.4 + */ + static void U_EXPORT2 operator delete[](void *p) U_NOEXCEPT; + +#if U_HAVE_PLACEMENT_NEW + /** + * Override for ICU4C C++ memory management for STL. + * See new(). + * @stable ICU 2.6 + */ + static inline void * U_EXPORT2 operator new(size_t, void *ptr) U_NOEXCEPT { return ptr; } + + /** + * Override for ICU4C C++ memory management for STL. + * See delete(). + * @stable ICU 2.6 + */ + static inline void U_EXPORT2 operator delete(void *, void *) U_NOEXCEPT {} +#endif /* U_HAVE_PLACEMENT_NEW */ +#if U_HAVE_DEBUG_LOCATION_NEW + /** + * This method overrides the MFC debug version of the operator new + * + * @param size The requested memory size + * @param file The file where the allocation was requested + * @param line The line where the allocation was requested + */ + static void * U_EXPORT2 operator new(size_t size, const char* file, int line) U_NOEXCEPT; + /** + * This method provides a matching delete for the MFC debug new + * + * @param p The pointer to the allocated memory + * @param file The file where the allocation was requested + * @param line The line where the allocation was requested + */ + static void U_EXPORT2 operator delete(void* p, const char* file, int line) U_NOEXCEPT; +#endif /* U_HAVE_DEBUG_LOCATION_NEW */ +#endif /* U_OVERRIDE_CXX_ALLOCATION */ + + /* + * Assignment operator not declared. The compiler will provide one + * which does nothing since this class does not contain any data members. + * API/code coverage may show the assignment operator as present and + * untested - ignore. + * Subclasses need this assignment operator if they use compiler-provided + * assignment operators of their own. An alternative to not declaring one + * here would be to declare and empty-implement a protected or public one. + UMemory &UMemory::operator=(const UMemory &); + */ +}; + +/** + * UObject is the common ICU "boilerplate" class. + * UObject inherits UMemory (starting with ICU 2.4), + * and all other public ICU C++ classes + * are derived from UObject (starting with ICU 2.2). + * + * UObject contains common virtual functions, in particular a virtual destructor. + * + * The clone() function is not available in UObject because it is not + * implemented by all ICU classes. + * Many ICU services provide a clone() function for their class trees, + * defined on the service's C++ base class + * (which itself is a subclass of UObject). + * + * @stable ICU 2.2 + */ +class U_COMMON_API UObject : public UMemory { +public: + /** + * Destructor. + * + * @stable ICU 2.2 + */ + virtual ~UObject(); + + /** + * ICU4C "poor man's RTTI", returns a UClassID for the actual ICU class. + * The base class implementation returns a dummy value. + * + * Use compiler RTTI rather than ICU's "poor man's RTTI". + * Since ICU 4.6, new ICU C++ class hierarchies do not implement "poor man's RTTI". + * + * @stable ICU 2.2 + */ + virtual UClassID getDynamicClassID() const; + +protected: + // the following functions are protected to prevent instantiation and + // direct use of UObject itself + + // default constructor + // inline UObject() {} + + // copy constructor + // inline UObject(const UObject &other) {} + +#if 0 + // TODO Sometime in the future. Implement operator==(). + // (This comment inserted in 2.2) + // some or all of the following "boilerplate" functions may be made public + // in a future ICU4C release when all subclasses implement them + + // assignment operator + // (not virtual, see "Taligent's Guide to Designing Programs" pp.73..74) + // commented out because the implementation is the same as a compiler's default + // UObject &operator=(const UObject &other) { return *this; } + + // comparison operators + virtual inline UBool operator==(const UObject &other) const { return this==&other; } + inline UBool operator!=(const UObject &other) const { return !operator==(other); } + + // clone() commented out from the base class: + // some compilers do not support co-variant return types + // (i.e., subclasses would have to return UObject * as well, instead of SubClass *) + // see also UObject class documentation. + // virtual UObject *clone() const; +#endif + + /* + * Assignment operator not declared. The compiler will provide one + * which does nothing since this class does not contain any data members. + * API/code coverage may show the assignment operator as present and + * untested - ignore. + * Subclasses need this assignment operator if they use compiler-provided + * assignment operators of their own. An alternative to not declaring one + * here would be to declare and empty-implement a protected or public one. + UObject &UObject::operator=(const UObject &); + */ +}; + +#ifndef U_HIDE_INTERNAL_API +/** + * This is a simple macro to add ICU RTTI to an ICU object implementation. + * This does not go into the header. This should only be used in *.cpp files. + * + * @param myClass The name of the class that needs RTTI defined. + * @internal + */ +#define UOBJECT_DEFINE_RTTI_IMPLEMENTATION(myClass) \ + UClassID U_EXPORT2 myClass::getStaticClassID() { \ + static char classID = 0; \ + return (UClassID)&classID; \ + } \ + UClassID myClass::getDynamicClassID() const \ + { return myClass::getStaticClassID(); } + + +/** + * This macro adds ICU RTTI to an ICU abstract class implementation. + * This macro should be invoked in *.cpp files. The corresponding + * header should declare getStaticClassID. + * + * @param myClass The name of the class that needs RTTI defined. + * @internal + */ +#define UOBJECT_DEFINE_ABSTRACT_RTTI_IMPLEMENTATION(myClass) \ + UClassID U_EXPORT2 myClass::getStaticClassID() { \ + static char classID = 0; \ + return (UClassID)&classID; \ + } + +#endif /* U_HIDE_INTERNAL_API */ + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/urename.h b/thirdparty/icu4c/common/unicode/urename.h new file mode 100644 index 0000000000..20232cd209 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/urename.h @@ -0,0 +1,1922 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2002-2016, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* +* file name: urename.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* Created by: Perl script tools/genren.pl written by Vladimir Weinstein +* +* Contains data for renaming ICU exports. +* Gets included by umachine.h +* +* THIS FILE IS MACHINE-GENERATED, DON'T PLAY WITH IT IF YOU DON'T KNOW WHAT +* YOU ARE DOING, OTHERWISE VERY BAD THINGS WILL HAPPEN! +*/ + +#ifndef URENAME_H +#define URENAME_H + +/* U_DISABLE_RENAMING can be defined in the following ways: + * - when running configure, e.g. + * runConfigureICU Linux --disable-renaming + * - by changing the default setting of U_DISABLE_RENAMING in uconfig.h + */ + +#include "unicode/uconfig.h" + +#if !U_DISABLE_RENAMING + +// Disable Renaming for Visual Studio's IntelliSense feature, so that 'Go-to-Definition' (F12) will work. +#if !(defined(_MSC_VER) && defined(__INTELLISENSE__)) + +/* We need the U_ICU_ENTRY_POINT_RENAME definition. There's a default one in unicode/uvernum.h we can use, but we will give + the platform a chance to define it first. + Normally (if utypes.h or umachine.h was included first) this will not be necessary as it will already be defined. + */ + +#ifndef U_ICU_ENTRY_POINT_RENAME +#include "unicode/umachine.h" +#endif + +/* If we still don't have U_ICU_ENTRY_POINT_RENAME use the default. */ +#ifndef U_ICU_ENTRY_POINT_RENAME +#include "unicode/uvernum.h" +#endif + +/* Error out before the following defines cause very strange and unexpected code breakage */ +#ifndef U_ICU_ENTRY_POINT_RENAME +#error U_ICU_ENTRY_POINT_RENAME is not defined - cannot continue. Consider defining U_DISABLE_RENAMING if renaming should not be used. +#endif + + +/* C exports renaming data */ + +#define T_CString_int64ToString U_ICU_ENTRY_POINT_RENAME(T_CString_int64ToString) +#define T_CString_integerToString U_ICU_ENTRY_POINT_RENAME(T_CString_integerToString) +#define T_CString_stringToInteger U_ICU_ENTRY_POINT_RENAME(T_CString_stringToInteger) +#define T_CString_toLowerCase U_ICU_ENTRY_POINT_RENAME(T_CString_toLowerCase) +#define T_CString_toUpperCase U_ICU_ENTRY_POINT_RENAME(T_CString_toUpperCase) +#define UCNV_FROM_U_CALLBACK_ESCAPE U_ICU_ENTRY_POINT_RENAME(UCNV_FROM_U_CALLBACK_ESCAPE) +#define UCNV_FROM_U_CALLBACK_SKIP U_ICU_ENTRY_POINT_RENAME(UCNV_FROM_U_CALLBACK_SKIP) +#define UCNV_FROM_U_CALLBACK_STOP U_ICU_ENTRY_POINT_RENAME(UCNV_FROM_U_CALLBACK_STOP) +#define UCNV_FROM_U_CALLBACK_SUBSTITUTE U_ICU_ENTRY_POINT_RENAME(UCNV_FROM_U_CALLBACK_SUBSTITUTE) +#define UCNV_TO_U_CALLBACK_ESCAPE U_ICU_ENTRY_POINT_RENAME(UCNV_TO_U_CALLBACK_ESCAPE) +#define UCNV_TO_U_CALLBACK_SKIP U_ICU_ENTRY_POINT_RENAME(UCNV_TO_U_CALLBACK_SKIP) +#define UCNV_TO_U_CALLBACK_STOP U_ICU_ENTRY_POINT_RENAME(UCNV_TO_U_CALLBACK_STOP) +#define UCNV_TO_U_CALLBACK_SUBSTITUTE U_ICU_ENTRY_POINT_RENAME(UCNV_TO_U_CALLBACK_SUBSTITUTE) +#define UDataMemory_createNewInstance U_ICU_ENTRY_POINT_RENAME(UDataMemory_createNewInstance) +#define UDataMemory_init U_ICU_ENTRY_POINT_RENAME(UDataMemory_init) +#define UDataMemory_isLoaded U_ICU_ENTRY_POINT_RENAME(UDataMemory_isLoaded) +#define UDataMemory_normalizeDataPointer U_ICU_ENTRY_POINT_RENAME(UDataMemory_normalizeDataPointer) +#define UDataMemory_setData U_ICU_ENTRY_POINT_RENAME(UDataMemory_setData) +#define UDatamemory_assign U_ICU_ENTRY_POINT_RENAME(UDatamemory_assign) +#define _ASCIIData U_ICU_ENTRY_POINT_RENAME(_ASCIIData) +#define _Bocu1Data U_ICU_ENTRY_POINT_RENAME(_Bocu1Data) +#define _CESU8Data U_ICU_ENTRY_POINT_RENAME(_CESU8Data) +#define _CompoundTextData U_ICU_ENTRY_POINT_RENAME(_CompoundTextData) +#define _HZData U_ICU_ENTRY_POINT_RENAME(_HZData) +#define _IMAPData U_ICU_ENTRY_POINT_RENAME(_IMAPData) +#define _ISCIIData U_ICU_ENTRY_POINT_RENAME(_ISCIIData) +#define _ISO2022Data U_ICU_ENTRY_POINT_RENAME(_ISO2022Data) +#define _LMBCSData1 U_ICU_ENTRY_POINT_RENAME(_LMBCSData1) +#define _LMBCSData11 U_ICU_ENTRY_POINT_RENAME(_LMBCSData11) +#define _LMBCSData16 U_ICU_ENTRY_POINT_RENAME(_LMBCSData16) +#define _LMBCSData17 U_ICU_ENTRY_POINT_RENAME(_LMBCSData17) +#define _LMBCSData18 U_ICU_ENTRY_POINT_RENAME(_LMBCSData18) +#define _LMBCSData19 U_ICU_ENTRY_POINT_RENAME(_LMBCSData19) +#define _LMBCSData2 U_ICU_ENTRY_POINT_RENAME(_LMBCSData2) +#define _LMBCSData3 U_ICU_ENTRY_POINT_RENAME(_LMBCSData3) +#define _LMBCSData4 U_ICU_ENTRY_POINT_RENAME(_LMBCSData4) +#define _LMBCSData5 U_ICU_ENTRY_POINT_RENAME(_LMBCSData5) +#define _LMBCSData6 U_ICU_ENTRY_POINT_RENAME(_LMBCSData6) +#define _LMBCSData8 U_ICU_ENTRY_POINT_RENAME(_LMBCSData8) +#define _Latin1Data U_ICU_ENTRY_POINT_RENAME(_Latin1Data) +#define _MBCSData U_ICU_ENTRY_POINT_RENAME(_MBCSData) +#define _SCSUData U_ICU_ENTRY_POINT_RENAME(_SCSUData) +#define _UTF16BEData U_ICU_ENTRY_POINT_RENAME(_UTF16BEData) +#define _UTF16Data U_ICU_ENTRY_POINT_RENAME(_UTF16Data) +#define _UTF16LEData U_ICU_ENTRY_POINT_RENAME(_UTF16LEData) +#define _UTF16v2Data U_ICU_ENTRY_POINT_RENAME(_UTF16v2Data) +#define _UTF32BEData U_ICU_ENTRY_POINT_RENAME(_UTF32BEData) +#define _UTF32Data U_ICU_ENTRY_POINT_RENAME(_UTF32Data) +#define _UTF32LEData U_ICU_ENTRY_POINT_RENAME(_UTF32LEData) +#define _UTF7Data U_ICU_ENTRY_POINT_RENAME(_UTF7Data) +#define _UTF8Data U_ICU_ENTRY_POINT_RENAME(_UTF8Data) +#define _isUnicodeLocaleTypeSubtag U_ICU_ENTRY_POINT_RENAME(_isUnicodeLocaleTypeSubtag) +#define allowedHourFormatsCleanup U_ICU_ENTRY_POINT_RENAME(allowedHourFormatsCleanup) +#define cmemory_cleanup U_ICU_ENTRY_POINT_RENAME(cmemory_cleanup) +#define dayPeriodRulesCleanup U_ICU_ENTRY_POINT_RENAME(dayPeriodRulesCleanup) +#define deleteAllowedHourFormats U_ICU_ENTRY_POINT_RENAME(deleteAllowedHourFormats) +#define gTimeZoneFilesInitOnce U_ICU_ENTRY_POINT_RENAME(gTimeZoneFilesInitOnce) +#define initNumsysNames U_ICU_ENTRY_POINT_RENAME(initNumsysNames) +#define izrule_clone U_ICU_ENTRY_POINT_RENAME(izrule_clone) +#define izrule_close U_ICU_ENTRY_POINT_RENAME(izrule_close) +#define izrule_equals U_ICU_ENTRY_POINT_RENAME(izrule_equals) +#define izrule_getDSTSavings U_ICU_ENTRY_POINT_RENAME(izrule_getDSTSavings) +#define izrule_getDynamicClassID U_ICU_ENTRY_POINT_RENAME(izrule_getDynamicClassID) +#define izrule_getFinalStart U_ICU_ENTRY_POINT_RENAME(izrule_getFinalStart) +#define izrule_getFirstStart U_ICU_ENTRY_POINT_RENAME(izrule_getFirstStart) +#define izrule_getName U_ICU_ENTRY_POINT_RENAME(izrule_getName) +#define izrule_getNextStart U_ICU_ENTRY_POINT_RENAME(izrule_getNextStart) +#define izrule_getPreviousStart U_ICU_ENTRY_POINT_RENAME(izrule_getPreviousStart) +#define izrule_getRawOffset U_ICU_ENTRY_POINT_RENAME(izrule_getRawOffset) +#define izrule_getStaticClassID U_ICU_ENTRY_POINT_RENAME(izrule_getStaticClassID) +#define izrule_isEquivalentTo U_ICU_ENTRY_POINT_RENAME(izrule_isEquivalentTo) +#define izrule_open U_ICU_ENTRY_POINT_RENAME(izrule_open) +#define locale_getKeywordsStart U_ICU_ENTRY_POINT_RENAME(locale_getKeywordsStart) +#define locale_get_default U_ICU_ENTRY_POINT_RENAME(locale_get_default) +#define locale_set_default U_ICU_ENTRY_POINT_RENAME(locale_set_default) +#define numSysCleanup U_ICU_ENTRY_POINT_RENAME(numSysCleanup) +#define rbbi_cleanup U_ICU_ENTRY_POINT_RENAME(rbbi_cleanup) +#define pl_addFontRun U_ICU_ENTRY_POINT_RENAME(pl_addFontRun) +#define pl_addLocaleRun U_ICU_ENTRY_POINT_RENAME(pl_addLocaleRun) +#define pl_addValueRun U_ICU_ENTRY_POINT_RENAME(pl_addValueRun) +#define pl_close U_ICU_ENTRY_POINT_RENAME(pl_close) +#define pl_closeFontRuns U_ICU_ENTRY_POINT_RENAME(pl_closeFontRuns) +#define pl_closeLine U_ICU_ENTRY_POINT_RENAME(pl_closeLine) +#define pl_closeLocaleRuns U_ICU_ENTRY_POINT_RENAME(pl_closeLocaleRuns) +#define pl_closeValueRuns U_ICU_ENTRY_POINT_RENAME(pl_closeValueRuns) +#define pl_countLineRuns U_ICU_ENTRY_POINT_RENAME(pl_countLineRuns) +#define pl_create U_ICU_ENTRY_POINT_RENAME(pl_create) +#define pl_getAscent U_ICU_ENTRY_POINT_RENAME(pl_getAscent) +#define pl_getDescent U_ICU_ENTRY_POINT_RENAME(pl_getDescent) +#define pl_getFontRunCount U_ICU_ENTRY_POINT_RENAME(pl_getFontRunCount) +#define pl_getFontRunFont U_ICU_ENTRY_POINT_RENAME(pl_getFontRunFont) +#define pl_getFontRunLastLimit U_ICU_ENTRY_POINT_RENAME(pl_getFontRunLastLimit) +#define pl_getFontRunLimit U_ICU_ENTRY_POINT_RENAME(pl_getFontRunLimit) +#define pl_getLeading U_ICU_ENTRY_POINT_RENAME(pl_getLeading) +#define pl_getLineAscent U_ICU_ENTRY_POINT_RENAME(pl_getLineAscent) +#define pl_getLineDescent U_ICU_ENTRY_POINT_RENAME(pl_getLineDescent) +#define pl_getLineLeading U_ICU_ENTRY_POINT_RENAME(pl_getLineLeading) +#define pl_getLineVisualRun U_ICU_ENTRY_POINT_RENAME(pl_getLineVisualRun) +#define pl_getLineWidth U_ICU_ENTRY_POINT_RENAME(pl_getLineWidth) +#define pl_getLocaleRunCount U_ICU_ENTRY_POINT_RENAME(pl_getLocaleRunCount) +#define pl_getLocaleRunLastLimit U_ICU_ENTRY_POINT_RENAME(pl_getLocaleRunLastLimit) +#define pl_getLocaleRunLimit U_ICU_ENTRY_POINT_RENAME(pl_getLocaleRunLimit) +#define pl_getLocaleRunLocale U_ICU_ENTRY_POINT_RENAME(pl_getLocaleRunLocale) +#define pl_getParagraphLevel U_ICU_ENTRY_POINT_RENAME(pl_getParagraphLevel) +#define pl_getTextDirection U_ICU_ENTRY_POINT_RENAME(pl_getTextDirection) +#define pl_getValueRunCount U_ICU_ENTRY_POINT_RENAME(pl_getValueRunCount) +#define pl_getValueRunLastLimit U_ICU_ENTRY_POINT_RENAME(pl_getValueRunLastLimit) +#define pl_getValueRunLimit U_ICU_ENTRY_POINT_RENAME(pl_getValueRunLimit) +#define pl_getValueRunValue U_ICU_ENTRY_POINT_RENAME(pl_getValueRunValue) +#define pl_getVisualRunAscent U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunAscent) +#define pl_getVisualRunDescent U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunDescent) +#define pl_getVisualRunDirection U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunDirection) +#define pl_getVisualRunFont U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunFont) +#define pl_getVisualRunGlyphCount U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunGlyphCount) +#define pl_getVisualRunGlyphToCharMap U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunGlyphToCharMap) +#define pl_getVisualRunGlyphs U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunGlyphs) +#define pl_getVisualRunLeading U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunLeading) +#define pl_getVisualRunPositions U_ICU_ENTRY_POINT_RENAME(pl_getVisualRunPositions) +#define pl_isComplex U_ICU_ENTRY_POINT_RENAME(pl_isComplex) +#define pl_nextLine U_ICU_ENTRY_POINT_RENAME(pl_nextLine) +#define pl_openEmptyFontRuns U_ICU_ENTRY_POINT_RENAME(pl_openEmptyFontRuns) +#define pl_openEmptyLocaleRuns U_ICU_ENTRY_POINT_RENAME(pl_openEmptyLocaleRuns) +#define pl_openEmptyValueRuns U_ICU_ENTRY_POINT_RENAME(pl_openEmptyValueRuns) +#define pl_openFontRuns U_ICU_ENTRY_POINT_RENAME(pl_openFontRuns) +#define pl_openLocaleRuns U_ICU_ENTRY_POINT_RENAME(pl_openLocaleRuns) +#define pl_openValueRuns U_ICU_ENTRY_POINT_RENAME(pl_openValueRuns) +#define pl_reflow U_ICU_ENTRY_POINT_RENAME(pl_reflow) +#define pl_resetFontRuns U_ICU_ENTRY_POINT_RENAME(pl_resetFontRuns) +#define pl_resetLocaleRuns U_ICU_ENTRY_POINT_RENAME(pl_resetLocaleRuns) +#define pl_resetValueRuns U_ICU_ENTRY_POINT_RENAME(pl_resetValueRuns) +#define res_countArrayItems U_ICU_ENTRY_POINT_RENAME(res_countArrayItems) +#define res_findResource U_ICU_ENTRY_POINT_RENAME(res_findResource) +#define res_getAlias U_ICU_ENTRY_POINT_RENAME(res_getAlias) +#define res_getArrayItem U_ICU_ENTRY_POINT_RENAME(res_getArrayItem) +#define res_getBinaryNoTrace U_ICU_ENTRY_POINT_RENAME(res_getBinaryNoTrace) +#define res_getIntVectorNoTrace U_ICU_ENTRY_POINT_RENAME(res_getIntVectorNoTrace) +#define res_getPublicType U_ICU_ENTRY_POINT_RENAME(res_getPublicType) +#define res_getResource U_ICU_ENTRY_POINT_RENAME(res_getResource) +#define res_getStringNoTrace U_ICU_ENTRY_POINT_RENAME(res_getStringNoTrace) +#define res_getTableItemByIndex U_ICU_ENTRY_POINT_RENAME(res_getTableItemByIndex) +#define res_getTableItemByKey U_ICU_ENTRY_POINT_RENAME(res_getTableItemByKey) +#define res_load U_ICU_ENTRY_POINT_RENAME(res_load) +#define res_read U_ICU_ENTRY_POINT_RENAME(res_read) +#define res_unload U_ICU_ENTRY_POINT_RENAME(res_unload) +#define u_UCharsToChars U_ICU_ENTRY_POINT_RENAME(u_UCharsToChars) +#define u_asciiToUpper U_ICU_ENTRY_POINT_RENAME(u_asciiToUpper) +#define u_austrcpy U_ICU_ENTRY_POINT_RENAME(u_austrcpy) +#define u_austrncpy U_ICU_ENTRY_POINT_RENAME(u_austrncpy) +#define u_caseInsensitivePrefixMatch U_ICU_ENTRY_POINT_RENAME(u_caseInsensitivePrefixMatch) +#define u_catclose U_ICU_ENTRY_POINT_RENAME(u_catclose) +#define u_catgets U_ICU_ENTRY_POINT_RENAME(u_catgets) +#define u_catopen U_ICU_ENTRY_POINT_RENAME(u_catopen) +#define u_charAge U_ICU_ENTRY_POINT_RENAME(u_charAge) +#define u_charDigitValue U_ICU_ENTRY_POINT_RENAME(u_charDigitValue) +#define u_charDirection U_ICU_ENTRY_POINT_RENAME(u_charDirection) +#define u_charFromName U_ICU_ENTRY_POINT_RENAME(u_charFromName) +#define u_charMirror U_ICU_ENTRY_POINT_RENAME(u_charMirror) +#define u_charName U_ICU_ENTRY_POINT_RENAME(u_charName) +#define u_charType U_ICU_ENTRY_POINT_RENAME(u_charType) +#define u_charsToUChars U_ICU_ENTRY_POINT_RENAME(u_charsToUChars) +#define u_cleanup U_ICU_ENTRY_POINT_RENAME(u_cleanup) +#define u_countChar32 U_ICU_ENTRY_POINT_RENAME(u_countChar32) +#define u_digit U_ICU_ENTRY_POINT_RENAME(u_digit) +#define u_enumCharNames U_ICU_ENTRY_POINT_RENAME(u_enumCharNames) +#define u_enumCharTypes U_ICU_ENTRY_POINT_RENAME(u_enumCharTypes) +#define u_errorName U_ICU_ENTRY_POINT_RENAME(u_errorName) +#define u_fadopt U_ICU_ENTRY_POINT_RENAME(u_fadopt) +#define u_fclose U_ICU_ENTRY_POINT_RENAME(u_fclose) +#define u_feof U_ICU_ENTRY_POINT_RENAME(u_feof) +#define u_fflush U_ICU_ENTRY_POINT_RENAME(u_fflush) +#define u_fgetConverter U_ICU_ENTRY_POINT_RENAME(u_fgetConverter) +#define u_fgetNumberFormat U_ICU_ENTRY_POINT_RENAME(u_fgetNumberFormat) +#define u_fgetc U_ICU_ENTRY_POINT_RENAME(u_fgetc) +#define u_fgetcodepage U_ICU_ENTRY_POINT_RENAME(u_fgetcodepage) +#define u_fgetcx U_ICU_ENTRY_POINT_RENAME(u_fgetcx) +#define u_fgetfile U_ICU_ENTRY_POINT_RENAME(u_fgetfile) +#define u_fgetlocale U_ICU_ENTRY_POINT_RENAME(u_fgetlocale) +#define u_fgets U_ICU_ENTRY_POINT_RENAME(u_fgets) +#define u_file_read U_ICU_ENTRY_POINT_RENAME(u_file_read) +#define u_file_write U_ICU_ENTRY_POINT_RENAME(u_file_write) +#define u_file_write_flush U_ICU_ENTRY_POINT_RENAME(u_file_write_flush) +#define u_finit U_ICU_ENTRY_POINT_RENAME(u_finit) +#define u_flushDefaultConverter U_ICU_ENTRY_POINT_RENAME(u_flushDefaultConverter) +#define u_foldCase U_ICU_ENTRY_POINT_RENAME(u_foldCase) +#define u_fopen U_ICU_ENTRY_POINT_RENAME(u_fopen) +#define u_fopen_u U_ICU_ENTRY_POINT_RENAME(u_fopen_u) +#define u_forDigit U_ICU_ENTRY_POINT_RENAME(u_forDigit) +#define u_formatMessage U_ICU_ENTRY_POINT_RENAME(u_formatMessage) +#define u_formatMessageWithError U_ICU_ENTRY_POINT_RENAME(u_formatMessageWithError) +#define u_fprintf U_ICU_ENTRY_POINT_RENAME(u_fprintf) +#define u_fprintf_u U_ICU_ENTRY_POINT_RENAME(u_fprintf_u) +#define u_fputc U_ICU_ENTRY_POINT_RENAME(u_fputc) +#define u_fputs U_ICU_ENTRY_POINT_RENAME(u_fputs) +#define u_frewind U_ICU_ENTRY_POINT_RENAME(u_frewind) +#define u_fscanf U_ICU_ENTRY_POINT_RENAME(u_fscanf) +#define u_fscanf_u U_ICU_ENTRY_POINT_RENAME(u_fscanf_u) +#define u_fsetcodepage U_ICU_ENTRY_POINT_RENAME(u_fsetcodepage) +#define u_fsetlocale U_ICU_ENTRY_POINT_RENAME(u_fsetlocale) +#define u_fsettransliterator U_ICU_ENTRY_POINT_RENAME(u_fsettransliterator) +#define u_fstropen U_ICU_ENTRY_POINT_RENAME(u_fstropen) +#define u_fungetc U_ICU_ENTRY_POINT_RENAME(u_fungetc) +#define u_getBidiPairedBracket U_ICU_ENTRY_POINT_RENAME(u_getBidiPairedBracket) +#define u_getBinaryPropertySet U_ICU_ENTRY_POINT_RENAME(u_getBinaryPropertySet) +#define u_getCombiningClass U_ICU_ENTRY_POINT_RENAME(u_getCombiningClass) +#define u_getDataDirectory U_ICU_ENTRY_POINT_RENAME(u_getDataDirectory) +#define u_getDataVersion U_ICU_ENTRY_POINT_RENAME(u_getDataVersion) +#define u_getDefaultConverter U_ICU_ENTRY_POINT_RENAME(u_getDefaultConverter) +#define u_getFC_NFKC_Closure U_ICU_ENTRY_POINT_RENAME(u_getFC_NFKC_Closure) +#define u_getISOComment U_ICU_ENTRY_POINT_RENAME(u_getISOComment) +#define u_getIntPropertyMap U_ICU_ENTRY_POINT_RENAME(u_getIntPropertyMap) +#define u_getIntPropertyMaxValue U_ICU_ENTRY_POINT_RENAME(u_getIntPropertyMaxValue) +#define u_getIntPropertyMinValue U_ICU_ENTRY_POINT_RENAME(u_getIntPropertyMinValue) +#define u_getIntPropertyValue U_ICU_ENTRY_POINT_RENAME(u_getIntPropertyValue) +#define u_getMainProperties U_ICU_ENTRY_POINT_RENAME(u_getMainProperties) +#define u_getNumericValue U_ICU_ENTRY_POINT_RENAME(u_getNumericValue) +#define u_getPropertyEnum U_ICU_ENTRY_POINT_RENAME(u_getPropertyEnum) +#define u_getPropertyName U_ICU_ENTRY_POINT_RENAME(u_getPropertyName) +#define u_getPropertyValueEnum U_ICU_ENTRY_POINT_RENAME(u_getPropertyValueEnum) +#define u_getPropertyValueName U_ICU_ENTRY_POINT_RENAME(u_getPropertyValueName) +#define u_getTimeZoneFilesDirectory U_ICU_ENTRY_POINT_RENAME(u_getTimeZoneFilesDirectory) +#define u_getUnicodeProperties U_ICU_ENTRY_POINT_RENAME(u_getUnicodeProperties) +#define u_getUnicodeVersion U_ICU_ENTRY_POINT_RENAME(u_getUnicodeVersion) +#define u_getVersion U_ICU_ENTRY_POINT_RENAME(u_getVersion) +#define u_get_stdout U_ICU_ENTRY_POINT_RENAME(u_get_stdout) +#define u_hasBinaryProperty U_ICU_ENTRY_POINT_RENAME(u_hasBinaryProperty) +#define u_init U_ICU_ENTRY_POINT_RENAME(u_init) +#define u_isIDIgnorable U_ICU_ENTRY_POINT_RENAME(u_isIDIgnorable) +#define u_isIDPart U_ICU_ENTRY_POINT_RENAME(u_isIDPart) +#define u_isIDStart U_ICU_ENTRY_POINT_RENAME(u_isIDStart) +#define u_isISOControl U_ICU_ENTRY_POINT_RENAME(u_isISOControl) +#define u_isJavaIDPart U_ICU_ENTRY_POINT_RENAME(u_isJavaIDPart) +#define u_isJavaIDStart U_ICU_ENTRY_POINT_RENAME(u_isJavaIDStart) +#define u_isJavaSpaceChar U_ICU_ENTRY_POINT_RENAME(u_isJavaSpaceChar) +#define u_isMirrored U_ICU_ENTRY_POINT_RENAME(u_isMirrored) +#define u_isUAlphabetic U_ICU_ENTRY_POINT_RENAME(u_isUAlphabetic) +#define u_isULowercase U_ICU_ENTRY_POINT_RENAME(u_isULowercase) +#define u_isUUppercase U_ICU_ENTRY_POINT_RENAME(u_isUUppercase) +#define u_isUWhiteSpace U_ICU_ENTRY_POINT_RENAME(u_isUWhiteSpace) +#define u_isWhitespace U_ICU_ENTRY_POINT_RENAME(u_isWhitespace) +#define u_isalnum U_ICU_ENTRY_POINT_RENAME(u_isalnum) +#define u_isalnumPOSIX U_ICU_ENTRY_POINT_RENAME(u_isalnumPOSIX) +#define u_isalpha U_ICU_ENTRY_POINT_RENAME(u_isalpha) +#define u_isbase U_ICU_ENTRY_POINT_RENAME(u_isbase) +#define u_isblank U_ICU_ENTRY_POINT_RENAME(u_isblank) +#define u_iscntrl U_ICU_ENTRY_POINT_RENAME(u_iscntrl) +#define u_isdefined U_ICU_ENTRY_POINT_RENAME(u_isdefined) +#define u_isdigit U_ICU_ENTRY_POINT_RENAME(u_isdigit) +#define u_isgraph U_ICU_ENTRY_POINT_RENAME(u_isgraph) +#define u_isgraphPOSIX U_ICU_ENTRY_POINT_RENAME(u_isgraphPOSIX) +#define u_islower U_ICU_ENTRY_POINT_RENAME(u_islower) +#define u_isprint U_ICU_ENTRY_POINT_RENAME(u_isprint) +#define u_isprintPOSIX U_ICU_ENTRY_POINT_RENAME(u_isprintPOSIX) +#define u_ispunct U_ICU_ENTRY_POINT_RENAME(u_ispunct) +#define u_isspace U_ICU_ENTRY_POINT_RENAME(u_isspace) +#define u_istitle U_ICU_ENTRY_POINT_RENAME(u_istitle) +#define u_isupper U_ICU_ENTRY_POINT_RENAME(u_isupper) +#define u_isxdigit U_ICU_ENTRY_POINT_RENAME(u_isxdigit) +#define u_locbund_close U_ICU_ENTRY_POINT_RENAME(u_locbund_close) +#define u_locbund_getNumberFormat U_ICU_ENTRY_POINT_RENAME(u_locbund_getNumberFormat) +#define u_locbund_init U_ICU_ENTRY_POINT_RENAME(u_locbund_init) +#define u_memcasecmp U_ICU_ENTRY_POINT_RENAME(u_memcasecmp) +#define u_memchr U_ICU_ENTRY_POINT_RENAME(u_memchr) +#define u_memchr32 U_ICU_ENTRY_POINT_RENAME(u_memchr32) +#define u_memcmp U_ICU_ENTRY_POINT_RENAME(u_memcmp) +#define u_memcmpCodePointOrder U_ICU_ENTRY_POINT_RENAME(u_memcmpCodePointOrder) +#define u_memcpy U_ICU_ENTRY_POINT_RENAME(u_memcpy) +#define u_memmove U_ICU_ENTRY_POINT_RENAME(u_memmove) +#define u_memrchr U_ICU_ENTRY_POINT_RENAME(u_memrchr) +#define u_memrchr32 U_ICU_ENTRY_POINT_RENAME(u_memrchr32) +#define u_memset U_ICU_ENTRY_POINT_RENAME(u_memset) +#define u_parseMessage U_ICU_ENTRY_POINT_RENAME(u_parseMessage) +#define u_parseMessageWithError U_ICU_ENTRY_POINT_RENAME(u_parseMessageWithError) +#define u_printf U_ICU_ENTRY_POINT_RENAME(u_printf) +#define u_printf_parse U_ICU_ENTRY_POINT_RENAME(u_printf_parse) +#define u_printf_u U_ICU_ENTRY_POINT_RENAME(u_printf_u) +#define u_releaseDefaultConverter U_ICU_ENTRY_POINT_RENAME(u_releaseDefaultConverter) +#define u_scanf_parse U_ICU_ENTRY_POINT_RENAME(u_scanf_parse) +#define u_setAtomicIncDecFunctions U_ICU_ENTRY_POINT_RENAME(u_setAtomicIncDecFunctions) +#define u_setDataDirectory U_ICU_ENTRY_POINT_RENAME(u_setDataDirectory) +#define u_setMemoryFunctions U_ICU_ENTRY_POINT_RENAME(u_setMemoryFunctions) +#define u_setMutexFunctions U_ICU_ENTRY_POINT_RENAME(u_setMutexFunctions) +#define u_setTimeZoneFilesDirectory U_ICU_ENTRY_POINT_RENAME(u_setTimeZoneFilesDirectory) +#define u_shapeArabic U_ICU_ENTRY_POINT_RENAME(u_shapeArabic) +#define u_snprintf U_ICU_ENTRY_POINT_RENAME(u_snprintf) +#define u_snprintf_u U_ICU_ENTRY_POINT_RENAME(u_snprintf_u) +#define u_sprintf U_ICU_ENTRY_POINT_RENAME(u_sprintf) +#define u_sprintf_u U_ICU_ENTRY_POINT_RENAME(u_sprintf_u) +#define u_sscanf U_ICU_ENTRY_POINT_RENAME(u_sscanf) +#define u_sscanf_u U_ICU_ENTRY_POINT_RENAME(u_sscanf_u) +#define u_strCaseCompare U_ICU_ENTRY_POINT_RENAME(u_strCaseCompare) +#define u_strCompare U_ICU_ENTRY_POINT_RENAME(u_strCompare) +#define u_strCompareIter U_ICU_ENTRY_POINT_RENAME(u_strCompareIter) +#define u_strFindFirst U_ICU_ENTRY_POINT_RENAME(u_strFindFirst) +#define u_strFindLast U_ICU_ENTRY_POINT_RENAME(u_strFindLast) +#define u_strFoldCase U_ICU_ENTRY_POINT_RENAME(u_strFoldCase) +#define u_strFromJavaModifiedUTF8WithSub U_ICU_ENTRY_POINT_RENAME(u_strFromJavaModifiedUTF8WithSub) +#define u_strFromPunycode U_ICU_ENTRY_POINT_RENAME(u_strFromPunycode) +#define u_strFromUTF32 U_ICU_ENTRY_POINT_RENAME(u_strFromUTF32) +#define u_strFromUTF32WithSub U_ICU_ENTRY_POINT_RENAME(u_strFromUTF32WithSub) +#define u_strFromUTF8 U_ICU_ENTRY_POINT_RENAME(u_strFromUTF8) +#define u_strFromUTF8Lenient U_ICU_ENTRY_POINT_RENAME(u_strFromUTF8Lenient) +#define u_strFromUTF8WithSub U_ICU_ENTRY_POINT_RENAME(u_strFromUTF8WithSub) +#define u_strFromWCS U_ICU_ENTRY_POINT_RENAME(u_strFromWCS) +#define u_strHasMoreChar32Than U_ICU_ENTRY_POINT_RENAME(u_strHasMoreChar32Than) +#define u_strToJavaModifiedUTF8 U_ICU_ENTRY_POINT_RENAME(u_strToJavaModifiedUTF8) +#define u_strToLower U_ICU_ENTRY_POINT_RENAME(u_strToLower) +#define u_strToPunycode U_ICU_ENTRY_POINT_RENAME(u_strToPunycode) +#define u_strToTitle U_ICU_ENTRY_POINT_RENAME(u_strToTitle) +#define u_strToUTF32 U_ICU_ENTRY_POINT_RENAME(u_strToUTF32) +#define u_strToUTF32WithSub U_ICU_ENTRY_POINT_RENAME(u_strToUTF32WithSub) +#define u_strToUTF8 U_ICU_ENTRY_POINT_RENAME(u_strToUTF8) +#define u_strToUTF8WithSub U_ICU_ENTRY_POINT_RENAME(u_strToUTF8WithSub) +#define u_strToUpper U_ICU_ENTRY_POINT_RENAME(u_strToUpper) +#define u_strToWCS U_ICU_ENTRY_POINT_RENAME(u_strToWCS) +#define u_strcasecmp U_ICU_ENTRY_POINT_RENAME(u_strcasecmp) +#define u_strcat U_ICU_ENTRY_POINT_RENAME(u_strcat) +#define u_strchr U_ICU_ENTRY_POINT_RENAME(u_strchr) +#define u_strchr32 U_ICU_ENTRY_POINT_RENAME(u_strchr32) +#define u_strcmp U_ICU_ENTRY_POINT_RENAME(u_strcmp) +#define u_strcmpCodePointOrder U_ICU_ENTRY_POINT_RENAME(u_strcmpCodePointOrder) +#define u_strcmpFold U_ICU_ENTRY_POINT_RENAME(u_strcmpFold) +#define u_strcpy U_ICU_ENTRY_POINT_RENAME(u_strcpy) +#define u_strcspn U_ICU_ENTRY_POINT_RENAME(u_strcspn) +#define u_strlen U_ICU_ENTRY_POINT_RENAME(u_strlen) +#define u_strncasecmp U_ICU_ENTRY_POINT_RENAME(u_strncasecmp) +#define u_strncat U_ICU_ENTRY_POINT_RENAME(u_strncat) +#define u_strncmp U_ICU_ENTRY_POINT_RENAME(u_strncmp) +#define u_strncmpCodePointOrder U_ICU_ENTRY_POINT_RENAME(u_strncmpCodePointOrder) +#define u_strncpy U_ICU_ENTRY_POINT_RENAME(u_strncpy) +#define u_strpbrk U_ICU_ENTRY_POINT_RENAME(u_strpbrk) +#define u_strrchr U_ICU_ENTRY_POINT_RENAME(u_strrchr) +#define u_strrchr32 U_ICU_ENTRY_POINT_RENAME(u_strrchr32) +#define u_strrstr U_ICU_ENTRY_POINT_RENAME(u_strrstr) +#define u_strspn U_ICU_ENTRY_POINT_RENAME(u_strspn) +#define u_strstr U_ICU_ENTRY_POINT_RENAME(u_strstr) +#define u_strtok_r U_ICU_ENTRY_POINT_RENAME(u_strtok_r) +#define u_terminateChars U_ICU_ENTRY_POINT_RENAME(u_terminateChars) +#define u_terminateUChar32s U_ICU_ENTRY_POINT_RENAME(u_terminateUChar32s) +#define u_terminateUChars U_ICU_ENTRY_POINT_RENAME(u_terminateUChars) +#define u_terminateWChars U_ICU_ENTRY_POINT_RENAME(u_terminateWChars) +#define u_tolower U_ICU_ENTRY_POINT_RENAME(u_tolower) +#define u_totitle U_ICU_ENTRY_POINT_RENAME(u_totitle) +#define u_toupper U_ICU_ENTRY_POINT_RENAME(u_toupper) +#define u_uastrcpy U_ICU_ENTRY_POINT_RENAME(u_uastrcpy) +#define u_uastrncpy U_ICU_ENTRY_POINT_RENAME(u_uastrncpy) +#define u_unescape U_ICU_ENTRY_POINT_RENAME(u_unescape) +#define u_unescapeAt U_ICU_ENTRY_POINT_RENAME(u_unescapeAt) +#define u_versionFromString U_ICU_ENTRY_POINT_RENAME(u_versionFromString) +#define u_versionFromUString U_ICU_ENTRY_POINT_RENAME(u_versionFromUString) +#define u_versionToString U_ICU_ENTRY_POINT_RENAME(u_versionToString) +#define u_vformatMessage U_ICU_ENTRY_POINT_RENAME(u_vformatMessage) +#define u_vformatMessageWithError U_ICU_ENTRY_POINT_RENAME(u_vformatMessageWithError) +#define u_vfprintf U_ICU_ENTRY_POINT_RENAME(u_vfprintf) +#define u_vfprintf_u U_ICU_ENTRY_POINT_RENAME(u_vfprintf_u) +#define u_vfscanf U_ICU_ENTRY_POINT_RENAME(u_vfscanf) +#define u_vfscanf_u U_ICU_ENTRY_POINT_RENAME(u_vfscanf_u) +#define u_vparseMessage U_ICU_ENTRY_POINT_RENAME(u_vparseMessage) +#define u_vparseMessageWithError U_ICU_ENTRY_POINT_RENAME(u_vparseMessageWithError) +#define u_vsnprintf U_ICU_ENTRY_POINT_RENAME(u_vsnprintf) +#define u_vsnprintf_u U_ICU_ENTRY_POINT_RENAME(u_vsnprintf_u) +#define u_vsprintf U_ICU_ENTRY_POINT_RENAME(u_vsprintf) +#define u_vsprintf_u U_ICU_ENTRY_POINT_RENAME(u_vsprintf_u) +#define u_vsscanf U_ICU_ENTRY_POINT_RENAME(u_vsscanf) +#define u_vsscanf_u U_ICU_ENTRY_POINT_RENAME(u_vsscanf_u) +#define u_writeIdenticalLevelRun U_ICU_ENTRY_POINT_RENAME(u_writeIdenticalLevelRun) +#define ubidi_addPropertyStarts U_ICU_ENTRY_POINT_RENAME(ubidi_addPropertyStarts) +#define ubidi_close U_ICU_ENTRY_POINT_RENAME(ubidi_close) +#define ubidi_countParagraphs U_ICU_ENTRY_POINT_RENAME(ubidi_countParagraphs) +#define ubidi_countRuns U_ICU_ENTRY_POINT_RENAME(ubidi_countRuns) +#define ubidi_getBaseDirection U_ICU_ENTRY_POINT_RENAME(ubidi_getBaseDirection) +#define ubidi_getClass U_ICU_ENTRY_POINT_RENAME(ubidi_getClass) +#define ubidi_getClassCallback U_ICU_ENTRY_POINT_RENAME(ubidi_getClassCallback) +#define ubidi_getCustomizedClass U_ICU_ENTRY_POINT_RENAME(ubidi_getCustomizedClass) +#define ubidi_getDirection U_ICU_ENTRY_POINT_RENAME(ubidi_getDirection) +#define ubidi_getJoiningGroup U_ICU_ENTRY_POINT_RENAME(ubidi_getJoiningGroup) +#define ubidi_getJoiningType U_ICU_ENTRY_POINT_RENAME(ubidi_getJoiningType) +#define ubidi_getLength U_ICU_ENTRY_POINT_RENAME(ubidi_getLength) +#define ubidi_getLevelAt U_ICU_ENTRY_POINT_RENAME(ubidi_getLevelAt) +#define ubidi_getLevels U_ICU_ENTRY_POINT_RENAME(ubidi_getLevels) +#define ubidi_getLogicalIndex U_ICU_ENTRY_POINT_RENAME(ubidi_getLogicalIndex) +#define ubidi_getLogicalMap U_ICU_ENTRY_POINT_RENAME(ubidi_getLogicalMap) +#define ubidi_getLogicalRun U_ICU_ENTRY_POINT_RENAME(ubidi_getLogicalRun) +#define ubidi_getMaxValue U_ICU_ENTRY_POINT_RENAME(ubidi_getMaxValue) +#define ubidi_getMemory U_ICU_ENTRY_POINT_RENAME(ubidi_getMemory) +#define ubidi_getMirror U_ICU_ENTRY_POINT_RENAME(ubidi_getMirror) +#define ubidi_getPairedBracket U_ICU_ENTRY_POINT_RENAME(ubidi_getPairedBracket) +#define ubidi_getPairedBracketType U_ICU_ENTRY_POINT_RENAME(ubidi_getPairedBracketType) +#define ubidi_getParaLevel U_ICU_ENTRY_POINT_RENAME(ubidi_getParaLevel) +#define ubidi_getParaLevelAtIndex U_ICU_ENTRY_POINT_RENAME(ubidi_getParaLevelAtIndex) +#define ubidi_getParagraph U_ICU_ENTRY_POINT_RENAME(ubidi_getParagraph) +#define ubidi_getParagraphByIndex U_ICU_ENTRY_POINT_RENAME(ubidi_getParagraphByIndex) +#define ubidi_getProcessedLength U_ICU_ENTRY_POINT_RENAME(ubidi_getProcessedLength) +#define ubidi_getReorderingMode U_ICU_ENTRY_POINT_RENAME(ubidi_getReorderingMode) +#define ubidi_getReorderingOptions U_ICU_ENTRY_POINT_RENAME(ubidi_getReorderingOptions) +#define ubidi_getResultLength U_ICU_ENTRY_POINT_RENAME(ubidi_getResultLength) +#define ubidi_getRuns U_ICU_ENTRY_POINT_RENAME(ubidi_getRuns) +#define ubidi_getText U_ICU_ENTRY_POINT_RENAME(ubidi_getText) +#define ubidi_getVisualIndex U_ICU_ENTRY_POINT_RENAME(ubidi_getVisualIndex) +#define ubidi_getVisualMap U_ICU_ENTRY_POINT_RENAME(ubidi_getVisualMap) +#define ubidi_getVisualRun U_ICU_ENTRY_POINT_RENAME(ubidi_getVisualRun) +#define ubidi_invertMap U_ICU_ENTRY_POINT_RENAME(ubidi_invertMap) +#define ubidi_isBidiControl U_ICU_ENTRY_POINT_RENAME(ubidi_isBidiControl) +#define ubidi_isInverse U_ICU_ENTRY_POINT_RENAME(ubidi_isInverse) +#define ubidi_isJoinControl U_ICU_ENTRY_POINT_RENAME(ubidi_isJoinControl) +#define ubidi_isMirrored U_ICU_ENTRY_POINT_RENAME(ubidi_isMirrored) +#define ubidi_isOrderParagraphsLTR U_ICU_ENTRY_POINT_RENAME(ubidi_isOrderParagraphsLTR) +#define ubidi_open U_ICU_ENTRY_POINT_RENAME(ubidi_open) +#define ubidi_openSized U_ICU_ENTRY_POINT_RENAME(ubidi_openSized) +#define ubidi_orderParagraphsLTR U_ICU_ENTRY_POINT_RENAME(ubidi_orderParagraphsLTR) +#define ubidi_reorderLogical U_ICU_ENTRY_POINT_RENAME(ubidi_reorderLogical) +#define ubidi_reorderVisual U_ICU_ENTRY_POINT_RENAME(ubidi_reorderVisual) +#define ubidi_setClassCallback U_ICU_ENTRY_POINT_RENAME(ubidi_setClassCallback) +#define ubidi_setContext U_ICU_ENTRY_POINT_RENAME(ubidi_setContext) +#define ubidi_setInverse U_ICU_ENTRY_POINT_RENAME(ubidi_setInverse) +#define ubidi_setLine U_ICU_ENTRY_POINT_RENAME(ubidi_setLine) +#define ubidi_setPara U_ICU_ENTRY_POINT_RENAME(ubidi_setPara) +#define ubidi_setReorderingMode U_ICU_ENTRY_POINT_RENAME(ubidi_setReorderingMode) +#define ubidi_setReorderingOptions U_ICU_ENTRY_POINT_RENAME(ubidi_setReorderingOptions) +#define ubidi_writeReordered U_ICU_ENTRY_POINT_RENAME(ubidi_writeReordered) +#define ubidi_writeReverse U_ICU_ENTRY_POINT_RENAME(ubidi_writeReverse) +#define ubiditransform_close U_ICU_ENTRY_POINT_RENAME(ubiditransform_close) +#define ubiditransform_open U_ICU_ENTRY_POINT_RENAME(ubiditransform_open) +#define ubiditransform_transform U_ICU_ENTRY_POINT_RENAME(ubiditransform_transform) +#define ublock_getCode U_ICU_ENTRY_POINT_RENAME(ublock_getCode) +#define ubrk_close U_ICU_ENTRY_POINT_RENAME(ubrk_close) +#define ubrk_countAvailable U_ICU_ENTRY_POINT_RENAME(ubrk_countAvailable) +#define ubrk_current U_ICU_ENTRY_POINT_RENAME(ubrk_current) +#define ubrk_first U_ICU_ENTRY_POINT_RENAME(ubrk_first) +#define ubrk_following U_ICU_ENTRY_POINT_RENAME(ubrk_following) +#define ubrk_getAvailable U_ICU_ENTRY_POINT_RENAME(ubrk_getAvailable) +#define ubrk_getBinaryRules U_ICU_ENTRY_POINT_RENAME(ubrk_getBinaryRules) +#define ubrk_getLocaleByType U_ICU_ENTRY_POINT_RENAME(ubrk_getLocaleByType) +#define ubrk_getRuleStatus U_ICU_ENTRY_POINT_RENAME(ubrk_getRuleStatus) +#define ubrk_getRuleStatusVec U_ICU_ENTRY_POINT_RENAME(ubrk_getRuleStatusVec) +#define ubrk_isBoundary U_ICU_ENTRY_POINT_RENAME(ubrk_isBoundary) +#define ubrk_last U_ICU_ENTRY_POINT_RENAME(ubrk_last) +#define ubrk_next U_ICU_ENTRY_POINT_RENAME(ubrk_next) +#define ubrk_open U_ICU_ENTRY_POINT_RENAME(ubrk_open) +#define ubrk_openBinaryRules U_ICU_ENTRY_POINT_RENAME(ubrk_openBinaryRules) +#define ubrk_openRules U_ICU_ENTRY_POINT_RENAME(ubrk_openRules) +#define ubrk_preceding U_ICU_ENTRY_POINT_RENAME(ubrk_preceding) +#define ubrk_previous U_ICU_ENTRY_POINT_RENAME(ubrk_previous) +#define ubrk_refreshUText U_ICU_ENTRY_POINT_RENAME(ubrk_refreshUText) +#define ubrk_safeClone U_ICU_ENTRY_POINT_RENAME(ubrk_safeClone) +#define ubrk_setText U_ICU_ENTRY_POINT_RENAME(ubrk_setText) +#define ubrk_setUText U_ICU_ENTRY_POINT_RENAME(ubrk_setUText) +#define ubrk_swap U_ICU_ENTRY_POINT_RENAME(ubrk_swap) +#define ucache_compareKeys U_ICU_ENTRY_POINT_RENAME(ucache_compareKeys) +#define ucache_deleteKey U_ICU_ENTRY_POINT_RENAME(ucache_deleteKey) +#define ucache_hashKeys U_ICU_ENTRY_POINT_RENAME(ucache_hashKeys) +#define ucal_add U_ICU_ENTRY_POINT_RENAME(ucal_add) +#define ucal_clear U_ICU_ENTRY_POINT_RENAME(ucal_clear) +#define ucal_clearField U_ICU_ENTRY_POINT_RENAME(ucal_clearField) +#define ucal_clone U_ICU_ENTRY_POINT_RENAME(ucal_clone) +#define ucal_close U_ICU_ENTRY_POINT_RENAME(ucal_close) +#define ucal_countAvailable U_ICU_ENTRY_POINT_RENAME(ucal_countAvailable) +#define ucal_equivalentTo U_ICU_ENTRY_POINT_RENAME(ucal_equivalentTo) +#define ucal_get U_ICU_ENTRY_POINT_RENAME(ucal_get) +#define ucal_getAttribute U_ICU_ENTRY_POINT_RENAME(ucal_getAttribute) +#define ucal_getAvailable U_ICU_ENTRY_POINT_RENAME(ucal_getAvailable) +#define ucal_getCanonicalTimeZoneID U_ICU_ENTRY_POINT_RENAME(ucal_getCanonicalTimeZoneID) +#define ucal_getDSTSavings U_ICU_ENTRY_POINT_RENAME(ucal_getDSTSavings) +#define ucal_getDayOfWeekType U_ICU_ENTRY_POINT_RENAME(ucal_getDayOfWeekType) +#define ucal_getDefaultTimeZone U_ICU_ENTRY_POINT_RENAME(ucal_getDefaultTimeZone) +#define ucal_getFieldDifference U_ICU_ENTRY_POINT_RENAME(ucal_getFieldDifference) +#define ucal_getGregorianChange U_ICU_ENTRY_POINT_RENAME(ucal_getGregorianChange) +#define ucal_getHostTimeZone U_ICU_ENTRY_POINT_RENAME(ucal_getHostTimeZone) +#define ucal_getKeywordValuesForLocale U_ICU_ENTRY_POINT_RENAME(ucal_getKeywordValuesForLocale) +#define ucal_getLimit U_ICU_ENTRY_POINT_RENAME(ucal_getLimit) +#define ucal_getLocaleByType U_ICU_ENTRY_POINT_RENAME(ucal_getLocaleByType) +#define ucal_getMillis U_ICU_ENTRY_POINT_RENAME(ucal_getMillis) +#define ucal_getNow U_ICU_ENTRY_POINT_RENAME(ucal_getNow) +#define ucal_getTZDataVersion U_ICU_ENTRY_POINT_RENAME(ucal_getTZDataVersion) +#define ucal_getTimeZoneDisplayName U_ICU_ENTRY_POINT_RENAME(ucal_getTimeZoneDisplayName) +#define ucal_getTimeZoneID U_ICU_ENTRY_POINT_RENAME(ucal_getTimeZoneID) +#define ucal_getTimeZoneIDForWindowsID U_ICU_ENTRY_POINT_RENAME(ucal_getTimeZoneIDForWindowsID) +#define ucal_getTimeZoneTransitionDate U_ICU_ENTRY_POINT_RENAME(ucal_getTimeZoneTransitionDate) +#define ucal_getType U_ICU_ENTRY_POINT_RENAME(ucal_getType) +#define ucal_getWeekendTransition U_ICU_ENTRY_POINT_RENAME(ucal_getWeekendTransition) +#define ucal_getWindowsTimeZoneID U_ICU_ENTRY_POINT_RENAME(ucal_getWindowsTimeZoneID) +#define ucal_inDaylightTime U_ICU_ENTRY_POINT_RENAME(ucal_inDaylightTime) +#define ucal_isSet U_ICU_ENTRY_POINT_RENAME(ucal_isSet) +#define ucal_isWeekend U_ICU_ENTRY_POINT_RENAME(ucal_isWeekend) +#define ucal_open U_ICU_ENTRY_POINT_RENAME(ucal_open) +#define ucal_openCountryTimeZones U_ICU_ENTRY_POINT_RENAME(ucal_openCountryTimeZones) +#define ucal_openTimeZoneIDEnumeration U_ICU_ENTRY_POINT_RENAME(ucal_openTimeZoneIDEnumeration) +#define ucal_openTimeZones U_ICU_ENTRY_POINT_RENAME(ucal_openTimeZones) +#define ucal_roll U_ICU_ENTRY_POINT_RENAME(ucal_roll) +#define ucal_set U_ICU_ENTRY_POINT_RENAME(ucal_set) +#define ucal_setAttribute U_ICU_ENTRY_POINT_RENAME(ucal_setAttribute) +#define ucal_setDate U_ICU_ENTRY_POINT_RENAME(ucal_setDate) +#define ucal_setDateTime U_ICU_ENTRY_POINT_RENAME(ucal_setDateTime) +#define ucal_setDefaultTimeZone U_ICU_ENTRY_POINT_RENAME(ucal_setDefaultTimeZone) +#define ucal_setGregorianChange U_ICU_ENTRY_POINT_RENAME(ucal_setGregorianChange) +#define ucal_setMillis U_ICU_ENTRY_POINT_RENAME(ucal_setMillis) +#define ucal_setTimeZone U_ICU_ENTRY_POINT_RENAME(ucal_setTimeZone) +#define ucase_addCaseClosure U_ICU_ENTRY_POINT_RENAME(ucase_addCaseClosure) +#define ucase_addPropertyStarts U_ICU_ENTRY_POINT_RENAME(ucase_addPropertyStarts) +#define ucase_addStringCaseClosure U_ICU_ENTRY_POINT_RENAME(ucase_addStringCaseClosure) +#define ucase_fold U_ICU_ENTRY_POINT_RENAME(ucase_fold) +#define ucase_getCaseLocale U_ICU_ENTRY_POINT_RENAME(ucase_getCaseLocale) +#define ucase_getTrie U_ICU_ENTRY_POINT_RENAME(ucase_getTrie) +#define ucase_getType U_ICU_ENTRY_POINT_RENAME(ucase_getType) +#define ucase_getTypeOrIgnorable U_ICU_ENTRY_POINT_RENAME(ucase_getTypeOrIgnorable) +#define ucase_hasBinaryProperty U_ICU_ENTRY_POINT_RENAME(ucase_hasBinaryProperty) +#define ucase_isCaseSensitive U_ICU_ENTRY_POINT_RENAME(ucase_isCaseSensitive) +#define ucase_isSoftDotted U_ICU_ENTRY_POINT_RENAME(ucase_isSoftDotted) +#define ucase_toFullFolding U_ICU_ENTRY_POINT_RENAME(ucase_toFullFolding) +#define ucase_toFullLower U_ICU_ENTRY_POINT_RENAME(ucase_toFullLower) +#define ucase_toFullTitle U_ICU_ENTRY_POINT_RENAME(ucase_toFullTitle) +#define ucase_toFullUpper U_ICU_ENTRY_POINT_RENAME(ucase_toFullUpper) +#define ucase_tolower U_ICU_ENTRY_POINT_RENAME(ucase_tolower) +#define ucase_totitle U_ICU_ENTRY_POINT_RENAME(ucase_totitle) +#define ucase_toupper U_ICU_ENTRY_POINT_RENAME(ucase_toupper) +#define ucasemap_close U_ICU_ENTRY_POINT_RENAME(ucasemap_close) +#define ucasemap_getBreakIterator U_ICU_ENTRY_POINT_RENAME(ucasemap_getBreakIterator) +#define ucasemap_getLocale U_ICU_ENTRY_POINT_RENAME(ucasemap_getLocale) +#define ucasemap_getOptions U_ICU_ENTRY_POINT_RENAME(ucasemap_getOptions) +#define ucasemap_internalUTF8ToTitle U_ICU_ENTRY_POINT_RENAME(ucasemap_internalUTF8ToTitle) +#define ucasemap_open U_ICU_ENTRY_POINT_RENAME(ucasemap_open) +#define ucasemap_setBreakIterator U_ICU_ENTRY_POINT_RENAME(ucasemap_setBreakIterator) +#define ucasemap_setLocale U_ICU_ENTRY_POINT_RENAME(ucasemap_setLocale) +#define ucasemap_setOptions U_ICU_ENTRY_POINT_RENAME(ucasemap_setOptions) +#define ucasemap_toTitle U_ICU_ENTRY_POINT_RENAME(ucasemap_toTitle) +#define ucasemap_utf8FoldCase U_ICU_ENTRY_POINT_RENAME(ucasemap_utf8FoldCase) +#define ucasemap_utf8ToLower U_ICU_ENTRY_POINT_RENAME(ucasemap_utf8ToLower) +#define ucasemap_utf8ToTitle U_ICU_ENTRY_POINT_RENAME(ucasemap_utf8ToTitle) +#define ucasemap_utf8ToUpper U_ICU_ENTRY_POINT_RENAME(ucasemap_utf8ToUpper) +#define ucfpos_close U_ICU_ENTRY_POINT_RENAME(ucfpos_close) +#define ucfpos_constrainCategory U_ICU_ENTRY_POINT_RENAME(ucfpos_constrainCategory) +#define ucfpos_constrainField U_ICU_ENTRY_POINT_RENAME(ucfpos_constrainField) +#define ucfpos_getCategory U_ICU_ENTRY_POINT_RENAME(ucfpos_getCategory) +#define ucfpos_getField U_ICU_ENTRY_POINT_RENAME(ucfpos_getField) +#define ucfpos_getIndexes U_ICU_ENTRY_POINT_RENAME(ucfpos_getIndexes) +#define ucfpos_getInt64IterationContext U_ICU_ENTRY_POINT_RENAME(ucfpos_getInt64IterationContext) +#define ucfpos_matchesField U_ICU_ENTRY_POINT_RENAME(ucfpos_matchesField) +#define ucfpos_open U_ICU_ENTRY_POINT_RENAME(ucfpos_open) +#define ucfpos_reset U_ICU_ENTRY_POINT_RENAME(ucfpos_reset) +#define ucfpos_setInt64IterationContext U_ICU_ENTRY_POINT_RENAME(ucfpos_setInt64IterationContext) +#define ucfpos_setState U_ICU_ENTRY_POINT_RENAME(ucfpos_setState) +#define uchar_addPropertyStarts U_ICU_ENTRY_POINT_RENAME(uchar_addPropertyStarts) +#define uchar_swapNames U_ICU_ENTRY_POINT_RENAME(uchar_swapNames) +#define ucln_cleanupOne U_ICU_ENTRY_POINT_RENAME(ucln_cleanupOne) +#define ucln_common_registerCleanup U_ICU_ENTRY_POINT_RENAME(ucln_common_registerCleanup) +#define ucln_i18n_registerCleanup U_ICU_ENTRY_POINT_RENAME(ucln_i18n_registerCleanup) +#define ucln_io_registerCleanup U_ICU_ENTRY_POINT_RENAME(ucln_io_registerCleanup) +#define ucln_lib_cleanup U_ICU_ENTRY_POINT_RENAME(ucln_lib_cleanup) +#define ucln_registerCleanup U_ICU_ENTRY_POINT_RENAME(ucln_registerCleanup) +#define ucnv_MBCSFromUChar32 U_ICU_ENTRY_POINT_RENAME(ucnv_MBCSFromUChar32) +#define ucnv_MBCSFromUnicodeWithOffsets U_ICU_ENTRY_POINT_RENAME(ucnv_MBCSFromUnicodeWithOffsets) +#define ucnv_MBCSGetFilteredUnicodeSetForUnicode U_ICU_ENTRY_POINT_RENAME(ucnv_MBCSGetFilteredUnicodeSetForUnicode) +#define ucnv_MBCSGetType U_ICU_ENTRY_POINT_RENAME(ucnv_MBCSGetType) +#define ucnv_MBCSGetUnicodeSetForUnicode U_ICU_ENTRY_POINT_RENAME(ucnv_MBCSGetUnicodeSetForUnicode) +#define ucnv_MBCSIsLeadByte U_ICU_ENTRY_POINT_RENAME(ucnv_MBCSIsLeadByte) +#define ucnv_MBCSSimpleGetNextUChar U_ICU_ENTRY_POINT_RENAME(ucnv_MBCSSimpleGetNextUChar) +#define ucnv_MBCSToUnicodeWithOffsets U_ICU_ENTRY_POINT_RENAME(ucnv_MBCSToUnicodeWithOffsets) +#define ucnv_bld_countAvailableConverters U_ICU_ENTRY_POINT_RENAME(ucnv_bld_countAvailableConverters) +#define ucnv_bld_getAvailableConverter U_ICU_ENTRY_POINT_RENAME(ucnv_bld_getAvailableConverter) +#define ucnv_canCreateConverter U_ICU_ENTRY_POINT_RENAME(ucnv_canCreateConverter) +#define ucnv_cbFromUWriteBytes U_ICU_ENTRY_POINT_RENAME(ucnv_cbFromUWriteBytes) +#define ucnv_cbFromUWriteSub U_ICU_ENTRY_POINT_RENAME(ucnv_cbFromUWriteSub) +#define ucnv_cbFromUWriteUChars U_ICU_ENTRY_POINT_RENAME(ucnv_cbFromUWriteUChars) +#define ucnv_cbToUWriteSub U_ICU_ENTRY_POINT_RENAME(ucnv_cbToUWriteSub) +#define ucnv_cbToUWriteUChars U_ICU_ENTRY_POINT_RENAME(ucnv_cbToUWriteUChars) +#define ucnv_close U_ICU_ENTRY_POINT_RENAME(ucnv_close) +#define ucnv_compareNames U_ICU_ENTRY_POINT_RENAME(ucnv_compareNames) +#define ucnv_convert U_ICU_ENTRY_POINT_RENAME(ucnv_convert) +#define ucnv_convertEx U_ICU_ENTRY_POINT_RENAME(ucnv_convertEx) +#define ucnv_countAliases U_ICU_ENTRY_POINT_RENAME(ucnv_countAliases) +#define ucnv_countAvailable U_ICU_ENTRY_POINT_RENAME(ucnv_countAvailable) +#define ucnv_countStandards U_ICU_ENTRY_POINT_RENAME(ucnv_countStandards) +#define ucnv_createAlgorithmicConverter U_ICU_ENTRY_POINT_RENAME(ucnv_createAlgorithmicConverter) +#define ucnv_createConverter U_ICU_ENTRY_POINT_RENAME(ucnv_createConverter) +#define ucnv_createConverterFromPackage U_ICU_ENTRY_POINT_RENAME(ucnv_createConverterFromPackage) +#define ucnv_createConverterFromSharedData U_ICU_ENTRY_POINT_RENAME(ucnv_createConverterFromSharedData) +#define ucnv_detectUnicodeSignature U_ICU_ENTRY_POINT_RENAME(ucnv_detectUnicodeSignature) +#define ucnv_enableCleanup U_ICU_ENTRY_POINT_RENAME(ucnv_enableCleanup) +#define ucnv_extContinueMatchFromU U_ICU_ENTRY_POINT_RENAME(ucnv_extContinueMatchFromU) +#define ucnv_extContinueMatchToU U_ICU_ENTRY_POINT_RENAME(ucnv_extContinueMatchToU) +#define ucnv_extGetUnicodeSet U_ICU_ENTRY_POINT_RENAME(ucnv_extGetUnicodeSet) +#define ucnv_extInitialMatchFromU U_ICU_ENTRY_POINT_RENAME(ucnv_extInitialMatchFromU) +#define ucnv_extInitialMatchToU U_ICU_ENTRY_POINT_RENAME(ucnv_extInitialMatchToU) +#define ucnv_extSimpleMatchFromU U_ICU_ENTRY_POINT_RENAME(ucnv_extSimpleMatchFromU) +#define ucnv_extSimpleMatchToU U_ICU_ENTRY_POINT_RENAME(ucnv_extSimpleMatchToU) +#define ucnv_fixFileSeparator U_ICU_ENTRY_POINT_RENAME(ucnv_fixFileSeparator) +#define ucnv_flushCache U_ICU_ENTRY_POINT_RENAME(ucnv_flushCache) +#define ucnv_fromAlgorithmic U_ICU_ENTRY_POINT_RENAME(ucnv_fromAlgorithmic) +#define ucnv_fromUChars U_ICU_ENTRY_POINT_RENAME(ucnv_fromUChars) +#define ucnv_fromUCountPending U_ICU_ENTRY_POINT_RENAME(ucnv_fromUCountPending) +#define ucnv_fromUWriteBytes U_ICU_ENTRY_POINT_RENAME(ucnv_fromUWriteBytes) +#define ucnv_fromUnicode U_ICU_ENTRY_POINT_RENAME(ucnv_fromUnicode) +#define ucnv_fromUnicode_UTF8 U_ICU_ENTRY_POINT_RENAME(ucnv_fromUnicode_UTF8) +#define ucnv_fromUnicode_UTF8_OFFSETS_LOGIC U_ICU_ENTRY_POINT_RENAME(ucnv_fromUnicode_UTF8_OFFSETS_LOGIC) +#define ucnv_getAlias U_ICU_ENTRY_POINT_RENAME(ucnv_getAlias) +#define ucnv_getAliases U_ICU_ENTRY_POINT_RENAME(ucnv_getAliases) +#define ucnv_getAvailableName U_ICU_ENTRY_POINT_RENAME(ucnv_getAvailableName) +#define ucnv_getCCSID U_ICU_ENTRY_POINT_RENAME(ucnv_getCCSID) +#define ucnv_getCanonicalName U_ICU_ENTRY_POINT_RENAME(ucnv_getCanonicalName) +#define ucnv_getCompleteUnicodeSet U_ICU_ENTRY_POINT_RENAME(ucnv_getCompleteUnicodeSet) +#define ucnv_getDefaultName U_ICU_ENTRY_POINT_RENAME(ucnv_getDefaultName) +#define ucnv_getDisplayName U_ICU_ENTRY_POINT_RENAME(ucnv_getDisplayName) +#define ucnv_getFromUCallBack U_ICU_ENTRY_POINT_RENAME(ucnv_getFromUCallBack) +#define ucnv_getInvalidChars U_ICU_ENTRY_POINT_RENAME(ucnv_getInvalidChars) +#define ucnv_getInvalidUChars U_ICU_ENTRY_POINT_RENAME(ucnv_getInvalidUChars) +#define ucnv_getMaxCharSize U_ICU_ENTRY_POINT_RENAME(ucnv_getMaxCharSize) +#define ucnv_getMinCharSize U_ICU_ENTRY_POINT_RENAME(ucnv_getMinCharSize) +#define ucnv_getName U_ICU_ENTRY_POINT_RENAME(ucnv_getName) +#define ucnv_getNextUChar U_ICU_ENTRY_POINT_RENAME(ucnv_getNextUChar) +#define ucnv_getNonSurrogateUnicodeSet U_ICU_ENTRY_POINT_RENAME(ucnv_getNonSurrogateUnicodeSet) +#define ucnv_getPlatform U_ICU_ENTRY_POINT_RENAME(ucnv_getPlatform) +#define ucnv_getStandard U_ICU_ENTRY_POINT_RENAME(ucnv_getStandard) +#define ucnv_getStandardName U_ICU_ENTRY_POINT_RENAME(ucnv_getStandardName) +#define ucnv_getStarters U_ICU_ENTRY_POINT_RENAME(ucnv_getStarters) +#define ucnv_getSubstChars U_ICU_ENTRY_POINT_RENAME(ucnv_getSubstChars) +#define ucnv_getToUCallBack U_ICU_ENTRY_POINT_RENAME(ucnv_getToUCallBack) +#define ucnv_getType U_ICU_ENTRY_POINT_RENAME(ucnv_getType) +#define ucnv_getUnicodeSet U_ICU_ENTRY_POINT_RENAME(ucnv_getUnicodeSet) +#define ucnv_incrementRefCount U_ICU_ENTRY_POINT_RENAME(ucnv_incrementRefCount) +#define ucnv_io_countKnownConverters U_ICU_ENTRY_POINT_RENAME(ucnv_io_countKnownConverters) +#define ucnv_io_getConverterName U_ICU_ENTRY_POINT_RENAME(ucnv_io_getConverterName) +#define ucnv_io_stripASCIIForCompare U_ICU_ENTRY_POINT_RENAME(ucnv_io_stripASCIIForCompare) +#define ucnv_io_stripEBCDICForCompare U_ICU_ENTRY_POINT_RENAME(ucnv_io_stripEBCDICForCompare) +#define ucnv_isAmbiguous U_ICU_ENTRY_POINT_RENAME(ucnv_isAmbiguous) +#define ucnv_isFixedWidth U_ICU_ENTRY_POINT_RENAME(ucnv_isFixedWidth) +#define ucnv_load U_ICU_ENTRY_POINT_RENAME(ucnv_load) +#define ucnv_loadSharedData U_ICU_ENTRY_POINT_RENAME(ucnv_loadSharedData) +#define ucnv_open U_ICU_ENTRY_POINT_RENAME(ucnv_open) +#define ucnv_openAllNames U_ICU_ENTRY_POINT_RENAME(ucnv_openAllNames) +#define ucnv_openCCSID U_ICU_ENTRY_POINT_RENAME(ucnv_openCCSID) +#define ucnv_openPackage U_ICU_ENTRY_POINT_RENAME(ucnv_openPackage) +#define ucnv_openStandardNames U_ICU_ENTRY_POINT_RENAME(ucnv_openStandardNames) +#define ucnv_openU U_ICU_ENTRY_POINT_RENAME(ucnv_openU) +#define ucnv_reset U_ICU_ENTRY_POINT_RENAME(ucnv_reset) +#define ucnv_resetFromUnicode U_ICU_ENTRY_POINT_RENAME(ucnv_resetFromUnicode) +#define ucnv_resetToUnicode U_ICU_ENTRY_POINT_RENAME(ucnv_resetToUnicode) +#define ucnv_safeClone U_ICU_ENTRY_POINT_RENAME(ucnv_safeClone) +#define ucnv_setDefaultName U_ICU_ENTRY_POINT_RENAME(ucnv_setDefaultName) +#define ucnv_setFallback U_ICU_ENTRY_POINT_RENAME(ucnv_setFallback) +#define ucnv_setFromUCallBack U_ICU_ENTRY_POINT_RENAME(ucnv_setFromUCallBack) +#define ucnv_setSubstChars U_ICU_ENTRY_POINT_RENAME(ucnv_setSubstChars) +#define ucnv_setSubstString U_ICU_ENTRY_POINT_RENAME(ucnv_setSubstString) +#define ucnv_setToUCallBack U_ICU_ENTRY_POINT_RENAME(ucnv_setToUCallBack) +#define ucnv_swap U_ICU_ENTRY_POINT_RENAME(ucnv_swap) +#define ucnv_swapAliases U_ICU_ENTRY_POINT_RENAME(ucnv_swapAliases) +#define ucnv_toAlgorithmic U_ICU_ENTRY_POINT_RENAME(ucnv_toAlgorithmic) +#define ucnv_toUChars U_ICU_ENTRY_POINT_RENAME(ucnv_toUChars) +#define ucnv_toUCountPending U_ICU_ENTRY_POINT_RENAME(ucnv_toUCountPending) +#define ucnv_toUWriteCodePoint U_ICU_ENTRY_POINT_RENAME(ucnv_toUWriteCodePoint) +#define ucnv_toUWriteUChars U_ICU_ENTRY_POINT_RENAME(ucnv_toUWriteUChars) +#define ucnv_toUnicode U_ICU_ENTRY_POINT_RENAME(ucnv_toUnicode) +#define ucnv_unload U_ICU_ENTRY_POINT_RENAME(ucnv_unload) +#define ucnv_unloadSharedDataIfReady U_ICU_ENTRY_POINT_RENAME(ucnv_unloadSharedDataIfReady) +#define ucnv_usesFallback U_ICU_ENTRY_POINT_RENAME(ucnv_usesFallback) +#define ucnvsel_close U_ICU_ENTRY_POINT_RENAME(ucnvsel_close) +#define ucnvsel_open U_ICU_ENTRY_POINT_RENAME(ucnvsel_open) +#define ucnvsel_openFromSerialized U_ICU_ENTRY_POINT_RENAME(ucnvsel_openFromSerialized) +#define ucnvsel_selectForString U_ICU_ENTRY_POINT_RENAME(ucnvsel_selectForString) +#define ucnvsel_selectForUTF8 U_ICU_ENTRY_POINT_RENAME(ucnvsel_selectForUTF8) +#define ucnvsel_serialize U_ICU_ENTRY_POINT_RENAME(ucnvsel_serialize) +#define ucol_cloneBinary U_ICU_ENTRY_POINT_RENAME(ucol_cloneBinary) +#define ucol_close U_ICU_ENTRY_POINT_RENAME(ucol_close) +#define ucol_closeElements U_ICU_ENTRY_POINT_RENAME(ucol_closeElements) +#define ucol_countAvailable U_ICU_ENTRY_POINT_RENAME(ucol_countAvailable) +#define ucol_equal U_ICU_ENTRY_POINT_RENAME(ucol_equal) +#define ucol_equals U_ICU_ENTRY_POINT_RENAME(ucol_equals) +#define ucol_getAttribute U_ICU_ENTRY_POINT_RENAME(ucol_getAttribute) +#define ucol_getAvailable U_ICU_ENTRY_POINT_RENAME(ucol_getAvailable) +#define ucol_getBound U_ICU_ENTRY_POINT_RENAME(ucol_getBound) +#define ucol_getContractions U_ICU_ENTRY_POINT_RENAME(ucol_getContractions) +#define ucol_getContractionsAndExpansions U_ICU_ENTRY_POINT_RENAME(ucol_getContractionsAndExpansions) +#define ucol_getDisplayName U_ICU_ENTRY_POINT_RENAME(ucol_getDisplayName) +#define ucol_getEquivalentReorderCodes U_ICU_ENTRY_POINT_RENAME(ucol_getEquivalentReorderCodes) +#define ucol_getFunctionalEquivalent U_ICU_ENTRY_POINT_RENAME(ucol_getFunctionalEquivalent) +#define ucol_getKeywordValues U_ICU_ENTRY_POINT_RENAME(ucol_getKeywordValues) +#define ucol_getKeywordValuesForLocale U_ICU_ENTRY_POINT_RENAME(ucol_getKeywordValuesForLocale) +#define ucol_getKeywords U_ICU_ENTRY_POINT_RENAME(ucol_getKeywords) +#define ucol_getLocale U_ICU_ENTRY_POINT_RENAME(ucol_getLocale) +#define ucol_getLocaleByType U_ICU_ENTRY_POINT_RENAME(ucol_getLocaleByType) +#define ucol_getMaxExpansion U_ICU_ENTRY_POINT_RENAME(ucol_getMaxExpansion) +#define ucol_getMaxVariable U_ICU_ENTRY_POINT_RENAME(ucol_getMaxVariable) +#define ucol_getOffset U_ICU_ENTRY_POINT_RENAME(ucol_getOffset) +#define ucol_getReorderCodes U_ICU_ENTRY_POINT_RENAME(ucol_getReorderCodes) +#define ucol_getRules U_ICU_ENTRY_POINT_RENAME(ucol_getRules) +#define ucol_getRulesEx U_ICU_ENTRY_POINT_RENAME(ucol_getRulesEx) +#define ucol_getShortDefinitionString U_ICU_ENTRY_POINT_RENAME(ucol_getShortDefinitionString) +#define ucol_getSortKey U_ICU_ENTRY_POINT_RENAME(ucol_getSortKey) +#define ucol_getStrength U_ICU_ENTRY_POINT_RENAME(ucol_getStrength) +#define ucol_getTailoredSet U_ICU_ENTRY_POINT_RENAME(ucol_getTailoredSet) +#define ucol_getUCAVersion U_ICU_ENTRY_POINT_RENAME(ucol_getUCAVersion) +#define ucol_getUnsafeSet U_ICU_ENTRY_POINT_RENAME(ucol_getUnsafeSet) +#define ucol_getVariableTop U_ICU_ENTRY_POINT_RENAME(ucol_getVariableTop) +#define ucol_getVersion U_ICU_ENTRY_POINT_RENAME(ucol_getVersion) +#define ucol_greater U_ICU_ENTRY_POINT_RENAME(ucol_greater) +#define ucol_greaterOrEqual U_ICU_ENTRY_POINT_RENAME(ucol_greaterOrEqual) +#define ucol_keyHashCode U_ICU_ENTRY_POINT_RENAME(ucol_keyHashCode) +#define ucol_looksLikeCollationBinary U_ICU_ENTRY_POINT_RENAME(ucol_looksLikeCollationBinary) +#define ucol_mergeSortkeys U_ICU_ENTRY_POINT_RENAME(ucol_mergeSortkeys) +#define ucol_next U_ICU_ENTRY_POINT_RENAME(ucol_next) +#define ucol_nextSortKeyPart U_ICU_ENTRY_POINT_RENAME(ucol_nextSortKeyPart) +#define ucol_normalizeShortDefinitionString U_ICU_ENTRY_POINT_RENAME(ucol_normalizeShortDefinitionString) +#define ucol_open U_ICU_ENTRY_POINT_RENAME(ucol_open) +#define ucol_openAvailableLocales U_ICU_ENTRY_POINT_RENAME(ucol_openAvailableLocales) +#define ucol_openBinary U_ICU_ENTRY_POINT_RENAME(ucol_openBinary) +#define ucol_openElements U_ICU_ENTRY_POINT_RENAME(ucol_openElements) +#define ucol_openFromShortString U_ICU_ENTRY_POINT_RENAME(ucol_openFromShortString) +#define ucol_openRules U_ICU_ENTRY_POINT_RENAME(ucol_openRules) +#define ucol_prepareShortStringOpen U_ICU_ENTRY_POINT_RENAME(ucol_prepareShortStringOpen) +#define ucol_previous U_ICU_ENTRY_POINT_RENAME(ucol_previous) +#define ucol_primaryOrder U_ICU_ENTRY_POINT_RENAME(ucol_primaryOrder) +#define ucol_reset U_ICU_ENTRY_POINT_RENAME(ucol_reset) +#define ucol_restoreVariableTop U_ICU_ENTRY_POINT_RENAME(ucol_restoreVariableTop) +#define ucol_safeClone U_ICU_ENTRY_POINT_RENAME(ucol_safeClone) +#define ucol_secondaryOrder U_ICU_ENTRY_POINT_RENAME(ucol_secondaryOrder) +#define ucol_setAttribute U_ICU_ENTRY_POINT_RENAME(ucol_setAttribute) +#define ucol_setMaxVariable U_ICU_ENTRY_POINT_RENAME(ucol_setMaxVariable) +#define ucol_setOffset U_ICU_ENTRY_POINT_RENAME(ucol_setOffset) +#define ucol_setReorderCodes U_ICU_ENTRY_POINT_RENAME(ucol_setReorderCodes) +#define ucol_setStrength U_ICU_ENTRY_POINT_RENAME(ucol_setStrength) +#define ucol_setText U_ICU_ENTRY_POINT_RENAME(ucol_setText) +#define ucol_setVariableTop U_ICU_ENTRY_POINT_RENAME(ucol_setVariableTop) +#define ucol_strcoll U_ICU_ENTRY_POINT_RENAME(ucol_strcoll) +#define ucol_strcollIter U_ICU_ENTRY_POINT_RENAME(ucol_strcollIter) +#define ucol_strcollUTF8 U_ICU_ENTRY_POINT_RENAME(ucol_strcollUTF8) +#define ucol_swap U_ICU_ENTRY_POINT_RENAME(ucol_swap) +#define ucol_swapInverseUCA U_ICU_ENTRY_POINT_RENAME(ucol_swapInverseUCA) +#define ucol_tertiaryOrder U_ICU_ENTRY_POINT_RENAME(ucol_tertiaryOrder) +#define ucpmap_get U_ICU_ENTRY_POINT_RENAME(ucpmap_get) +#define ucpmap_getRange U_ICU_ENTRY_POINT_RENAME(ucpmap_getRange) +#define ucptrie_close U_ICU_ENTRY_POINT_RENAME(ucptrie_close) +#define ucptrie_get U_ICU_ENTRY_POINT_RENAME(ucptrie_get) +#define ucptrie_getRange U_ICU_ENTRY_POINT_RENAME(ucptrie_getRange) +#define ucptrie_getType U_ICU_ENTRY_POINT_RENAME(ucptrie_getType) +#define ucptrie_getValueWidth U_ICU_ENTRY_POINT_RENAME(ucptrie_getValueWidth) +#define ucptrie_internalGetRange U_ICU_ENTRY_POINT_RENAME(ucptrie_internalGetRange) +#define ucptrie_internalSmallIndex U_ICU_ENTRY_POINT_RENAME(ucptrie_internalSmallIndex) +#define ucptrie_internalSmallU8Index U_ICU_ENTRY_POINT_RENAME(ucptrie_internalSmallU8Index) +#define ucptrie_internalU8PrevIndex U_ICU_ENTRY_POINT_RENAME(ucptrie_internalU8PrevIndex) +#define ucptrie_openFromBinary U_ICU_ENTRY_POINT_RENAME(ucptrie_openFromBinary) +#define ucptrie_swap U_ICU_ENTRY_POINT_RENAME(ucptrie_swap) +#define ucptrie_toBinary U_ICU_ENTRY_POINT_RENAME(ucptrie_toBinary) +#define ucsdet_close U_ICU_ENTRY_POINT_RENAME(ucsdet_close) +#define ucsdet_detect U_ICU_ENTRY_POINT_RENAME(ucsdet_detect) +#define ucsdet_detectAll U_ICU_ENTRY_POINT_RENAME(ucsdet_detectAll) +#define ucsdet_enableInputFilter U_ICU_ENTRY_POINT_RENAME(ucsdet_enableInputFilter) +#define ucsdet_getAllDetectableCharsets U_ICU_ENTRY_POINT_RENAME(ucsdet_getAllDetectableCharsets) +#define ucsdet_getConfidence U_ICU_ENTRY_POINT_RENAME(ucsdet_getConfidence) +#define ucsdet_getDetectableCharsets U_ICU_ENTRY_POINT_RENAME(ucsdet_getDetectableCharsets) +#define ucsdet_getLanguage U_ICU_ENTRY_POINT_RENAME(ucsdet_getLanguage) +#define ucsdet_getName U_ICU_ENTRY_POINT_RENAME(ucsdet_getName) +#define ucsdet_getUChars U_ICU_ENTRY_POINT_RENAME(ucsdet_getUChars) +#define ucsdet_isInputFilterEnabled U_ICU_ENTRY_POINT_RENAME(ucsdet_isInputFilterEnabled) +#define ucsdet_open U_ICU_ENTRY_POINT_RENAME(ucsdet_open) +#define ucsdet_setDeclaredEncoding U_ICU_ENTRY_POINT_RENAME(ucsdet_setDeclaredEncoding) +#define ucsdet_setDetectableCharset U_ICU_ENTRY_POINT_RENAME(ucsdet_setDetectableCharset) +#define ucsdet_setText U_ICU_ENTRY_POINT_RENAME(ucsdet_setText) +#define ucurr_countCurrencies U_ICU_ENTRY_POINT_RENAME(ucurr_countCurrencies) +#define ucurr_forLocale U_ICU_ENTRY_POINT_RENAME(ucurr_forLocale) +#define ucurr_forLocaleAndDate U_ICU_ENTRY_POINT_RENAME(ucurr_forLocaleAndDate) +#define ucurr_getDefaultFractionDigits U_ICU_ENTRY_POINT_RENAME(ucurr_getDefaultFractionDigits) +#define ucurr_getDefaultFractionDigitsForUsage U_ICU_ENTRY_POINT_RENAME(ucurr_getDefaultFractionDigitsForUsage) +#define ucurr_getKeywordValuesForLocale U_ICU_ENTRY_POINT_RENAME(ucurr_getKeywordValuesForLocale) +#define ucurr_getName U_ICU_ENTRY_POINT_RENAME(ucurr_getName) +#define ucurr_getNumericCode U_ICU_ENTRY_POINT_RENAME(ucurr_getNumericCode) +#define ucurr_getPluralName U_ICU_ENTRY_POINT_RENAME(ucurr_getPluralName) +#define ucurr_getRoundingIncrement U_ICU_ENTRY_POINT_RENAME(ucurr_getRoundingIncrement) +#define ucurr_getRoundingIncrementForUsage U_ICU_ENTRY_POINT_RENAME(ucurr_getRoundingIncrementForUsage) +#define ucurr_isAvailable U_ICU_ENTRY_POINT_RENAME(ucurr_isAvailable) +#define ucurr_openISOCurrencies U_ICU_ENTRY_POINT_RENAME(ucurr_openISOCurrencies) +#define ucurr_register U_ICU_ENTRY_POINT_RENAME(ucurr_register) +#define ucurr_unregister U_ICU_ENTRY_POINT_RENAME(ucurr_unregister) +#define udat_adoptNumberFormat U_ICU_ENTRY_POINT_RENAME(udat_adoptNumberFormat) +#define udat_adoptNumberFormatForFields U_ICU_ENTRY_POINT_RENAME(udat_adoptNumberFormatForFields) +#define udat_applyPattern U_ICU_ENTRY_POINT_RENAME(udat_applyPattern) +#define udat_applyPatternRelative U_ICU_ENTRY_POINT_RENAME(udat_applyPatternRelative) +#define udat_clone U_ICU_ENTRY_POINT_RENAME(udat_clone) +#define udat_close U_ICU_ENTRY_POINT_RENAME(udat_close) +#define udat_countAvailable U_ICU_ENTRY_POINT_RENAME(udat_countAvailable) +#define udat_countSymbols U_ICU_ENTRY_POINT_RENAME(udat_countSymbols) +#define udat_format U_ICU_ENTRY_POINT_RENAME(udat_format) +#define udat_formatCalendar U_ICU_ENTRY_POINT_RENAME(udat_formatCalendar) +#define udat_formatCalendarForFields U_ICU_ENTRY_POINT_RENAME(udat_formatCalendarForFields) +#define udat_formatForFields U_ICU_ENTRY_POINT_RENAME(udat_formatForFields) +#define udat_get2DigitYearStart U_ICU_ENTRY_POINT_RENAME(udat_get2DigitYearStart) +#define udat_getAvailable U_ICU_ENTRY_POINT_RENAME(udat_getAvailable) +#define udat_getBooleanAttribute U_ICU_ENTRY_POINT_RENAME(udat_getBooleanAttribute) +#define udat_getCalendar U_ICU_ENTRY_POINT_RENAME(udat_getCalendar) +#define udat_getContext U_ICU_ENTRY_POINT_RENAME(udat_getContext) +#define udat_getLocaleByType U_ICU_ENTRY_POINT_RENAME(udat_getLocaleByType) +#define udat_getNumberFormat U_ICU_ENTRY_POINT_RENAME(udat_getNumberFormat) +#define udat_getNumberFormatForField U_ICU_ENTRY_POINT_RENAME(udat_getNumberFormatForField) +#define udat_getSymbols U_ICU_ENTRY_POINT_RENAME(udat_getSymbols) +#define udat_isLenient U_ICU_ENTRY_POINT_RENAME(udat_isLenient) +#define udat_open U_ICU_ENTRY_POINT_RENAME(udat_open) +#define udat_parse U_ICU_ENTRY_POINT_RENAME(udat_parse) +#define udat_parseCalendar U_ICU_ENTRY_POINT_RENAME(udat_parseCalendar) +#define udat_registerOpener U_ICU_ENTRY_POINT_RENAME(udat_registerOpener) +#define udat_set2DigitYearStart U_ICU_ENTRY_POINT_RENAME(udat_set2DigitYearStart) +#define udat_setBooleanAttribute U_ICU_ENTRY_POINT_RENAME(udat_setBooleanAttribute) +#define udat_setCalendar U_ICU_ENTRY_POINT_RENAME(udat_setCalendar) +#define udat_setContext U_ICU_ENTRY_POINT_RENAME(udat_setContext) +#define udat_setLenient U_ICU_ENTRY_POINT_RENAME(udat_setLenient) +#define udat_setNumberFormat U_ICU_ENTRY_POINT_RENAME(udat_setNumberFormat) +#define udat_setSymbols U_ICU_ENTRY_POINT_RENAME(udat_setSymbols) +#define udat_toCalendarDateField U_ICU_ENTRY_POINT_RENAME(udat_toCalendarDateField) +#define udat_toPattern U_ICU_ENTRY_POINT_RENAME(udat_toPattern) +#define udat_toPatternRelativeDate U_ICU_ENTRY_POINT_RENAME(udat_toPatternRelativeDate) +#define udat_toPatternRelativeTime U_ICU_ENTRY_POINT_RENAME(udat_toPatternRelativeTime) +#define udat_unregisterOpener U_ICU_ENTRY_POINT_RENAME(udat_unregisterOpener) +#define udata_checkCommonData U_ICU_ENTRY_POINT_RENAME(udata_checkCommonData) +#define udata_close U_ICU_ENTRY_POINT_RENAME(udata_close) +#define udata_closeSwapper U_ICU_ENTRY_POINT_RENAME(udata_closeSwapper) +#define udata_getHeaderSize U_ICU_ENTRY_POINT_RENAME(udata_getHeaderSize) +#define udata_getInfo U_ICU_ENTRY_POINT_RENAME(udata_getInfo) +#define udata_getInfoSize U_ICU_ENTRY_POINT_RENAME(udata_getInfoSize) +#define udata_getLength U_ICU_ENTRY_POINT_RENAME(udata_getLength) +#define udata_getMemory U_ICU_ENTRY_POINT_RENAME(udata_getMemory) +#define udata_getRawMemory U_ICU_ENTRY_POINT_RENAME(udata_getRawMemory) +#define udata_open U_ICU_ENTRY_POINT_RENAME(udata_open) +#define udata_openChoice U_ICU_ENTRY_POINT_RENAME(udata_openChoice) +#define udata_openSwapper U_ICU_ENTRY_POINT_RENAME(udata_openSwapper) +#define udata_openSwapperForInputData U_ICU_ENTRY_POINT_RENAME(udata_openSwapperForInputData) +#define udata_printError U_ICU_ENTRY_POINT_RENAME(udata_printError) +#define udata_readInt16 U_ICU_ENTRY_POINT_RENAME(udata_readInt16) +#define udata_readInt32 U_ICU_ENTRY_POINT_RENAME(udata_readInt32) +#define udata_setAppData U_ICU_ENTRY_POINT_RENAME(udata_setAppData) +#define udata_setCommonData U_ICU_ENTRY_POINT_RENAME(udata_setCommonData) +#define udata_setFileAccess U_ICU_ENTRY_POINT_RENAME(udata_setFileAccess) +#define udata_swapDataHeader U_ICU_ENTRY_POINT_RENAME(udata_swapDataHeader) +#define udata_swapInvStringBlock U_ICU_ENTRY_POINT_RENAME(udata_swapInvStringBlock) +#define udatpg_addPattern U_ICU_ENTRY_POINT_RENAME(udatpg_addPattern) +#define udatpg_clone U_ICU_ENTRY_POINT_RENAME(udatpg_clone) +#define udatpg_close U_ICU_ENTRY_POINT_RENAME(udatpg_close) +#define udatpg_getAppendItemFormat U_ICU_ENTRY_POINT_RENAME(udatpg_getAppendItemFormat) +#define udatpg_getAppendItemName U_ICU_ENTRY_POINT_RENAME(udatpg_getAppendItemName) +#define udatpg_getBaseSkeleton U_ICU_ENTRY_POINT_RENAME(udatpg_getBaseSkeleton) +#define udatpg_getBestPattern U_ICU_ENTRY_POINT_RENAME(udatpg_getBestPattern) +#define udatpg_getBestPatternWithOptions U_ICU_ENTRY_POINT_RENAME(udatpg_getBestPatternWithOptions) +#define udatpg_getDateTimeFormat U_ICU_ENTRY_POINT_RENAME(udatpg_getDateTimeFormat) +#define udatpg_getDecimal U_ICU_ENTRY_POINT_RENAME(udatpg_getDecimal) +#define udatpg_getDefaultHourCycle U_ICU_ENTRY_POINT_RENAME(udatpg_getDefaultHourCycle) +#define udatpg_getFieldDisplayName U_ICU_ENTRY_POINT_RENAME(udatpg_getFieldDisplayName) +#define udatpg_getPatternForSkeleton U_ICU_ENTRY_POINT_RENAME(udatpg_getPatternForSkeleton) +#define udatpg_getSkeleton U_ICU_ENTRY_POINT_RENAME(udatpg_getSkeleton) +#define udatpg_open U_ICU_ENTRY_POINT_RENAME(udatpg_open) +#define udatpg_openBaseSkeletons U_ICU_ENTRY_POINT_RENAME(udatpg_openBaseSkeletons) +#define udatpg_openEmpty U_ICU_ENTRY_POINT_RENAME(udatpg_openEmpty) +#define udatpg_openSkeletons U_ICU_ENTRY_POINT_RENAME(udatpg_openSkeletons) +#define udatpg_replaceFieldTypes U_ICU_ENTRY_POINT_RENAME(udatpg_replaceFieldTypes) +#define udatpg_replaceFieldTypesWithOptions U_ICU_ENTRY_POINT_RENAME(udatpg_replaceFieldTypesWithOptions) +#define udatpg_setAppendItemFormat U_ICU_ENTRY_POINT_RENAME(udatpg_setAppendItemFormat) +#define udatpg_setAppendItemName U_ICU_ENTRY_POINT_RENAME(udatpg_setAppendItemName) +#define udatpg_setDateTimeFormat U_ICU_ENTRY_POINT_RENAME(udatpg_setDateTimeFormat) +#define udatpg_setDecimal U_ICU_ENTRY_POINT_RENAME(udatpg_setDecimal) +#define udict_swap U_ICU_ENTRY_POINT_RENAME(udict_swap) +#define udtitvfmt_close U_ICU_ENTRY_POINT_RENAME(udtitvfmt_close) +#define udtitvfmt_closeResult U_ICU_ENTRY_POINT_RENAME(udtitvfmt_closeResult) +#define udtitvfmt_format U_ICU_ENTRY_POINT_RENAME(udtitvfmt_format) +#define udtitvfmt_formatCalendarToResult U_ICU_ENTRY_POINT_RENAME(udtitvfmt_formatCalendarToResult) +#define udtitvfmt_formatToResult U_ICU_ENTRY_POINT_RENAME(udtitvfmt_formatToResult) +#define udtitvfmt_getContext U_ICU_ENTRY_POINT_RENAME(udtitvfmt_getContext) +#define udtitvfmt_open U_ICU_ENTRY_POINT_RENAME(udtitvfmt_open) +#define udtitvfmt_openResult U_ICU_ENTRY_POINT_RENAME(udtitvfmt_openResult) +#define udtitvfmt_resultAsValue U_ICU_ENTRY_POINT_RENAME(udtitvfmt_resultAsValue) +#define udtitvfmt_setContext U_ICU_ENTRY_POINT_RENAME(udtitvfmt_setContext) +#define uenum_close U_ICU_ENTRY_POINT_RENAME(uenum_close) +#define uenum_count U_ICU_ENTRY_POINT_RENAME(uenum_count) +#define uenum_next U_ICU_ENTRY_POINT_RENAME(uenum_next) +#define uenum_nextDefault U_ICU_ENTRY_POINT_RENAME(uenum_nextDefault) +#define uenum_openCharStringsEnumeration U_ICU_ENTRY_POINT_RENAME(uenum_openCharStringsEnumeration) +#define uenum_openFromStringEnumeration U_ICU_ENTRY_POINT_RENAME(uenum_openFromStringEnumeration) +#define uenum_openUCharStringsEnumeration U_ICU_ENTRY_POINT_RENAME(uenum_openUCharStringsEnumeration) +#define uenum_reset U_ICU_ENTRY_POINT_RENAME(uenum_reset) +#define uenum_unext U_ICU_ENTRY_POINT_RENAME(uenum_unext) +#define uenum_unextDefault U_ICU_ENTRY_POINT_RENAME(uenum_unextDefault) +#define ufieldpositer_close U_ICU_ENTRY_POINT_RENAME(ufieldpositer_close) +#define ufieldpositer_next U_ICU_ENTRY_POINT_RENAME(ufieldpositer_next) +#define ufieldpositer_open U_ICU_ENTRY_POINT_RENAME(ufieldpositer_open) +#define ufile_getch U_ICU_ENTRY_POINT_RENAME(ufile_getch) +#define ufile_getch32 U_ICU_ENTRY_POINT_RENAME(ufile_getch32) +#define ufmt_close U_ICU_ENTRY_POINT_RENAME(ufmt_close) +#define ufmt_getArrayItemByIndex U_ICU_ENTRY_POINT_RENAME(ufmt_getArrayItemByIndex) +#define ufmt_getArrayLength U_ICU_ENTRY_POINT_RENAME(ufmt_getArrayLength) +#define ufmt_getDate U_ICU_ENTRY_POINT_RENAME(ufmt_getDate) +#define ufmt_getDecNumChars U_ICU_ENTRY_POINT_RENAME(ufmt_getDecNumChars) +#define ufmt_getDouble U_ICU_ENTRY_POINT_RENAME(ufmt_getDouble) +#define ufmt_getInt64 U_ICU_ENTRY_POINT_RENAME(ufmt_getInt64) +#define ufmt_getLong U_ICU_ENTRY_POINT_RENAME(ufmt_getLong) +#define ufmt_getObject U_ICU_ENTRY_POINT_RENAME(ufmt_getObject) +#define ufmt_getType U_ICU_ENTRY_POINT_RENAME(ufmt_getType) +#define ufmt_getUChars U_ICU_ENTRY_POINT_RENAME(ufmt_getUChars) +#define ufmt_isNumeric U_ICU_ENTRY_POINT_RENAME(ufmt_isNumeric) +#define ufmt_open U_ICU_ENTRY_POINT_RENAME(ufmt_open) +#define ufmtval_getString U_ICU_ENTRY_POINT_RENAME(ufmtval_getString) +#define ufmtval_nextPosition U_ICU_ENTRY_POINT_RENAME(ufmtval_nextPosition) +#define ugender_getInstance U_ICU_ENTRY_POINT_RENAME(ugender_getInstance) +#define ugender_getListGender U_ICU_ENTRY_POINT_RENAME(ugender_getListGender) +#define uhash_close U_ICU_ENTRY_POINT_RENAME(uhash_close) +#define uhash_compareCaselessUnicodeString U_ICU_ENTRY_POINT_RENAME(uhash_compareCaselessUnicodeString) +#define uhash_compareChars U_ICU_ENTRY_POINT_RENAME(uhash_compareChars) +#define uhash_compareIChars U_ICU_ENTRY_POINT_RENAME(uhash_compareIChars) +#define uhash_compareLong U_ICU_ENTRY_POINT_RENAME(uhash_compareLong) +#define uhash_compareScriptSet U_ICU_ENTRY_POINT_RENAME(uhash_compareScriptSet) +#define uhash_compareUChars U_ICU_ENTRY_POINT_RENAME(uhash_compareUChars) +#define uhash_compareUnicodeString U_ICU_ENTRY_POINT_RENAME(uhash_compareUnicodeString) +#define uhash_count U_ICU_ENTRY_POINT_RENAME(uhash_count) +#define uhash_deleteHashtable U_ICU_ENTRY_POINT_RENAME(uhash_deleteHashtable) +#define uhash_deleteScriptSet U_ICU_ENTRY_POINT_RENAME(uhash_deleteScriptSet) +#define uhash_equals U_ICU_ENTRY_POINT_RENAME(uhash_equals) +#define uhash_equalsScriptSet U_ICU_ENTRY_POINT_RENAME(uhash_equalsScriptSet) +#define uhash_find U_ICU_ENTRY_POINT_RENAME(uhash_find) +#define uhash_get U_ICU_ENTRY_POINT_RENAME(uhash_get) +#define uhash_geti U_ICU_ENTRY_POINT_RENAME(uhash_geti) +#define uhash_hashCaselessUnicodeString U_ICU_ENTRY_POINT_RENAME(uhash_hashCaselessUnicodeString) +#define uhash_hashChars U_ICU_ENTRY_POINT_RENAME(uhash_hashChars) +#define uhash_hashIChars U_ICU_ENTRY_POINT_RENAME(uhash_hashIChars) +#define uhash_hashLong U_ICU_ENTRY_POINT_RENAME(uhash_hashLong) +#define uhash_hashScriptSet U_ICU_ENTRY_POINT_RENAME(uhash_hashScriptSet) +#define uhash_hashUChars U_ICU_ENTRY_POINT_RENAME(uhash_hashUChars) +#define uhash_hashUnicodeString U_ICU_ENTRY_POINT_RENAME(uhash_hashUnicodeString) +#define uhash_iget U_ICU_ENTRY_POINT_RENAME(uhash_iget) +#define uhash_igeti U_ICU_ENTRY_POINT_RENAME(uhash_igeti) +#define uhash_init U_ICU_ENTRY_POINT_RENAME(uhash_init) +#define uhash_initSize U_ICU_ENTRY_POINT_RENAME(uhash_initSize) +#define uhash_iput U_ICU_ENTRY_POINT_RENAME(uhash_iput) +#define uhash_iputi U_ICU_ENTRY_POINT_RENAME(uhash_iputi) +#define uhash_iremove U_ICU_ENTRY_POINT_RENAME(uhash_iremove) +#define uhash_iremovei U_ICU_ENTRY_POINT_RENAME(uhash_iremovei) +#define uhash_nextElement U_ICU_ENTRY_POINT_RENAME(uhash_nextElement) +#define uhash_open U_ICU_ENTRY_POINT_RENAME(uhash_open) +#define uhash_openSize U_ICU_ENTRY_POINT_RENAME(uhash_openSize) +#define uhash_put U_ICU_ENTRY_POINT_RENAME(uhash_put) +#define uhash_puti U_ICU_ENTRY_POINT_RENAME(uhash_puti) +#define uhash_remove U_ICU_ENTRY_POINT_RENAME(uhash_remove) +#define uhash_removeAll U_ICU_ENTRY_POINT_RENAME(uhash_removeAll) +#define uhash_removeElement U_ICU_ENTRY_POINT_RENAME(uhash_removeElement) +#define uhash_removei U_ICU_ENTRY_POINT_RENAME(uhash_removei) +#define uhash_setKeyComparator U_ICU_ENTRY_POINT_RENAME(uhash_setKeyComparator) +#define uhash_setKeyDeleter U_ICU_ENTRY_POINT_RENAME(uhash_setKeyDeleter) +#define uhash_setKeyHasher U_ICU_ENTRY_POINT_RENAME(uhash_setKeyHasher) +#define uhash_setResizePolicy U_ICU_ENTRY_POINT_RENAME(uhash_setResizePolicy) +#define uhash_setValueComparator U_ICU_ENTRY_POINT_RENAME(uhash_setValueComparator) +#define uhash_setValueDeleter U_ICU_ENTRY_POINT_RENAME(uhash_setValueDeleter) +#define uidna_IDNToASCII U_ICU_ENTRY_POINT_RENAME(uidna_IDNToASCII) +#define uidna_IDNToUnicode U_ICU_ENTRY_POINT_RENAME(uidna_IDNToUnicode) +#define uidna_close U_ICU_ENTRY_POINT_RENAME(uidna_close) +#define uidna_compare U_ICU_ENTRY_POINT_RENAME(uidna_compare) +#define uidna_labelToASCII U_ICU_ENTRY_POINT_RENAME(uidna_labelToASCII) +#define uidna_labelToASCII_UTF8 U_ICU_ENTRY_POINT_RENAME(uidna_labelToASCII_UTF8) +#define uidna_labelToUnicode U_ICU_ENTRY_POINT_RENAME(uidna_labelToUnicode) +#define uidna_labelToUnicodeUTF8 U_ICU_ENTRY_POINT_RENAME(uidna_labelToUnicodeUTF8) +#define uidna_nameToASCII U_ICU_ENTRY_POINT_RENAME(uidna_nameToASCII) +#define uidna_nameToASCII_UTF8 U_ICU_ENTRY_POINT_RENAME(uidna_nameToASCII_UTF8) +#define uidna_nameToUnicode U_ICU_ENTRY_POINT_RENAME(uidna_nameToUnicode) +#define uidna_nameToUnicodeUTF8 U_ICU_ENTRY_POINT_RENAME(uidna_nameToUnicodeUTF8) +#define uidna_openUTS46 U_ICU_ENTRY_POINT_RENAME(uidna_openUTS46) +#define uidna_toASCII U_ICU_ENTRY_POINT_RENAME(uidna_toASCII) +#define uidna_toUnicode U_ICU_ENTRY_POINT_RENAME(uidna_toUnicode) +#define uiter_current32 U_ICU_ENTRY_POINT_RENAME(uiter_current32) +#define uiter_getState U_ICU_ENTRY_POINT_RENAME(uiter_getState) +#define uiter_next32 U_ICU_ENTRY_POINT_RENAME(uiter_next32) +#define uiter_previous32 U_ICU_ENTRY_POINT_RENAME(uiter_previous32) +#define uiter_setCharacterIterator U_ICU_ENTRY_POINT_RENAME(uiter_setCharacterIterator) +#define uiter_setReplaceable U_ICU_ENTRY_POINT_RENAME(uiter_setReplaceable) +#define uiter_setState U_ICU_ENTRY_POINT_RENAME(uiter_setState) +#define uiter_setString U_ICU_ENTRY_POINT_RENAME(uiter_setString) +#define uiter_setUTF16BE U_ICU_ENTRY_POINT_RENAME(uiter_setUTF16BE) +#define uiter_setUTF8 U_ICU_ENTRY_POINT_RENAME(uiter_setUTF8) +#define uldn_close U_ICU_ENTRY_POINT_RENAME(uldn_close) +#define uldn_getContext U_ICU_ENTRY_POINT_RENAME(uldn_getContext) +#define uldn_getDialectHandling U_ICU_ENTRY_POINT_RENAME(uldn_getDialectHandling) +#define uldn_getLocale U_ICU_ENTRY_POINT_RENAME(uldn_getLocale) +#define uldn_keyDisplayName U_ICU_ENTRY_POINT_RENAME(uldn_keyDisplayName) +#define uldn_keyValueDisplayName U_ICU_ENTRY_POINT_RENAME(uldn_keyValueDisplayName) +#define uldn_languageDisplayName U_ICU_ENTRY_POINT_RENAME(uldn_languageDisplayName) +#define uldn_localeDisplayName U_ICU_ENTRY_POINT_RENAME(uldn_localeDisplayName) +#define uldn_open U_ICU_ENTRY_POINT_RENAME(uldn_open) +#define uldn_openForContext U_ICU_ENTRY_POINT_RENAME(uldn_openForContext) +#define uldn_regionDisplayName U_ICU_ENTRY_POINT_RENAME(uldn_regionDisplayName) +#define uldn_scriptCodeDisplayName U_ICU_ENTRY_POINT_RENAME(uldn_scriptCodeDisplayName) +#define uldn_scriptDisplayName U_ICU_ENTRY_POINT_RENAME(uldn_scriptDisplayName) +#define uldn_variantDisplayName U_ICU_ENTRY_POINT_RENAME(uldn_variantDisplayName) +#define ulist_addItemBeginList U_ICU_ENTRY_POINT_RENAME(ulist_addItemBeginList) +#define ulist_addItemEndList U_ICU_ENTRY_POINT_RENAME(ulist_addItemEndList) +#define ulist_close_keyword_values_iterator U_ICU_ENTRY_POINT_RENAME(ulist_close_keyword_values_iterator) +#define ulist_containsString U_ICU_ENTRY_POINT_RENAME(ulist_containsString) +#define ulist_count_keyword_values U_ICU_ENTRY_POINT_RENAME(ulist_count_keyword_values) +#define ulist_createEmptyList U_ICU_ENTRY_POINT_RENAME(ulist_createEmptyList) +#define ulist_deleteList U_ICU_ENTRY_POINT_RENAME(ulist_deleteList) +#define ulist_getListFromEnum U_ICU_ENTRY_POINT_RENAME(ulist_getListFromEnum) +#define ulist_getListSize U_ICU_ENTRY_POINT_RENAME(ulist_getListSize) +#define ulist_getNext U_ICU_ENTRY_POINT_RENAME(ulist_getNext) +#define ulist_next_keyword_value U_ICU_ENTRY_POINT_RENAME(ulist_next_keyword_value) +#define ulist_removeString U_ICU_ENTRY_POINT_RENAME(ulist_removeString) +#define ulist_resetList U_ICU_ENTRY_POINT_RENAME(ulist_resetList) +#define ulist_reset_keyword_values_iterator U_ICU_ENTRY_POINT_RENAME(ulist_reset_keyword_values_iterator) +#define ulistfmt_close U_ICU_ENTRY_POINT_RENAME(ulistfmt_close) +#define ulistfmt_closeResult U_ICU_ENTRY_POINT_RENAME(ulistfmt_closeResult) +#define ulistfmt_format U_ICU_ENTRY_POINT_RENAME(ulistfmt_format) +#define ulistfmt_formatStringsToResult U_ICU_ENTRY_POINT_RENAME(ulistfmt_formatStringsToResult) +#define ulistfmt_open U_ICU_ENTRY_POINT_RENAME(ulistfmt_open) +#define ulistfmt_openForType U_ICU_ENTRY_POINT_RENAME(ulistfmt_openForType) +#define ulistfmt_openResult U_ICU_ENTRY_POINT_RENAME(ulistfmt_openResult) +#define ulistfmt_resultAsValue U_ICU_ENTRY_POINT_RENAME(ulistfmt_resultAsValue) +#define uloc_acceptLanguage U_ICU_ENTRY_POINT_RENAME(uloc_acceptLanguage) +#define uloc_acceptLanguageFromHTTP U_ICU_ENTRY_POINT_RENAME(uloc_acceptLanguageFromHTTP) +#define uloc_addLikelySubtags U_ICU_ENTRY_POINT_RENAME(uloc_addLikelySubtags) +#define uloc_canonicalize U_ICU_ENTRY_POINT_RENAME(uloc_canonicalize) +#define uloc_countAvailable U_ICU_ENTRY_POINT_RENAME(uloc_countAvailable) +#define uloc_forLanguageTag U_ICU_ENTRY_POINT_RENAME(uloc_forLanguageTag) +#define uloc_getAvailable U_ICU_ENTRY_POINT_RENAME(uloc_getAvailable) +#define uloc_getBaseName U_ICU_ENTRY_POINT_RENAME(uloc_getBaseName) +#define uloc_getCharacterOrientation U_ICU_ENTRY_POINT_RENAME(uloc_getCharacterOrientation) +#define uloc_getCountry U_ICU_ENTRY_POINT_RENAME(uloc_getCountry) +#define uloc_getCurrentCountryID U_ICU_ENTRY_POINT_RENAME(uloc_getCurrentCountryID) +#define uloc_getCurrentLanguageID U_ICU_ENTRY_POINT_RENAME(uloc_getCurrentLanguageID) +#define uloc_getDefault U_ICU_ENTRY_POINT_RENAME(uloc_getDefault) +#define uloc_getDisplayCountry U_ICU_ENTRY_POINT_RENAME(uloc_getDisplayCountry) +#define uloc_getDisplayKeyword U_ICU_ENTRY_POINT_RENAME(uloc_getDisplayKeyword) +#define uloc_getDisplayKeywordValue U_ICU_ENTRY_POINT_RENAME(uloc_getDisplayKeywordValue) +#define uloc_getDisplayLanguage U_ICU_ENTRY_POINT_RENAME(uloc_getDisplayLanguage) +#define uloc_getDisplayName U_ICU_ENTRY_POINT_RENAME(uloc_getDisplayName) +#define uloc_getDisplayScript U_ICU_ENTRY_POINT_RENAME(uloc_getDisplayScript) +#define uloc_getDisplayVariant U_ICU_ENTRY_POINT_RENAME(uloc_getDisplayVariant) +#define uloc_getISO3Country U_ICU_ENTRY_POINT_RENAME(uloc_getISO3Country) +#define uloc_getISO3Language U_ICU_ENTRY_POINT_RENAME(uloc_getISO3Language) +#define uloc_getISOCountries U_ICU_ENTRY_POINT_RENAME(uloc_getISOCountries) +#define uloc_getISOLanguages U_ICU_ENTRY_POINT_RENAME(uloc_getISOLanguages) +#define uloc_getKeywordValue U_ICU_ENTRY_POINT_RENAME(uloc_getKeywordValue) +#define uloc_getLCID U_ICU_ENTRY_POINT_RENAME(uloc_getLCID) +#define uloc_getLanguage U_ICU_ENTRY_POINT_RENAME(uloc_getLanguage) +#define uloc_getLineOrientation U_ICU_ENTRY_POINT_RENAME(uloc_getLineOrientation) +#define uloc_getLocaleForLCID U_ICU_ENTRY_POINT_RENAME(uloc_getLocaleForLCID) +#define uloc_getName U_ICU_ENTRY_POINT_RENAME(uloc_getName) +#define uloc_getParent U_ICU_ENTRY_POINT_RENAME(uloc_getParent) +#define uloc_getScript U_ICU_ENTRY_POINT_RENAME(uloc_getScript) +#define uloc_getTableStringWithFallback U_ICU_ENTRY_POINT_RENAME(uloc_getTableStringWithFallback) +#define uloc_getVariant U_ICU_ENTRY_POINT_RENAME(uloc_getVariant) +#define uloc_isRightToLeft U_ICU_ENTRY_POINT_RENAME(uloc_isRightToLeft) +#define uloc_minimizeSubtags U_ICU_ENTRY_POINT_RENAME(uloc_minimizeSubtags) +#define uloc_openAvailableByType U_ICU_ENTRY_POINT_RENAME(uloc_openAvailableByType) +#define uloc_openKeywordList U_ICU_ENTRY_POINT_RENAME(uloc_openKeywordList) +#define uloc_openKeywords U_ICU_ENTRY_POINT_RENAME(uloc_openKeywords) +#define uloc_setDefault U_ICU_ENTRY_POINT_RENAME(uloc_setDefault) +#define uloc_setKeywordValue U_ICU_ENTRY_POINT_RENAME(uloc_setKeywordValue) +#define uloc_toLanguageTag U_ICU_ENTRY_POINT_RENAME(uloc_toLanguageTag) +#define uloc_toLegacyKey U_ICU_ENTRY_POINT_RENAME(uloc_toLegacyKey) +#define uloc_toLegacyType U_ICU_ENTRY_POINT_RENAME(uloc_toLegacyType) +#define uloc_toUnicodeLocaleKey U_ICU_ENTRY_POINT_RENAME(uloc_toUnicodeLocaleKey) +#define uloc_toUnicodeLocaleType U_ICU_ENTRY_POINT_RENAME(uloc_toUnicodeLocaleType) +#define ulocdata_close U_ICU_ENTRY_POINT_RENAME(ulocdata_close) +#define ulocdata_getCLDRVersion U_ICU_ENTRY_POINT_RENAME(ulocdata_getCLDRVersion) +#define ulocdata_getDelimiter U_ICU_ENTRY_POINT_RENAME(ulocdata_getDelimiter) +#define ulocdata_getExemplarSet U_ICU_ENTRY_POINT_RENAME(ulocdata_getExemplarSet) +#define ulocdata_getLocaleDisplayPattern U_ICU_ENTRY_POINT_RENAME(ulocdata_getLocaleDisplayPattern) +#define ulocdata_getLocaleSeparator U_ICU_ENTRY_POINT_RENAME(ulocdata_getLocaleSeparator) +#define ulocdata_getMeasurementSystem U_ICU_ENTRY_POINT_RENAME(ulocdata_getMeasurementSystem) +#define ulocdata_getNoSubstitute U_ICU_ENTRY_POINT_RENAME(ulocdata_getNoSubstitute) +#define ulocdata_getPaperSize U_ICU_ENTRY_POINT_RENAME(ulocdata_getPaperSize) +#define ulocdata_open U_ICU_ENTRY_POINT_RENAME(ulocdata_open) +#define ulocdata_setNoSubstitute U_ICU_ENTRY_POINT_RENAME(ulocdata_setNoSubstitute) +#define ulocimp_addLikelySubtags U_ICU_ENTRY_POINT_RENAME(ulocimp_addLikelySubtags) +#define ulocimp_canonicalize U_ICU_ENTRY_POINT_RENAME(ulocimp_canonicalize) +#define ulocimp_forLanguageTag U_ICU_ENTRY_POINT_RENAME(ulocimp_forLanguageTag) +#define ulocimp_getBaseName U_ICU_ENTRY_POINT_RENAME(ulocimp_getBaseName) +#define ulocimp_getCountry U_ICU_ENTRY_POINT_RENAME(ulocimp_getCountry) +#define ulocimp_getKeywordValue U_ICU_ENTRY_POINT_RENAME(ulocimp_getKeywordValue) +#define ulocimp_getKeywords U_ICU_ENTRY_POINT_RENAME(ulocimp_getKeywords) +#define ulocimp_getKnownCanonicalizedLocaleForTest U_ICU_ENTRY_POINT_RENAME(ulocimp_getKnownCanonicalizedLocaleForTest) +#define ulocimp_getLanguage U_ICU_ENTRY_POINT_RENAME(ulocimp_getLanguage) +#define ulocimp_getName U_ICU_ENTRY_POINT_RENAME(ulocimp_getName) +#define ulocimp_getRegionForSupplementalData U_ICU_ENTRY_POINT_RENAME(ulocimp_getRegionForSupplementalData) +#define ulocimp_getScript U_ICU_ENTRY_POINT_RENAME(ulocimp_getScript) +#define ulocimp_isCanonicalizedLocaleForTest U_ICU_ENTRY_POINT_RENAME(ulocimp_isCanonicalizedLocaleForTest) +#define ulocimp_minimizeSubtags U_ICU_ENTRY_POINT_RENAME(ulocimp_minimizeSubtags) +#define ulocimp_toBcpKey U_ICU_ENTRY_POINT_RENAME(ulocimp_toBcpKey) +#define ulocimp_toBcpType U_ICU_ENTRY_POINT_RENAME(ulocimp_toBcpType) +#define ulocimp_toLanguageTag U_ICU_ENTRY_POINT_RENAME(ulocimp_toLanguageTag) +#define ulocimp_toLegacyKey U_ICU_ENTRY_POINT_RENAME(ulocimp_toLegacyKey) +#define ulocimp_toLegacyType U_ICU_ENTRY_POINT_RENAME(ulocimp_toLegacyType) +#define ultag_isExtensionSubtags U_ICU_ENTRY_POINT_RENAME(ultag_isExtensionSubtags) +#define ultag_isLanguageSubtag U_ICU_ENTRY_POINT_RENAME(ultag_isLanguageSubtag) +#define ultag_isPrivateuseValueSubtags U_ICU_ENTRY_POINT_RENAME(ultag_isPrivateuseValueSubtags) +#define ultag_isRegionSubtag U_ICU_ENTRY_POINT_RENAME(ultag_isRegionSubtag) +#define ultag_isScriptSubtag U_ICU_ENTRY_POINT_RENAME(ultag_isScriptSubtag) +#define ultag_isTransformedExtensionSubtags U_ICU_ENTRY_POINT_RENAME(ultag_isTransformedExtensionSubtags) +#define ultag_isUnicodeExtensionSubtags U_ICU_ENTRY_POINT_RENAME(ultag_isUnicodeExtensionSubtags) +#define ultag_isUnicodeLocaleAttribute U_ICU_ENTRY_POINT_RENAME(ultag_isUnicodeLocaleAttribute) +#define ultag_isUnicodeLocaleAttributes U_ICU_ENTRY_POINT_RENAME(ultag_isUnicodeLocaleAttributes) +#define ultag_isUnicodeLocaleKey U_ICU_ENTRY_POINT_RENAME(ultag_isUnicodeLocaleKey) +#define ultag_isUnicodeLocaleType U_ICU_ENTRY_POINT_RENAME(ultag_isUnicodeLocaleType) +#define ultag_isVariantSubtags U_ICU_ENTRY_POINT_RENAME(ultag_isVariantSubtags) +#define umsg_applyPattern U_ICU_ENTRY_POINT_RENAME(umsg_applyPattern) +#define umsg_autoQuoteApostrophe U_ICU_ENTRY_POINT_RENAME(umsg_autoQuoteApostrophe) +#define umsg_clone U_ICU_ENTRY_POINT_RENAME(umsg_clone) +#define umsg_close U_ICU_ENTRY_POINT_RENAME(umsg_close) +#define umsg_format U_ICU_ENTRY_POINT_RENAME(umsg_format) +#define umsg_getLocale U_ICU_ENTRY_POINT_RENAME(umsg_getLocale) +#define umsg_open U_ICU_ENTRY_POINT_RENAME(umsg_open) +#define umsg_parse U_ICU_ENTRY_POINT_RENAME(umsg_parse) +#define umsg_setLocale U_ICU_ENTRY_POINT_RENAME(umsg_setLocale) +#define umsg_toPattern U_ICU_ENTRY_POINT_RENAME(umsg_toPattern) +#define umsg_vformat U_ICU_ENTRY_POINT_RENAME(umsg_vformat) +#define umsg_vparse U_ICU_ENTRY_POINT_RENAME(umsg_vparse) +#define umtx_lock U_ICU_ENTRY_POINT_RENAME(umtx_lock) +#define umtx_unlock U_ICU_ENTRY_POINT_RENAME(umtx_unlock) +#define umutablecptrie_buildImmutable U_ICU_ENTRY_POINT_RENAME(umutablecptrie_buildImmutable) +#define umutablecptrie_clone U_ICU_ENTRY_POINT_RENAME(umutablecptrie_clone) +#define umutablecptrie_close U_ICU_ENTRY_POINT_RENAME(umutablecptrie_close) +#define umutablecptrie_fromUCPMap U_ICU_ENTRY_POINT_RENAME(umutablecptrie_fromUCPMap) +#define umutablecptrie_fromUCPTrie U_ICU_ENTRY_POINT_RENAME(umutablecptrie_fromUCPTrie) +#define umutablecptrie_get U_ICU_ENTRY_POINT_RENAME(umutablecptrie_get) +#define umutablecptrie_getRange U_ICU_ENTRY_POINT_RENAME(umutablecptrie_getRange) +#define umutablecptrie_open U_ICU_ENTRY_POINT_RENAME(umutablecptrie_open) +#define umutablecptrie_set U_ICU_ENTRY_POINT_RENAME(umutablecptrie_set) +#define umutablecptrie_setRange U_ICU_ENTRY_POINT_RENAME(umutablecptrie_setRange) +#define uniset_getUnicode32Instance U_ICU_ENTRY_POINT_RENAME(uniset_getUnicode32Instance) +#define unorm2_append U_ICU_ENTRY_POINT_RENAME(unorm2_append) +#define unorm2_close U_ICU_ENTRY_POINT_RENAME(unorm2_close) +#define unorm2_composePair U_ICU_ENTRY_POINT_RENAME(unorm2_composePair) +#define unorm2_getCombiningClass U_ICU_ENTRY_POINT_RENAME(unorm2_getCombiningClass) +#define unorm2_getDecomposition U_ICU_ENTRY_POINT_RENAME(unorm2_getDecomposition) +#define unorm2_getInstance U_ICU_ENTRY_POINT_RENAME(unorm2_getInstance) +#define unorm2_getNFCInstance U_ICU_ENTRY_POINT_RENAME(unorm2_getNFCInstance) +#define unorm2_getNFDInstance U_ICU_ENTRY_POINT_RENAME(unorm2_getNFDInstance) +#define unorm2_getNFKCCasefoldInstance U_ICU_ENTRY_POINT_RENAME(unorm2_getNFKCCasefoldInstance) +#define unorm2_getNFKCInstance U_ICU_ENTRY_POINT_RENAME(unorm2_getNFKCInstance) +#define unorm2_getNFKDInstance U_ICU_ENTRY_POINT_RENAME(unorm2_getNFKDInstance) +#define unorm2_getRawDecomposition U_ICU_ENTRY_POINT_RENAME(unorm2_getRawDecomposition) +#define unorm2_hasBoundaryAfter U_ICU_ENTRY_POINT_RENAME(unorm2_hasBoundaryAfter) +#define unorm2_hasBoundaryBefore U_ICU_ENTRY_POINT_RENAME(unorm2_hasBoundaryBefore) +#define unorm2_isInert U_ICU_ENTRY_POINT_RENAME(unorm2_isInert) +#define unorm2_isNormalized U_ICU_ENTRY_POINT_RENAME(unorm2_isNormalized) +#define unorm2_normalize U_ICU_ENTRY_POINT_RENAME(unorm2_normalize) +#define unorm2_normalizeSecondAndAppend U_ICU_ENTRY_POINT_RENAME(unorm2_normalizeSecondAndAppend) +#define unorm2_openFiltered U_ICU_ENTRY_POINT_RENAME(unorm2_openFiltered) +#define unorm2_quickCheck U_ICU_ENTRY_POINT_RENAME(unorm2_quickCheck) +#define unorm2_spanQuickCheckYes U_ICU_ENTRY_POINT_RENAME(unorm2_spanQuickCheckYes) +#define unorm2_swap U_ICU_ENTRY_POINT_RENAME(unorm2_swap) +#define unorm_compare U_ICU_ENTRY_POINT_RENAME(unorm_compare) +#define unorm_concatenate U_ICU_ENTRY_POINT_RENAME(unorm_concatenate) +#define unorm_getFCD16 U_ICU_ENTRY_POINT_RENAME(unorm_getFCD16) +#define unorm_getQuickCheck U_ICU_ENTRY_POINT_RENAME(unorm_getQuickCheck) +#define unorm_isNormalized U_ICU_ENTRY_POINT_RENAME(unorm_isNormalized) +#define unorm_isNormalizedWithOptions U_ICU_ENTRY_POINT_RENAME(unorm_isNormalizedWithOptions) +#define unorm_next U_ICU_ENTRY_POINT_RENAME(unorm_next) +#define unorm_normalize U_ICU_ENTRY_POINT_RENAME(unorm_normalize) +#define unorm_previous U_ICU_ENTRY_POINT_RENAME(unorm_previous) +#define unorm_quickCheck U_ICU_ENTRY_POINT_RENAME(unorm_quickCheck) +#define unorm_quickCheckWithOptions U_ICU_ENTRY_POINT_RENAME(unorm_quickCheckWithOptions) +#define unum_applyPattern U_ICU_ENTRY_POINT_RENAME(unum_applyPattern) +#define unum_clone U_ICU_ENTRY_POINT_RENAME(unum_clone) +#define unum_close U_ICU_ENTRY_POINT_RENAME(unum_close) +#define unum_countAvailable U_ICU_ENTRY_POINT_RENAME(unum_countAvailable) +#define unum_format U_ICU_ENTRY_POINT_RENAME(unum_format) +#define unum_formatDecimal U_ICU_ENTRY_POINT_RENAME(unum_formatDecimal) +#define unum_formatDouble U_ICU_ENTRY_POINT_RENAME(unum_formatDouble) +#define unum_formatDoubleCurrency U_ICU_ENTRY_POINT_RENAME(unum_formatDoubleCurrency) +#define unum_formatDoubleForFields U_ICU_ENTRY_POINT_RENAME(unum_formatDoubleForFields) +#define unum_formatInt64 U_ICU_ENTRY_POINT_RENAME(unum_formatInt64) +#define unum_formatUFormattable U_ICU_ENTRY_POINT_RENAME(unum_formatUFormattable) +#define unum_getAttribute U_ICU_ENTRY_POINT_RENAME(unum_getAttribute) +#define unum_getAvailable U_ICU_ENTRY_POINT_RENAME(unum_getAvailable) +#define unum_getContext U_ICU_ENTRY_POINT_RENAME(unum_getContext) +#define unum_getDoubleAttribute U_ICU_ENTRY_POINT_RENAME(unum_getDoubleAttribute) +#define unum_getLocaleByType U_ICU_ENTRY_POINT_RENAME(unum_getLocaleByType) +#define unum_getSymbol U_ICU_ENTRY_POINT_RENAME(unum_getSymbol) +#define unum_getTextAttribute U_ICU_ENTRY_POINT_RENAME(unum_getTextAttribute) +#define unum_open U_ICU_ENTRY_POINT_RENAME(unum_open) +#define unum_parse U_ICU_ENTRY_POINT_RENAME(unum_parse) +#define unum_parseDecimal U_ICU_ENTRY_POINT_RENAME(unum_parseDecimal) +#define unum_parseDouble U_ICU_ENTRY_POINT_RENAME(unum_parseDouble) +#define unum_parseDoubleCurrency U_ICU_ENTRY_POINT_RENAME(unum_parseDoubleCurrency) +#define unum_parseInt64 U_ICU_ENTRY_POINT_RENAME(unum_parseInt64) +#define unum_parseToUFormattable U_ICU_ENTRY_POINT_RENAME(unum_parseToUFormattable) +#define unum_setAttribute U_ICU_ENTRY_POINT_RENAME(unum_setAttribute) +#define unum_setContext U_ICU_ENTRY_POINT_RENAME(unum_setContext) +#define unum_setDoubleAttribute U_ICU_ENTRY_POINT_RENAME(unum_setDoubleAttribute) +#define unum_setSymbol U_ICU_ENTRY_POINT_RENAME(unum_setSymbol) +#define unum_setTextAttribute U_ICU_ENTRY_POINT_RENAME(unum_setTextAttribute) +#define unum_toPattern U_ICU_ENTRY_POINT_RENAME(unum_toPattern) +#define unumf_close U_ICU_ENTRY_POINT_RENAME(unumf_close) +#define unumf_closeResult U_ICU_ENTRY_POINT_RENAME(unumf_closeResult) +#define unumf_formatDecimal U_ICU_ENTRY_POINT_RENAME(unumf_formatDecimal) +#define unumf_formatDouble U_ICU_ENTRY_POINT_RENAME(unumf_formatDouble) +#define unumf_formatInt U_ICU_ENTRY_POINT_RENAME(unumf_formatInt) +#define unumf_openForSkeletonAndLocale U_ICU_ENTRY_POINT_RENAME(unumf_openForSkeletonAndLocale) +#define unumf_openForSkeletonAndLocaleWithError U_ICU_ENTRY_POINT_RENAME(unumf_openForSkeletonAndLocaleWithError) +#define unumf_openResult U_ICU_ENTRY_POINT_RENAME(unumf_openResult) +#define unumf_resultAsValue U_ICU_ENTRY_POINT_RENAME(unumf_resultAsValue) +#define unumf_resultGetAllFieldPositions U_ICU_ENTRY_POINT_RENAME(unumf_resultGetAllFieldPositions) +#define unumf_resultNextFieldPosition U_ICU_ENTRY_POINT_RENAME(unumf_resultNextFieldPosition) +#define unumf_resultToDecimalNumber U_ICU_ENTRY_POINT_RENAME(unumf_resultToDecimalNumber) +#define unumf_resultToString U_ICU_ENTRY_POINT_RENAME(unumf_resultToString) +#define unumrf_close U_ICU_ENTRY_POINT_RENAME(unumrf_close) +#define unumrf_closeResult U_ICU_ENTRY_POINT_RENAME(unumrf_closeResult) +#define unumrf_formatDecimalRange U_ICU_ENTRY_POINT_RENAME(unumrf_formatDecimalRange) +#define unumrf_formatDoubleRange U_ICU_ENTRY_POINT_RENAME(unumrf_formatDoubleRange) +#define unumrf_openForSkeletonWithCollapseAndIdentityFallback U_ICU_ENTRY_POINT_RENAME(unumrf_openForSkeletonWithCollapseAndIdentityFallback) +#define unumrf_openResult U_ICU_ENTRY_POINT_RENAME(unumrf_openResult) +#define unumrf_resultAsValue U_ICU_ENTRY_POINT_RENAME(unumrf_resultAsValue) +#define unumrf_resultGetFirstDecimalNumber U_ICU_ENTRY_POINT_RENAME(unumrf_resultGetFirstDecimalNumber) +#define unumrf_resultGetIdentityResult U_ICU_ENTRY_POINT_RENAME(unumrf_resultGetIdentityResult) +#define unumrf_resultGetSecondDecimalNumber U_ICU_ENTRY_POINT_RENAME(unumrf_resultGetSecondDecimalNumber) +#define unumsys_close U_ICU_ENTRY_POINT_RENAME(unumsys_close) +#define unumsys_getDescription U_ICU_ENTRY_POINT_RENAME(unumsys_getDescription) +#define unumsys_getName U_ICU_ENTRY_POINT_RENAME(unumsys_getName) +#define unumsys_getRadix U_ICU_ENTRY_POINT_RENAME(unumsys_getRadix) +#define unumsys_isAlgorithmic U_ICU_ENTRY_POINT_RENAME(unumsys_isAlgorithmic) +#define unumsys_open U_ICU_ENTRY_POINT_RENAME(unumsys_open) +#define unumsys_openAvailableNames U_ICU_ENTRY_POINT_RENAME(unumsys_openAvailableNames) +#define unumsys_openByName U_ICU_ENTRY_POINT_RENAME(unumsys_openByName) +#define uplrules_close U_ICU_ENTRY_POINT_RENAME(uplrules_close) +#define uplrules_getKeywords U_ICU_ENTRY_POINT_RENAME(uplrules_getKeywords) +#define uplrules_open U_ICU_ENTRY_POINT_RENAME(uplrules_open) +#define uplrules_openForType U_ICU_ENTRY_POINT_RENAME(uplrules_openForType) +#define uplrules_select U_ICU_ENTRY_POINT_RENAME(uplrules_select) +#define uplrules_selectForRange U_ICU_ENTRY_POINT_RENAME(uplrules_selectForRange) +#define uplrules_selectFormatted U_ICU_ENTRY_POINT_RENAME(uplrules_selectFormatted) +#define uplrules_selectWithFormat U_ICU_ENTRY_POINT_RENAME(uplrules_selectWithFormat) +#define uplug_closeLibrary U_ICU_ENTRY_POINT_RENAME(uplug_closeLibrary) +#define uplug_findLibrary U_ICU_ENTRY_POINT_RENAME(uplug_findLibrary) +#define uplug_getConfiguration U_ICU_ENTRY_POINT_RENAME(uplug_getConfiguration) +#define uplug_getContext U_ICU_ENTRY_POINT_RENAME(uplug_getContext) +#define uplug_getCurrentLevel U_ICU_ENTRY_POINT_RENAME(uplug_getCurrentLevel) +#define uplug_getLibrary U_ICU_ENTRY_POINT_RENAME(uplug_getLibrary) +#define uplug_getLibraryName U_ICU_ENTRY_POINT_RENAME(uplug_getLibraryName) +#define uplug_getPlugInternal U_ICU_ENTRY_POINT_RENAME(uplug_getPlugInternal) +#define uplug_getPlugLevel U_ICU_ENTRY_POINT_RENAME(uplug_getPlugLevel) +#define uplug_getPlugLoadStatus U_ICU_ENTRY_POINT_RENAME(uplug_getPlugLoadStatus) +#define uplug_getPlugName U_ICU_ENTRY_POINT_RENAME(uplug_getPlugName) +#define uplug_getPluginFile U_ICU_ENTRY_POINT_RENAME(uplug_getPluginFile) +#define uplug_getSymbolName U_ICU_ENTRY_POINT_RENAME(uplug_getSymbolName) +#define uplug_init U_ICU_ENTRY_POINT_RENAME(uplug_init) +#define uplug_loadPlugFromEntrypoint U_ICU_ENTRY_POINT_RENAME(uplug_loadPlugFromEntrypoint) +#define uplug_loadPlugFromLibrary U_ICU_ENTRY_POINT_RENAME(uplug_loadPlugFromLibrary) +#define uplug_nextPlug U_ICU_ENTRY_POINT_RENAME(uplug_nextPlug) +#define uplug_openLibrary U_ICU_ENTRY_POINT_RENAME(uplug_openLibrary) +#define uplug_removePlug U_ICU_ENTRY_POINT_RENAME(uplug_removePlug) +#define uplug_setContext U_ICU_ENTRY_POINT_RENAME(uplug_setContext) +#define uplug_setPlugLevel U_ICU_ENTRY_POINT_RENAME(uplug_setPlugLevel) +#define uplug_setPlugName U_ICU_ENTRY_POINT_RENAME(uplug_setPlugName) +#define uplug_setPlugNoUnload U_ICU_ENTRY_POINT_RENAME(uplug_setPlugNoUnload) +#define uprops_addPropertyStarts U_ICU_ENTRY_POINT_RENAME(uprops_addPropertyStarts) +#define uprops_getSource U_ICU_ENTRY_POINT_RENAME(uprops_getSource) +#define upropsvec_addPropertyStarts U_ICU_ENTRY_POINT_RENAME(upropsvec_addPropertyStarts) +#define uprv_add32_overflow U_ICU_ENTRY_POINT_RENAME(uprv_add32_overflow) +#define uprv_aestrncpy U_ICU_ENTRY_POINT_RENAME(uprv_aestrncpy) +#define uprv_asciiFromEbcdic U_ICU_ENTRY_POINT_RENAME(uprv_asciiFromEbcdic) +#define uprv_asciitolower U_ICU_ENTRY_POINT_RENAME(uprv_asciitolower) +#define uprv_calloc U_ICU_ENTRY_POINT_RENAME(uprv_calloc) +#define uprv_ceil U_ICU_ENTRY_POINT_RENAME(uprv_ceil) +#define uprv_compareASCIIPropertyNames U_ICU_ENTRY_POINT_RENAME(uprv_compareASCIIPropertyNames) +#define uprv_compareEBCDICPropertyNames U_ICU_ENTRY_POINT_RENAME(uprv_compareEBCDICPropertyNames) +#define uprv_compareInvAscii U_ICU_ENTRY_POINT_RENAME(uprv_compareInvAscii) +#define uprv_compareInvEbcdic U_ICU_ENTRY_POINT_RENAME(uprv_compareInvEbcdic) +#define uprv_compareInvEbcdicAsAscii U_ICU_ENTRY_POINT_RENAME(uprv_compareInvEbcdicAsAscii) +#define uprv_convertToLCID U_ICU_ENTRY_POINT_RENAME(uprv_convertToLCID) +#define uprv_convertToLCIDPlatform U_ICU_ENTRY_POINT_RENAME(uprv_convertToLCIDPlatform) +#define uprv_convertToPosix U_ICU_ENTRY_POINT_RENAME(uprv_convertToPosix) +#define uprv_copyAscii U_ICU_ENTRY_POINT_RENAME(uprv_copyAscii) +#define uprv_copyEbcdic U_ICU_ENTRY_POINT_RENAME(uprv_copyEbcdic) +#define uprv_decContextClearStatus U_ICU_ENTRY_POINT_RENAME(uprv_decContextClearStatus) +#define uprv_decContextDefault U_ICU_ENTRY_POINT_RENAME(uprv_decContextDefault) +#define uprv_decContextGetRounding U_ICU_ENTRY_POINT_RENAME(uprv_decContextGetRounding) +#define uprv_decContextGetStatus U_ICU_ENTRY_POINT_RENAME(uprv_decContextGetStatus) +#define uprv_decContextRestoreStatus U_ICU_ENTRY_POINT_RENAME(uprv_decContextRestoreStatus) +#define uprv_decContextSaveStatus U_ICU_ENTRY_POINT_RENAME(uprv_decContextSaveStatus) +#define uprv_decContextSetRounding U_ICU_ENTRY_POINT_RENAME(uprv_decContextSetRounding) +#define uprv_decContextSetStatus U_ICU_ENTRY_POINT_RENAME(uprv_decContextSetStatus) +#define uprv_decContextSetStatusFromString U_ICU_ENTRY_POINT_RENAME(uprv_decContextSetStatusFromString) +#define uprv_decContextSetStatusFromStringQuiet U_ICU_ENTRY_POINT_RENAME(uprv_decContextSetStatusFromStringQuiet) +#define uprv_decContextSetStatusQuiet U_ICU_ENTRY_POINT_RENAME(uprv_decContextSetStatusQuiet) +#define uprv_decContextStatusToString U_ICU_ENTRY_POINT_RENAME(uprv_decContextStatusToString) +#define uprv_decContextTestSavedStatus U_ICU_ENTRY_POINT_RENAME(uprv_decContextTestSavedStatus) +#define uprv_decContextTestStatus U_ICU_ENTRY_POINT_RENAME(uprv_decContextTestStatus) +#define uprv_decContextZeroStatus U_ICU_ENTRY_POINT_RENAME(uprv_decContextZeroStatus) +#define uprv_decNumberAbs U_ICU_ENTRY_POINT_RENAME(uprv_decNumberAbs) +#define uprv_decNumberAdd U_ICU_ENTRY_POINT_RENAME(uprv_decNumberAdd) +#define uprv_decNumberAnd U_ICU_ENTRY_POINT_RENAME(uprv_decNumberAnd) +#define uprv_decNumberClassToString U_ICU_ENTRY_POINT_RENAME(uprv_decNumberClassToString) +#define uprv_decNumberCompare U_ICU_ENTRY_POINT_RENAME(uprv_decNumberCompare) +#define uprv_decNumberCompareSignal U_ICU_ENTRY_POINT_RENAME(uprv_decNumberCompareSignal) +#define uprv_decNumberCompareTotal U_ICU_ENTRY_POINT_RENAME(uprv_decNumberCompareTotal) +#define uprv_decNumberCompareTotalMag U_ICU_ENTRY_POINT_RENAME(uprv_decNumberCompareTotalMag) +#define uprv_decNumberCopy U_ICU_ENTRY_POINT_RENAME(uprv_decNumberCopy) +#define uprv_decNumberCopyAbs U_ICU_ENTRY_POINT_RENAME(uprv_decNumberCopyAbs) +#define uprv_decNumberCopyNegate U_ICU_ENTRY_POINT_RENAME(uprv_decNumberCopyNegate) +#define uprv_decNumberCopySign U_ICU_ENTRY_POINT_RENAME(uprv_decNumberCopySign) +#define uprv_decNumberDivide U_ICU_ENTRY_POINT_RENAME(uprv_decNumberDivide) +#define uprv_decNumberDivideInteger U_ICU_ENTRY_POINT_RENAME(uprv_decNumberDivideInteger) +#define uprv_decNumberExp U_ICU_ENTRY_POINT_RENAME(uprv_decNumberExp) +#define uprv_decNumberFMA U_ICU_ENTRY_POINT_RENAME(uprv_decNumberFMA) +#define uprv_decNumberFromInt32 U_ICU_ENTRY_POINT_RENAME(uprv_decNumberFromInt32) +#define uprv_decNumberFromString U_ICU_ENTRY_POINT_RENAME(uprv_decNumberFromString) +#define uprv_decNumberFromUInt32 U_ICU_ENTRY_POINT_RENAME(uprv_decNumberFromUInt32) +#define uprv_decNumberGetBCD U_ICU_ENTRY_POINT_RENAME(uprv_decNumberGetBCD) +#define uprv_decNumberInvert U_ICU_ENTRY_POINT_RENAME(uprv_decNumberInvert) +#define uprv_decNumberIsNormal U_ICU_ENTRY_POINT_RENAME(uprv_decNumberIsNormal) +#define uprv_decNumberIsSubnormal U_ICU_ENTRY_POINT_RENAME(uprv_decNumberIsSubnormal) +#define uprv_decNumberLn U_ICU_ENTRY_POINT_RENAME(uprv_decNumberLn) +#define uprv_decNumberLog10 U_ICU_ENTRY_POINT_RENAME(uprv_decNumberLog10) +#define uprv_decNumberLogB U_ICU_ENTRY_POINT_RENAME(uprv_decNumberLogB) +#define uprv_decNumberMax U_ICU_ENTRY_POINT_RENAME(uprv_decNumberMax) +#define uprv_decNumberMaxMag U_ICU_ENTRY_POINT_RENAME(uprv_decNumberMaxMag) +#define uprv_decNumberMin U_ICU_ENTRY_POINT_RENAME(uprv_decNumberMin) +#define uprv_decNumberMinMag U_ICU_ENTRY_POINT_RENAME(uprv_decNumberMinMag) +#define uprv_decNumberMinus U_ICU_ENTRY_POINT_RENAME(uprv_decNumberMinus) +#define uprv_decNumberMultiply U_ICU_ENTRY_POINT_RENAME(uprv_decNumberMultiply) +#define uprv_decNumberNextMinus U_ICU_ENTRY_POINT_RENAME(uprv_decNumberNextMinus) +#define uprv_decNumberNextPlus U_ICU_ENTRY_POINT_RENAME(uprv_decNumberNextPlus) +#define uprv_decNumberNextToward U_ICU_ENTRY_POINT_RENAME(uprv_decNumberNextToward) +#define uprv_decNumberNormalize U_ICU_ENTRY_POINT_RENAME(uprv_decNumberNormalize) +#define uprv_decNumberOr U_ICU_ENTRY_POINT_RENAME(uprv_decNumberOr) +#define uprv_decNumberPlus U_ICU_ENTRY_POINT_RENAME(uprv_decNumberPlus) +#define uprv_decNumberPower U_ICU_ENTRY_POINT_RENAME(uprv_decNumberPower) +#define uprv_decNumberQuantize U_ICU_ENTRY_POINT_RENAME(uprv_decNumberQuantize) +#define uprv_decNumberReduce U_ICU_ENTRY_POINT_RENAME(uprv_decNumberReduce) +#define uprv_decNumberRemainder U_ICU_ENTRY_POINT_RENAME(uprv_decNumberRemainder) +#define uprv_decNumberRemainderNear U_ICU_ENTRY_POINT_RENAME(uprv_decNumberRemainderNear) +#define uprv_decNumberRescale U_ICU_ENTRY_POINT_RENAME(uprv_decNumberRescale) +#define uprv_decNumberRotate U_ICU_ENTRY_POINT_RENAME(uprv_decNumberRotate) +#define uprv_decNumberSameQuantum U_ICU_ENTRY_POINT_RENAME(uprv_decNumberSameQuantum) +#define uprv_decNumberScaleB U_ICU_ENTRY_POINT_RENAME(uprv_decNumberScaleB) +#define uprv_decNumberSetBCD U_ICU_ENTRY_POINT_RENAME(uprv_decNumberSetBCD) +#define uprv_decNumberShift U_ICU_ENTRY_POINT_RENAME(uprv_decNumberShift) +#define uprv_decNumberSquareRoot U_ICU_ENTRY_POINT_RENAME(uprv_decNumberSquareRoot) +#define uprv_decNumberSubtract U_ICU_ENTRY_POINT_RENAME(uprv_decNumberSubtract) +#define uprv_decNumberToEngString U_ICU_ENTRY_POINT_RENAME(uprv_decNumberToEngString) +#define uprv_decNumberToInt32 U_ICU_ENTRY_POINT_RENAME(uprv_decNumberToInt32) +#define uprv_decNumberToIntegralExact U_ICU_ENTRY_POINT_RENAME(uprv_decNumberToIntegralExact) +#define uprv_decNumberToIntegralValue U_ICU_ENTRY_POINT_RENAME(uprv_decNumberToIntegralValue) +#define uprv_decNumberToString U_ICU_ENTRY_POINT_RENAME(uprv_decNumberToString) +#define uprv_decNumberToUInt32 U_ICU_ENTRY_POINT_RENAME(uprv_decNumberToUInt32) +#define uprv_decNumberTrim U_ICU_ENTRY_POINT_RENAME(uprv_decNumberTrim) +#define uprv_decNumberVersion U_ICU_ENTRY_POINT_RENAME(uprv_decNumberVersion) +#define uprv_decNumberXor U_ICU_ENTRY_POINT_RENAME(uprv_decNumberXor) +#define uprv_decNumberZero U_ICU_ENTRY_POINT_RENAME(uprv_decNumberZero) +#define uprv_deleteConditionalCE32 U_ICU_ENTRY_POINT_RENAME(uprv_deleteConditionalCE32) +#define uprv_deleteUObject U_ICU_ENTRY_POINT_RENAME(uprv_deleteUObject) +#define uprv_dl_close U_ICU_ENTRY_POINT_RENAME(uprv_dl_close) +#define uprv_dl_open U_ICU_ENTRY_POINT_RENAME(uprv_dl_open) +#define uprv_dlsym_func U_ICU_ENTRY_POINT_RENAME(uprv_dlsym_func) +#define uprv_eastrncpy U_ICU_ENTRY_POINT_RENAME(uprv_eastrncpy) +#define uprv_ebcdicFromAscii U_ICU_ENTRY_POINT_RENAME(uprv_ebcdicFromAscii) +#define uprv_ebcdicToAscii U_ICU_ENTRY_POINT_RENAME(uprv_ebcdicToAscii) +#define uprv_ebcdicToLowercaseAscii U_ICU_ENTRY_POINT_RENAME(uprv_ebcdicToLowercaseAscii) +#define uprv_ebcdictolower U_ICU_ENTRY_POINT_RENAME(uprv_ebcdictolower) +#define uprv_fabs U_ICU_ENTRY_POINT_RENAME(uprv_fabs) +#define uprv_floor U_ICU_ENTRY_POINT_RENAME(uprv_floor) +#define uprv_fmax U_ICU_ENTRY_POINT_RENAME(uprv_fmax) +#define uprv_fmin U_ICU_ENTRY_POINT_RENAME(uprv_fmin) +#define uprv_fmod U_ICU_ENTRY_POINT_RENAME(uprv_fmod) +#define uprv_free U_ICU_ENTRY_POINT_RENAME(uprv_free) +#define uprv_getCharNameCharacters U_ICU_ENTRY_POINT_RENAME(uprv_getCharNameCharacters) +#define uprv_getDefaultLocaleID U_ICU_ENTRY_POINT_RENAME(uprv_getDefaultLocaleID) +#define uprv_getInfinity U_ICU_ENTRY_POINT_RENAME(uprv_getInfinity) +#define uprv_getMaxCharNameLength U_ICU_ENTRY_POINT_RENAME(uprv_getMaxCharNameLength) +#define uprv_getMaxValues U_ICU_ENTRY_POINT_RENAME(uprv_getMaxValues) +#define uprv_getNaN U_ICU_ENTRY_POINT_RENAME(uprv_getNaN) +#define uprv_getRawUTCtime U_ICU_ENTRY_POINT_RENAME(uprv_getRawUTCtime) +#define uprv_getStaticCurrencyName U_ICU_ENTRY_POINT_RENAME(uprv_getStaticCurrencyName) +#define uprv_getUTCtime U_ICU_ENTRY_POINT_RENAME(uprv_getUTCtime) +#define uprv_int32Comparator U_ICU_ENTRY_POINT_RENAME(uprv_int32Comparator) +#define uprv_isASCIILetter U_ICU_ENTRY_POINT_RENAME(uprv_isASCIILetter) +#define uprv_isEbcdicAtSign U_ICU_ENTRY_POINT_RENAME(uprv_isEbcdicAtSign) +#define uprv_isInfinite U_ICU_ENTRY_POINT_RENAME(uprv_isInfinite) +#define uprv_isInvariantString U_ICU_ENTRY_POINT_RENAME(uprv_isInvariantString) +#define uprv_isInvariantUString U_ICU_ENTRY_POINT_RENAME(uprv_isInvariantUString) +#define uprv_isNaN U_ICU_ENTRY_POINT_RENAME(uprv_isNaN) +#define uprv_isNegativeInfinity U_ICU_ENTRY_POINT_RENAME(uprv_isNegativeInfinity) +#define uprv_isPositiveInfinity U_ICU_ENTRY_POINT_RENAME(uprv_isPositiveInfinity) +#define uprv_itou U_ICU_ENTRY_POINT_RENAME(uprv_itou) +#define uprv_log U_ICU_ENTRY_POINT_RENAME(uprv_log) +#define uprv_malloc U_ICU_ENTRY_POINT_RENAME(uprv_malloc) +#define uprv_mapFile U_ICU_ENTRY_POINT_RENAME(uprv_mapFile) +#define uprv_max U_ICU_ENTRY_POINT_RENAME(uprv_max) +#define uprv_maxMantissa U_ICU_ENTRY_POINT_RENAME(uprv_maxMantissa) +#define uprv_maximumPtr U_ICU_ENTRY_POINT_RENAME(uprv_maximumPtr) +#define uprv_min U_ICU_ENTRY_POINT_RENAME(uprv_min) +#define uprv_modf U_ICU_ENTRY_POINT_RENAME(uprv_modf) +#define uprv_mul32_overflow U_ICU_ENTRY_POINT_RENAME(uprv_mul32_overflow) +#define uprv_parseCurrency U_ICU_ENTRY_POINT_RENAME(uprv_parseCurrency) +#define uprv_pathIsAbsolute U_ICU_ENTRY_POINT_RENAME(uprv_pathIsAbsolute) +#define uprv_pow U_ICU_ENTRY_POINT_RENAME(uprv_pow) +#define uprv_pow10 U_ICU_ENTRY_POINT_RENAME(uprv_pow10) +#define uprv_realloc U_ICU_ENTRY_POINT_RENAME(uprv_realloc) +#define uprv_round U_ICU_ENTRY_POINT_RENAME(uprv_round) +#define uprv_sortArray U_ICU_ENTRY_POINT_RENAME(uprv_sortArray) +#define uprv_stableBinarySearch U_ICU_ENTRY_POINT_RENAME(uprv_stableBinarySearch) +#define uprv_strCompare U_ICU_ENTRY_POINT_RENAME(uprv_strCompare) +#define uprv_strdup U_ICU_ENTRY_POINT_RENAME(uprv_strdup) +#define uprv_stricmp U_ICU_ENTRY_POINT_RENAME(uprv_stricmp) +#define uprv_strndup U_ICU_ENTRY_POINT_RENAME(uprv_strndup) +#define uprv_strnicmp U_ICU_ENTRY_POINT_RENAME(uprv_strnicmp) +#define uprv_syntaxError U_ICU_ENTRY_POINT_RENAME(uprv_syntaxError) +#define uprv_timezone U_ICU_ENTRY_POINT_RENAME(uprv_timezone) +#define uprv_toupper U_ICU_ENTRY_POINT_RENAME(uprv_toupper) +#define uprv_trunc U_ICU_ENTRY_POINT_RENAME(uprv_trunc) +#define uprv_tzname U_ICU_ENTRY_POINT_RENAME(uprv_tzname) +#define uprv_tzname_clear_cache U_ICU_ENTRY_POINT_RENAME(uprv_tzname_clear_cache) +#define uprv_tzset U_ICU_ENTRY_POINT_RENAME(uprv_tzset) +#define uprv_uint16Comparator U_ICU_ENTRY_POINT_RENAME(uprv_uint16Comparator) +#define uprv_uint32Comparator U_ICU_ENTRY_POINT_RENAME(uprv_uint32Comparator) +#define uprv_unmapFile U_ICU_ENTRY_POINT_RENAME(uprv_unmapFile) +#define upvec_cloneArray U_ICU_ENTRY_POINT_RENAME(upvec_cloneArray) +#define upvec_close U_ICU_ENTRY_POINT_RENAME(upvec_close) +#define upvec_compact U_ICU_ENTRY_POINT_RENAME(upvec_compact) +#define upvec_compactToUTrie2Handler U_ICU_ENTRY_POINT_RENAME(upvec_compactToUTrie2Handler) +#define upvec_compactToUTrie2WithRowIndexes U_ICU_ENTRY_POINT_RENAME(upvec_compactToUTrie2WithRowIndexes) +#define upvec_getArray U_ICU_ENTRY_POINT_RENAME(upvec_getArray) +#define upvec_getRow U_ICU_ENTRY_POINT_RENAME(upvec_getRow) +#define upvec_getValue U_ICU_ENTRY_POINT_RENAME(upvec_getValue) +#define upvec_open U_ICU_ENTRY_POINT_RENAME(upvec_open) +#define upvec_setValue U_ICU_ENTRY_POINT_RENAME(upvec_setValue) +#define uregex_appendReplacement U_ICU_ENTRY_POINT_RENAME(uregex_appendReplacement) +#define uregex_appendReplacementUText U_ICU_ENTRY_POINT_RENAME(uregex_appendReplacementUText) +#define uregex_appendTail U_ICU_ENTRY_POINT_RENAME(uregex_appendTail) +#define uregex_appendTailUText U_ICU_ENTRY_POINT_RENAME(uregex_appendTailUText) +#define uregex_clone U_ICU_ENTRY_POINT_RENAME(uregex_clone) +#define uregex_close U_ICU_ENTRY_POINT_RENAME(uregex_close) +#define uregex_end U_ICU_ENTRY_POINT_RENAME(uregex_end) +#define uregex_end64 U_ICU_ENTRY_POINT_RENAME(uregex_end64) +#define uregex_find U_ICU_ENTRY_POINT_RENAME(uregex_find) +#define uregex_find64 U_ICU_ENTRY_POINT_RENAME(uregex_find64) +#define uregex_findNext U_ICU_ENTRY_POINT_RENAME(uregex_findNext) +#define uregex_flags U_ICU_ENTRY_POINT_RENAME(uregex_flags) +#define uregex_getFindProgressCallback U_ICU_ENTRY_POINT_RENAME(uregex_getFindProgressCallback) +#define uregex_getMatchCallback U_ICU_ENTRY_POINT_RENAME(uregex_getMatchCallback) +#define uregex_getStackLimit U_ICU_ENTRY_POINT_RENAME(uregex_getStackLimit) +#define uregex_getText U_ICU_ENTRY_POINT_RENAME(uregex_getText) +#define uregex_getTimeLimit U_ICU_ENTRY_POINT_RENAME(uregex_getTimeLimit) +#define uregex_getUText U_ICU_ENTRY_POINT_RENAME(uregex_getUText) +#define uregex_group U_ICU_ENTRY_POINT_RENAME(uregex_group) +#define uregex_groupCount U_ICU_ENTRY_POINT_RENAME(uregex_groupCount) +#define uregex_groupNumberFromCName U_ICU_ENTRY_POINT_RENAME(uregex_groupNumberFromCName) +#define uregex_groupNumberFromName U_ICU_ENTRY_POINT_RENAME(uregex_groupNumberFromName) +#define uregex_groupUText U_ICU_ENTRY_POINT_RENAME(uregex_groupUText) +#define uregex_hasAnchoringBounds U_ICU_ENTRY_POINT_RENAME(uregex_hasAnchoringBounds) +#define uregex_hasTransparentBounds U_ICU_ENTRY_POINT_RENAME(uregex_hasTransparentBounds) +#define uregex_hitEnd U_ICU_ENTRY_POINT_RENAME(uregex_hitEnd) +#define uregex_lookingAt U_ICU_ENTRY_POINT_RENAME(uregex_lookingAt) +#define uregex_lookingAt64 U_ICU_ENTRY_POINT_RENAME(uregex_lookingAt64) +#define uregex_matches U_ICU_ENTRY_POINT_RENAME(uregex_matches) +#define uregex_matches64 U_ICU_ENTRY_POINT_RENAME(uregex_matches64) +#define uregex_open U_ICU_ENTRY_POINT_RENAME(uregex_open) +#define uregex_openC U_ICU_ENTRY_POINT_RENAME(uregex_openC) +#define uregex_openUText U_ICU_ENTRY_POINT_RENAME(uregex_openUText) +#define uregex_pattern U_ICU_ENTRY_POINT_RENAME(uregex_pattern) +#define uregex_patternUText U_ICU_ENTRY_POINT_RENAME(uregex_patternUText) +#define uregex_refreshUText U_ICU_ENTRY_POINT_RENAME(uregex_refreshUText) +#define uregex_regionEnd U_ICU_ENTRY_POINT_RENAME(uregex_regionEnd) +#define uregex_regionEnd64 U_ICU_ENTRY_POINT_RENAME(uregex_regionEnd64) +#define uregex_regionStart U_ICU_ENTRY_POINT_RENAME(uregex_regionStart) +#define uregex_regionStart64 U_ICU_ENTRY_POINT_RENAME(uregex_regionStart64) +#define uregex_replaceAll U_ICU_ENTRY_POINT_RENAME(uregex_replaceAll) +#define uregex_replaceAllUText U_ICU_ENTRY_POINT_RENAME(uregex_replaceAllUText) +#define uregex_replaceFirst U_ICU_ENTRY_POINT_RENAME(uregex_replaceFirst) +#define uregex_replaceFirstUText U_ICU_ENTRY_POINT_RENAME(uregex_replaceFirstUText) +#define uregex_requireEnd U_ICU_ENTRY_POINT_RENAME(uregex_requireEnd) +#define uregex_reset U_ICU_ENTRY_POINT_RENAME(uregex_reset) +#define uregex_reset64 U_ICU_ENTRY_POINT_RENAME(uregex_reset64) +#define uregex_setFindProgressCallback U_ICU_ENTRY_POINT_RENAME(uregex_setFindProgressCallback) +#define uregex_setMatchCallback U_ICU_ENTRY_POINT_RENAME(uregex_setMatchCallback) +#define uregex_setRegion U_ICU_ENTRY_POINT_RENAME(uregex_setRegion) +#define uregex_setRegion64 U_ICU_ENTRY_POINT_RENAME(uregex_setRegion64) +#define uregex_setRegionAndStart U_ICU_ENTRY_POINT_RENAME(uregex_setRegionAndStart) +#define uregex_setStackLimit U_ICU_ENTRY_POINT_RENAME(uregex_setStackLimit) +#define uregex_setText U_ICU_ENTRY_POINT_RENAME(uregex_setText) +#define uregex_setTimeLimit U_ICU_ENTRY_POINT_RENAME(uregex_setTimeLimit) +#define uregex_setUText U_ICU_ENTRY_POINT_RENAME(uregex_setUText) +#define uregex_split U_ICU_ENTRY_POINT_RENAME(uregex_split) +#define uregex_splitUText U_ICU_ENTRY_POINT_RENAME(uregex_splitUText) +#define uregex_start U_ICU_ENTRY_POINT_RENAME(uregex_start) +#define uregex_start64 U_ICU_ENTRY_POINT_RENAME(uregex_start64) +#define uregex_ucstr_unescape_charAt U_ICU_ENTRY_POINT_RENAME(uregex_ucstr_unescape_charAt) +#define uregex_useAnchoringBounds U_ICU_ENTRY_POINT_RENAME(uregex_useAnchoringBounds) +#define uregex_useTransparentBounds U_ICU_ENTRY_POINT_RENAME(uregex_useTransparentBounds) +#define uregex_utext_unescape_charAt U_ICU_ENTRY_POINT_RENAME(uregex_utext_unescape_charAt) +#define uregion_areEqual U_ICU_ENTRY_POINT_RENAME(uregion_areEqual) +#define uregion_contains U_ICU_ENTRY_POINT_RENAME(uregion_contains) +#define uregion_getAvailable U_ICU_ENTRY_POINT_RENAME(uregion_getAvailable) +#define uregion_getContainedRegions U_ICU_ENTRY_POINT_RENAME(uregion_getContainedRegions) +#define uregion_getContainedRegionsOfType U_ICU_ENTRY_POINT_RENAME(uregion_getContainedRegionsOfType) +#define uregion_getContainingRegion U_ICU_ENTRY_POINT_RENAME(uregion_getContainingRegion) +#define uregion_getContainingRegionOfType U_ICU_ENTRY_POINT_RENAME(uregion_getContainingRegionOfType) +#define uregion_getNumericCode U_ICU_ENTRY_POINT_RENAME(uregion_getNumericCode) +#define uregion_getPreferredValues U_ICU_ENTRY_POINT_RENAME(uregion_getPreferredValues) +#define uregion_getRegionCode U_ICU_ENTRY_POINT_RENAME(uregion_getRegionCode) +#define uregion_getRegionFromCode U_ICU_ENTRY_POINT_RENAME(uregion_getRegionFromCode) +#define uregion_getRegionFromNumericCode U_ICU_ENTRY_POINT_RENAME(uregion_getRegionFromNumericCode) +#define uregion_getType U_ICU_ENTRY_POINT_RENAME(uregion_getType) +#define ureldatefmt_close U_ICU_ENTRY_POINT_RENAME(ureldatefmt_close) +#define ureldatefmt_closeResult U_ICU_ENTRY_POINT_RENAME(ureldatefmt_closeResult) +#define ureldatefmt_combineDateAndTime U_ICU_ENTRY_POINT_RENAME(ureldatefmt_combineDateAndTime) +#define ureldatefmt_format U_ICU_ENTRY_POINT_RENAME(ureldatefmt_format) +#define ureldatefmt_formatNumeric U_ICU_ENTRY_POINT_RENAME(ureldatefmt_formatNumeric) +#define ureldatefmt_formatNumericToResult U_ICU_ENTRY_POINT_RENAME(ureldatefmt_formatNumericToResult) +#define ureldatefmt_formatToResult U_ICU_ENTRY_POINT_RENAME(ureldatefmt_formatToResult) +#define ureldatefmt_open U_ICU_ENTRY_POINT_RENAME(ureldatefmt_open) +#define ureldatefmt_openResult U_ICU_ENTRY_POINT_RENAME(ureldatefmt_openResult) +#define ureldatefmt_resultAsValue U_ICU_ENTRY_POINT_RENAME(ureldatefmt_resultAsValue) +#define ures_close U_ICU_ENTRY_POINT_RENAME(ures_close) +#define ures_copyResb U_ICU_ENTRY_POINT_RENAME(ures_copyResb) +#define ures_countArrayItems U_ICU_ENTRY_POINT_RENAME(ures_countArrayItems) +#define ures_findResource U_ICU_ENTRY_POINT_RENAME(ures_findResource) +#define ures_findSubResource U_ICU_ENTRY_POINT_RENAME(ures_findSubResource) +#define ures_getAllItemsWithFallback U_ICU_ENTRY_POINT_RENAME(ures_getAllItemsWithFallback) +#define ures_getBinary U_ICU_ENTRY_POINT_RENAME(ures_getBinary) +#define ures_getByIndex U_ICU_ENTRY_POINT_RENAME(ures_getByIndex) +#define ures_getByKey U_ICU_ENTRY_POINT_RENAME(ures_getByKey) +#define ures_getByKeyWithFallback U_ICU_ENTRY_POINT_RENAME(ures_getByKeyWithFallback) +#define ures_getFunctionalEquivalent U_ICU_ENTRY_POINT_RENAME(ures_getFunctionalEquivalent) +#define ures_getInt U_ICU_ENTRY_POINT_RENAME(ures_getInt) +#define ures_getIntVector U_ICU_ENTRY_POINT_RENAME(ures_getIntVector) +#define ures_getKey U_ICU_ENTRY_POINT_RENAME(ures_getKey) +#define ures_getKeywordValues U_ICU_ENTRY_POINT_RENAME(ures_getKeywordValues) +#define ures_getLocale U_ICU_ENTRY_POINT_RENAME(ures_getLocale) +#define ures_getLocaleByType U_ICU_ENTRY_POINT_RENAME(ures_getLocaleByType) +#define ures_getLocaleInternal U_ICU_ENTRY_POINT_RENAME(ures_getLocaleInternal) +#define ures_getName U_ICU_ENTRY_POINT_RENAME(ures_getName) +#define ures_getNextResource U_ICU_ENTRY_POINT_RENAME(ures_getNextResource) +#define ures_getNextString U_ICU_ENTRY_POINT_RENAME(ures_getNextString) +#define ures_getSize U_ICU_ENTRY_POINT_RENAME(ures_getSize) +#define ures_getString U_ICU_ENTRY_POINT_RENAME(ures_getString) +#define ures_getStringByIndex U_ICU_ENTRY_POINT_RENAME(ures_getStringByIndex) +#define ures_getStringByKey U_ICU_ENTRY_POINT_RENAME(ures_getStringByKey) +#define ures_getStringByKeyWithFallback U_ICU_ENTRY_POINT_RENAME(ures_getStringByKeyWithFallback) +#define ures_getType U_ICU_ENTRY_POINT_RENAME(ures_getType) +#define ures_getUInt U_ICU_ENTRY_POINT_RENAME(ures_getUInt) +#define ures_getUTF8String U_ICU_ENTRY_POINT_RENAME(ures_getUTF8String) +#define ures_getUTF8StringByIndex U_ICU_ENTRY_POINT_RENAME(ures_getUTF8StringByIndex) +#define ures_getUTF8StringByKey U_ICU_ENTRY_POINT_RENAME(ures_getUTF8StringByKey) +#define ures_getValueWithFallback U_ICU_ENTRY_POINT_RENAME(ures_getValueWithFallback) +#define ures_getVersion U_ICU_ENTRY_POINT_RENAME(ures_getVersion) +#define ures_getVersionByKey U_ICU_ENTRY_POINT_RENAME(ures_getVersionByKey) +#define ures_getVersionNumber U_ICU_ENTRY_POINT_RENAME(ures_getVersionNumber) +#define ures_getVersionNumberInternal U_ICU_ENTRY_POINT_RENAME(ures_getVersionNumberInternal) +#define ures_hasNext U_ICU_ENTRY_POINT_RENAME(ures_hasNext) +#define ures_initStackObject U_ICU_ENTRY_POINT_RENAME(ures_initStackObject) +#define ures_open U_ICU_ENTRY_POINT_RENAME(ures_open) +#define ures_openAvailableLocales U_ICU_ENTRY_POINT_RENAME(ures_openAvailableLocales) +#define ures_openDirect U_ICU_ENTRY_POINT_RENAME(ures_openDirect) +#define ures_openDirectFillIn U_ICU_ENTRY_POINT_RENAME(ures_openDirectFillIn) +#define ures_openFillIn U_ICU_ENTRY_POINT_RENAME(ures_openFillIn) +#define ures_openNoDefault U_ICU_ENTRY_POINT_RENAME(ures_openNoDefault) +#define ures_openU U_ICU_ENTRY_POINT_RENAME(ures_openU) +#define ures_resetIterator U_ICU_ENTRY_POINT_RENAME(ures_resetIterator) +#define ures_swap U_ICU_ENTRY_POINT_RENAME(ures_swap) +#define uscript_breaksBetweenLetters U_ICU_ENTRY_POINT_RENAME(uscript_breaksBetweenLetters) +#define uscript_closeRun U_ICU_ENTRY_POINT_RENAME(uscript_closeRun) +#define uscript_getCode U_ICU_ENTRY_POINT_RENAME(uscript_getCode) +#define uscript_getName U_ICU_ENTRY_POINT_RENAME(uscript_getName) +#define uscript_getSampleString U_ICU_ENTRY_POINT_RENAME(uscript_getSampleString) +#define uscript_getSampleUnicodeString U_ICU_ENTRY_POINT_RENAME(uscript_getSampleUnicodeString) +#define uscript_getScript U_ICU_ENTRY_POINT_RENAME(uscript_getScript) +#define uscript_getScriptExtensions U_ICU_ENTRY_POINT_RENAME(uscript_getScriptExtensions) +#define uscript_getShortName U_ICU_ENTRY_POINT_RENAME(uscript_getShortName) +#define uscript_getUsage U_ICU_ENTRY_POINT_RENAME(uscript_getUsage) +#define uscript_hasScript U_ICU_ENTRY_POINT_RENAME(uscript_hasScript) +#define uscript_isCased U_ICU_ENTRY_POINT_RENAME(uscript_isCased) +#define uscript_isRightToLeft U_ICU_ENTRY_POINT_RENAME(uscript_isRightToLeft) +#define uscript_nextRun U_ICU_ENTRY_POINT_RENAME(uscript_nextRun) +#define uscript_openRun U_ICU_ENTRY_POINT_RENAME(uscript_openRun) +#define uscript_resetRun U_ICU_ENTRY_POINT_RENAME(uscript_resetRun) +#define uscript_setRunText U_ICU_ENTRY_POINT_RENAME(uscript_setRunText) +#define usearch_close U_ICU_ENTRY_POINT_RENAME(usearch_close) +#define usearch_first U_ICU_ENTRY_POINT_RENAME(usearch_first) +#define usearch_following U_ICU_ENTRY_POINT_RENAME(usearch_following) +#define usearch_getAttribute U_ICU_ENTRY_POINT_RENAME(usearch_getAttribute) +#define usearch_getBreakIterator U_ICU_ENTRY_POINT_RENAME(usearch_getBreakIterator) +#define usearch_getCollator U_ICU_ENTRY_POINT_RENAME(usearch_getCollator) +#define usearch_getMatchedLength U_ICU_ENTRY_POINT_RENAME(usearch_getMatchedLength) +#define usearch_getMatchedStart U_ICU_ENTRY_POINT_RENAME(usearch_getMatchedStart) +#define usearch_getMatchedText U_ICU_ENTRY_POINT_RENAME(usearch_getMatchedText) +#define usearch_getOffset U_ICU_ENTRY_POINT_RENAME(usearch_getOffset) +#define usearch_getPattern U_ICU_ENTRY_POINT_RENAME(usearch_getPattern) +#define usearch_getText U_ICU_ENTRY_POINT_RENAME(usearch_getText) +#define usearch_handleNextCanonical U_ICU_ENTRY_POINT_RENAME(usearch_handleNextCanonical) +#define usearch_handleNextExact U_ICU_ENTRY_POINT_RENAME(usearch_handleNextExact) +#define usearch_handlePreviousCanonical U_ICU_ENTRY_POINT_RENAME(usearch_handlePreviousCanonical) +#define usearch_handlePreviousExact U_ICU_ENTRY_POINT_RENAME(usearch_handlePreviousExact) +#define usearch_last U_ICU_ENTRY_POINT_RENAME(usearch_last) +#define usearch_next U_ICU_ENTRY_POINT_RENAME(usearch_next) +#define usearch_open U_ICU_ENTRY_POINT_RENAME(usearch_open) +#define usearch_openFromCollator U_ICU_ENTRY_POINT_RENAME(usearch_openFromCollator) +#define usearch_preceding U_ICU_ENTRY_POINT_RENAME(usearch_preceding) +#define usearch_previous U_ICU_ENTRY_POINT_RENAME(usearch_previous) +#define usearch_reset U_ICU_ENTRY_POINT_RENAME(usearch_reset) +#define usearch_search U_ICU_ENTRY_POINT_RENAME(usearch_search) +#define usearch_searchBackwards U_ICU_ENTRY_POINT_RENAME(usearch_searchBackwards) +#define usearch_setAttribute U_ICU_ENTRY_POINT_RENAME(usearch_setAttribute) +#define usearch_setBreakIterator U_ICU_ENTRY_POINT_RENAME(usearch_setBreakIterator) +#define usearch_setCollator U_ICU_ENTRY_POINT_RENAME(usearch_setCollator) +#define usearch_setOffset U_ICU_ENTRY_POINT_RENAME(usearch_setOffset) +#define usearch_setPattern U_ICU_ENTRY_POINT_RENAME(usearch_setPattern) +#define usearch_setText U_ICU_ENTRY_POINT_RENAME(usearch_setText) +#define uset_add U_ICU_ENTRY_POINT_RENAME(uset_add) +#define uset_addAll U_ICU_ENTRY_POINT_RENAME(uset_addAll) +#define uset_addAllCodePoints U_ICU_ENTRY_POINT_RENAME(uset_addAllCodePoints) +#define uset_addRange U_ICU_ENTRY_POINT_RENAME(uset_addRange) +#define uset_addString U_ICU_ENTRY_POINT_RENAME(uset_addString) +#define uset_applyIntPropertyValue U_ICU_ENTRY_POINT_RENAME(uset_applyIntPropertyValue) +#define uset_applyPattern U_ICU_ENTRY_POINT_RENAME(uset_applyPattern) +#define uset_applyPropertyAlias U_ICU_ENTRY_POINT_RENAME(uset_applyPropertyAlias) +#define uset_charAt U_ICU_ENTRY_POINT_RENAME(uset_charAt) +#define uset_clear U_ICU_ENTRY_POINT_RENAME(uset_clear) +#define uset_clone U_ICU_ENTRY_POINT_RENAME(uset_clone) +#define uset_cloneAsThawed U_ICU_ENTRY_POINT_RENAME(uset_cloneAsThawed) +#define uset_close U_ICU_ENTRY_POINT_RENAME(uset_close) +#define uset_closeOver U_ICU_ENTRY_POINT_RENAME(uset_closeOver) +#define uset_compact U_ICU_ENTRY_POINT_RENAME(uset_compact) +#define uset_complement U_ICU_ENTRY_POINT_RENAME(uset_complement) +#define uset_complementAll U_ICU_ENTRY_POINT_RENAME(uset_complementAll) +#define uset_contains U_ICU_ENTRY_POINT_RENAME(uset_contains) +#define uset_containsAll U_ICU_ENTRY_POINT_RENAME(uset_containsAll) +#define uset_containsAllCodePoints U_ICU_ENTRY_POINT_RENAME(uset_containsAllCodePoints) +#define uset_containsNone U_ICU_ENTRY_POINT_RENAME(uset_containsNone) +#define uset_containsRange U_ICU_ENTRY_POINT_RENAME(uset_containsRange) +#define uset_containsSome U_ICU_ENTRY_POINT_RENAME(uset_containsSome) +#define uset_containsString U_ICU_ENTRY_POINT_RENAME(uset_containsString) +#define uset_equals U_ICU_ENTRY_POINT_RENAME(uset_equals) +#define uset_freeze U_ICU_ENTRY_POINT_RENAME(uset_freeze) +#define uset_getItem U_ICU_ENTRY_POINT_RENAME(uset_getItem) +#define uset_getItemCount U_ICU_ENTRY_POINT_RENAME(uset_getItemCount) +#define uset_getSerializedRange U_ICU_ENTRY_POINT_RENAME(uset_getSerializedRange) +#define uset_getSerializedRangeCount U_ICU_ENTRY_POINT_RENAME(uset_getSerializedRangeCount) +#define uset_getSerializedSet U_ICU_ENTRY_POINT_RENAME(uset_getSerializedSet) +#define uset_indexOf U_ICU_ENTRY_POINT_RENAME(uset_indexOf) +#define uset_isEmpty U_ICU_ENTRY_POINT_RENAME(uset_isEmpty) +#define uset_isFrozen U_ICU_ENTRY_POINT_RENAME(uset_isFrozen) +#define uset_open U_ICU_ENTRY_POINT_RENAME(uset_open) +#define uset_openEmpty U_ICU_ENTRY_POINT_RENAME(uset_openEmpty) +#define uset_openPattern U_ICU_ENTRY_POINT_RENAME(uset_openPattern) +#define uset_openPatternOptions U_ICU_ENTRY_POINT_RENAME(uset_openPatternOptions) +#define uset_remove U_ICU_ENTRY_POINT_RENAME(uset_remove) +#define uset_removeAll U_ICU_ENTRY_POINT_RENAME(uset_removeAll) +#define uset_removeAllStrings U_ICU_ENTRY_POINT_RENAME(uset_removeAllStrings) +#define uset_removeRange U_ICU_ENTRY_POINT_RENAME(uset_removeRange) +#define uset_removeString U_ICU_ENTRY_POINT_RENAME(uset_removeString) +#define uset_resemblesPattern U_ICU_ENTRY_POINT_RENAME(uset_resemblesPattern) +#define uset_retain U_ICU_ENTRY_POINT_RENAME(uset_retain) +#define uset_retainAll U_ICU_ENTRY_POINT_RENAME(uset_retainAll) +#define uset_serialize U_ICU_ENTRY_POINT_RENAME(uset_serialize) +#define uset_serializedContains U_ICU_ENTRY_POINT_RENAME(uset_serializedContains) +#define uset_set U_ICU_ENTRY_POINT_RENAME(uset_set) +#define uset_setSerializedToOne U_ICU_ENTRY_POINT_RENAME(uset_setSerializedToOne) +#define uset_size U_ICU_ENTRY_POINT_RENAME(uset_size) +#define uset_span U_ICU_ENTRY_POINT_RENAME(uset_span) +#define uset_spanBack U_ICU_ENTRY_POINT_RENAME(uset_spanBack) +#define uset_spanBackUTF8 U_ICU_ENTRY_POINT_RENAME(uset_spanBackUTF8) +#define uset_spanUTF8 U_ICU_ENTRY_POINT_RENAME(uset_spanUTF8) +#define uset_toPattern U_ICU_ENTRY_POINT_RENAME(uset_toPattern) +#define uspoof_areConfusable U_ICU_ENTRY_POINT_RENAME(uspoof_areConfusable) +#define uspoof_areConfusableUTF8 U_ICU_ENTRY_POINT_RENAME(uspoof_areConfusableUTF8) +#define uspoof_areConfusableUnicodeString U_ICU_ENTRY_POINT_RENAME(uspoof_areConfusableUnicodeString) +#define uspoof_check U_ICU_ENTRY_POINT_RENAME(uspoof_check) +#define uspoof_check2 U_ICU_ENTRY_POINT_RENAME(uspoof_check2) +#define uspoof_check2UTF8 U_ICU_ENTRY_POINT_RENAME(uspoof_check2UTF8) +#define uspoof_check2UnicodeString U_ICU_ENTRY_POINT_RENAME(uspoof_check2UnicodeString) +#define uspoof_checkUTF8 U_ICU_ENTRY_POINT_RENAME(uspoof_checkUTF8) +#define uspoof_checkUnicodeString U_ICU_ENTRY_POINT_RENAME(uspoof_checkUnicodeString) +#define uspoof_clone U_ICU_ENTRY_POINT_RENAME(uspoof_clone) +#define uspoof_close U_ICU_ENTRY_POINT_RENAME(uspoof_close) +#define uspoof_closeCheckResult U_ICU_ENTRY_POINT_RENAME(uspoof_closeCheckResult) +#define uspoof_getAllowedChars U_ICU_ENTRY_POINT_RENAME(uspoof_getAllowedChars) +#define uspoof_getAllowedLocales U_ICU_ENTRY_POINT_RENAME(uspoof_getAllowedLocales) +#define uspoof_getAllowedUnicodeSet U_ICU_ENTRY_POINT_RENAME(uspoof_getAllowedUnicodeSet) +#define uspoof_getCheckResultChecks U_ICU_ENTRY_POINT_RENAME(uspoof_getCheckResultChecks) +#define uspoof_getCheckResultNumerics U_ICU_ENTRY_POINT_RENAME(uspoof_getCheckResultNumerics) +#define uspoof_getCheckResultRestrictionLevel U_ICU_ENTRY_POINT_RENAME(uspoof_getCheckResultRestrictionLevel) +#define uspoof_getChecks U_ICU_ENTRY_POINT_RENAME(uspoof_getChecks) +#define uspoof_getInclusionSet U_ICU_ENTRY_POINT_RENAME(uspoof_getInclusionSet) +#define uspoof_getInclusionUnicodeSet U_ICU_ENTRY_POINT_RENAME(uspoof_getInclusionUnicodeSet) +#define uspoof_getRecommendedSet U_ICU_ENTRY_POINT_RENAME(uspoof_getRecommendedSet) +#define uspoof_getRecommendedUnicodeSet U_ICU_ENTRY_POINT_RENAME(uspoof_getRecommendedUnicodeSet) +#define uspoof_getRestrictionLevel U_ICU_ENTRY_POINT_RENAME(uspoof_getRestrictionLevel) +#define uspoof_getSkeleton U_ICU_ENTRY_POINT_RENAME(uspoof_getSkeleton) +#define uspoof_getSkeletonUTF8 U_ICU_ENTRY_POINT_RENAME(uspoof_getSkeletonUTF8) +#define uspoof_getSkeletonUnicodeString U_ICU_ENTRY_POINT_RENAME(uspoof_getSkeletonUnicodeString) +#define uspoof_internalInitStatics U_ICU_ENTRY_POINT_RENAME(uspoof_internalInitStatics) +#define uspoof_open U_ICU_ENTRY_POINT_RENAME(uspoof_open) +#define uspoof_openCheckResult U_ICU_ENTRY_POINT_RENAME(uspoof_openCheckResult) +#define uspoof_openFromSerialized U_ICU_ENTRY_POINT_RENAME(uspoof_openFromSerialized) +#define uspoof_openFromSource U_ICU_ENTRY_POINT_RENAME(uspoof_openFromSource) +#define uspoof_serialize U_ICU_ENTRY_POINT_RENAME(uspoof_serialize) +#define uspoof_setAllowedChars U_ICU_ENTRY_POINT_RENAME(uspoof_setAllowedChars) +#define uspoof_setAllowedLocales U_ICU_ENTRY_POINT_RENAME(uspoof_setAllowedLocales) +#define uspoof_setAllowedUnicodeSet U_ICU_ENTRY_POINT_RENAME(uspoof_setAllowedUnicodeSet) +#define uspoof_setChecks U_ICU_ENTRY_POINT_RENAME(uspoof_setChecks) +#define uspoof_setRestrictionLevel U_ICU_ENTRY_POINT_RENAME(uspoof_setRestrictionLevel) +#define uspoof_swap U_ICU_ENTRY_POINT_RENAME(uspoof_swap) +#define usprep_close U_ICU_ENTRY_POINT_RENAME(usprep_close) +#define usprep_open U_ICU_ENTRY_POINT_RENAME(usprep_open) +#define usprep_openByType U_ICU_ENTRY_POINT_RENAME(usprep_openByType) +#define usprep_prepare U_ICU_ENTRY_POINT_RENAME(usprep_prepare) +#define usprep_swap U_ICU_ENTRY_POINT_RENAME(usprep_swap) +#define ustr_hashCharsN U_ICU_ENTRY_POINT_RENAME(ustr_hashCharsN) +#define ustr_hashICharsN U_ICU_ENTRY_POINT_RENAME(ustr_hashICharsN) +#define ustr_hashUCharsN U_ICU_ENTRY_POINT_RENAME(ustr_hashUCharsN) +#define ustrcase_getCaseLocale U_ICU_ENTRY_POINT_RENAME(ustrcase_getCaseLocale) +#define ustrcase_getTitleBreakIterator U_ICU_ENTRY_POINT_RENAME(ustrcase_getTitleBreakIterator) +#define ustrcase_internalFold U_ICU_ENTRY_POINT_RENAME(ustrcase_internalFold) +#define ustrcase_internalToLower U_ICU_ENTRY_POINT_RENAME(ustrcase_internalToLower) +#define ustrcase_internalToTitle U_ICU_ENTRY_POINT_RENAME(ustrcase_internalToTitle) +#define ustrcase_internalToUpper U_ICU_ENTRY_POINT_RENAME(ustrcase_internalToUpper) +#define ustrcase_map U_ICU_ENTRY_POINT_RENAME(ustrcase_map) +#define ustrcase_mapWithOverlap U_ICU_ENTRY_POINT_RENAME(ustrcase_mapWithOverlap) +#define utext_char32At U_ICU_ENTRY_POINT_RENAME(utext_char32At) +#define utext_clone U_ICU_ENTRY_POINT_RENAME(utext_clone) +#define utext_close U_ICU_ENTRY_POINT_RENAME(utext_close) +#define utext_copy U_ICU_ENTRY_POINT_RENAME(utext_copy) +#define utext_current32 U_ICU_ENTRY_POINT_RENAME(utext_current32) +#define utext_equals U_ICU_ENTRY_POINT_RENAME(utext_equals) +#define utext_extract U_ICU_ENTRY_POINT_RENAME(utext_extract) +#define utext_freeze U_ICU_ENTRY_POINT_RENAME(utext_freeze) +#define utext_getNativeIndex U_ICU_ENTRY_POINT_RENAME(utext_getNativeIndex) +#define utext_getPreviousNativeIndex U_ICU_ENTRY_POINT_RENAME(utext_getPreviousNativeIndex) +#define utext_hasMetaData U_ICU_ENTRY_POINT_RENAME(utext_hasMetaData) +#define utext_isLengthExpensive U_ICU_ENTRY_POINT_RENAME(utext_isLengthExpensive) +#define utext_isWritable U_ICU_ENTRY_POINT_RENAME(utext_isWritable) +#define utext_moveIndex32 U_ICU_ENTRY_POINT_RENAME(utext_moveIndex32) +#define utext_nativeLength U_ICU_ENTRY_POINT_RENAME(utext_nativeLength) +#define utext_next32 U_ICU_ENTRY_POINT_RENAME(utext_next32) +#define utext_next32From U_ICU_ENTRY_POINT_RENAME(utext_next32From) +#define utext_openCharacterIterator U_ICU_ENTRY_POINT_RENAME(utext_openCharacterIterator) +#define utext_openConstUnicodeString U_ICU_ENTRY_POINT_RENAME(utext_openConstUnicodeString) +#define utext_openReplaceable U_ICU_ENTRY_POINT_RENAME(utext_openReplaceable) +#define utext_openUChars U_ICU_ENTRY_POINT_RENAME(utext_openUChars) +#define utext_openUTF8 U_ICU_ENTRY_POINT_RENAME(utext_openUTF8) +#define utext_openUnicodeString U_ICU_ENTRY_POINT_RENAME(utext_openUnicodeString) +#define utext_previous32 U_ICU_ENTRY_POINT_RENAME(utext_previous32) +#define utext_previous32From U_ICU_ENTRY_POINT_RENAME(utext_previous32From) +#define utext_replace U_ICU_ENTRY_POINT_RENAME(utext_replace) +#define utext_setNativeIndex U_ICU_ENTRY_POINT_RENAME(utext_setNativeIndex) +#define utext_setup U_ICU_ENTRY_POINT_RENAME(utext_setup) +#define utf8_appendCharSafeBody U_ICU_ENTRY_POINT_RENAME(utf8_appendCharSafeBody) +#define utf8_back1SafeBody U_ICU_ENTRY_POINT_RENAME(utf8_back1SafeBody) +#define utf8_countTrailBytes U_ICU_ENTRY_POINT_RENAME(utf8_countTrailBytes) +#define utf8_nextCharSafeBody U_ICU_ENTRY_POINT_RENAME(utf8_nextCharSafeBody) +#define utf8_prevCharSafeBody U_ICU_ENTRY_POINT_RENAME(utf8_prevCharSafeBody) +#define utmscale_fromInt64 U_ICU_ENTRY_POINT_RENAME(utmscale_fromInt64) +#define utmscale_getTimeScaleValue U_ICU_ENTRY_POINT_RENAME(utmscale_getTimeScaleValue) +#define utmscale_toInt64 U_ICU_ENTRY_POINT_RENAME(utmscale_toInt64) +#define utrace_cleanup U_ICU_ENTRY_POINT_RENAME(utrace_cleanup) +#define utrace_data U_ICU_ENTRY_POINT_RENAME(utrace_data) +#define utrace_entry U_ICU_ENTRY_POINT_RENAME(utrace_entry) +#define utrace_exit U_ICU_ENTRY_POINT_RENAME(utrace_exit) +#define utrace_format U_ICU_ENTRY_POINT_RENAME(utrace_format) +#define utrace_functionName U_ICU_ENTRY_POINT_RENAME(utrace_functionName) +#define utrace_getFunctions U_ICU_ENTRY_POINT_RENAME(utrace_getFunctions) +#define utrace_getLevel U_ICU_ENTRY_POINT_RENAME(utrace_getLevel) +#define utrace_setFunctions U_ICU_ENTRY_POINT_RENAME(utrace_setFunctions) +#define utrace_setLevel U_ICU_ENTRY_POINT_RENAME(utrace_setLevel) +#define utrace_vformat U_ICU_ENTRY_POINT_RENAME(utrace_vformat) +#define utrans_clone U_ICU_ENTRY_POINT_RENAME(utrans_clone) +#define utrans_close U_ICU_ENTRY_POINT_RENAME(utrans_close) +#define utrans_countAvailableIDs U_ICU_ENTRY_POINT_RENAME(utrans_countAvailableIDs) +#define utrans_getAvailableID U_ICU_ENTRY_POINT_RENAME(utrans_getAvailableID) +#define utrans_getID U_ICU_ENTRY_POINT_RENAME(utrans_getID) +#define utrans_getSourceSet U_ICU_ENTRY_POINT_RENAME(utrans_getSourceSet) +#define utrans_getUnicodeID U_ICU_ENTRY_POINT_RENAME(utrans_getUnicodeID) +#define utrans_open U_ICU_ENTRY_POINT_RENAME(utrans_open) +#define utrans_openIDs U_ICU_ENTRY_POINT_RENAME(utrans_openIDs) +#define utrans_openInverse U_ICU_ENTRY_POINT_RENAME(utrans_openInverse) +#define utrans_openU U_ICU_ENTRY_POINT_RENAME(utrans_openU) +#define utrans_register U_ICU_ENTRY_POINT_RENAME(utrans_register) +#define utrans_rep_caseContextIterator U_ICU_ENTRY_POINT_RENAME(utrans_rep_caseContextIterator) +#define utrans_setFilter U_ICU_ENTRY_POINT_RENAME(utrans_setFilter) +#define utrans_stripRules U_ICU_ENTRY_POINT_RENAME(utrans_stripRules) +#define utrans_toRules U_ICU_ENTRY_POINT_RENAME(utrans_toRules) +#define utrans_trans U_ICU_ENTRY_POINT_RENAME(utrans_trans) +#define utrans_transIncremental U_ICU_ENTRY_POINT_RENAME(utrans_transIncremental) +#define utrans_transIncrementalUChars U_ICU_ENTRY_POINT_RENAME(utrans_transIncrementalUChars) +#define utrans_transUChars U_ICU_ENTRY_POINT_RENAME(utrans_transUChars) +#define utrans_transliterator_cleanup U_ICU_ENTRY_POINT_RENAME(utrans_transliterator_cleanup) +#define utrans_unregister U_ICU_ENTRY_POINT_RENAME(utrans_unregister) +#define utrans_unregisterID U_ICU_ENTRY_POINT_RENAME(utrans_unregisterID) +#define utrie2_clone U_ICU_ENTRY_POINT_RENAME(utrie2_clone) +#define utrie2_cloneAsThawed U_ICU_ENTRY_POINT_RENAME(utrie2_cloneAsThawed) +#define utrie2_close U_ICU_ENTRY_POINT_RENAME(utrie2_close) +#define utrie2_enum U_ICU_ENTRY_POINT_RENAME(utrie2_enum) +#define utrie2_enumForLeadSurrogate U_ICU_ENTRY_POINT_RENAME(utrie2_enumForLeadSurrogate) +#define utrie2_freeze U_ICU_ENTRY_POINT_RENAME(utrie2_freeze) +#define utrie2_fromUTrie U_ICU_ENTRY_POINT_RENAME(utrie2_fromUTrie) +#define utrie2_get32 U_ICU_ENTRY_POINT_RENAME(utrie2_get32) +#define utrie2_get32FromLeadSurrogateCodeUnit U_ICU_ENTRY_POINT_RENAME(utrie2_get32FromLeadSurrogateCodeUnit) +#define utrie2_internalU8NextIndex U_ICU_ENTRY_POINT_RENAME(utrie2_internalU8NextIndex) +#define utrie2_internalU8PrevIndex U_ICU_ENTRY_POINT_RENAME(utrie2_internalU8PrevIndex) +#define utrie2_isFrozen U_ICU_ENTRY_POINT_RENAME(utrie2_isFrozen) +#define utrie2_open U_ICU_ENTRY_POINT_RENAME(utrie2_open) +#define utrie2_openDummy U_ICU_ENTRY_POINT_RENAME(utrie2_openDummy) +#define utrie2_openFromSerialized U_ICU_ENTRY_POINT_RENAME(utrie2_openFromSerialized) +#define utrie2_serialize U_ICU_ENTRY_POINT_RENAME(utrie2_serialize) +#define utrie2_set32 U_ICU_ENTRY_POINT_RENAME(utrie2_set32) +#define utrie2_set32ForLeadSurrogateCodeUnit U_ICU_ENTRY_POINT_RENAME(utrie2_set32ForLeadSurrogateCodeUnit) +#define utrie2_setRange32 U_ICU_ENTRY_POINT_RENAME(utrie2_setRange32) +#define utrie2_swap U_ICU_ENTRY_POINT_RENAME(utrie2_swap) +#define utrie_clone U_ICU_ENTRY_POINT_RENAME(utrie_clone) +#define utrie_close U_ICU_ENTRY_POINT_RENAME(utrie_close) +#define utrie_defaultGetFoldingOffset U_ICU_ENTRY_POINT_RENAME(utrie_defaultGetFoldingOffset) +#define utrie_enum U_ICU_ENTRY_POINT_RENAME(utrie_enum) +#define utrie_get32 U_ICU_ENTRY_POINT_RENAME(utrie_get32) +#define utrie_getData U_ICU_ENTRY_POINT_RENAME(utrie_getData) +#define utrie_open U_ICU_ENTRY_POINT_RENAME(utrie_open) +#define utrie_serialize U_ICU_ENTRY_POINT_RENAME(utrie_serialize) +#define utrie_set32 U_ICU_ENTRY_POINT_RENAME(utrie_set32) +#define utrie_setRange32 U_ICU_ENTRY_POINT_RENAME(utrie_setRange32) +#define utrie_swap U_ICU_ENTRY_POINT_RENAME(utrie_swap) +#define utrie_swapAnyVersion U_ICU_ENTRY_POINT_RENAME(utrie_swapAnyVersion) +#define utrie_unserialize U_ICU_ENTRY_POINT_RENAME(utrie_unserialize) +#define utrie_unserializeDummy U_ICU_ENTRY_POINT_RENAME(utrie_unserializeDummy) +#define vzone_clone U_ICU_ENTRY_POINT_RENAME(vzone_clone) +#define vzone_close U_ICU_ENTRY_POINT_RENAME(vzone_close) +#define vzone_countTransitionRules U_ICU_ENTRY_POINT_RENAME(vzone_countTransitionRules) +#define vzone_equals U_ICU_ENTRY_POINT_RENAME(vzone_equals) +#define vzone_getDynamicClassID U_ICU_ENTRY_POINT_RENAME(vzone_getDynamicClassID) +#define vzone_getLastModified U_ICU_ENTRY_POINT_RENAME(vzone_getLastModified) +#define vzone_getNextTransition U_ICU_ENTRY_POINT_RENAME(vzone_getNextTransition) +#define vzone_getOffset U_ICU_ENTRY_POINT_RENAME(vzone_getOffset) +#define vzone_getOffset2 U_ICU_ENTRY_POINT_RENAME(vzone_getOffset2) +#define vzone_getOffset3 U_ICU_ENTRY_POINT_RENAME(vzone_getOffset3) +#define vzone_getPreviousTransition U_ICU_ENTRY_POINT_RENAME(vzone_getPreviousTransition) +#define vzone_getRawOffset U_ICU_ENTRY_POINT_RENAME(vzone_getRawOffset) +#define vzone_getStaticClassID U_ICU_ENTRY_POINT_RENAME(vzone_getStaticClassID) +#define vzone_getTZURL U_ICU_ENTRY_POINT_RENAME(vzone_getTZURL) +#define vzone_hasSameRules U_ICU_ENTRY_POINT_RENAME(vzone_hasSameRules) +#define vzone_inDaylightTime U_ICU_ENTRY_POINT_RENAME(vzone_inDaylightTime) +#define vzone_openData U_ICU_ENTRY_POINT_RENAME(vzone_openData) +#define vzone_openID U_ICU_ENTRY_POINT_RENAME(vzone_openID) +#define vzone_setLastModified U_ICU_ENTRY_POINT_RENAME(vzone_setLastModified) +#define vzone_setRawOffset U_ICU_ENTRY_POINT_RENAME(vzone_setRawOffset) +#define vzone_setTZURL U_ICU_ENTRY_POINT_RENAME(vzone_setTZURL) +#define vzone_useDaylightTime U_ICU_ENTRY_POINT_RENAME(vzone_useDaylightTime) +#define vzone_write U_ICU_ENTRY_POINT_RENAME(vzone_write) +#define vzone_writeFromStart U_ICU_ENTRY_POINT_RENAME(vzone_writeFromStart) +#define vzone_writeSimple U_ICU_ENTRY_POINT_RENAME(vzone_writeSimple) +#define zrule_close U_ICU_ENTRY_POINT_RENAME(zrule_close) +#define zrule_equals U_ICU_ENTRY_POINT_RENAME(zrule_equals) +#define zrule_getDSTSavings U_ICU_ENTRY_POINT_RENAME(zrule_getDSTSavings) +#define zrule_getName U_ICU_ENTRY_POINT_RENAME(zrule_getName) +#define zrule_getRawOffset U_ICU_ENTRY_POINT_RENAME(zrule_getRawOffset) +#define zrule_isEquivalentTo U_ICU_ENTRY_POINT_RENAME(zrule_isEquivalentTo) +#define ztrans_adoptFrom U_ICU_ENTRY_POINT_RENAME(ztrans_adoptFrom) +#define ztrans_adoptTo U_ICU_ENTRY_POINT_RENAME(ztrans_adoptTo) +#define ztrans_clone U_ICU_ENTRY_POINT_RENAME(ztrans_clone) +#define ztrans_close U_ICU_ENTRY_POINT_RENAME(ztrans_close) +#define ztrans_equals U_ICU_ENTRY_POINT_RENAME(ztrans_equals) +#define ztrans_getDynamicClassID U_ICU_ENTRY_POINT_RENAME(ztrans_getDynamicClassID) +#define ztrans_getFrom U_ICU_ENTRY_POINT_RENAME(ztrans_getFrom) +#define ztrans_getStaticClassID U_ICU_ENTRY_POINT_RENAME(ztrans_getStaticClassID) +#define ztrans_getTime U_ICU_ENTRY_POINT_RENAME(ztrans_getTime) +#define ztrans_getTo U_ICU_ENTRY_POINT_RENAME(ztrans_getTo) +#define ztrans_open U_ICU_ENTRY_POINT_RENAME(ztrans_open) +#define ztrans_openEmpty U_ICU_ENTRY_POINT_RENAME(ztrans_openEmpty) +#define ztrans_setFrom U_ICU_ENTRY_POINT_RENAME(ztrans_setFrom) +#define ztrans_setTime U_ICU_ENTRY_POINT_RENAME(ztrans_setTime) +#define ztrans_setTo U_ICU_ENTRY_POINT_RENAME(ztrans_setTo) + +#endif /* !(defined(_MSC_VER) && defined(__INTELLISENSE__)) */ +#endif /* U_DISABLE_RENAMING */ +#endif /* URENAME_H */ + diff --git a/thirdparty/icu4c/common/unicode/urep.h b/thirdparty/icu4c/common/unicode/urep.h new file mode 100644 index 0000000000..932202ddb0 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/urep.h @@ -0,0 +1,157 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* Copyright (C) 1997-2010, International Business Machines +* Corporation and others. All Rights Reserved. +****************************************************************************** +* Date Name Description +* 06/23/00 aliu Creation. +****************************************************************************** +*/ + +#ifndef __UREP_H +#define __UREP_H + +#include "unicode/utypes.h" + +U_CDECL_BEGIN + +/******************************************************************** + * General Notes + ******************************************************************** + * TODO + * Add usage scenario + * Add test code + * Talk about pinning + * Talk about "can truncate result if out of memory" + */ + +/******************************************************************** + * Data Structures + ********************************************************************/ +/** + * \file + * \brief C API: Callbacks for UReplaceable + */ +/** + * An opaque replaceable text object. This will be manipulated only + * through the caller-supplied UReplaceableFunctor struct. Related + * to the C++ class Replaceable. + * This is currently only used in the Transliterator C API, see utrans.h . + * @stable ICU 2.0 + */ +typedef void* UReplaceable; + +/** + * A set of function pointers that transliterators use to manipulate a + * UReplaceable. The caller should supply the required functions to + * manipulate their text appropriately. Related to the C++ class + * Replaceable. + * @stable ICU 2.0 + */ +typedef struct UReplaceableCallbacks { + + /** + * Function pointer that returns the number of UChar code units in + * this text. + * + * @param rep A pointer to "this" UReplaceable object. + * @return The length of the text. + * @stable ICU 2.0 + */ + int32_t (*length)(const UReplaceable* rep); + + /** + * Function pointer that returns a UChar code units at the given + * offset into this text; 0 <= offset < n, where n is the value + * returned by (*length)(rep). See unistr.h for a description of + * charAt() vs. char32At(). + * + * @param rep A pointer to "this" UReplaceable object. + * @param offset The index at which to fetch the UChar (code unit). + * @return The UChar (code unit) at offset, or U+FFFF if the offset is out of bounds. + * @stable ICU 2.0 + */ + UChar (*charAt)(const UReplaceable* rep, + int32_t offset); + + /** + * Function pointer that returns a UChar32 code point at the given + * offset into this text. See unistr.h for a description of + * charAt() vs. char32At(). + * + * @param rep A pointer to "this" UReplaceable object. + * @param offset The index at which to fetch the UChar32 (code point). + * @return The UChar32 (code point) at offset, or U+FFFF if the offset is out of bounds. + * @stable ICU 2.0 + */ + UChar32 (*char32At)(const UReplaceable* rep, + int32_t offset); + + /** + * Function pointer that replaces text between start and limit in + * this text with the given text. Attributes (out of band info) + * should be retained. + * + * @param rep A pointer to "this" UReplaceable object. + * @param start the starting index of the text to be replaced, + * inclusive. + * @param limit the ending index of the text to be replaced, + * exclusive. + * @param text the new text to replace the UChars from + * start..limit-1. + * @param textLength the number of UChars at text, or -1 if text + * is null-terminated. + * @stable ICU 2.0 + */ + void (*replace)(UReplaceable* rep, + int32_t start, + int32_t limit, + const UChar* text, + int32_t textLength); + + /** + * Function pointer that copies the characters in the range + * [<tt>start</tt>, <tt>limit</tt>) into the array <tt>dst</tt>. + * + * @param rep A pointer to "this" UReplaceable object. + * @param start offset of first character which will be copied + * into the array + * @param limit offset immediately following the last character to + * be copied + * @param dst array in which to copy characters. The length of + * <tt>dst</tt> must be at least <tt>(limit - start)</tt>. + * @stable ICU 2.1 + */ + void (*extract)(UReplaceable* rep, + int32_t start, + int32_t limit, + UChar* dst); + + /** + * Function pointer that copies text between start and limit in + * this text to another index in the text. Attributes (out of + * band info) should be retained. After this call, there will be + * (at least) two copies of the characters originally located at + * start..limit-1. + * + * @param rep A pointer to "this" UReplaceable object. + * @param start the starting index of the text to be copied, + * inclusive. + * @param limit the ending index of the text to be copied, + * exclusive. + * @param dest the index at which the copy of the UChars should be + * inserted. + * @stable ICU 2.0 + */ + void (*copy)(UReplaceable* rep, + int32_t start, + int32_t limit, + int32_t dest); + +} UReplaceableCallbacks; + +U_CDECL_END + +#endif diff --git a/thirdparty/icu4c/common/unicode/ures.h b/thirdparty/icu4c/common/unicode/ures.h new file mode 100644 index 0000000000..fff84043e8 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ures.h @@ -0,0 +1,911 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1997-2016, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* +* File URES.H (formerly CRESBUND.H) +* +* Modification History: +* +* Date Name Description +* 04/01/97 aliu Creation. +* 02/22/99 damiba overhaul. +* 04/04/99 helena Fixed internal header inclusion. +* 04/15/99 Madhu Updated Javadoc +* 06/14/99 stephen Removed functions taking a filename suffix. +* 07/20/99 stephen Language-independent typedef to void* +* 11/09/99 weiv Added ures_getLocale() +* 06/24/02 weiv Added support for resource sharing +****************************************************************************** +*/ + +#ifndef URES_H +#define URES_H + +#include "unicode/utypes.h" +#include "unicode/uloc.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * \file + * \brief C API: Resource Bundle + * + * <h2>C API: Resource Bundle</h2> + * + * C API representing a collection of resource information pertaining to a given + * locale. A resource bundle provides a way of accessing locale- specific information in + * a data file. You create a resource bundle that manages the resources for a given + * locale and then ask it for individual resources. + * <P> + * Resource bundles in ICU4C are currently defined using text files which conform to the following + * <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/bnf_rb.txt">BNF definition</a>. + * More on resource bundle concepts and syntax can be found in the + * <a href="http://icu-project.org/userguide/ResourceManagement.html">Users Guide</a>. + * <P> + */ + +/** + * UResourceBundle is an opaque type for handles for resource bundles in C APIs. + * @stable ICU 2.0 + */ +struct UResourceBundle; + +/** + * @stable ICU 2.0 + */ +typedef struct UResourceBundle UResourceBundle; + +/** + * Numeric constants for types of resource items. + * @see ures_getType + * @stable ICU 2.0 + */ +typedef enum { + /** Resource type constant for "no resource". @stable ICU 2.6 */ + URES_NONE=-1, + + /** Resource type constant for 16-bit Unicode strings. @stable ICU 2.6 */ + URES_STRING=0, + + /** Resource type constant for binary data. @stable ICU 2.6 */ + URES_BINARY=1, + + /** Resource type constant for tables of key-value pairs. @stable ICU 2.6 */ + URES_TABLE=2, + + /** + * Resource type constant for aliases; + * internally stores a string which identifies the actual resource + * storing the data (can be in a different resource bundle). + * Resolved internally before delivering the actual resource through the API. + * @stable ICU 2.6 + */ + URES_ALIAS=3, + + /** + * Resource type constant for a single 28-bit integer, interpreted as + * signed or unsigned by the ures_getInt() or ures_getUInt() function. + * @see ures_getInt + * @see ures_getUInt + * @stable ICU 2.6 + */ + URES_INT=7, + + /** Resource type constant for arrays of resources. @stable ICU 2.6 */ + URES_ARRAY=8, + + /** + * Resource type constant for vectors of 32-bit integers. + * @see ures_getIntVector + * @stable ICU 2.6 + */ + URES_INT_VECTOR = 14, +#ifndef U_HIDE_DEPRECATED_API + /** @deprecated ICU 2.6 Use the URES_ constant instead. */ + RES_NONE=URES_NONE, + /** @deprecated ICU 2.6 Use the URES_ constant instead. */ + RES_STRING=URES_STRING, + /** @deprecated ICU 2.6 Use the URES_ constant instead. */ + RES_BINARY=URES_BINARY, + /** @deprecated ICU 2.6 Use the URES_ constant instead. */ + RES_TABLE=URES_TABLE, + /** @deprecated ICU 2.6 Use the URES_ constant instead. */ + RES_ALIAS=URES_ALIAS, + /** @deprecated ICU 2.6 Use the URES_ constant instead. */ + RES_INT=URES_INT, + /** @deprecated ICU 2.6 Use the URES_ constant instead. */ + RES_ARRAY=URES_ARRAY, + /** @deprecated ICU 2.6 Use the URES_ constant instead. */ + RES_INT_VECTOR=URES_INT_VECTOR, + /** @deprecated ICU 2.6 Not used. */ + RES_RESERVED=15, + + /** + * One more than the highest normal UResType value. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + URES_LIMIT = 16 +#endif // U_HIDE_DEPRECATED_API +} UResType; + +/* + * Functions to create and destroy resource bundles. + */ + +/** + * Opens a UResourceBundle, from which users can extract strings by using + * their corresponding keys. + * Note that the caller is responsible of calling <TT>ures_close</TT> on each successfully + * opened resource bundle. + * @param packageName The packageName and locale together point to an ICU udata object, + * as defined by <code> udata_open( packageName, "res", locale, err) </code> + * or equivalent. Typically, packageName will refer to a (.dat) file, or to + * a package registered with udata_setAppData(). Using a full file or directory + * pathname for packageName is deprecated. If NULL, ICU data will be used. + * @param locale specifies the locale for which we want to open the resource + * if NULL, the default locale will be used. If strlen(locale) == 0 + * root locale will be used. + * + * @param status fills in the outgoing error code. + * The UErrorCode err parameter is used to return status information to the user. To + * check whether the construction succeeded or not, you should check the value of + * U_SUCCESS(err). If you wish more detailed information, you can check for + * informational status results which still indicate success. U_USING_FALLBACK_WARNING + * indicates that a fall back locale was used. For example, 'de_CH' was requested, + * but nothing was found there, so 'de' was used. U_USING_DEFAULT_WARNING indicates that + * the default locale data or root locale data was used; neither the requested locale + * nor any of its fall back locales could be found. Please see the users guide for more + * information on this topic. + * @return a newly allocated resource bundle. + * @see ures_close + * @stable ICU 2.0 + */ +U_CAPI UResourceBundle* U_EXPORT2 +ures_open(const char* packageName, + const char* locale, + UErrorCode* status); + + +/** This function does not care what kind of localeID is passed in. It simply opens a bundle with + * that name. Fallback mechanism is disabled for the new bundle. If the requested bundle contains + * an %%ALIAS directive, the results are undefined. + * @param packageName The packageName and locale together point to an ICU udata object, + * as defined by <code> udata_open( packageName, "res", locale, err) </code> + * or equivalent. Typically, packageName will refer to a (.dat) file, or to + * a package registered with udata_setAppData(). Using a full file or directory + * pathname for packageName is deprecated. If NULL, ICU data will be used. + * @param locale specifies the locale for which we want to open the resource + * if NULL, the default locale will be used. If strlen(locale) == 0 + * root locale will be used. + * + * @param status fills in the outgoing error code. Either U_ZERO_ERROR or U_MISSING_RESOURCE_ERROR + * @return a newly allocated resource bundle or NULL if it doesn't exist. + * @see ures_close + * @stable ICU 2.0 + */ +U_CAPI UResourceBundle* U_EXPORT2 +ures_openDirect(const char* packageName, + const char* locale, + UErrorCode* status); + +/** + * Same as ures_open() but takes a const UChar *path. + * This path will be converted to char * using the default converter, + * then ures_open() is called. + * + * @param packageName The packageName and locale together point to an ICU udata object, + * as defined by <code> udata_open( packageName, "res", locale, err) </code> + * or equivalent. Typically, packageName will refer to a (.dat) file, or to + * a package registered with udata_setAppData(). Using a full file or directory + * pathname for packageName is deprecated. If NULL, ICU data will be used. + * @param locale specifies the locale for which we want to open the resource + * if NULL, the default locale will be used. If strlen(locale) == 0 + * root locale will be used. + * @param status fills in the outgoing error code. + * @return a newly allocated resource bundle. + * @see ures_open + * @stable ICU 2.0 + */ +U_CAPI UResourceBundle* U_EXPORT2 +ures_openU(const UChar* packageName, + const char* locale, + UErrorCode* status); + +#ifndef U_HIDE_DEPRECATED_API +/** + * Returns the number of strings/arrays in resource bundles. + * Better to use ures_getSize, as this function will be deprecated. + * + *@param resourceBundle resource bundle containing the desired strings + *@param resourceKey key tagging the resource + *@param err fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a non-failing error + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_FALLBACK_WARNING </TT> + *@return: for <STRONG>Arrays</STRONG>: returns the number of resources in the array + * <STRONG>Tables</STRONG>: returns the number of resources in the table + * <STRONG>single string</STRONG>: returns 1 + *@see ures_getSize + * @deprecated ICU 2.8 User ures_getSize instead + */ +U_DEPRECATED int32_t U_EXPORT2 +ures_countArrayItems(const UResourceBundle* resourceBundle, + const char* resourceKey, + UErrorCode* err); +#endif /* U_HIDE_DEPRECATED_API */ + +/** + * Close a resource bundle, all pointers returned from the various ures_getXXX calls + * on this particular bundle should be considered invalid henceforth. + * + * @param resourceBundle a pointer to a resourceBundle struct. Can be NULL. + * @see ures_open + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ures_close(UResourceBundle* resourceBundle); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUResourceBundlePointer + * "Smart pointer" class, closes a UResourceBundle via ures_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUResourceBundlePointer, UResourceBundle, ures_close); + +U_NAMESPACE_END + +#endif + +#ifndef U_HIDE_DEPRECATED_API +/** + * Return the version number associated with this ResourceBundle as a string. Please + * use ures_getVersion as this function is going to be deprecated. + * + * @param resourceBundle The resource bundle for which the version is checked. + * @return A version number string as specified in the resource bundle or its parent. + * The caller does not own this string. + * @see ures_getVersion + * @deprecated ICU 2.8 Use ures_getVersion instead. + */ +U_DEPRECATED const char* U_EXPORT2 +ures_getVersionNumber(const UResourceBundle* resourceBundle); +#endif /* U_HIDE_DEPRECATED_API */ + +/** + * Return the version number associated with this ResourceBundle as an + * UVersionInfo array. + * + * @param resB The resource bundle for which the version is checked. + * @param versionInfo A UVersionInfo array that is filled with the version number + * as specified in the resource bundle or its parent. + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ures_getVersion(const UResourceBundle* resB, + UVersionInfo versionInfo); + +#ifndef U_HIDE_DEPRECATED_API +/** + * Return the name of the Locale associated with this ResourceBundle. This API allows + * you to query for the real locale of the resource. For example, if you requested + * "en_US_CALIFORNIA" and only "en_US" bundle exists, "en_US" will be returned. + * For subresources, the locale where this resource comes from will be returned. + * If fallback has occurred, getLocale will reflect this. + * + * @param resourceBundle resource bundle in question + * @param status just for catching illegal arguments + * @return A Locale name + * @deprecated ICU 2.8 Use ures_getLocaleByType instead. + */ +U_DEPRECATED const char* U_EXPORT2 +ures_getLocale(const UResourceBundle* resourceBundle, + UErrorCode* status); +#endif /* U_HIDE_DEPRECATED_API */ + +/** + * Return the name of the Locale associated with this ResourceBundle. + * You can choose between requested, valid and real locale. + * + * @param resourceBundle resource bundle in question + * @param type You can choose between requested, valid and actual + * locale. For description see the definition of + * ULocDataLocaleType in uloc.h + * @param status just for catching illegal arguments + * @return A Locale name + * @stable ICU 2.8 + */ +U_CAPI const char* U_EXPORT2 +ures_getLocaleByType(const UResourceBundle* resourceBundle, + ULocDataLocaleType type, + UErrorCode* status); + + +#ifndef U_HIDE_INTERNAL_API +/** + * Same as ures_open() but uses the fill-in parameter instead of allocating a new bundle. + * + * TODO need to revisit usefulness of this function + * and usage model for fillIn parameters without knowing sizeof(UResourceBundle) + * @param r The existing UResourceBundle to fill in. If NULL then status will be + * set to U_ILLEGAL_ARGUMENT_ERROR. + * @param packageName The packageName and locale together point to an ICU udata object, + * as defined by <code> udata_open( packageName, "res", locale, err) </code> + * or equivalent. Typically, packageName will refer to a (.dat) file, or to + * a package registered with udata_setAppData(). Using a full file or directory + * pathname for packageName is deprecated. If NULL, ICU data will be used. + * @param localeID specifies the locale for which we want to open the resource + * @param status The error code. + * @internal + */ +U_CAPI void U_EXPORT2 +ures_openFillIn(UResourceBundle *r, + const char* packageName, + const char* localeID, + UErrorCode* status); +#endif /* U_HIDE_INTERNAL_API */ + +/** + * Returns a string from a string resource type + * + * @param resourceBundle a string resource + * @param len fills in the length of resulting string + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * Always check the value of status. Don't count on returning NULL. + * could be a non-failing error + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return a pointer to a zero-terminated UChar array which lives in a memory mapped/DLL file. + * @see ures_getBinary + * @see ures_getIntVector + * @see ures_getInt + * @see ures_getUInt + * @stable ICU 2.0 + */ +U_CAPI const UChar* U_EXPORT2 +ures_getString(const UResourceBundle* resourceBundle, + int32_t* len, + UErrorCode* status); + +/** + * Returns a UTF-8 string from a string resource. + * The UTF-8 string may be returnable directly as a pointer, or + * it may need to be copied, or transformed from UTF-16 using u_strToUTF8() + * or equivalent. + * + * If forceCopy==true, then the string is always written to the dest buffer + * and dest is returned. + * + * If forceCopy==false, then the string is returned as a pointer if possible, + * without needing a dest buffer (it can be NULL). If the string needs to be + * copied or transformed, then it may be placed into dest at an arbitrary offset. + * + * If the string is to be written to dest, then U_BUFFER_OVERFLOW_ERROR and + * U_STRING_NOT_TERMINATED_WARNING are set if appropriate, as usual. + * + * If the string is transformed from UTF-16, then a conversion error may occur + * if an unpaired surrogate is encountered. If the function is successful, then + * the output UTF-8 string is always well-formed. + * + * @param resB Resource bundle. + * @param dest Destination buffer. Can be NULL only if capacity=*length==0. + * @param length Input: Capacity of destination buffer. + * Output: Actual length of the UTF-8 string, not counting the + * terminating NUL, even in case of U_BUFFER_OVERFLOW_ERROR. + * Can be NULL, meaning capacity=0 and the string length is not + * returned to the caller. + * @param forceCopy If true, then the output string will always be written to + * dest, with U_BUFFER_OVERFLOW_ERROR and + * U_STRING_NOT_TERMINATED_WARNING set if appropriate. + * If false, then the dest buffer may or may not contain a + * copy of the string. dest may or may not be modified. + * If a copy needs to be written, then the UErrorCode parameter + * indicates overflow etc. as usual. + * @param status Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to the UTF-8 string. It may be dest, or at some offset + * from dest (only if !forceCopy), or in unrelated memory. + * Always NUL-terminated unless the string was written to dest and + * length==capacity (in which case U_STRING_NOT_TERMINATED_WARNING is set). + * + * @see ures_getString + * @see u_strToUTF8 + * @stable ICU 3.6 + */ +U_CAPI const char * U_EXPORT2 +ures_getUTF8String(const UResourceBundle *resB, + char *dest, int32_t *length, + UBool forceCopy, + UErrorCode *status); + +/** + * Returns a binary data from a binary resource. + * + * @param resourceBundle a string resource + * @param len fills in the length of resulting byte chunk + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * Always check the value of status. Don't count on returning NULL. + * could be a non-failing error + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return a pointer to a chunk of unsigned bytes which live in a memory mapped/DLL file. + * @see ures_getString + * @see ures_getIntVector + * @see ures_getInt + * @see ures_getUInt + * @stable ICU 2.0 + */ +U_CAPI const uint8_t* U_EXPORT2 +ures_getBinary(const UResourceBundle* resourceBundle, + int32_t* len, + UErrorCode* status); + +/** + * Returns a 32 bit integer array from a resource. + * + * @param resourceBundle an int vector resource + * @param len fills in the length of resulting byte chunk + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * Always check the value of status. Don't count on returning NULL. + * could be a non-failing error + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return a pointer to a chunk of integers which live in a memory mapped/DLL file. + * @see ures_getBinary + * @see ures_getString + * @see ures_getInt + * @see ures_getUInt + * @stable ICU 2.0 + */ +U_CAPI const int32_t* U_EXPORT2 +ures_getIntVector(const UResourceBundle* resourceBundle, + int32_t* len, + UErrorCode* status); + +/** + * Returns an unsigned integer from a resource. + * This integer is originally 28 bits. + * + * @param resourceBundle a string resource + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a non-failing error + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return an integer value + * @see ures_getInt + * @see ures_getIntVector + * @see ures_getBinary + * @see ures_getString + * @stable ICU 2.0 + */ +U_CAPI uint32_t U_EXPORT2 +ures_getUInt(const UResourceBundle* resourceBundle, + UErrorCode *status); + +/** + * Returns a signed integer from a resource. + * This integer is originally 28 bit and the sign gets propagated. + * + * @param resourceBundle a string resource + * @param status fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a non-failing error + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return an integer value + * @see ures_getUInt + * @see ures_getIntVector + * @see ures_getBinary + * @see ures_getString + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ures_getInt(const UResourceBundle* resourceBundle, + UErrorCode *status); + +/** + * Returns the size of a resource. Size for scalar types is always 1, + * and for vector/table types is the number of child resources. + * @warning Integer array is treated as a scalar type. There are no + * APIs to access individual members of an integer array. It + * is always returned as a whole. + * @param resourceBundle a resource + * @return number of resources in a given resource. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +ures_getSize(const UResourceBundle *resourceBundle); + +/** + * Returns the type of a resource. Available types are defined in enum UResType + * + * @param resourceBundle a resource + * @return type of the given resource. + * @see UResType + * @stable ICU 2.0 + */ +U_CAPI UResType U_EXPORT2 +ures_getType(const UResourceBundle *resourceBundle); + +/** + * Returns the key associated with a given resource. Not all the resources have a key - only + * those that are members of a table. + * + * @param resourceBundle a resource + * @return a key associated to this resource, or NULL if it doesn't have a key + * @stable ICU 2.0 + */ +U_CAPI const char * U_EXPORT2 +ures_getKey(const UResourceBundle *resourceBundle); + +/* ITERATION API + This API provides means for iterating through a resource +*/ + +/** + * Resets the internal context of a resource so that iteration starts from the first element. + * + * @param resourceBundle a resource + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +ures_resetIterator(UResourceBundle *resourceBundle); + +/** + * Checks whether the given resource has another element to iterate over. + * + * @param resourceBundle a resource + * @return true if there are more elements, false if there is no more elements + * @stable ICU 2.0 + */ +U_CAPI UBool U_EXPORT2 +ures_hasNext(const UResourceBundle *resourceBundle); + +/** + * Returns the next resource in a given resource or NULL if there are no more resources + * to iterate over. Features a fill-in parameter. + * + * @param resourceBundle a resource + * @param fillIn if NULL a new UResourceBundle struct is allocated and must be closed by the caller. + * Alternatively, you can supply a struct to be filled by this function. + * @param status fills in the outgoing error code. You may still get a non NULL result even if an + * error occurred. Check status instead. + * @return a pointer to a UResourceBundle struct. If fill in param was NULL, caller must close it + * @stable ICU 2.0 + */ +U_CAPI UResourceBundle* U_EXPORT2 +ures_getNextResource(UResourceBundle *resourceBundle, + UResourceBundle *fillIn, + UErrorCode *status); + +/** + * Returns the next string in a given resource or NULL if there are no more resources + * to iterate over. + * + * @param resourceBundle a resource + * @param len fill in length of the string + * @param key fill in for key associated with this string. NULL if no key + * @param status fills in the outgoing error code. If an error occurred, we may return NULL, but don't + * count on it. Check status instead! + * @return a pointer to a zero-terminated UChar array which lives in a memory mapped/DLL file. + * @stable ICU 2.0 + */ +U_CAPI const UChar* U_EXPORT2 +ures_getNextString(UResourceBundle *resourceBundle, + int32_t* len, + const char ** key, + UErrorCode *status); + +/** + * Returns the resource in a given resource at the specified index. Features a fill-in parameter. + * + * @param resourceBundle the resource bundle from which to get a sub-resource + * @param indexR an index to the wanted resource. + * @param fillIn if NULL a new UResourceBundle struct is allocated and must be closed by the caller. + * Alternatively, you can supply a struct to be filled by this function. + * @param status fills in the outgoing error code. Don't count on NULL being returned if an error has + * occurred. Check status instead. + * @return a pointer to a UResourceBundle struct. If fill in param was NULL, caller must close it + * @stable ICU 2.0 + */ +U_CAPI UResourceBundle* U_EXPORT2 +ures_getByIndex(const UResourceBundle *resourceBundle, + int32_t indexR, + UResourceBundle *fillIn, + UErrorCode *status); + +/** + * Returns the string in a given resource at the specified index. + * + * @param resourceBundle a resource + * @param indexS an index to the wanted string. + * @param len fill in length of the string + * @param status fills in the outgoing error code. If an error occurred, we may return NULL, but don't + * count on it. Check status instead! + * @return a pointer to a zero-terminated UChar array which lives in a memory mapped/DLL file. + * @stable ICU 2.0 + */ +U_CAPI const UChar* U_EXPORT2 +ures_getStringByIndex(const UResourceBundle *resourceBundle, + int32_t indexS, + int32_t* len, + UErrorCode *status); + +/** + * Returns a UTF-8 string from a resource at the specified index. + * The UTF-8 string may be returnable directly as a pointer, or + * it may need to be copied, or transformed from UTF-16 using u_strToUTF8() + * or equivalent. + * + * If forceCopy==true, then the string is always written to the dest buffer + * and dest is returned. + * + * If forceCopy==false, then the string is returned as a pointer if possible, + * without needing a dest buffer (it can be NULL). If the string needs to be + * copied or transformed, then it may be placed into dest at an arbitrary offset. + * + * If the string is to be written to dest, then U_BUFFER_OVERFLOW_ERROR and + * U_STRING_NOT_TERMINATED_WARNING are set if appropriate, as usual. + * + * If the string is transformed from UTF-16, then a conversion error may occur + * if an unpaired surrogate is encountered. If the function is successful, then + * the output UTF-8 string is always well-formed. + * + * @param resB Resource bundle. + * @param stringIndex An index to the wanted string. + * @param dest Destination buffer. Can be NULL only if capacity=*length==0. + * @param pLength Input: Capacity of destination buffer. + * Output: Actual length of the UTF-8 string, not counting the + * terminating NUL, even in case of U_BUFFER_OVERFLOW_ERROR. + * Can be NULL, meaning capacity=0 and the string length is not + * returned to the caller. + * @param forceCopy If true, then the output string will always be written to + * dest, with U_BUFFER_OVERFLOW_ERROR and + * U_STRING_NOT_TERMINATED_WARNING set if appropriate. + * If false, then the dest buffer may or may not contain a + * copy of the string. dest may or may not be modified. + * If a copy needs to be written, then the UErrorCode parameter + * indicates overflow etc. as usual. + * @param status Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to the UTF-8 string. It may be dest, or at some offset + * from dest (only if !forceCopy), or in unrelated memory. + * Always NUL-terminated unless the string was written to dest and + * length==capacity (in which case U_STRING_NOT_TERMINATED_WARNING is set). + * + * @see ures_getStringByIndex + * @see u_strToUTF8 + * @stable ICU 3.6 + */ +U_CAPI const char * U_EXPORT2 +ures_getUTF8StringByIndex(const UResourceBundle *resB, + int32_t stringIndex, + char *dest, int32_t *pLength, + UBool forceCopy, + UErrorCode *status); + +/** + * Returns a resource in a given resource that has a given key. This procedure works only with table + * resources. Features a fill-in parameter. + * + * @param resourceBundle a resource + * @param key a key associated with the wanted resource + * @param fillIn if NULL a new UResourceBundle struct is allocated and must be closed by the caller. + * Alternatively, you can supply a struct to be filled by this function. + * @param status fills in the outgoing error code. + * @return a pointer to a UResourceBundle struct. If fill in param was NULL, caller must close it + * @stable ICU 2.0 + */ +U_CAPI UResourceBundle* U_EXPORT2 +ures_getByKey(const UResourceBundle *resourceBundle, + const char* key, + UResourceBundle *fillIn, + UErrorCode *status); + +/** + * Returns a string in a given resource that has a given key. This procedure works only with table + * resources. + * + * @param resB a resource + * @param key a key associated with the wanted string + * @param len fill in length of the string + * @param status fills in the outgoing error code. If an error occurred, we may return NULL, but don't + * count on it. Check status instead! + * @return a pointer to a zero-terminated UChar array which lives in a memory mapped/DLL file. + * @stable ICU 2.0 + */ +U_CAPI const UChar* U_EXPORT2 +ures_getStringByKey(const UResourceBundle *resB, + const char* key, + int32_t* len, + UErrorCode *status); + +/** + * Returns a UTF-8 string from a resource and a key. + * This function works only with table resources. + * + * The UTF-8 string may be returnable directly as a pointer, or + * it may need to be copied, or transformed from UTF-16 using u_strToUTF8() + * or equivalent. + * + * If forceCopy==true, then the string is always written to the dest buffer + * and dest is returned. + * + * If forceCopy==false, then the string is returned as a pointer if possible, + * without needing a dest buffer (it can be NULL). If the string needs to be + * copied or transformed, then it may be placed into dest at an arbitrary offset. + * + * If the string is to be written to dest, then U_BUFFER_OVERFLOW_ERROR and + * U_STRING_NOT_TERMINATED_WARNING are set if appropriate, as usual. + * + * If the string is transformed from UTF-16, then a conversion error may occur + * if an unpaired surrogate is encountered. If the function is successful, then + * the output UTF-8 string is always well-formed. + * + * @param resB Resource bundle. + * @param key A key associated with the wanted resource + * @param dest Destination buffer. Can be NULL only if capacity=*length==0. + * @param pLength Input: Capacity of destination buffer. + * Output: Actual length of the UTF-8 string, not counting the + * terminating NUL, even in case of U_BUFFER_OVERFLOW_ERROR. + * Can be NULL, meaning capacity=0 and the string length is not + * returned to the caller. + * @param forceCopy If true, then the output string will always be written to + * dest, with U_BUFFER_OVERFLOW_ERROR and + * U_STRING_NOT_TERMINATED_WARNING set if appropriate. + * If false, then the dest buffer may or may not contain a + * copy of the string. dest may or may not be modified. + * If a copy needs to be written, then the UErrorCode parameter + * indicates overflow etc. as usual. + * @param status Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to the UTF-8 string. It may be dest, or at some offset + * from dest (only if !forceCopy), or in unrelated memory. + * Always NUL-terminated unless the string was written to dest and + * length==capacity (in which case U_STRING_NOT_TERMINATED_WARNING is set). + * + * @see ures_getStringByKey + * @see u_strToUTF8 + * @stable ICU 3.6 + */ +U_CAPI const char * U_EXPORT2 +ures_getUTF8StringByKey(const UResourceBundle *resB, + const char *key, + char *dest, int32_t *pLength, + UBool forceCopy, + UErrorCode *status); + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/unistr.h" + +U_NAMESPACE_BEGIN +/** + * Returns the string value from a string resource bundle. + * + * @param resB a resource, should have type URES_STRING + * @param status: fills in the outgoing error code + * could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found + * could be a non-failing error + * e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT> + * @return The string value, or a bogus string if there is a failure UErrorCode. + * @stable ICU 2.0 + */ +inline UnicodeString +ures_getUnicodeString(const UResourceBundle *resB, UErrorCode* status) { + UnicodeString result; + int32_t len = 0; + const UChar *r = ures_getString(resB, &len, status); + if(U_SUCCESS(*status)) { + result.setTo(true, r, len); + } else { + result.setToBogus(); + } + return result; +} + +/** + * Returns the next string in a resource, or an empty string if there are no more resources + * to iterate over. + * Use ures_getNextString() instead to distinguish between + * the end of the iteration and a real empty string value. + * + * @param resB a resource + * @param key fill in for key associated with this string + * @param status fills in the outgoing error code + * @return The string value, or a bogus string if there is a failure UErrorCode. + * @stable ICU 2.0 + */ +inline UnicodeString +ures_getNextUnicodeString(UResourceBundle *resB, const char ** key, UErrorCode* status) { + UnicodeString result; + int32_t len = 0; + const UChar* r = ures_getNextString(resB, &len, key, status); + if(U_SUCCESS(*status)) { + result.setTo(true, r, len); + } else { + result.setToBogus(); + } + return result; +} + +/** + * Returns the string in a given resource array or table at the specified index. + * + * @param resB a resource + * @param indexS an index to the wanted string. + * @param status fills in the outgoing error code + * @return The string value, or a bogus string if there is a failure UErrorCode. + * @stable ICU 2.0 + */ +inline UnicodeString +ures_getUnicodeStringByIndex(const UResourceBundle *resB, int32_t indexS, UErrorCode* status) { + UnicodeString result; + int32_t len = 0; + const UChar* r = ures_getStringByIndex(resB, indexS, &len, status); + if(U_SUCCESS(*status)) { + result.setTo(true, r, len); + } else { + result.setToBogus(); + } + return result; +} + +/** + * Returns a string in a resource that has a given key. + * This procedure works only with table resources. + * + * @param resB a resource + * @param key a key associated with the wanted string + * @param status fills in the outgoing error code + * @return The string value, or a bogus string if there is a failure UErrorCode. + * @stable ICU 2.0 + */ +inline UnicodeString +ures_getUnicodeStringByKey(const UResourceBundle *resB, const char* key, UErrorCode* status) { + UnicodeString result; + int32_t len = 0; + const UChar* r = ures_getStringByKey(resB, key, &len, status); + if(U_SUCCESS(*status)) { + result.setTo(true, r, len); + } else { + result.setToBogus(); + } + return result; +} + +U_NAMESPACE_END + +#endif + +/** + * Create a string enumerator, owned by the caller, of all locales located within + * the specified resource tree. + * @param packageName name of the tree, such as (NULL) or U_ICUDATA_ALIAS or or "ICUDATA-coll" + * This call is similar to uloc_getAvailable(). + * @param status error code + * @stable ICU 3.2 + */ +U_CAPI UEnumeration* U_EXPORT2 +ures_openAvailableLocales(const char *packageName, UErrorCode *status); + + +#endif /*_URES*/ +/*eof*/ diff --git a/thirdparty/icu4c/common/unicode/uscript.h b/thirdparty/icu4c/common/unicode/uscript.h new file mode 100644 index 0000000000..8448afda76 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uscript.h @@ -0,0 +1,708 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* + ********************************************************************** + * Copyright (C) 1997-2016, International Business Machines + * Corporation and others. All Rights Reserved. + ********************************************************************** + * + * File USCRIPT.H + * + * Modification History: + * + * Date Name Description + * 07/06/2001 Ram Creation. + ****************************************************************************** + */ + +#ifndef USCRIPT_H +#define USCRIPT_H +#include "unicode/utypes.h" + +/** + * \file + * \brief C API: Unicode Script Information + */ + +/** + * Constants for ISO 15924 script codes. + * + * The current set of script code constants supports at least all scripts + * that are encoded in the version of Unicode which ICU currently supports. + * The names of the constants are usually derived from the + * Unicode script property value aliases. + * See UAX #24 Unicode Script Property (http://www.unicode.org/reports/tr24/) + * and http://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt . + * + * In addition, constants for many ISO 15924 script codes + * are included, for use with language tags, CLDR data, and similar. + * Some of those codes are not used in the Unicode Character Database (UCD). + * For example, there are no characters that have a UCD script property value of + * Hans or Hant. All Han ideographs have the Hani script property value in Unicode. + * + * Private-use codes Qaaa..Qabx are not included, except as used in the UCD or in CLDR. + * + * Starting with ICU 55, script codes are only added when their scripts + * have been or will certainly be encoded in Unicode, + * and have been assigned Unicode script property value aliases, + * to ensure that their script names are stable and match the names of the constants. + * Script codes like Latf and Aran that are not subject to separate encoding + * may be added at any time. + * + * @stable ICU 2.2 + */ +typedef enum UScriptCode { + /* + * Note: UScriptCode constants and their ISO script code comments + * are parsed by preparseucd.py. + * It matches lines like + * USCRIPT_<Unicode Script value name> = <integer>, / * <ISO script code> * / + */ + + /** @stable ICU 2.2 */ + USCRIPT_INVALID_CODE = -1, + /** @stable ICU 2.2 */ + USCRIPT_COMMON = 0, /* Zyyy */ + /** @stable ICU 2.2 */ + USCRIPT_INHERITED = 1, /* Zinh */ /* "Code for inherited script", for non-spacing combining marks; also Qaai */ + /** @stable ICU 2.2 */ + USCRIPT_ARABIC = 2, /* Arab */ + /** @stable ICU 2.2 */ + USCRIPT_ARMENIAN = 3, /* Armn */ + /** @stable ICU 2.2 */ + USCRIPT_BENGALI = 4, /* Beng */ + /** @stable ICU 2.2 */ + USCRIPT_BOPOMOFO = 5, /* Bopo */ + /** @stable ICU 2.2 */ + USCRIPT_CHEROKEE = 6, /* Cher */ + /** @stable ICU 2.2 */ + USCRIPT_COPTIC = 7, /* Copt */ + /** @stable ICU 2.2 */ + USCRIPT_CYRILLIC = 8, /* Cyrl */ + /** @stable ICU 2.2 */ + USCRIPT_DESERET = 9, /* Dsrt */ + /** @stable ICU 2.2 */ + USCRIPT_DEVANAGARI = 10, /* Deva */ + /** @stable ICU 2.2 */ + USCRIPT_ETHIOPIC = 11, /* Ethi */ + /** @stable ICU 2.2 */ + USCRIPT_GEORGIAN = 12, /* Geor */ + /** @stable ICU 2.2 */ + USCRIPT_GOTHIC = 13, /* Goth */ + /** @stable ICU 2.2 */ + USCRIPT_GREEK = 14, /* Grek */ + /** @stable ICU 2.2 */ + USCRIPT_GUJARATI = 15, /* Gujr */ + /** @stable ICU 2.2 */ + USCRIPT_GURMUKHI = 16, /* Guru */ + /** @stable ICU 2.2 */ + USCRIPT_HAN = 17, /* Hani */ + /** @stable ICU 2.2 */ + USCRIPT_HANGUL = 18, /* Hang */ + /** @stable ICU 2.2 */ + USCRIPT_HEBREW = 19, /* Hebr */ + /** @stable ICU 2.2 */ + USCRIPT_HIRAGANA = 20, /* Hira */ + /** @stable ICU 2.2 */ + USCRIPT_KANNADA = 21, /* Knda */ + /** @stable ICU 2.2 */ + USCRIPT_KATAKANA = 22, /* Kana */ + /** @stable ICU 2.2 */ + USCRIPT_KHMER = 23, /* Khmr */ + /** @stable ICU 2.2 */ + USCRIPT_LAO = 24, /* Laoo */ + /** @stable ICU 2.2 */ + USCRIPT_LATIN = 25, /* Latn */ + /** @stable ICU 2.2 */ + USCRIPT_MALAYALAM = 26, /* Mlym */ + /** @stable ICU 2.2 */ + USCRIPT_MONGOLIAN = 27, /* Mong */ + /** @stable ICU 2.2 */ + USCRIPT_MYANMAR = 28, /* Mymr */ + /** @stable ICU 2.2 */ + USCRIPT_OGHAM = 29, /* Ogam */ + /** @stable ICU 2.2 */ + USCRIPT_OLD_ITALIC = 30, /* Ital */ + /** @stable ICU 2.2 */ + USCRIPT_ORIYA = 31, /* Orya */ + /** @stable ICU 2.2 */ + USCRIPT_RUNIC = 32, /* Runr */ + /** @stable ICU 2.2 */ + USCRIPT_SINHALA = 33, /* Sinh */ + /** @stable ICU 2.2 */ + USCRIPT_SYRIAC = 34, /* Syrc */ + /** @stable ICU 2.2 */ + USCRIPT_TAMIL = 35, /* Taml */ + /** @stable ICU 2.2 */ + USCRIPT_TELUGU = 36, /* Telu */ + /** @stable ICU 2.2 */ + USCRIPT_THAANA = 37, /* Thaa */ + /** @stable ICU 2.2 */ + USCRIPT_THAI = 38, /* Thai */ + /** @stable ICU 2.2 */ + USCRIPT_TIBETAN = 39, /* Tibt */ + /** Canadian_Aboriginal script. @stable ICU 2.6 */ + USCRIPT_CANADIAN_ABORIGINAL = 40, /* Cans */ + /** Canadian_Aboriginal script (alias). @stable ICU 2.2 */ + USCRIPT_UCAS = USCRIPT_CANADIAN_ABORIGINAL, + /** @stable ICU 2.2 */ + USCRIPT_YI = 41, /* Yiii */ + /* New scripts in Unicode 3.2 */ + /** @stable ICU 2.2 */ + USCRIPT_TAGALOG = 42, /* Tglg */ + /** @stable ICU 2.2 */ + USCRIPT_HANUNOO = 43, /* Hano */ + /** @stable ICU 2.2 */ + USCRIPT_BUHID = 44, /* Buhd */ + /** @stable ICU 2.2 */ + USCRIPT_TAGBANWA = 45, /* Tagb */ + + /* New scripts in Unicode 4 */ + /** @stable ICU 2.6 */ + USCRIPT_BRAILLE = 46, /* Brai */ + /** @stable ICU 2.6 */ + USCRIPT_CYPRIOT = 47, /* Cprt */ + /** @stable ICU 2.6 */ + USCRIPT_LIMBU = 48, /* Limb */ + /** @stable ICU 2.6 */ + USCRIPT_LINEAR_B = 49, /* Linb */ + /** @stable ICU 2.6 */ + USCRIPT_OSMANYA = 50, /* Osma */ + /** @stable ICU 2.6 */ + USCRIPT_SHAVIAN = 51, /* Shaw */ + /** @stable ICU 2.6 */ + USCRIPT_TAI_LE = 52, /* Tale */ + /** @stable ICU 2.6 */ + USCRIPT_UGARITIC = 53, /* Ugar */ + + /** New script code in Unicode 4.0.1 @stable ICU 3.0 */ + USCRIPT_KATAKANA_OR_HIRAGANA = 54,/*Hrkt */ + + /* New scripts in Unicode 4.1 */ + /** @stable ICU 3.4 */ + USCRIPT_BUGINESE = 55, /* Bugi */ + /** @stable ICU 3.4 */ + USCRIPT_GLAGOLITIC = 56, /* Glag */ + /** @stable ICU 3.4 */ + USCRIPT_KHAROSHTHI = 57, /* Khar */ + /** @stable ICU 3.4 */ + USCRIPT_SYLOTI_NAGRI = 58, /* Sylo */ + /** @stable ICU 3.4 */ + USCRIPT_NEW_TAI_LUE = 59, /* Talu */ + /** @stable ICU 3.4 */ + USCRIPT_TIFINAGH = 60, /* Tfng */ + /** @stable ICU 3.4 */ + USCRIPT_OLD_PERSIAN = 61, /* Xpeo */ + + /* New script codes from Unicode and ISO 15924 */ + /** @stable ICU 3.6 */ + USCRIPT_BALINESE = 62, /* Bali */ + /** @stable ICU 3.6 */ + USCRIPT_BATAK = 63, /* Batk */ + /** @stable ICU 3.6 */ + USCRIPT_BLISSYMBOLS = 64, /* Blis */ + /** @stable ICU 3.6 */ + USCRIPT_BRAHMI = 65, /* Brah */ + /** @stable ICU 3.6 */ + USCRIPT_CHAM = 66, /* Cham */ + /** @stable ICU 3.6 */ + USCRIPT_CIRTH = 67, /* Cirt */ + /** @stable ICU 3.6 */ + USCRIPT_OLD_CHURCH_SLAVONIC_CYRILLIC = 68, /* Cyrs */ + /** @stable ICU 3.6 */ + USCRIPT_DEMOTIC_EGYPTIAN = 69, /* Egyd */ + /** @stable ICU 3.6 */ + USCRIPT_HIERATIC_EGYPTIAN = 70, /* Egyh */ + /** @stable ICU 3.6 */ + USCRIPT_EGYPTIAN_HIEROGLYPHS = 71, /* Egyp */ + /** @stable ICU 3.6 */ + USCRIPT_KHUTSURI = 72, /* Geok */ + /** @stable ICU 3.6 */ + USCRIPT_SIMPLIFIED_HAN = 73, /* Hans */ + /** @stable ICU 3.6 */ + USCRIPT_TRADITIONAL_HAN = 74, /* Hant */ + /** @stable ICU 3.6 */ + USCRIPT_PAHAWH_HMONG = 75, /* Hmng */ + /** @stable ICU 3.6 */ + USCRIPT_OLD_HUNGARIAN = 76, /* Hung */ + /** @stable ICU 3.6 */ + USCRIPT_HARAPPAN_INDUS = 77, /* Inds */ + /** @stable ICU 3.6 */ + USCRIPT_JAVANESE = 78, /* Java */ + /** @stable ICU 3.6 */ + USCRIPT_KAYAH_LI = 79, /* Kali */ + /** @stable ICU 3.6 */ + USCRIPT_LATIN_FRAKTUR = 80, /* Latf */ + /** @stable ICU 3.6 */ + USCRIPT_LATIN_GAELIC = 81, /* Latg */ + /** @stable ICU 3.6 */ + USCRIPT_LEPCHA = 82, /* Lepc */ + /** @stable ICU 3.6 */ + USCRIPT_LINEAR_A = 83, /* Lina */ + /** @stable ICU 4.6 */ + USCRIPT_MANDAIC = 84, /* Mand */ + /** @stable ICU 3.6 */ + USCRIPT_MANDAEAN = USCRIPT_MANDAIC, + /** @stable ICU 3.6 */ + USCRIPT_MAYAN_HIEROGLYPHS = 85, /* Maya */ + /** @stable ICU 4.6 */ + USCRIPT_MEROITIC_HIEROGLYPHS = 86, /* Mero */ + /** @stable ICU 3.6 */ + USCRIPT_MEROITIC = USCRIPT_MEROITIC_HIEROGLYPHS, + /** @stable ICU 3.6 */ + USCRIPT_NKO = 87, /* Nkoo */ + /** @stable ICU 3.6 */ + USCRIPT_ORKHON = 88, /* Orkh */ + /** @stable ICU 3.6 */ + USCRIPT_OLD_PERMIC = 89, /* Perm */ + /** @stable ICU 3.6 */ + USCRIPT_PHAGS_PA = 90, /* Phag */ + /** @stable ICU 3.6 */ + USCRIPT_PHOENICIAN = 91, /* Phnx */ + /** @stable ICU 52 */ + USCRIPT_MIAO = 92, /* Plrd */ + /** @stable ICU 3.6 */ + USCRIPT_PHONETIC_POLLARD = USCRIPT_MIAO, + /** @stable ICU 3.6 */ + USCRIPT_RONGORONGO = 93, /* Roro */ + /** @stable ICU 3.6 */ + USCRIPT_SARATI = 94, /* Sara */ + /** @stable ICU 3.6 */ + USCRIPT_ESTRANGELO_SYRIAC = 95, /* Syre */ + /** @stable ICU 3.6 */ + USCRIPT_WESTERN_SYRIAC = 96, /* Syrj */ + /** @stable ICU 3.6 */ + USCRIPT_EASTERN_SYRIAC = 97, /* Syrn */ + /** @stable ICU 3.6 */ + USCRIPT_TENGWAR = 98, /* Teng */ + /** @stable ICU 3.6 */ + USCRIPT_VAI = 99, /* Vaii */ + /** @stable ICU 3.6 */ + USCRIPT_VISIBLE_SPEECH = 100,/* Visp */ + /** @stable ICU 3.6 */ + USCRIPT_CUNEIFORM = 101,/* Xsux */ + /** @stable ICU 3.6 */ + USCRIPT_UNWRITTEN_LANGUAGES = 102,/* Zxxx */ + /** @stable ICU 3.6 */ + USCRIPT_UNKNOWN = 103,/* Zzzz */ /* Unknown="Code for uncoded script", for unassigned code points */ + + /** @stable ICU 3.8 */ + USCRIPT_CARIAN = 104,/* Cari */ + /** @stable ICU 3.8 */ + USCRIPT_JAPANESE = 105,/* Jpan */ + /** @stable ICU 3.8 */ + USCRIPT_LANNA = 106,/* Lana */ + /** @stable ICU 3.8 */ + USCRIPT_LYCIAN = 107,/* Lyci */ + /** @stable ICU 3.8 */ + USCRIPT_LYDIAN = 108,/* Lydi */ + /** @stable ICU 3.8 */ + USCRIPT_OL_CHIKI = 109,/* Olck */ + /** @stable ICU 3.8 */ + USCRIPT_REJANG = 110,/* Rjng */ + /** @stable ICU 3.8 */ + USCRIPT_SAURASHTRA = 111,/* Saur */ + /** Sutton SignWriting @stable ICU 3.8 */ + USCRIPT_SIGN_WRITING = 112,/* Sgnw */ + /** @stable ICU 3.8 */ + USCRIPT_SUNDANESE = 113,/* Sund */ + /** @stable ICU 3.8 */ + USCRIPT_MOON = 114,/* Moon */ + /** @stable ICU 3.8 */ + USCRIPT_MEITEI_MAYEK = 115,/* Mtei */ + + /** @stable ICU 4.0 */ + USCRIPT_IMPERIAL_ARAMAIC = 116,/* Armi */ + /** @stable ICU 4.0 */ + USCRIPT_AVESTAN = 117,/* Avst */ + /** @stable ICU 4.0 */ + USCRIPT_CHAKMA = 118,/* Cakm */ + /** @stable ICU 4.0 */ + USCRIPT_KOREAN = 119,/* Kore */ + /** @stable ICU 4.0 */ + USCRIPT_KAITHI = 120,/* Kthi */ + /** @stable ICU 4.0 */ + USCRIPT_MANICHAEAN = 121,/* Mani */ + /** @stable ICU 4.0 */ + USCRIPT_INSCRIPTIONAL_PAHLAVI = 122,/* Phli */ + /** @stable ICU 4.0 */ + USCRIPT_PSALTER_PAHLAVI = 123,/* Phlp */ + /** @stable ICU 4.0 */ + USCRIPT_BOOK_PAHLAVI = 124,/* Phlv */ + /** @stable ICU 4.0 */ + USCRIPT_INSCRIPTIONAL_PARTHIAN = 125,/* Prti */ + /** @stable ICU 4.0 */ + USCRIPT_SAMARITAN = 126,/* Samr */ + /** @stable ICU 4.0 */ + USCRIPT_TAI_VIET = 127,/* Tavt */ + /** @stable ICU 4.0 */ + USCRIPT_MATHEMATICAL_NOTATION = 128,/* Zmth */ + /** @stable ICU 4.0 */ + USCRIPT_SYMBOLS = 129,/* Zsym */ + + /** @stable ICU 4.4 */ + USCRIPT_BAMUM = 130,/* Bamu */ + /** @stable ICU 4.4 */ + USCRIPT_LISU = 131,/* Lisu */ + /** @stable ICU 4.4 */ + USCRIPT_NAKHI_GEBA = 132,/* Nkgb */ + /** @stable ICU 4.4 */ + USCRIPT_OLD_SOUTH_ARABIAN = 133,/* Sarb */ + + /** @stable ICU 4.6 */ + USCRIPT_BASSA_VAH = 134,/* Bass */ + /** @stable ICU 54 */ + USCRIPT_DUPLOYAN = 135,/* Dupl */ +#ifndef U_HIDE_DEPRECATED_API + /** @deprecated ICU 54 Typo, use USCRIPT_DUPLOYAN */ + USCRIPT_DUPLOYAN_SHORTAND = USCRIPT_DUPLOYAN, +#endif /* U_HIDE_DEPRECATED_API */ + /** @stable ICU 4.6 */ + USCRIPT_ELBASAN = 136,/* Elba */ + /** @stable ICU 4.6 */ + USCRIPT_GRANTHA = 137,/* Gran */ + /** @stable ICU 4.6 */ + USCRIPT_KPELLE = 138,/* Kpel */ + /** @stable ICU 4.6 */ + USCRIPT_LOMA = 139,/* Loma */ + /** Mende Kikakui @stable ICU 4.6 */ + USCRIPT_MENDE = 140,/* Mend */ + /** @stable ICU 4.6 */ + USCRIPT_MEROITIC_CURSIVE = 141,/* Merc */ + /** @stable ICU 4.6 */ + USCRIPT_OLD_NORTH_ARABIAN = 142,/* Narb */ + /** @stable ICU 4.6 */ + USCRIPT_NABATAEAN = 143,/* Nbat */ + /** @stable ICU 4.6 */ + USCRIPT_PALMYRENE = 144,/* Palm */ + /** @stable ICU 54 */ + USCRIPT_KHUDAWADI = 145,/* Sind */ + /** @stable ICU 4.6 */ + USCRIPT_SINDHI = USCRIPT_KHUDAWADI, + /** @stable ICU 4.6 */ + USCRIPT_WARANG_CITI = 146,/* Wara */ + + /** @stable ICU 4.8 */ + USCRIPT_AFAKA = 147,/* Afak */ + /** @stable ICU 4.8 */ + USCRIPT_JURCHEN = 148,/* Jurc */ + /** @stable ICU 4.8 */ + USCRIPT_MRO = 149,/* Mroo */ + /** @stable ICU 4.8 */ + USCRIPT_NUSHU = 150,/* Nshu */ + /** @stable ICU 4.8 */ + USCRIPT_SHARADA = 151,/* Shrd */ + /** @stable ICU 4.8 */ + USCRIPT_SORA_SOMPENG = 152,/* Sora */ + /** @stable ICU 4.8 */ + USCRIPT_TAKRI = 153,/* Takr */ + /** @stable ICU 4.8 */ + USCRIPT_TANGUT = 154,/* Tang */ + /** @stable ICU 4.8 */ + USCRIPT_WOLEAI = 155,/* Wole */ + + /** @stable ICU 49 */ + USCRIPT_ANATOLIAN_HIEROGLYPHS = 156,/* Hluw */ + /** @stable ICU 49 */ + USCRIPT_KHOJKI = 157,/* Khoj */ + /** @stable ICU 49 */ + USCRIPT_TIRHUTA = 158,/* Tirh */ + + /** @stable ICU 52 */ + USCRIPT_CAUCASIAN_ALBANIAN = 159,/* Aghb */ + /** @stable ICU 52 */ + USCRIPT_MAHAJANI = 160,/* Mahj */ + + /** @stable ICU 54 */ + USCRIPT_AHOM = 161,/* Ahom */ + /** @stable ICU 54 */ + USCRIPT_HATRAN = 162,/* Hatr */ + /** @stable ICU 54 */ + USCRIPT_MODI = 163,/* Modi */ + /** @stable ICU 54 */ + USCRIPT_MULTANI = 164,/* Mult */ + /** @stable ICU 54 */ + USCRIPT_PAU_CIN_HAU = 165,/* Pauc */ + /** @stable ICU 54 */ + USCRIPT_SIDDHAM = 166,/* Sidd */ + + /** @stable ICU 58 */ + USCRIPT_ADLAM = 167,/* Adlm */ + /** @stable ICU 58 */ + USCRIPT_BHAIKSUKI = 168,/* Bhks */ + /** @stable ICU 58 */ + USCRIPT_MARCHEN = 169,/* Marc */ + /** @stable ICU 58 */ + USCRIPT_NEWA = 170,/* Newa */ + /** @stable ICU 58 */ + USCRIPT_OSAGE = 171,/* Osge */ + + /** @stable ICU 58 */ + USCRIPT_HAN_WITH_BOPOMOFO = 172,/* Hanb */ + /** @stable ICU 58 */ + USCRIPT_JAMO = 173,/* Jamo */ + /** @stable ICU 58 */ + USCRIPT_SYMBOLS_EMOJI = 174,/* Zsye */ + + /** @stable ICU 60 */ + USCRIPT_MASARAM_GONDI = 175,/* Gonm */ + /** @stable ICU 60 */ + USCRIPT_SOYOMBO = 176,/* Soyo */ + /** @stable ICU 60 */ + USCRIPT_ZANABAZAR_SQUARE = 177,/* Zanb */ + + /** @stable ICU 62 */ + USCRIPT_DOGRA = 178,/* Dogr */ + /** @stable ICU 62 */ + USCRIPT_GUNJALA_GONDI = 179,/* Gong */ + /** @stable ICU 62 */ + USCRIPT_MAKASAR = 180,/* Maka */ + /** @stable ICU 62 */ + USCRIPT_MEDEFAIDRIN = 181,/* Medf */ + /** @stable ICU 62 */ + USCRIPT_HANIFI_ROHINGYA = 182,/* Rohg */ + /** @stable ICU 62 */ + USCRIPT_SOGDIAN = 183,/* Sogd */ + /** @stable ICU 62 */ + USCRIPT_OLD_SOGDIAN = 184,/* Sogo */ + + /** @stable ICU 64 */ + USCRIPT_ELYMAIC = 185,/* Elym */ + /** @stable ICU 64 */ + USCRIPT_NYIAKENG_PUACHUE_HMONG = 186,/* Hmnp */ + /** @stable ICU 64 */ + USCRIPT_NANDINAGARI = 187,/* Nand */ + /** @stable ICU 64 */ + USCRIPT_WANCHO = 188,/* Wcho */ + + /** @stable ICU 66 */ + USCRIPT_CHORASMIAN = 189,/* Chrs */ + /** @stable ICU 66 */ + USCRIPT_DIVES_AKURU = 190,/* Diak */ + /** @stable ICU 66 */ + USCRIPT_KHITAN_SMALL_SCRIPT = 191,/* Kits */ + /** @stable ICU 66 */ + USCRIPT_YEZIDI = 192,/* Yezi */ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UScriptCode value. + * The highest value is available via u_getIntPropertyMaxValue(UCHAR_SCRIPT). + * + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + USCRIPT_CODE_LIMIT = 193 +#endif // U_HIDE_DEPRECATED_API +} UScriptCode; + +/** + * Gets the script codes associated with the given locale or ISO 15924 abbreviation or name. + * Fills in USCRIPT_MALAYALAM given "Malayam" OR "Mlym". + * Fills in USCRIPT_LATIN given "en" OR "en_US" + * If the required capacity is greater than the capacity of the destination buffer, + * then the error code is set to U_BUFFER_OVERFLOW_ERROR and the required capacity is returned. + * + * <p>Note: To search by short or long script alias only, use + * u_getPropertyValueEnum(UCHAR_SCRIPT, alias) instead. That does + * a fast lookup with no access of the locale data. + * + * @param nameOrAbbrOrLocale name of the script, as given in + * PropertyValueAliases.txt, or ISO 15924 code or locale + * @param fillIn the UScriptCode buffer to fill in the script code + * @param capacity the capacity (size) of UScriptCode buffer passed in. + * @param err the error status code. + * @return The number of script codes filled in the buffer passed in + * @stable ICU 2.4 + */ +U_CAPI int32_t U_EXPORT2 +uscript_getCode(const char* nameOrAbbrOrLocale,UScriptCode* fillIn,int32_t capacity,UErrorCode *err); + +/** + * Returns the long Unicode script name, if there is one. + * Otherwise returns the 4-letter ISO 15924 script code. + * Returns "Malayam" given USCRIPT_MALAYALAM. + * + * @param scriptCode UScriptCode enum + * @return long script name as given in PropertyValueAliases.txt, or the 4-letter code, + * or NULL if scriptCode is invalid + * @stable ICU 2.4 + */ +U_CAPI const char* U_EXPORT2 +uscript_getName(UScriptCode scriptCode); + +/** + * Returns the 4-letter ISO 15924 script code, + * which is the same as the short Unicode script name if Unicode has names for the script. + * Returns "Mlym" given USCRIPT_MALAYALAM. + * + * @param scriptCode UScriptCode enum + * @return short script name (4-letter code), or NULL if scriptCode is invalid + * @stable ICU 2.4 + */ +U_CAPI const char* U_EXPORT2 +uscript_getShortName(UScriptCode scriptCode); + +/** + * Gets the script code associated with the given codepoint. + * Returns USCRIPT_MALAYALAM given 0x0D02 + * @param codepoint UChar32 codepoint + * @param err the error status code. + * @return The UScriptCode, or 0 if codepoint is invalid + * @stable ICU 2.4 + */ +U_CAPI UScriptCode U_EXPORT2 +uscript_getScript(UChar32 codepoint, UErrorCode *err); + +/** + * Do the Script_Extensions of code point c contain script sc? + * If c does not have explicit Script_Extensions, then this tests whether + * c has the Script property value sc. + * + * Some characters are commonly used in multiple scripts. + * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. + * @param c code point + * @param sc script code + * @return true if sc is in Script_Extensions(c) + * @stable ICU 49 + */ +U_CAPI UBool U_EXPORT2 +uscript_hasScript(UChar32 c, UScriptCode sc); + +/** + * Writes code point c's Script_Extensions as a list of UScriptCode values + * to the output scripts array and returns the number of script codes. + * - If c does have Script_Extensions, then the Script property value + * (normally Common or Inherited) is not included. + * - If c does not have Script_Extensions, then the one Script code is written to the output array. + * - If c is not a valid code point, then the one USCRIPT_UNKNOWN code is written. + * In other words, if the return value is 1, + * then the output array contains exactly c's single Script code. + * If the return value is n>=2, then the output array contains c's n Script_Extensions script codes. + * + * Some characters are commonly used in multiple scripts. + * For more information, see UAX #24: http://www.unicode.org/reports/tr24/. + * + * If there are more than capacity script codes to be written, then + * U_BUFFER_OVERFLOW_ERROR is set and the number of Script_Extensions is returned. + * (Usual ICU buffer handling behavior.) + * + * @param c code point + * @param scripts output script code array + * @param capacity capacity of the scripts array + * @param errorCode Standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return number of script codes in c's Script_Extensions, or 1 for the single Script value, + * written to scripts unless U_BUFFER_OVERFLOW_ERROR indicates insufficient capacity + * @stable ICU 49 + */ +U_CAPI int32_t U_EXPORT2 +uscript_getScriptExtensions(UChar32 c, + UScriptCode *scripts, int32_t capacity, + UErrorCode *errorCode); + +/** + * Script usage constants. + * See UAX #31 Unicode Identifier and Pattern Syntax. + * http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Exclusion_from_Identifiers + * + * @stable ICU 51 + */ +typedef enum UScriptUsage { + /** Not encoded in Unicode. @stable ICU 51 */ + USCRIPT_USAGE_NOT_ENCODED, + /** Unknown script usage. @stable ICU 51 */ + USCRIPT_USAGE_UNKNOWN, + /** Candidate for Exclusion from Identifiers. @stable ICU 51 */ + USCRIPT_USAGE_EXCLUDED, + /** Limited Use script. @stable ICU 51 */ + USCRIPT_USAGE_LIMITED_USE, + /** Aspirational Use script. @stable ICU 51 */ + USCRIPT_USAGE_ASPIRATIONAL, + /** Recommended script. @stable ICU 51 */ + USCRIPT_USAGE_RECOMMENDED +} UScriptUsage; + +/** + * Writes the script sample character string. + * This string normally consists of one code point but might be longer. + * The string is empty if the script is not encoded. + * + * @param script script code + * @param dest output string array + * @param capacity number of UChars in the dest array + * @param pErrorCode standard ICU in/out error code, must pass U_SUCCESS() on input + * @return the string length, even if U_BUFFER_OVERFLOW_ERROR + * @stable ICU 51 + */ +U_CAPI int32_t U_EXPORT2 +uscript_getSampleString(UScriptCode script, UChar *dest, int32_t capacity, UErrorCode *pErrorCode); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN +class UnicodeString; +U_NAMESPACE_END + +/** + * Returns the script sample character string. + * This string normally consists of one code point but might be longer. + * The string is empty if the script is not encoded. + * + * @param script script code + * @return the sample character string + * @stable ICU 51 + */ +U_COMMON_API icu::UnicodeString U_EXPORT2 +uscript_getSampleUnicodeString(UScriptCode script); + +#endif + +/** + * Returns the script usage according to UAX #31 Unicode Identifier and Pattern Syntax. + * Returns USCRIPT_USAGE_NOT_ENCODED if the script is not encoded in Unicode. + * + * @param script script code + * @return script usage + * @see UScriptUsage + * @stable ICU 51 + */ +U_CAPI UScriptUsage U_EXPORT2 +uscript_getUsage(UScriptCode script); + +/** + * Returns true if the script is written right-to-left. + * For example, Arab and Hebr. + * + * @param script script code + * @return true if the script is right-to-left + * @stable ICU 51 + */ +U_CAPI UBool U_EXPORT2 +uscript_isRightToLeft(UScriptCode script); + +/** + * Returns true if the script allows line breaks between letters (excluding hyphenation). + * Such a script typically requires dictionary-based line breaking. + * For example, Hani and Thai. + * + * @param script script code + * @return true if the script allows line breaks between letters + * @stable ICU 51 + */ +U_CAPI UBool U_EXPORT2 +uscript_breaksBetweenLetters(UScriptCode script); + +/** + * Returns true if in modern (or most recent) usage of the script case distinctions are customary. + * For example, Latn and Cyrl. + * + * @param script script code + * @return true if the script is cased + * @stable ICU 51 + */ +U_CAPI UBool U_EXPORT2 +uscript_isCased(UScriptCode script); + +#endif diff --git a/thirdparty/icu4c/common/unicode/uset.h b/thirdparty/icu4c/common/unicode/uset.h new file mode 100644 index 0000000000..502ea8dc14 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uset.h @@ -0,0 +1,1137 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2002-2014, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: uset.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2002mar07 +* created by: Markus W. Scherer +* +* C version of UnicodeSet. +*/ + + +/** + * \file + * \brief C API: Unicode Set + * + * <p>This is a C wrapper around the C++ UnicodeSet class.</p> + */ + +#ifndef __USET_H__ +#define __USET_H__ + +#include "unicode/utypes.h" +#include "unicode/uchar.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +#ifndef USET_DEFINED + +#ifndef U_IN_DOXYGEN +#define USET_DEFINED +#endif +/** + * USet is the C API type corresponding to C++ class UnicodeSet. + * Use the uset_* API to manipulate. Create with + * uset_open*, and destroy with uset_close. + * @stable ICU 2.4 + */ +typedef struct USet USet; +#endif + +/** + * Bitmask values to be passed to uset_openPatternOptions() or + * uset_applyPattern() taking an option parameter. + * @stable ICU 2.4 + */ +enum { + /** + * Ignore white space within patterns unless quoted or escaped. + * @stable ICU 2.4 + */ + USET_IGNORE_SPACE = 1, + + /** + * Enable case insensitive matching. E.g., "[ab]" with this flag + * will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will + * match all except 'a', 'A', 'b', and 'B'. This performs a full + * closure over case mappings, e.g. U+017F for s. + * + * The resulting set is a superset of the input for the code points but + * not for the strings. + * It performs a case mapping closure of the code points and adds + * full case folding strings for the code points, and reduces strings of + * the original set to their full case folding equivalents. + * + * This is designed for case-insensitive matches, for example + * in regular expressions. The full code point case closure allows checking of + * an input character directly against the closure set. + * Strings are matched by comparing the case-folded form from the closure + * set with an incremental case folding of the string in question. + * + * The closure set will also contain single code points if the original + * set contained case-equivalent strings (like U+00DF for "ss" or "Ss" etc.). + * This is not necessary (that is, redundant) for the above matching method + * but results in the same closure sets regardless of whether the original + * set contained the code point or a string. + * + * @stable ICU 2.4 + */ + USET_CASE_INSENSITIVE = 2, + + /** + * Enable case insensitive matching. E.g., "[ab]" with this flag + * will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will + * match all except 'a', 'A', 'b', and 'B'. This adds the lower-, + * title-, and uppercase mappings as well as the case folding + * of each existing element in the set. + * @stable ICU 3.2 + */ + USET_ADD_CASE_MAPPINGS = 4 +}; + +/** + * Argument values for whether span() and similar functions continue while + * the current character is contained vs. not contained in the set. + * + * The functionality is straightforward for sets with only single code points, + * without strings (which is the common case): + * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE work the same. + * - USET_SPAN_CONTAINED and USET_SPAN_SIMPLE are inverses of USET_SPAN_NOT_CONTAINED. + * - span() and spanBack() partition any string the same way when + * alternating between span(USET_SPAN_NOT_CONTAINED) and + * span(either "contained" condition). + * - Using a complemented (inverted) set and the opposite span conditions + * yields the same results. + * + * When a set contains multi-code point strings, then these statements may not + * be true, depending on the strings in the set (for example, whether they + * overlap with each other) and the string that is processed. + * For a set with strings: + * - The complement of the set contains the opposite set of code points, + * but the same set of strings. + * Therefore, complementing both the set and the span conditions + * may yield different results. + * - When starting spans at different positions in a string + * (span(s, ...) vs. span(s+1, ...)) the ends of the spans may be different + * because a set string may start before the later position. + * - span(USET_SPAN_SIMPLE) may be shorter than + * span(USET_SPAN_CONTAINED) because it will not recursively try + * all possible paths. + * For example, with a set which contains the three strings "xy", "xya" and "ax", + * span("xyax", USET_SPAN_CONTAINED) will return 4 but + * span("xyax", USET_SPAN_SIMPLE) will return 3. + * span(USET_SPAN_SIMPLE) will never be longer than + * span(USET_SPAN_CONTAINED). + * - With either "contained" condition, span() and spanBack() may partition + * a string in different ways. + * For example, with a set which contains the two strings "ab" and "ba", + * and when processing the string "aba", + * span() will yield contained/not-contained boundaries of { 0, 2, 3 } + * while spanBack() will yield boundaries of { 0, 1, 3 }. + * + * Note: If it is important to get the same boundaries whether iterating forward + * or backward through a string, then either only span() should be used and + * the boundaries cached for backward operation, or an ICU BreakIterator + * could be used. + * + * Note: Unpaired surrogates are treated like surrogate code points. + * Similarly, set strings match only on code point boundaries, + * never in the middle of a surrogate pair. + * Illegal UTF-8 sequences are treated like U+FFFD. + * When processing UTF-8 strings, malformed set strings + * (strings with unpaired surrogates which cannot be converted to UTF-8) + * are ignored. + * + * @stable ICU 3.8 + */ +typedef enum USetSpanCondition { + /** + * Continues a span() while there is no set element at the current position. + * Increments by one code point at a time. + * Stops before the first set element (character or string). + * (For code points only, this is like while contains(current)==false). + * + * When span() returns, the substring between where it started and the position + * it returned consists only of characters that are not in the set, + * and none of its strings overlap with the span. + * + * @stable ICU 3.8 + */ + USET_SPAN_NOT_CONTAINED = 0, + /** + * Spans the longest substring that is a concatenation of set elements (characters or strings). + * (For characters only, this is like while contains(current)==true). + * + * When span() returns, the substring between where it started and the position + * it returned consists only of set elements (characters or strings) that are in the set. + * + * If a set contains strings, then the span will be the longest substring for which there + * exists at least one non-overlapping concatenation of set elements (characters or strings). + * This is equivalent to a POSIX regular expression for <code>(OR of each set element)*</code>. + * (Java/ICU/Perl regex stops at the first match of an OR.) + * + * @stable ICU 3.8 + */ + USET_SPAN_CONTAINED = 1, + /** + * Continues a span() while there is a set element at the current position. + * Increments by the longest matching element at each position. + * (For characters only, this is like while contains(current)==true). + * + * When span() returns, the substring between where it started and the position + * it returned consists only of set elements (characters or strings) that are in the set. + * + * If a set only contains single characters, then this is the same + * as USET_SPAN_CONTAINED. + * + * If a set contains strings, then the span will be the longest substring + * with a match at each position with the longest single set element (character or string). + * + * Use this span condition together with other longest-match algorithms, + * such as ICU converters (ucnv_getUnicodeSet()). + * + * @stable ICU 3.8 + */ + USET_SPAN_SIMPLE = 2, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the last span condition. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + USET_SPAN_CONDITION_COUNT +#endif // U_HIDE_DEPRECATED_API +} USetSpanCondition; + +enum { + /** + * Capacity of USerializedSet::staticArray. + * Enough for any single-code point set. + * Also provides padding for nice sizeof(USerializedSet). + * @stable ICU 2.4 + */ + USET_SERIALIZED_STATIC_ARRAY_CAPACITY=8 +}; + +/** + * A serialized form of a Unicode set. Limited manipulations are + * possible directly on a serialized set. See below. + * @stable ICU 2.4 + */ +typedef struct USerializedSet { + /** + * The serialized Unicode Set. + * @stable ICU 2.4 + */ + const uint16_t *array; + /** + * The length of the array that contains BMP characters. + * @stable ICU 2.4 + */ + int32_t bmpLength; + /** + * The total length of the array. + * @stable ICU 2.4 + */ + int32_t length; + /** + * A small buffer for the array to reduce memory allocations. + * @stable ICU 2.4 + */ + uint16_t staticArray[USET_SERIALIZED_STATIC_ARRAY_CAPACITY]; +} USerializedSet; + +/********************************************************************* + * USet API + *********************************************************************/ + +/** + * Create an empty USet object. + * Equivalent to uset_open(1, 0). + * @return a newly created USet. The caller must call uset_close() on + * it when done. + * @stable ICU 4.2 + */ +U_CAPI USet* U_EXPORT2 +uset_openEmpty(void); + +/** + * Creates a USet object that contains the range of characters + * start..end, inclusive. If <code>start > end</code> + * then an empty set is created (same as using uset_openEmpty()). + * @param start first character of the range, inclusive + * @param end last character of the range, inclusive + * @return a newly created USet. The caller must call uset_close() on + * it when done. + * @stable ICU 2.4 + */ +U_CAPI USet* U_EXPORT2 +uset_open(UChar32 start, UChar32 end); + +/** + * Creates a set from the given pattern. See the UnicodeSet class + * description for the syntax of the pattern language. + * @param pattern a string specifying what characters are in the set + * @param patternLength the length of the pattern, or -1 if null + * terminated + * @param ec the error code + * @stable ICU 2.4 + */ +U_CAPI USet* U_EXPORT2 +uset_openPattern(const UChar* pattern, int32_t patternLength, + UErrorCode* ec); + +/** + * Creates a set from the given pattern. See the UnicodeSet class + * description for the syntax of the pattern language. + * @param pattern a string specifying what characters are in the set + * @param patternLength the length of the pattern, or -1 if null + * terminated + * @param options bitmask for options to apply to the pattern. + * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE. + * @param ec the error code + * @stable ICU 2.4 + */ +U_CAPI USet* U_EXPORT2 +uset_openPatternOptions(const UChar* pattern, int32_t patternLength, + uint32_t options, + UErrorCode* ec); + +/** + * Disposes of the storage used by a USet object. This function should + * be called exactly once for objects returned by uset_open(). + * @param set the object to dispose of + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +uset_close(USet* set); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUSetPointer + * "Smart pointer" class, closes a USet via uset_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUSetPointer, USet, uset_close); + +U_NAMESPACE_END + +#endif + +/** + * Returns a copy of this object. + * If this set is frozen, then the clone will be frozen as well. + * Use uset_cloneAsThawed() for a mutable clone of a frozen set. + * @param set the original set + * @return the newly allocated copy of the set + * @see uset_cloneAsThawed + * @stable ICU 3.8 + */ +U_CAPI USet * U_EXPORT2 +uset_clone(const USet *set); + +/** + * Determines whether the set has been frozen (made immutable) or not. + * See the ICU4J Freezable interface for details. + * @param set the set + * @return true/false for whether the set has been frozen + * @see uset_freeze + * @see uset_cloneAsThawed + * @stable ICU 3.8 + */ +U_CAPI UBool U_EXPORT2 +uset_isFrozen(const USet *set); + +/** + * Freeze the set (make it immutable). + * Once frozen, it cannot be unfrozen and is therefore thread-safe + * until it is deleted. + * See the ICU4J Freezable interface for details. + * Freezing the set may also make some operations faster, for example + * uset_contains() and uset_span(). + * A frozen set will not be modified. (It remains frozen.) + * @param set the set + * @return the same set, now frozen + * @see uset_isFrozen + * @see uset_cloneAsThawed + * @stable ICU 3.8 + */ +U_CAPI void U_EXPORT2 +uset_freeze(USet *set); + +/** + * Clone the set and make the clone mutable. + * See the ICU4J Freezable interface for details. + * @param set the set + * @return the mutable clone + * @see uset_freeze + * @see uset_isFrozen + * @see uset_clone + * @stable ICU 3.8 + */ +U_CAPI USet * U_EXPORT2 +uset_cloneAsThawed(const USet *set); + +/** + * Causes the USet object to represent the range <code>start - end</code>. + * If <code>start > end</code> then this USet is set to an empty range. + * A frozen set will not be modified. + * @param set the object to set to the given range + * @param start first character in the set, inclusive + * @param end last character in the set, inclusive + * @stable ICU 3.2 + */ +U_CAPI void U_EXPORT2 +uset_set(USet* set, + UChar32 start, UChar32 end); + +/** + * Modifies the set to represent the set specified by the given + * pattern. See the UnicodeSet class description for the syntax of + * the pattern language. See also the User Guide chapter about UnicodeSet. + * <em>Empties the set passed before applying the pattern.</em> + * A frozen set will not be modified. + * @param set The set to which the pattern is to be applied. + * @param pattern A pointer to UChar string specifying what characters are in the set. + * The character at pattern[0] must be a '['. + * @param patternLength The length of the UChar string. -1 if NUL terminated. + * @param options A bitmask for options to apply to the pattern. + * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE. + * @param status Returns an error if the pattern cannot be parsed. + * @return Upon successful parse, the value is either + * the index of the character after the closing ']' + * of the parsed pattern. + * If the status code indicates failure, then the return value + * is the index of the error in the source. + * + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +uset_applyPattern(USet *set, + const UChar *pattern, int32_t patternLength, + uint32_t options, + UErrorCode *status); + +/** + * Modifies the set to contain those code points which have the given value + * for the given binary or enumerated property, as returned by + * u_getIntPropertyValue. Prior contents of this set are lost. + * A frozen set will not be modified. + * + * @param set the object to contain the code points defined by the property + * + * @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1 + * or UCHAR_INT_START..UCHAR_INT_LIMIT-1 + * or UCHAR_MASK_START..UCHAR_MASK_LIMIT-1. + * + * @param value a value in the range u_getIntPropertyMinValue(prop).. + * u_getIntPropertyMaxValue(prop), with one exception. If prop is + * UCHAR_GENERAL_CATEGORY_MASK, then value should not be a UCharCategory, but + * rather a mask value produced by U_GET_GC_MASK(). This allows grouped + * categories such as [:L:] to be represented. + * + * @param ec error code input/output parameter + * + * @stable ICU 3.2 + */ +U_CAPI void U_EXPORT2 +uset_applyIntPropertyValue(USet* set, + UProperty prop, int32_t value, UErrorCode* ec); + +/** + * Modifies the set to contain those code points which have the + * given value for the given property. Prior contents of this + * set are lost. + * A frozen set will not be modified. + * + * @param set the object to contain the code points defined by the given + * property and value alias + * + * @param prop a string specifying a property alias, either short or long. + * The name is matched loosely. See PropertyAliases.txt for names and a + * description of loose matching. If the value string is empty, then this + * string is interpreted as either a General_Category value alias, a Script + * value alias, a binary property alias, or a special ID. Special IDs are + * matched loosely and correspond to the following sets: + * + * "ANY" = [\\u0000-\\U0010FFFF], + * "ASCII" = [\\u0000-\\u007F], + * "Assigned" = [:^Cn:]. + * + * @param propLength the length of the prop, or -1 if NULL + * + * @param value a string specifying a value alias, either short or long. + * The name is matched loosely. See PropertyValueAliases.txt for names + * and a description of loose matching. In addition to aliases listed, + * numeric values and canonical combining classes may be expressed + * numerically, e.g., ("nv", "0.5") or ("ccc", "220"). The value string + * may also be empty. + * + * @param valueLength the length of the value, or -1 if NULL + * + * @param ec error code input/output parameter + * + * @stable ICU 3.2 + */ +U_CAPI void U_EXPORT2 +uset_applyPropertyAlias(USet* set, + const UChar *prop, int32_t propLength, + const UChar *value, int32_t valueLength, + UErrorCode* ec); + +/** + * Return true if the given position, in the given pattern, appears + * to be the start of a UnicodeSet pattern. + * + * @param pattern a string specifying the pattern + * @param patternLength the length of the pattern, or -1 if NULL + * @param pos the given position + * @stable ICU 3.2 + */ +U_CAPI UBool U_EXPORT2 +uset_resemblesPattern(const UChar *pattern, int32_t patternLength, + int32_t pos); + +/** + * Returns a string representation of this set. If the result of + * calling this function is passed to a uset_openPattern(), it + * will produce another set that is equal to this one. + * @param set the set + * @param result the string to receive the rules, may be NULL + * @param resultCapacity the capacity of result, may be 0 if result is NULL + * @param escapeUnprintable if true then convert unprintable + * character to their hex escape representations, \\uxxxx or + * \\Uxxxxxxxx. Unprintable characters are those other than + * U+000A, U+0020..U+007E. + * @param ec error code. + * @return length of string, possibly larger than resultCapacity + * @stable ICU 2.4 + */ +U_CAPI int32_t U_EXPORT2 +uset_toPattern(const USet* set, + UChar* result, int32_t resultCapacity, + UBool escapeUnprintable, + UErrorCode* ec); + +/** + * Adds the given character to the given USet. After this call, + * uset_contains(set, c) will return true. + * A frozen set will not be modified. + * @param set the object to which to add the character + * @param c the character to add + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +uset_add(USet* set, UChar32 c); + +/** + * Adds all of the elements in the specified set to this set if + * they're not already present. This operation effectively + * modifies this set so that its value is the <i>union</i> of the two + * sets. The behavior of this operation is unspecified if the specified + * collection is modified while the operation is in progress. + * A frozen set will not be modified. + * + * @param set the object to which to add the set + * @param additionalSet the source set whose elements are to be added to this set. + * @stable ICU 2.6 + */ +U_CAPI void U_EXPORT2 +uset_addAll(USet* set, const USet *additionalSet); + +/** + * Adds the given range of characters to the given USet. After this call, + * uset_contains(set, start, end) will return true. + * A frozen set will not be modified. + * @param set the object to which to add the character + * @param start the first character of the range to add, inclusive + * @param end the last character of the range to add, inclusive + * @stable ICU 2.2 + */ +U_CAPI void U_EXPORT2 +uset_addRange(USet* set, UChar32 start, UChar32 end); + +/** + * Adds the given string to the given USet. After this call, + * uset_containsString(set, str, strLen) will return true. + * A frozen set will not be modified. + * @param set the object to which to add the character + * @param str the string to add + * @param strLen the length of the string or -1 if null terminated. + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +uset_addString(USet* set, const UChar* str, int32_t strLen); + +/** + * Adds each of the characters in this string to the set. Thus "ch" => {"c", "h"} + * If this set already any particular character, it has no effect on that character. + * A frozen set will not be modified. + * @param set the object to which to add the character + * @param str the source string + * @param strLen the length of the string or -1 if null terminated. + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +uset_addAllCodePoints(USet* set, const UChar *str, int32_t strLen); + +/** + * Removes the given character from the given USet. After this call, + * uset_contains(set, c) will return false. + * A frozen set will not be modified. + * @param set the object from which to remove the character + * @param c the character to remove + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +uset_remove(USet* set, UChar32 c); + +/** + * Removes the given range of characters from the given USet. After this call, + * uset_contains(set, start, end) will return false. + * A frozen set will not be modified. + * @param set the object to which to add the character + * @param start the first character of the range to remove, inclusive + * @param end the last character of the range to remove, inclusive + * @stable ICU 2.2 + */ +U_CAPI void U_EXPORT2 +uset_removeRange(USet* set, UChar32 start, UChar32 end); + +/** + * Removes the given string to the given USet. After this call, + * uset_containsString(set, str, strLen) will return false. + * A frozen set will not be modified. + * @param set the object to which to add the character + * @param str the string to remove + * @param strLen the length of the string or -1 if null terminated. + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +uset_removeString(USet* set, const UChar* str, int32_t strLen); + +/** + * Removes from this set all of its elements that are contained in the + * specified set. This operation effectively modifies this + * set so that its value is the <i>asymmetric set difference</i> of + * the two sets. + * A frozen set will not be modified. + * @param set the object from which the elements are to be removed + * @param removeSet the object that defines which elements will be + * removed from this set + * @stable ICU 3.2 + */ +U_CAPI void U_EXPORT2 +uset_removeAll(USet* set, const USet* removeSet); + +/** + * Retain only the elements in this set that are contained in the + * specified range. If <code>start > end</code> then an empty range is + * retained, leaving the set empty. This is equivalent to + * a boolean logic AND, or a set INTERSECTION. + * A frozen set will not be modified. + * + * @param set the object for which to retain only the specified range + * @param start first character, inclusive, of range to be retained + * to this set. + * @param end last character, inclusive, of range to be retained + * to this set. + * @stable ICU 3.2 + */ +U_CAPI void U_EXPORT2 +uset_retain(USet* set, UChar32 start, UChar32 end); + +/** + * Retains only the elements in this set that are contained in the + * specified set. In other words, removes from this set all of + * its elements that are not contained in the specified set. This + * operation effectively modifies this set so that its value is + * the <i>intersection</i> of the two sets. + * A frozen set will not be modified. + * + * @param set the object on which to perform the retain + * @param retain set that defines which elements this set will retain + * @stable ICU 3.2 + */ +U_CAPI void U_EXPORT2 +uset_retainAll(USet* set, const USet* retain); + +/** + * Reallocate this objects internal structures to take up the least + * possible space, without changing this object's value. + * A frozen set will not be modified. + * + * @param set the object on which to perfrom the compact + * @stable ICU 3.2 + */ +U_CAPI void U_EXPORT2 +uset_compact(USet* set); + +/** + * Inverts this set. This operation modifies this set so that + * its value is its complement. This operation does not affect + * the multicharacter strings, if any. + * A frozen set will not be modified. + * @param set the set + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +uset_complement(USet* set); + +/** + * Complements in this set all elements contained in the specified + * set. Any character in the other set will be removed if it is + * in this set, or will be added if it is not in this set. + * A frozen set will not be modified. + * + * @param set the set with which to complement + * @param complement set that defines which elements will be xor'ed + * from this set. + * @stable ICU 3.2 + */ +U_CAPI void U_EXPORT2 +uset_complementAll(USet* set, const USet* complement); + +/** + * Removes all of the elements from this set. This set will be + * empty after this call returns. + * A frozen set will not be modified. + * @param set the set + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +uset_clear(USet* set); + +/** + * Close this set over the given attribute. For the attribute + * USET_CASE, the result is to modify this set so that: + * + * 1. For each character or string 'a' in this set, all strings or + * characters 'b' such that foldCase(a) == foldCase(b) are added + * to this set. + * + * 2. For each string 'e' in the resulting set, if e != + * foldCase(e), 'e' will be removed. + * + * Example: [aq\\u00DF{Bc}{bC}{Fi}] => [aAqQ\\u00DF\\uFB01{ss}{bc}{fi}] + * + * (Here foldCase(x) refers to the operation u_strFoldCase, and a + * == b denotes that the contents are the same, not pointer + * comparison.) + * + * A frozen set will not be modified. + * + * @param set the set + * + * @param attributes bitmask for attributes to close over. + * Currently only the USET_CASE bit is supported. Any undefined bits + * are ignored. + * @stable ICU 4.2 + */ +U_CAPI void U_EXPORT2 +uset_closeOver(USet* set, int32_t attributes); + +/** + * Remove all strings from this set. + * + * @param set the set + * @stable ICU 4.2 + */ +U_CAPI void U_EXPORT2 +uset_removeAllStrings(USet* set); + +/** + * Returns true if the given USet contains no characters and no + * strings. + * @param set the set + * @return true if set is empty + * @stable ICU 2.4 + */ +U_CAPI UBool U_EXPORT2 +uset_isEmpty(const USet* set); + +/** + * Returns true if the given USet contains the given character. + * This function works faster with a frozen set. + * @param set the set + * @param c The codepoint to check for within the set + * @return true if set contains c + * @stable ICU 2.4 + */ +U_CAPI UBool U_EXPORT2 +uset_contains(const USet* set, UChar32 c); + +/** + * Returns true if the given USet contains all characters c + * where start <= c && c <= end. + * @param set the set + * @param start the first character of the range to test, inclusive + * @param end the last character of the range to test, inclusive + * @return true if set contains the range + * @stable ICU 2.2 + */ +U_CAPI UBool U_EXPORT2 +uset_containsRange(const USet* set, UChar32 start, UChar32 end); + +/** + * Returns true if the given USet contains the given string. + * @param set the set + * @param str the string + * @param strLen the length of the string or -1 if null terminated. + * @return true if set contains str + * @stable ICU 2.4 + */ +U_CAPI UBool U_EXPORT2 +uset_containsString(const USet* set, const UChar* str, int32_t strLen); + +/** + * Returns the index of the given character within this set, where + * the set is ordered by ascending code point. If the character + * is not in this set, return -1. The inverse of this method is + * <code>charAt()</code>. + * @param set the set + * @param c the character to obtain the index for + * @return an index from 0..size()-1, or -1 + * @stable ICU 3.2 + */ +U_CAPI int32_t U_EXPORT2 +uset_indexOf(const USet* set, UChar32 c); + +/** + * Returns the character at the given index within this set, where + * the set is ordered by ascending code point. If the index is + * out of range, return (UChar32)-1. The inverse of this method is + * <code>indexOf()</code>. + * @param set the set + * @param charIndex an index from 0..size()-1 to obtain the char for + * @return the character at the given index, or (UChar32)-1. + * @stable ICU 3.2 + */ +U_CAPI UChar32 U_EXPORT2 +uset_charAt(const USet* set, int32_t charIndex); + +/** + * Returns the number of characters and strings contained in the given + * USet. + * @param set the set + * @return a non-negative integer counting the characters and strings + * contained in set + * @stable ICU 2.4 + */ +U_CAPI int32_t U_EXPORT2 +uset_size(const USet* set); + +/** + * Returns the number of items in this set. An item is either a range + * of characters or a single multicharacter string. + * @param set the set + * @return a non-negative integer counting the character ranges + * and/or strings contained in set + * @stable ICU 2.4 + */ +U_CAPI int32_t U_EXPORT2 +uset_getItemCount(const USet* set); + +/** + * Returns an item of this set. An item is either a range of + * characters or a single multicharacter string. + * @param set the set + * @param itemIndex a non-negative integer in the range 0.. + * uset_getItemCount(set)-1 + * @param start pointer to variable to receive first character + * in range, inclusive + * @param end pointer to variable to receive last character in range, + * inclusive + * @param str buffer to receive the string, may be NULL + * @param strCapacity capacity of str, or 0 if str is NULL + * @param ec error code + * @return the length of the string (>= 2), or 0 if the item is a + * range, in which case it is the range *start..*end, or -1 if + * itemIndex is out of range + * @stable ICU 2.4 + */ +U_CAPI int32_t U_EXPORT2 +uset_getItem(const USet* set, int32_t itemIndex, + UChar32* start, UChar32* end, + UChar* str, int32_t strCapacity, + UErrorCode* ec); + +/** + * Returns true if set1 contains all the characters and strings + * of set2. It answers the question, 'Is set1 a superset of set2?' + * @param set1 set to be checked for containment + * @param set2 set to be checked for containment + * @return true if the test condition is met + * @stable ICU 3.2 + */ +U_CAPI UBool U_EXPORT2 +uset_containsAll(const USet* set1, const USet* set2); + +/** + * Returns true if this set contains all the characters + * of the given string. This is does not check containment of grapheme + * clusters, like uset_containsString. + * @param set set of characters to be checked for containment + * @param str string containing codepoints to be checked for containment + * @param strLen the length of the string or -1 if null terminated. + * @return true if the test condition is met + * @stable ICU 3.4 + */ +U_CAPI UBool U_EXPORT2 +uset_containsAllCodePoints(const USet* set, const UChar *str, int32_t strLen); + +/** + * Returns true if set1 contains none of the characters and strings + * of set2. It answers the question, 'Is set1 a disjoint set of set2?' + * @param set1 set to be checked for containment + * @param set2 set to be checked for containment + * @return true if the test condition is met + * @stable ICU 3.2 + */ +U_CAPI UBool U_EXPORT2 +uset_containsNone(const USet* set1, const USet* set2); + +/** + * Returns true if set1 contains some of the characters and strings + * of set2. It answers the question, 'Does set1 and set2 have an intersection?' + * @param set1 set to be checked for containment + * @param set2 set to be checked for containment + * @return true if the test condition is met + * @stable ICU 3.2 + */ +U_CAPI UBool U_EXPORT2 +uset_containsSome(const USet* set1, const USet* set2); + +/** + * Returns the length of the initial substring of the input string which + * consists only of characters and strings that are contained in this set + * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), + * or only of characters and strings that are not contained + * in this set (USET_SPAN_NOT_CONTAINED). + * See USetSpanCondition for details. + * Similar to the strspn() C library function. + * Unpaired surrogates are treated according to contains() of their surrogate code points. + * This function works faster with a frozen set and with a non-negative string length argument. + * @param set the set + * @param s start of the string + * @param length of the string; can be -1 for NUL-terminated + * @param spanCondition specifies the containment condition + * @return the length of the initial substring according to the spanCondition; + * 0 if the start of the string does not fit the spanCondition + * @stable ICU 3.8 + * @see USetSpanCondition + */ +U_CAPI int32_t U_EXPORT2 +uset_span(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition); + +/** + * Returns the start of the trailing substring of the input string which + * consists only of characters and strings that are contained in this set + * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), + * or only of characters and strings that are not contained + * in this set (USET_SPAN_NOT_CONTAINED). + * See USetSpanCondition for details. + * Unpaired surrogates are treated according to contains() of their surrogate code points. + * This function works faster with a frozen set and with a non-negative string length argument. + * @param set the set + * @param s start of the string + * @param length of the string; can be -1 for NUL-terminated + * @param spanCondition specifies the containment condition + * @return the start of the trailing substring according to the spanCondition; + * the string length if the end of the string does not fit the spanCondition + * @stable ICU 3.8 + * @see USetSpanCondition + */ +U_CAPI int32_t U_EXPORT2 +uset_spanBack(const USet *set, const UChar *s, int32_t length, USetSpanCondition spanCondition); + +/** + * Returns the length of the initial substring of the input string which + * consists only of characters and strings that are contained in this set + * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), + * or only of characters and strings that are not contained + * in this set (USET_SPAN_NOT_CONTAINED). + * See USetSpanCondition for details. + * Similar to the strspn() C library function. + * Malformed byte sequences are treated according to contains(0xfffd). + * This function works faster with a frozen set and with a non-negative string length argument. + * @param set the set + * @param s start of the string (UTF-8) + * @param length of the string; can be -1 for NUL-terminated + * @param spanCondition specifies the containment condition + * @return the length of the initial substring according to the spanCondition; + * 0 if the start of the string does not fit the spanCondition + * @stable ICU 3.8 + * @see USetSpanCondition + */ +U_CAPI int32_t U_EXPORT2 +uset_spanUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition); + +/** + * Returns the start of the trailing substring of the input string which + * consists only of characters and strings that are contained in this set + * (USET_SPAN_CONTAINED, USET_SPAN_SIMPLE), + * or only of characters and strings that are not contained + * in this set (USET_SPAN_NOT_CONTAINED). + * See USetSpanCondition for details. + * Malformed byte sequences are treated according to contains(0xfffd). + * This function works faster with a frozen set and with a non-negative string length argument. + * @param set the set + * @param s start of the string (UTF-8) + * @param length of the string; can be -1 for NUL-terminated + * @param spanCondition specifies the containment condition + * @return the start of the trailing substring according to the spanCondition; + * the string length if the end of the string does not fit the spanCondition + * @stable ICU 3.8 + * @see USetSpanCondition + */ +U_CAPI int32_t U_EXPORT2 +uset_spanBackUTF8(const USet *set, const char *s, int32_t length, USetSpanCondition spanCondition); + +/** + * Returns true if set1 contains all of the characters and strings + * of set2, and vis versa. It answers the question, 'Is set1 equal to set2?' + * @param set1 set to be checked for containment + * @param set2 set to be checked for containment + * @return true if the test condition is met + * @stable ICU 3.2 + */ +U_CAPI UBool U_EXPORT2 +uset_equals(const USet* set1, const USet* set2); + +/********************************************************************* + * Serialized set API + *********************************************************************/ + +/** + * Serializes this set into an array of 16-bit integers. Serialization + * (currently) only records the characters in the set; multicharacter + * strings are ignored. + * + * The array + * has following format (each line is one 16-bit integer): + * + * length = (n+2*m) | (m!=0?0x8000:0) + * bmpLength = n; present if m!=0 + * bmp[0] + * bmp[1] + * ... + * bmp[n-1] + * supp-high[0] + * supp-low[0] + * supp-high[1] + * supp-low[1] + * ... + * supp-high[m-1] + * supp-low[m-1] + * + * The array starts with a header. After the header are n bmp + * code points, then m supplementary code points. Either n or m + * or both may be zero. n+2*m is always <= 0x7FFF. + * + * If there are no supplementary characters (if m==0) then the + * header is one 16-bit integer, 'length', with value n. + * + * If there are supplementary characters (if m!=0) then the header + * is two 16-bit integers. The first, 'length', has value + * (n+2*m)|0x8000. The second, 'bmpLength', has value n. + * + * After the header the code points are stored in ascending order. + * Supplementary code points are stored as most significant 16 + * bits followed by least significant 16 bits. + * + * @param set the set + * @param dest pointer to buffer of destCapacity 16-bit integers. + * May be NULL only if destCapacity is zero. + * @param destCapacity size of dest, or zero. Must not be negative. + * @param pErrorCode pointer to the error code. Will be set to + * U_INDEX_OUTOFBOUNDS_ERROR if n+2*m > 0x7FFF. Will be set to + * U_BUFFER_OVERFLOW_ERROR if n+2*m+(m!=0?2:1) > destCapacity. + * @return the total length of the serialized format, including + * the header, that is, n+2*m+(m!=0?2:1), or 0 on error other + * than U_BUFFER_OVERFLOW_ERROR. + * @stable ICU 2.4 + */ +U_CAPI int32_t U_EXPORT2 +uset_serialize(const USet* set, uint16_t* dest, int32_t destCapacity, UErrorCode* pErrorCode); + +/** + * Given a serialized array, fill in the given serialized set object. + * @param fillSet pointer to result + * @param src pointer to start of array + * @param srcLength length of array + * @return true if the given array is valid, otherwise false + * @stable ICU 2.4 + */ +U_CAPI UBool U_EXPORT2 +uset_getSerializedSet(USerializedSet* fillSet, const uint16_t* src, int32_t srcLength); + +/** + * Set the USerializedSet to contain the given character (and nothing + * else). + * @param fillSet pointer to result + * @param c The codepoint to set + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +uset_setSerializedToOne(USerializedSet* fillSet, UChar32 c); + +/** + * Returns true if the given USerializedSet contains the given + * character. + * @param set the serialized set + * @param c The codepoint to check for within the set + * @return true if set contains c + * @stable ICU 2.4 + */ +U_CAPI UBool U_EXPORT2 +uset_serializedContains(const USerializedSet* set, UChar32 c); + +/** + * Returns the number of disjoint ranges of characters contained in + * the given serialized set. Ignores any strings contained in the + * set. + * @param set the serialized set + * @return a non-negative integer counting the character ranges + * contained in set + * @stable ICU 2.4 + */ +U_CAPI int32_t U_EXPORT2 +uset_getSerializedRangeCount(const USerializedSet* set); + +/** + * Returns a range of characters contained in the given serialized + * set. + * @param set the serialized set + * @param rangeIndex a non-negative integer in the range 0.. + * uset_getSerializedRangeCount(set)-1 + * @param pStart pointer to variable to receive first character + * in range, inclusive + * @param pEnd pointer to variable to receive last character in range, + * inclusive + * @return true if rangeIndex is valid, otherwise false + * @stable ICU 2.4 + */ +U_CAPI UBool U_EXPORT2 +uset_getSerializedRange(const USerializedSet* set, int32_t rangeIndex, + UChar32* pStart, UChar32* pEnd); + +#endif diff --git a/thirdparty/icu4c/common/unicode/usetiter.h b/thirdparty/icu4c/common/unicode/usetiter.h new file mode 100644 index 0000000000..a817ef72b3 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/usetiter.h @@ -0,0 +1,325 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (c) 2002-2014, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +*/ +#ifndef USETITER_H +#define USETITER_H + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API + +#include "unicode/uobject.h" +#include "unicode/unistr.h" + +/** + * \file + * \brief C++ API: UnicodeSetIterator iterates over the contents of a UnicodeSet. + */ + +U_NAMESPACE_BEGIN + +class UnicodeSet; +class UnicodeString; + +/** + * + * UnicodeSetIterator iterates over the contents of a UnicodeSet. It + * iterates over either code points or code point ranges. After all + * code points or ranges have been returned, it returns the + * multicharacter strings of the UnicodeSet, if any. + * + * This class is not intended to be subclassed. Consider any fields + * or methods declared as "protected" to be private. The use of + * protected in this class is an artifact of history. + * + * <p>To iterate over code points and strings, use a loop like this: + * <pre> + * UnicodeSetIterator it(set); + * while (it.next()) { + * processItem(it.getString()); + * } + * </pre> + * <p>Each item in the set is accessed as a string. Set elements + * consisting of single code points are returned as strings containing + * just the one code point. + * + * <p>To iterate over code point ranges, instead of individual code points, + * use a loop like this: + * <pre> + * UnicodeSetIterator it(set); + * while (it.nextRange()) { + * if (it.isString()) { + * processString(it.getString()); + * } else { + * processCodepointRange(it.getCodepoint(), it.getCodepointEnd()); + * } + * } + * </pre> + * @author M. Davis + * @stable ICU 2.4 + */ +class U_COMMON_API UnicodeSetIterator : public UObject { + + protected: + + /** + * Value of <tt>codepoint</tt> if the iterator points to a string. + * If <tt>codepoint == IS_STRING</tt>, then examine + * <tt>string</tt> for the current iteration result. + * @stable ICU 2.4 + */ + enum { IS_STRING = -1 }; + + /** + * Current code point, or the special value <tt>IS_STRING</tt>, if + * the iterator points to a string. + * @stable ICU 2.4 + */ + UChar32 codepoint; + + /** + * When iterating over ranges using <tt>nextRange()</tt>, + * <tt>codepointEnd</tt> contains the inclusive end of the + * iteration range, if <tt>codepoint != IS_STRING</tt>. If + * iterating over code points using <tt>next()</tt>, or if + * <tt>codepoint == IS_STRING</tt>, then the value of + * <tt>codepointEnd</tt> is undefined. + * @stable ICU 2.4 + */ + UChar32 codepointEnd; + + /** + * If <tt>codepoint == IS_STRING</tt>, then <tt>string</tt> points + * to the current string. If <tt>codepoint != IS_STRING</tt>, the + * value of <tt>string</tt> is undefined. + * @stable ICU 2.4 + */ + const UnicodeString* string; + + public: + + /** + * Create an iterator over the given set. The iterator is valid + * only so long as <tt>set</tt> is valid. + * @param set set to iterate over + * @stable ICU 2.4 + */ + UnicodeSetIterator(const UnicodeSet& set); + + /** + * Create an iterator over nothing. <tt>next()</tt> and + * <tt>nextRange()</tt> return false. This is a convenience + * constructor allowing the target to be set later. + * @stable ICU 2.4 + */ + UnicodeSetIterator(); + + /** + * Destructor. + * @stable ICU 2.4 + */ + virtual ~UnicodeSetIterator(); + + /** + * Returns true if the current element is a string. If so, the + * caller can retrieve it with <tt>getString()</tt>. If this + * method returns false, the current element is a code point or + * code point range, depending on whether <tt>next()</tt> or + * <tt>nextRange()</tt> was called. + * Elements of types string and codepoint can both be retrieved + * with the function <tt>getString()</tt>. + * Elements of type codepoint can also be retrieved with + * <tt>getCodepoint()</tt>. + * For ranges, <tt>getCodepoint()</tt> returns the starting codepoint + * of the range, and <tt>getCodepointEnd()</tt> returns the end + * of the range. + * @stable ICU 2.4 + */ + inline UBool isString() const; + + /** + * Returns the current code point, if <tt>isString()</tt> returned + * false. Otherwise returns an undefined result. + * @stable ICU 2.4 + */ + inline UChar32 getCodepoint() const; + + /** + * Returns the end of the current code point range, if + * <tt>isString()</tt> returned false and <tt>nextRange()</tt> was + * called. Otherwise returns an undefined result. + * @stable ICU 2.4 + */ + inline UChar32 getCodepointEnd() const; + + /** + * Returns the current string, if <tt>isString()</tt> returned + * true. If the current iteration item is a code point, a UnicodeString + * containing that single code point is returned. + * + * Ownership of the returned string remains with the iterator. + * The string is guaranteed to remain valid only until the iterator is + * advanced to the next item, or until the iterator is deleted. + * + * @stable ICU 2.4 + */ + const UnicodeString& getString(); + + /** + * Advances the iteration position to the next element in the set, + * which can be either a single code point or a string. + * If there are no more elements in the set, return false. + * + * <p> + * If <tt>isString() == true</tt>, the value is a + * string, otherwise the value is a + * single code point. Elements of either type can be retrieved + * with the function <tt>getString()</tt>, while elements of + * consisting of a single code point can be retrieved with + * <tt>getCodepoint()</tt> + * + * <p>The order of iteration is all code points in sorted order, + * followed by all strings sorted order. Do not mix + * calls to <tt>next()</tt> and <tt>nextRange()</tt> without + * calling <tt>reset()</tt> between them. The results of doing so + * are undefined. + * + * @return true if there was another element in the set. + * @stable ICU 2.4 + */ + UBool next(); + + /** + * Returns the next element in the set, either a code point range + * or a string. If there are no more elements in the set, return + * false. If <tt>isString() == true</tt>, the value is a + * string and can be accessed with <tt>getString()</tt>. Otherwise the value is a + * range of one or more code points from <tt>getCodepoint()</tt> to + * <tt>getCodepointeEnd()</tt> inclusive. + * + * <p>The order of iteration is all code points ranges in sorted + * order, followed by all strings sorted order. Ranges are + * disjoint and non-contiguous. The value returned from <tt>getString()</tt> + * is undefined unless <tt>isString() == true</tt>. Do not mix calls to + * <tt>next()</tt> and <tt>nextRange()</tt> without calling + * <tt>reset()</tt> between them. The results of doing so are + * undefined. + * + * @return true if there was another element in the set. + * @stable ICU 2.4 + */ + UBool nextRange(); + + /** + * Sets this iterator to visit the elements of the given set and + * resets it to the start of that set. The iterator is valid only + * so long as <tt>set</tt> is valid. + * @param set the set to iterate over. + * @stable ICU 2.4 + */ + void reset(const UnicodeSet& set); + + /** + * Resets this iterator to the start of the set. + * @stable ICU 2.4 + */ + void reset(); + + /** + * ICU "poor man's RTTI", returns a UClassID for this class. + * + * @stable ICU 2.4 + */ + static UClassID U_EXPORT2 getStaticClassID(); + + /** + * ICU "poor man's RTTI", returns a UClassID for the actual class. + * + * @stable ICU 2.4 + */ + virtual UClassID getDynamicClassID() const; + + // ======================= PRIVATES =========================== + + protected: + + // endElement and nextElements are really UChar32's, but we keep + // them as signed int32_t's so we can do comparisons with + // endElement set to -1. Leave them as int32_t's. + /** The set + * @stable ICU 2.4 + */ + const UnicodeSet* set; + /** End range + * @stable ICU 2.4 + */ + int32_t endRange; + /** Range + * @stable ICU 2.4 + */ + int32_t range; + /** End element + * @stable ICU 2.4 + */ + int32_t endElement; + /** Next element + * @stable ICU 2.4 + */ + int32_t nextElement; + //UBool abbreviated; + /** Next string + * @stable ICU 2.4 + */ + int32_t nextString; + /** String count + * @stable ICU 2.4 + */ + int32_t stringCount; + + /** + * Points to the string to use when the caller asks for a + * string and the current iteration item is a code point, not a string. + * @internal + */ + UnicodeString *cpString; + + /** Copy constructor. Disallowed. + * @stable ICU 2.4 + */ + UnicodeSetIterator(const UnicodeSetIterator&); // disallow + + /** Assignment operator. Disallowed. + * @stable ICU 2.4 + */ + UnicodeSetIterator& operator=(const UnicodeSetIterator&); // disallow + + /** Load range + * @stable ICU 2.4 + */ + virtual void loadRange(int32_t range); + +}; + +inline UBool UnicodeSetIterator::isString() const { + return codepoint == (UChar32)IS_STRING; +} + +inline UChar32 UnicodeSetIterator::getCodepoint() const { + return codepoint; +} + +inline UChar32 UnicodeSetIterator::getCodepointEnd() const { + return codepointEnd; +} + + +U_NAMESPACE_END + +#endif /* U_SHOW_CPLUSPLUS_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/ushape.h b/thirdparty/icu4c/common/unicode/ushape.h new file mode 100644 index 0000000000..fed4869abd --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ushape.h @@ -0,0 +1,476 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 2000-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* file name: ushape.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2000jun29 +* created by: Markus W. Scherer +*/ + +#ifndef __USHAPE_H__ +#define __USHAPE_H__ + +#include "unicode/utypes.h" + +/** + * \file + * \brief C API: Arabic shaping + * + */ + +/** + * Shape Arabic text on a character basis. + * + * <p>This function performs basic operations for "shaping" Arabic text. It is most + * useful for use with legacy data formats and legacy display technology + * (simple terminals). All operations are performed on Unicode characters.</p> + * + * <p>Text-based shaping means that some character code points in the text are + * replaced by others depending on the context. It transforms one kind of text + * into another. In comparison, modern displays for Arabic text select + * appropriate, context-dependent font glyphs for each text element, which means + * that they transform text into a glyph vector.</p> + * + * <p>Text transformations are necessary when modern display technology is not + * available or when text needs to be transformed to or from legacy formats that + * use "shaped" characters. Since the Arabic script is cursive, connecting + * adjacent letters to each other, computers select images for each letter based + * on the surrounding letters. This usually results in four images per Arabic + * letter: initial, middle, final, and isolated forms. In Unicode, on the other + * hand, letters are normally stored abstract, and a display system is expected + * to select the necessary glyphs. (This makes searching and other text + * processing easier because the same letter has only one code.) It is possible + * to mimic this with text transformations because there are characters in + * Unicode that are rendered as letters with a specific shape + * (or cursive connectivity). They were included for interoperability with + * legacy systems and codepages, and for unsophisticated display systems.</p> + * + * <p>A second kind of text transformations is supported for Arabic digits: + * For compatibility with legacy codepages that only include European digits, + * it is possible to replace one set of digits by another, changing the + * character code points. These operations can be performed for either + * Arabic-Indic Digits (U+0660...U+0669) or Eastern (Extended) Arabic-Indic + * digits (U+06f0...U+06f9).</p> + * + * <p>Some replacements may result in more or fewer characters (code points). + * By default, this means that the destination buffer may receive text with a + * length different from the source length. Some legacy systems rely on the + * length of the text to be constant. They expect extra spaces to be added + * or consumed either next to the affected character or at the end of the + * text.</p> + * + * <p>For details about the available operations, see the description of the + * <code>U_SHAPE_...</code> options.</p> + * + * @param source The input text. + * + * @param sourceLength The number of UChars in <code>source</code>. + * + * @param dest The destination buffer that will receive the results of the + * requested operations. It may be <code>NULL</code> only if + * <code>destSize</code> is 0. The source and destination must not + * overlap. + * + * @param destSize The size (capacity) of the destination buffer in UChars. + * If <code>destSize</code> is 0, then no output is produced, + * but the necessary buffer size is returned ("preflighting"). + * + * @param options This is a 32-bit set of flags that specify the operations + * that are performed on the input text. If no error occurs, + * then the result will always be written to the destination + * buffer. + * + * @param pErrorCode must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @return The number of UChars written to the destination buffer. + * If an error occurred, then no output was written, or it may be + * incomplete. If <code>U_BUFFER_OVERFLOW_ERROR</code> is set, then + * the return value indicates the necessary destination buffer size. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_shapeArabic(const UChar *source, int32_t sourceLength, + UChar *dest, int32_t destSize, + uint32_t options, + UErrorCode *pErrorCode); + +/** + * Memory option: allow the result to have a different length than the source. + * Affects: LamAlef options + * @stable ICU 2.0 + */ +#define U_SHAPE_LENGTH_GROW_SHRINK 0 + +/** + * Memory option: allow the result to have a different length than the source. + * Affects: LamAlef options + * This option is an alias to U_SHAPE_LENGTH_GROW_SHRINK + * @stable ICU 4.2 + */ +#define U_SHAPE_LAMALEF_RESIZE 0 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces next to modified characters. + * @stable ICU 2.0 + */ +#define U_SHAPE_LENGTH_FIXED_SPACES_NEAR 1 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces next to modified characters. + * Affects: LamAlef options + * This option is an alias to U_SHAPE_LENGTH_FIXED_SPACES_NEAR + * @stable ICU 4.2 + */ +#define U_SHAPE_LAMALEF_NEAR 1 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces at the end of the text. + * @stable ICU 2.0 + */ +#define U_SHAPE_LENGTH_FIXED_SPACES_AT_END 2 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces at the end of the text. + * Affects: LamAlef options + * This option is an alias to U_SHAPE_LENGTH_FIXED_SPACES_AT_END + * @stable ICU 4.2 + */ +#define U_SHAPE_LAMALEF_END 2 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces at the beginning of the text. + * @stable ICU 2.0 + */ +#define U_SHAPE_LENGTH_FIXED_SPACES_AT_BEGINNING 3 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces at the beginning of the text. + * Affects: LamAlef options + * This option is an alias to U_SHAPE_LENGTH_FIXED_SPACES_AT_BEGINNING + * @stable ICU 4.2 + */ +#define U_SHAPE_LAMALEF_BEGIN 3 + + +/** + * Memory option: the result must have the same length as the source. + * Shaping Mode: For each LAMALEF character found, expand LAMALEF using space at end. + * If there is no space at end, use spaces at beginning of the buffer. If there + * is no space at beginning of the buffer, use spaces at the near (i.e. the space + * after the LAMALEF character). + * If there are no spaces found, an error U_NO_SPACE_AVAILABLE (as defined in utypes.h) + * will be set in pErrorCode + * + * Deshaping Mode: Perform the same function as the flag equals U_SHAPE_LAMALEF_END. + * Affects: LamAlef options + * @stable ICU 4.2 + */ +#define U_SHAPE_LAMALEF_AUTO 0x10000 + +/** Bit mask for memory options. @stable ICU 2.0 */ +#define U_SHAPE_LENGTH_MASK 0x10003 /* Changed old value 3 */ + + +/** + * Bit mask for LamAlef memory options. + * @stable ICU 4.2 + */ +#define U_SHAPE_LAMALEF_MASK 0x10003 /* updated */ + +/** Direction indicator: the source is in logical (keyboard) order. @stable ICU 2.0 */ +#define U_SHAPE_TEXT_DIRECTION_LOGICAL 0 + +/** + * Direction indicator: + * the source is in visual RTL order, + * the rightmost displayed character stored first. + * This option is an alias to U_SHAPE_TEXT_DIRECTION_LOGICAL + * @stable ICU 4.2 + */ +#define U_SHAPE_TEXT_DIRECTION_VISUAL_RTL 0 + +/** + * Direction indicator: + * the source is in visual LTR order, + * the leftmost displayed character stored first. + * @stable ICU 2.0 + */ +#define U_SHAPE_TEXT_DIRECTION_VISUAL_LTR 4 + +/** Bit mask for direction indicators. @stable ICU 2.0 */ +#define U_SHAPE_TEXT_DIRECTION_MASK 4 + + +/** Letter shaping option: do not perform letter shaping. @stable ICU 2.0 */ +#define U_SHAPE_LETTERS_NOOP 0 + +/** Letter shaping option: replace abstract letter characters by "shaped" ones. @stable ICU 2.0 */ +#define U_SHAPE_LETTERS_SHAPE 8 + +/** Letter shaping option: replace "shaped" letter characters by abstract ones. @stable ICU 2.0 */ +#define U_SHAPE_LETTERS_UNSHAPE 0x10 + +/** + * Letter shaping option: replace abstract letter characters by "shaped" ones. + * The only difference with U_SHAPE_LETTERS_SHAPE is that Tashkeel letters + * are always "shaped" into the isolated form instead of the medial form + * (selecting code points from the Arabic Presentation Forms-B block). + * @stable ICU 2.0 + */ +#define U_SHAPE_LETTERS_SHAPE_TASHKEEL_ISOLATED 0x18 + + +/** Bit mask for letter shaping options. @stable ICU 2.0 */ +#define U_SHAPE_LETTERS_MASK 0x18 + + +/** Digit shaping option: do not perform digit shaping. @stable ICU 2.0 */ +#define U_SHAPE_DIGITS_NOOP 0 + +/** + * Digit shaping option: + * Replace European digits (U+0030...) by Arabic-Indic digits. + * @stable ICU 2.0 + */ +#define U_SHAPE_DIGITS_EN2AN 0x20 + +/** + * Digit shaping option: + * Replace Arabic-Indic digits by European digits (U+0030...). + * @stable ICU 2.0 + */ +#define U_SHAPE_DIGITS_AN2EN 0x40 + +/** + * Digit shaping option: + * Replace European digits (U+0030...) by Arabic-Indic digits if the most recent + * strongly directional character is an Arabic letter + * (<code>u_charDirection()</code> result <code>U_RIGHT_TO_LEFT_ARABIC</code> [AL]).<br> + * The direction of "preceding" depends on the direction indicator option. + * For the first characters, the preceding strongly directional character + * (initial state) is assumed to be not an Arabic letter + * (it is <code>U_LEFT_TO_RIGHT</code> [L] or <code>U_RIGHT_TO_LEFT</code> [R]). + * @stable ICU 2.0 + */ +#define U_SHAPE_DIGITS_ALEN2AN_INIT_LR 0x60 + +/** + * Digit shaping option: + * Replace European digits (U+0030...) by Arabic-Indic digits if the most recent + * strongly directional character is an Arabic letter + * (<code>u_charDirection()</code> result <code>U_RIGHT_TO_LEFT_ARABIC</code> [AL]).<br> + * The direction of "preceding" depends on the direction indicator option. + * For the first characters, the preceding strongly directional character + * (initial state) is assumed to be an Arabic letter. + * @stable ICU 2.0 + */ +#define U_SHAPE_DIGITS_ALEN2AN_INIT_AL 0x80 + +/** Not a valid option value. May be replaced by a new option. @stable ICU 2.0 */ +#define U_SHAPE_DIGITS_RESERVED 0xa0 + +/** Bit mask for digit shaping options. @stable ICU 2.0 */ +#define U_SHAPE_DIGITS_MASK 0xe0 + + +/** Digit type option: Use Arabic-Indic digits (U+0660...U+0669). @stable ICU 2.0 */ +#define U_SHAPE_DIGIT_TYPE_AN 0 + +/** Digit type option: Use Eastern (Extended) Arabic-Indic digits (U+06f0...U+06f9). @stable ICU 2.0 */ +#define U_SHAPE_DIGIT_TYPE_AN_EXTENDED 0x100 + +/** Not a valid option value. May be replaced by a new option. @stable ICU 2.0 */ +#define U_SHAPE_DIGIT_TYPE_RESERVED 0x200 + +/** Bit mask for digit type options. @stable ICU 2.0 */ +#define U_SHAPE_DIGIT_TYPE_MASK 0x300 /* I need to change this from 0x3f00 to 0x300 */ + +/** + * Tashkeel aggregation option: + * Replaces any combination of U+0651 with one of + * U+064C, U+064D, U+064E, U+064F, U+0650 with + * U+FC5E, U+FC5F, U+FC60, U+FC61, U+FC62 consecutively. + * @stable ICU 3.6 + */ +#define U_SHAPE_AGGREGATE_TASHKEEL 0x4000 +/** Tashkeel aggregation option: do not aggregate tashkeels. @stable ICU 3.6 */ +#define U_SHAPE_AGGREGATE_TASHKEEL_NOOP 0 +/** Bit mask for tashkeel aggregation. @stable ICU 3.6 */ +#define U_SHAPE_AGGREGATE_TASHKEEL_MASK 0x4000 + +/** + * Presentation form option: + * Don't replace Arabic Presentation Forms-A and Arabic Presentation Forms-B + * characters with 0+06xx characters, before shaping. + * @stable ICU 3.6 + */ +#define U_SHAPE_PRESERVE_PRESENTATION 0x8000 +/** Presentation form option: + * Replace Arabic Presentation Forms-A and Arabic Presentationo Forms-B with + * their unshaped correspondants in range 0+06xx, before shaping. + * @stable ICU 3.6 + */ +#define U_SHAPE_PRESERVE_PRESENTATION_NOOP 0 +/** Bit mask for preserve presentation form. @stable ICU 3.6 */ +#define U_SHAPE_PRESERVE_PRESENTATION_MASK 0x8000 + +/* Seen Tail option */ +/** + * Memory option: the result must have the same length as the source. + * Shaping mode: The SEEN family character will expand into two characters using space near + * the SEEN family character(i.e. the space after the character). + * If there are no spaces found, an error U_NO_SPACE_AVAILABLE (as defined in utypes.h) + * will be set in pErrorCode + * + * De-shaping mode: Any Seen character followed by Tail character will be + * replaced by one cell Seen and a space will replace the Tail. + * Affects: Seen options + * @stable ICU 4.2 + */ +#define U_SHAPE_SEEN_TWOCELL_NEAR 0x200000 + +/** + * Bit mask for Seen memory options. + * @stable ICU 4.2 + */ +#define U_SHAPE_SEEN_MASK 0x700000 + +/* YehHamza option */ +/** + * Memory option: the result must have the same length as the source. + * Shaping mode: The YEHHAMZA character will expand into two characters using space near it + * (i.e. the space after the character + * If there are no spaces found, an error U_NO_SPACE_AVAILABLE (as defined in utypes.h) + * will be set in pErrorCode + * + * De-shaping mode: Any Yeh (final or isolated) character followed by Hamza character will be + * replaced by one cell YehHamza and space will replace the Hamza. + * Affects: YehHamza options + * @stable ICU 4.2 + */ +#define U_SHAPE_YEHHAMZA_TWOCELL_NEAR 0x1000000 + + +/** + * Bit mask for YehHamza memory options. + * @stable ICU 4.2 + */ +#define U_SHAPE_YEHHAMZA_MASK 0x3800000 + +/* New Tashkeel options */ +/** + * Memory option: the result must have the same length as the source. + * Shaping mode: Tashkeel characters will be replaced by spaces. + * Spaces will be placed at beginning of the buffer + * + * De-shaping mode: N/A + * Affects: Tashkeel options + * @stable ICU 4.2 + */ +#define U_SHAPE_TASHKEEL_BEGIN 0x40000 + +/** + * Memory option: the result must have the same length as the source. + * Shaping mode: Tashkeel characters will be replaced by spaces. + * Spaces will be placed at end of the buffer + * + * De-shaping mode: N/A + * Affects: Tashkeel options + * @stable ICU 4.2 + */ +#define U_SHAPE_TASHKEEL_END 0x60000 + +/** + * Memory option: allow the result to have a different length than the source. + * Shaping mode: Tashkeel characters will be removed, buffer length will shrink. + * De-shaping mode: N/A + * + * Affect: Tashkeel options + * @stable ICU 4.2 + */ +#define U_SHAPE_TASHKEEL_RESIZE 0x80000 + +/** + * Memory option: the result must have the same length as the source. + * Shaping mode: Tashkeel characters will be replaced by Tatweel if it is connected to adjacent + * characters (i.e. shaped on Tatweel) or replaced by space if it is not connected. + * + * De-shaping mode: N/A + * Affects: YehHamza options + * @stable ICU 4.2 + */ +#define U_SHAPE_TASHKEEL_REPLACE_BY_TATWEEL 0xC0000 + +/** + * Bit mask for Tashkeel replacement with Space or Tatweel memory options. + * @stable ICU 4.2 + */ +#define U_SHAPE_TASHKEEL_MASK 0xE0000 + + +/* Space location Control options */ +/** + * This option affect the meaning of BEGIN and END options. if this option is not used the default + * for BEGIN and END will be as following: + * The Default (for both Visual LTR, Visual RTL and Logical Text) + * 1. BEGIN always refers to the start address of physical memory. + * 2. END always refers to the end address of physical memory. + * + * If this option is used it will swap the meaning of BEGIN and END only for Visual LTR text. + * + * The effect on BEGIN and END Memory Options will be as following: + * A. BEGIN For Visual LTR text: This will be the beginning (right side) of the visual text( + * corresponding to the physical memory address end for Visual LTR text, Same as END in + * default behavior) + * B. BEGIN For Logical text: Same as BEGIN in default behavior. + * C. END For Visual LTR text: This will be the end (left side) of the visual text (corresponding + * to the physical memory address beginning for Visual LTR text, Same as BEGIN in default behavior. + * D. END For Logical text: Same as END in default behavior). + * Affects: All LamAlef BEGIN, END and AUTO options. + * @stable ICU 4.2 + */ +#define U_SHAPE_SPACES_RELATIVE_TO_TEXT_BEGIN_END 0x4000000 + +/** + * Bit mask for swapping BEGIN and END for Visual LTR text + * @stable ICU 4.2 + */ +#define U_SHAPE_SPACES_RELATIVE_TO_TEXT_MASK 0x4000000 + +/** + * If this option is used, shaping will use the new Unicode code point for TAIL (i.e. 0xFE73). + * If this option is not specified (Default), old unofficial Unicode TAIL code point is used (i.e. 0x200B) + * De-shaping will not use this option as it will always search for both the new Unicode code point for the + * TAIL (i.e. 0xFE73) or the old unofficial Unicode TAIL code point (i.e. 0x200B) and de-shape the + * Seen-Family letter accordingly. + * + * Shaping Mode: Only shaping. + * De-shaping Mode: N/A. + * Affects: All Seen options + * @stable ICU 4.8 + */ +#define U_SHAPE_TAIL_NEW_UNICODE 0x8000000 + +/** + * Bit mask for new Unicode Tail option + * @stable ICU 4.8 + */ +#define U_SHAPE_TAIL_TYPE_MASK 0x8000000 + +#endif diff --git a/thirdparty/icu4c/common/unicode/usprep.h b/thirdparty/icu4c/common/unicode/usprep.h new file mode 100644 index 0000000000..f8a0f58e0d --- /dev/null +++ b/thirdparty/icu4c/common/unicode/usprep.h @@ -0,0 +1,274 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* + ******************************************************************************* + * + * Copyright (C) 2003-2014, International Business Machines + * Corporation and others. All Rights Reserved. + * + ******************************************************************************* + * file name: usprep.h + * encoding: UTF-8 + * tab size: 8 (not used) + * indentation:4 + * + * created on: 2003jul2 + * created by: Ram Viswanadha + */ + +#ifndef __USPREP_H__ +#define __USPREP_H__ + +/** + * \file + * \brief C API: Implements the StringPrep algorithm. + */ + +#include "unicode/utypes.h" + +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#endif // U_SHOW_CPLUSPLUS_API + +/** + * + * StringPrep API implements the StingPrep framework as described by RFC 3454. + * StringPrep prepares Unicode strings for use in network protocols. + * Profiles of StingPrep are set of rules and data according to with the + * Unicode Strings are prepared. Each profiles contains tables which describe + * how a code point should be treated. The tables are broadly classified into + * <ul> + * <li> Unassigned Table: Contains code points that are unassigned + * in the Unicode Version supported by StringPrep. Currently + * RFC 3454 supports Unicode 3.2. </li> + * <li> Prohibited Table: Contains code points that are prohibited from + * the output of the StringPrep processing function. </li> + * <li> Mapping Table: Contains code points that are deleted from the output or case mapped. </li> + * </ul> + * + * The procedure for preparing Unicode strings: + * <ol> + * <li> Map: For each character in the input, check if it has a mapping + * and, if so, replace it with its mapping. </li> + * <li> Normalize: Possibly normalize the result of step 1 using Unicode + * normalization. </li> + * <li> Prohibit: Check for any characters that are not allowed in the + * output. If any are found, return an error.</li> + * <li> Check bidi: Possibly check for right-to-left characters, and if + * any are found, make sure that the whole string satisfies the + * requirements for bidirectional strings. If the string does not + * satisfy the requirements for bidirectional strings, return an + * error. </li> + * </ol> + * @author Ram Viswanadha + */ +#if !UCONFIG_NO_IDNA + +#include "unicode/parseerr.h" + +/** + * The StringPrep profile + * @stable ICU 2.8 + */ +typedef struct UStringPrepProfile UStringPrepProfile; + + +/** + * Option to prohibit processing of unassigned code points in the input + * + * @see usprep_prepare + * @stable ICU 2.8 + */ +#define USPREP_DEFAULT 0x0000 + +/** + * Option to allow processing of unassigned code points in the input + * + * @see usprep_prepare + * @stable ICU 2.8 + */ +#define USPREP_ALLOW_UNASSIGNED 0x0001 + +/** + * enums for the standard stringprep profile types + * supported by usprep_openByType. + * @see usprep_openByType + * @stable ICU 4.2 + */ +typedef enum UStringPrepProfileType { + /** + * RFC3491 Nameprep + * @stable ICU 4.2 + */ + USPREP_RFC3491_NAMEPREP, + /** + * RFC3530 nfs4_cs_prep + * @stable ICU 4.2 + */ + USPREP_RFC3530_NFS4_CS_PREP, + /** + * RFC3530 nfs4_cs_prep with case insensitive option + * @stable ICU 4.2 + */ + USPREP_RFC3530_NFS4_CS_PREP_CI, + /** + * RFC3530 nfs4_cis_prep + * @stable ICU 4.2 + */ + USPREP_RFC3530_NFS4_CIS_PREP, + /** + * RFC3530 nfs4_mixed_prep for prefix + * @stable ICU 4.2 + */ + USPREP_RFC3530_NFS4_MIXED_PREP_PREFIX, + /** + * RFC3530 nfs4_mixed_prep for suffix + * @stable ICU 4.2 + */ + USPREP_RFC3530_NFS4_MIXED_PREP_SUFFIX, + /** + * RFC3722 iSCSI + * @stable ICU 4.2 + */ + USPREP_RFC3722_ISCSI, + /** + * RFC3920 XMPP Nodeprep + * @stable ICU 4.2 + */ + USPREP_RFC3920_NODEPREP, + /** + * RFC3920 XMPP Resourceprep + * @stable ICU 4.2 + */ + USPREP_RFC3920_RESOURCEPREP, + /** + * RFC4011 Policy MIB Stringprep + * @stable ICU 4.2 + */ + USPREP_RFC4011_MIB, + /** + * RFC4013 SASLprep + * @stable ICU 4.2 + */ + USPREP_RFC4013_SASLPREP, + /** + * RFC4505 trace + * @stable ICU 4.2 + */ + USPREP_RFC4505_TRACE, + /** + * RFC4518 LDAP + * @stable ICU 4.2 + */ + USPREP_RFC4518_LDAP, + /** + * RFC4518 LDAP for case ignore, numeric and stored prefix + * matching rules + * @stable ICU 4.2 + */ + USPREP_RFC4518_LDAP_CI +} UStringPrepProfileType; + +/** + * Creates a StringPrep profile from the data file. + * + * @param path string containing the full path pointing to the directory + * where the profile reside followed by the package name + * e.g. "/usr/resource/my_app/profiles/mydata" on a Unix system. + * if NULL, ICU default data files will be used. + * @param fileName name of the profile file to be opened + * @param status ICU error code in/out parameter. Must not be NULL. + * Must fulfill U_SUCCESS before the function call. + * @return Pointer to UStringPrepProfile that is opened. Should be closed by + * calling usprep_close() + * @see usprep_close() + * @stable ICU 2.8 + */ +U_CAPI UStringPrepProfile* U_EXPORT2 +usprep_open(const char* path, + const char* fileName, + UErrorCode* status); + +/** + * Creates a StringPrep profile for the specified profile type. + * + * @param type The profile type + * @param status ICU error code in/out parameter. Must not be NULL. + * Must fulfill U_SUCCESS before the function call. + * @return Pointer to UStringPrepProfile that is opened. Should be closed by + * calling usprep_close() + * @see usprep_close() + * @stable ICU 4.2 + */ +U_CAPI UStringPrepProfile* U_EXPORT2 +usprep_openByType(UStringPrepProfileType type, + UErrorCode* status); + +/** + * Closes the profile + * @param profile The profile to close + * @stable ICU 2.8 + */ +U_CAPI void U_EXPORT2 +usprep_close(UStringPrepProfile* profile); + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUStringPrepProfilePointer + * "Smart pointer" class, closes a UStringPrepProfile via usprep_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUStringPrepProfilePointer, UStringPrepProfile, usprep_close); + +U_NAMESPACE_END + +#endif + +/** + * Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC), + * checks for prohibited and BiDi characters in the order defined by RFC 3454 + * depending on the options specified in the profile. + * + * @param prep The profile to use + * @param src Pointer to UChar buffer containing the string to prepare + * @param srcLength Number of characters in the source string + * @param dest Pointer to the destination buffer to receive the output + * @param destCapacity The capacity of destination array + * @param options A bit set of options: + * + * - USPREP_DEFAULT Prohibit processing of unassigned code points in the input + * + * - USPREP_ALLOW_UNASSIGNED Treat the unassigned code points are in the input + * as normal Unicode code points. + * + * @param parseError Pointer to UParseError struct to receive information on position + * of error if an error is encountered. Can be NULL. + * @param status ICU in/out error code parameter. + * U_INVALID_CHAR_FOUND if src contains + * unmatched single surrogates. + * U_INDEX_OUTOFBOUNDS_ERROR if src contains + * too many code points. + * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough + * @return The number of UChars in the destination buffer + * @stable ICU 2.8 + */ + +U_CAPI int32_t U_EXPORT2 +usprep_prepare( const UStringPrepProfile* prep, + const UChar* src, int32_t srcLength, + UChar* dest, int32_t destCapacity, + int32_t options, + UParseError* parseError, + UErrorCode* status ); + + +#endif /* #if !UCONFIG_NO_IDNA */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/ustring.h b/thirdparty/icu4c/common/unicode/ustring.h new file mode 100644 index 0000000000..10ea45ead1 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ustring.h @@ -0,0 +1,1689 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1998-2014, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* +* File ustring.h +* +* Modification History: +* +* Date Name Description +* 12/07/98 bertrand Creation. +****************************************************************************** +*/ + +#ifndef USTRING_H +#define USTRING_H + +#include "unicode/utypes.h" +#include "unicode/putil.h" +#include "unicode/uiter.h" + +/** + * \def UBRK_TYPEDEF_UBREAK_ITERATOR + * @internal + */ + +#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR +# define UBRK_TYPEDEF_UBREAK_ITERATOR +/** Simple declaration for u_strToTitle() to avoid including unicode/ubrk.h. @stable ICU 2.1*/ + typedef struct UBreakIterator UBreakIterator; +#endif + +/** + * \file + * \brief C API: Unicode string handling functions + * + * These C API functions provide general Unicode string handling. + * + * Some functions are equivalent in name, signature, and behavior to the ANSI C <string.h> + * functions. (For example, they do not check for bad arguments like NULL string pointers.) + * In some cases, only the thread-safe variant of such a function is implemented here + * (see u_strtok_r()). + * + * Other functions provide more Unicode-specific functionality like locale-specific + * upper/lower-casing and string comparison in code point order. + * + * ICU uses 16-bit Unicode (UTF-16) in the form of arrays of UChar code units. + * UTF-16 encodes each Unicode code point with either one or two UChar code units. + * (This is the default form of Unicode, and a forward-compatible extension of the original, + * fixed-width form that was known as UCS-2. UTF-16 superseded UCS-2 with Unicode 2.0 + * in 1996.) + * + * Some APIs accept a 32-bit UChar32 value for a single code point. + * + * ICU also handles 16-bit Unicode text with unpaired surrogates. + * Such text is not well-formed UTF-16. + * Code-point-related functions treat unpaired surrogates as surrogate code points, + * i.e., as separate units. + * + * Although UTF-16 is a variable-width encoding form (like some legacy multi-byte encodings), + * it is much more efficient even for random access because the code unit values + * for single-unit characters vs. lead units vs. trail units are completely disjoint. + * This means that it is easy to determine character (code point) boundaries from + * random offsets in the string. + * + * Unicode (UTF-16) string processing is optimized for the single-unit case. + * Although it is important to support supplementary characters + * (which use pairs of lead/trail code units called "surrogates"), + * their occurrence is rare. Almost all characters in modern use require only + * a single UChar code unit (i.e., their code point values are <=0xffff). + * + * For more details see the User Guide Strings chapter (http://icu-project.org/userguide/strings.html). + * For a discussion of the handling of unpaired surrogates see also + * Jitterbug 2145 and its icu mailing list proposal on 2002-sep-18. + */ + +/** + * \defgroup ustring_ustrlen String Length + * \ingroup ustring_strlen + */ +/*@{*/ +/** + * Determine the length of an array of UChar. + * + * @param s The array of UChars, NULL (U+0000) terminated. + * @return The number of UChars in <code>chars</code>, minus the terminator. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strlen(const UChar *s); +/*@}*/ + +/** + * Count Unicode code points in the length UChar code units of the string. + * A code point may occupy either one or two UChar code units. + * Counting code points involves reading all code units. + * + * This functions is basically the inverse of the U16_FWD_N() macro (see utf.h). + * + * @param s The input string. + * @param length The number of UChar code units to be checked, or -1 to count all + * code points before the first NUL (U+0000). + * @return The number of code points in the specified code units. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_countChar32(const UChar *s, int32_t length); + +/** + * Check if the string contains more Unicode code points than a certain number. + * This is more efficient than counting all code points in the entire string + * and comparing that number with a threshold. + * This function may not need to scan the string at all if the length is known + * (not -1 for NUL-termination) and falls within a certain range, and + * never needs to count more than 'number+1' code points. + * Logically equivalent to (u_countChar32(s, length)>number). + * A Unicode code point may occupy either one or two UChar code units. + * + * @param s The input string. + * @param length The length of the string, or -1 if it is NUL-terminated. + * @param number The number of code points in the string is compared against + * the 'number' parameter. + * @return Boolean value for whether the string contains more Unicode code points + * than 'number'. Same as (u_countChar32(s, length)>number). + * @stable ICU 2.4 + */ +U_CAPI UBool U_EXPORT2 +u_strHasMoreChar32Than(const UChar *s, int32_t length, int32_t number); + +/** + * Concatenate two ustrings. Appends a copy of <code>src</code>, + * including the null terminator, to <code>dst</code>. The initial copied + * character from <code>src</code> overwrites the null terminator in <code>dst</code>. + * + * @param dst The destination string. + * @param src The source string. + * @return A pointer to <code>dst</code>. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strcat(UChar *dst, + const UChar *src); + +/** + * Concatenate two ustrings. + * Appends at most <code>n</code> characters from <code>src</code> to <code>dst</code>. + * Adds a terminating NUL. + * If src is too long, then only <code>n-1</code> characters will be copied + * before the terminating NUL. + * If <code>n<=0</code> then dst is not modified. + * + * @param dst The destination string. + * @param src The source string (can be NULL/invalid if n<=0). + * @param n The maximum number of characters to append; no-op if <=0. + * @return A pointer to <code>dst</code>. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strncat(UChar *dst, + const UChar *src, + int32_t n); + +/** + * Find the first occurrence of a substring in a string. + * The substring is found at code point boundaries. + * That means that if the substring begins with + * a trail surrogate or ends with a lead surrogate, + * then it is found only if these surrogates stand alone in the text. + * Otherwise, the substring edge units would be matched against + * halves of surrogate pairs. + * + * @param s The string to search (NUL-terminated). + * @param substring The substring to find (NUL-terminated). + * @return A pointer to the first occurrence of <code>substring</code> in <code>s</code>, + * or <code>s</code> itself if the <code>substring</code> is empty, + * or <code>NULL</code> if <code>substring</code> is not in <code>s</code>. + * @stable ICU 2.0 + * + * @see u_strrstr + * @see u_strFindFirst + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strstr(const UChar *s, const UChar *substring); + +/** + * Find the first occurrence of a substring in a string. + * The substring is found at code point boundaries. + * That means that if the substring begins with + * a trail surrogate or ends with a lead surrogate, + * then it is found only if these surrogates stand alone in the text. + * Otherwise, the substring edge units would be matched against + * halves of surrogate pairs. + * + * @param s The string to search. + * @param length The length of s (number of UChars), or -1 if it is NUL-terminated. + * @param substring The substring to find (NUL-terminated). + * @param subLength The length of substring (number of UChars), or -1 if it is NUL-terminated. + * @return A pointer to the first occurrence of <code>substring</code> in <code>s</code>, + * or <code>s</code> itself if the <code>substring</code> is empty, + * or <code>NULL</code> if <code>substring</code> is not in <code>s</code>. + * @stable ICU 2.4 + * + * @see u_strstr + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strFindFirst(const UChar *s, int32_t length, const UChar *substring, int32_t subLength); + +/** + * Find the first occurrence of a BMP code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (NUL-terminated). + * @param c The BMP code point to find. + * @return A pointer to the first occurrence of <code>c</code> in <code>s</code> + * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. + * @stable ICU 2.0 + * + * @see u_strchr32 + * @see u_memchr + * @see u_strstr + * @see u_strFindFirst + */ +U_CAPI UChar * U_EXPORT2 +u_strchr(const UChar *s, UChar c); + +/** + * Find the first occurrence of a code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (NUL-terminated). + * @param c The code point to find. + * @return A pointer to the first occurrence of <code>c</code> in <code>s</code> + * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. + * @stable ICU 2.0 + * + * @see u_strchr + * @see u_memchr32 + * @see u_strstr + * @see u_strFindFirst + */ +U_CAPI UChar * U_EXPORT2 +u_strchr32(const UChar *s, UChar32 c); + +/** + * Find the last occurrence of a substring in a string. + * The substring is found at code point boundaries. + * That means that if the substring begins with + * a trail surrogate or ends with a lead surrogate, + * then it is found only if these surrogates stand alone in the text. + * Otherwise, the substring edge units would be matched against + * halves of surrogate pairs. + * + * @param s The string to search (NUL-terminated). + * @param substring The substring to find (NUL-terminated). + * @return A pointer to the last occurrence of <code>substring</code> in <code>s</code>, + * or <code>s</code> itself if the <code>substring</code> is empty, + * or <code>NULL</code> if <code>substring</code> is not in <code>s</code>. + * @stable ICU 2.4 + * + * @see u_strstr + * @see u_strFindFirst + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strrstr(const UChar *s, const UChar *substring); + +/** + * Find the last occurrence of a substring in a string. + * The substring is found at code point boundaries. + * That means that if the substring begins with + * a trail surrogate or ends with a lead surrogate, + * then it is found only if these surrogates stand alone in the text. + * Otherwise, the substring edge units would be matched against + * halves of surrogate pairs. + * + * @param s The string to search. + * @param length The length of s (number of UChars), or -1 if it is NUL-terminated. + * @param substring The substring to find (NUL-terminated). + * @param subLength The length of substring (number of UChars), or -1 if it is NUL-terminated. + * @return A pointer to the last occurrence of <code>substring</code> in <code>s</code>, + * or <code>s</code> itself if the <code>substring</code> is empty, + * or <code>NULL</code> if <code>substring</code> is not in <code>s</code>. + * @stable ICU 2.4 + * + * @see u_strstr + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strFindLast(const UChar *s, int32_t length, const UChar *substring, int32_t subLength); + +/** + * Find the last occurrence of a BMP code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (NUL-terminated). + * @param c The BMP code point to find. + * @return A pointer to the last occurrence of <code>c</code> in <code>s</code> + * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. + * @stable ICU 2.4 + * + * @see u_strrchr32 + * @see u_memrchr + * @see u_strrstr + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strrchr(const UChar *s, UChar c); + +/** + * Find the last occurrence of a code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (NUL-terminated). + * @param c The code point to find. + * @return A pointer to the last occurrence of <code>c</code> in <code>s</code> + * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. + * @stable ICU 2.4 + * + * @see u_strrchr + * @see u_memchr32 + * @see u_strrstr + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strrchr32(const UChar *s, UChar32 c); + +/** + * Locates the first occurrence in the string <code>string</code> of any of the characters + * in the string <code>matchSet</code>. + * Works just like C's strpbrk but with Unicode. + * + * @param string The string in which to search, NUL-terminated. + * @param matchSet A NUL-terminated string defining a set of code points + * for which to search in the text string. + * @return A pointer to the character in <code>string</code> that matches one of the + * characters in <code>matchSet</code>, or NULL if no such character is found. + * @stable ICU 2.0 + */ +U_CAPI UChar * U_EXPORT2 +u_strpbrk(const UChar *string, const UChar *matchSet); + +/** + * Returns the number of consecutive characters in <code>string</code>, + * beginning with the first, that do not occur somewhere in <code>matchSet</code>. + * Works just like C's strcspn but with Unicode. + * + * @param string The string in which to search, NUL-terminated. + * @param matchSet A NUL-terminated string defining a set of code points + * for which to search in the text string. + * @return The number of initial characters in <code>string</code> that do not + * occur in <code>matchSet</code>. + * @see u_strspn + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strcspn(const UChar *string, const UChar *matchSet); + +/** + * Returns the number of consecutive characters in <code>string</code>, + * beginning with the first, that occur somewhere in <code>matchSet</code>. + * Works just like C's strspn but with Unicode. + * + * @param string The string in which to search, NUL-terminated. + * @param matchSet A NUL-terminated string defining a set of code points + * for which to search in the text string. + * @return The number of initial characters in <code>string</code> that do + * occur in <code>matchSet</code>. + * @see u_strcspn + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strspn(const UChar *string, const UChar *matchSet); + +/** + * The string tokenizer API allows an application to break a string into + * tokens. Unlike strtok(), the saveState (the current pointer within the + * original string) is maintained in saveState. In the first call, the + * argument src is a pointer to the string. In subsequent calls to + * return successive tokens of that string, src must be specified as + * NULL. The value saveState is set by this function to maintain the + * function's position within the string, and on each subsequent call + * you must give this argument the same variable. This function does + * handle surrogate pairs. This function is similar to the strtok_r() + * the POSIX Threads Extension (1003.1c-1995) version. + * + * @param src String containing token(s). This string will be modified. + * After the first call to u_strtok_r(), this argument must + * be NULL to get to the next token. + * @param delim Set of delimiter characters (Unicode code points). + * @param saveState The current pointer within the original string, + * which is set by this function. The saveState + * parameter should the address of a local variable of type + * UChar *. (i.e. defined "UChar *myLocalSaveState" and use + * &myLocalSaveState for this parameter). + * @return A pointer to the next token found in src, or NULL + * when there are no more tokens. + * @stable ICU 2.0 + */ +U_CAPI UChar * U_EXPORT2 +u_strtok_r(UChar *src, + const UChar *delim, + UChar **saveState); + +/** + * Compare two Unicode strings for bitwise equality (code unit order). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @return 0 if <code>s1</code> and <code>s2</code> are bitwise equal; a negative + * value if <code>s1</code> is bitwise less than <code>s2,</code>; a positive + * value if <code>s1</code> is bitwise greater than <code>s2</code>. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strcmp(const UChar *s1, + const UChar *s2); + +/** + * Compare two Unicode strings in code point order. + * See u_strCompare for details. + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @return a negative/zero/positive integer corresponding to whether + * the first string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strcmpCodePointOrder(const UChar *s1, const UChar *s2); + +/** + * Compare two Unicode strings (binary order). + * + * The comparison can be done in code unit order or in code point order. + * They differ only in UTF-16 when + * comparing supplementary code points (U+10000..U+10ffff) + * to BMP code points near the end of the BMP (i.e., U+e000..U+ffff). + * In code unit order, high BMP code points sort after supplementary code points + * because they are stored as pairs of surrogates which are at U+d800..U+dfff. + * + * This functions works with strings of different explicitly specified lengths + * unlike the ANSI C-like u_strcmp() and u_memcmp() etc. + * NUL-terminated strings are possible with length arguments of -1. + * + * @param s1 First source string. + * @param length1 Length of first source string, or -1 if NUL-terminated. + * + * @param s2 Second source string. + * @param length2 Length of second source string, or -1 if NUL-terminated. + * + * @param codePointOrder Choose between code unit order (false) + * and code point order (true). + * + * @return <0 or 0 or >0 as usual for string comparisons + * + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +u_strCompare(const UChar *s1, int32_t length1, + const UChar *s2, int32_t length2, + UBool codePointOrder); + +/** + * Compare two Unicode strings (binary order) + * as presented by UCharIterator objects. + * Works otherwise just like u_strCompare(). + * + * Both iterators are reset to their start positions. + * When the function returns, it is undefined where the iterators + * have stopped. + * + * @param iter1 First source string iterator. + * @param iter2 Second source string iterator. + * @param codePointOrder Choose between code unit order (false) + * and code point order (true). + * + * @return <0 or 0 or >0 as usual for string comparisons + * + * @see u_strCompare + * + * @stable ICU 2.6 + */ +U_CAPI int32_t U_EXPORT2 +u_strCompareIter(UCharIterator *iter1, UCharIterator *iter2, UBool codePointOrder); + +/** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to + * u_strCompare(u_strFoldCase(s1, options), + * u_strFoldCase(s2, options), + * (options&U_COMPARE_CODE_POINT_ORDER)!=0). + * + * The comparison can be done in UTF-16 code unit order or in code point order. + * They differ only when comparing supplementary code points (U+10000..U+10ffff) + * to BMP code points near the end of the BMP (i.e., U+e000..U+ffff). + * In code unit order, high BMP code points sort after supplementary code points + * because they are stored as pairs of surrogates which are at U+d800..U+dfff. + * + * This functions works with strings of different explicitly specified lengths + * unlike the ANSI C-like u_strcmp() and u_memcmp() etc. + * NUL-terminated strings are possible with length arguments of -1. + * + * @param s1 First source string. + * @param length1 Length of first source string, or -1 if NUL-terminated. + * + * @param s2 Second source string. + * @param length2 Length of second source string, or -1 if NUL-terminated. + * + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @return <0 or 0 or >0 as usual for string comparisons + * + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +u_strCaseCompare(const UChar *s1, int32_t length1, + const UChar *s2, int32_t length2, + uint32_t options, + UErrorCode *pErrorCode); + +/** + * Compare two ustrings for bitwise equality. + * Compares at most <code>n</code> characters. + * + * @param ucs1 A string to compare (can be NULL/invalid if n<=0). + * @param ucs2 A string to compare (can be NULL/invalid if n<=0). + * @param n The maximum number of characters to compare; always returns 0 if n<=0. + * @return 0 if <code>s1</code> and <code>s2</code> are bitwise equal; a negative + * value if <code>s1</code> is bitwise less than <code>s2</code>; a positive + * value if <code>s1</code> is bitwise greater than <code>s2</code>. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strncmp(const UChar *ucs1, + const UChar *ucs2, + int32_t n); + +/** + * Compare two Unicode strings in code point order. + * This is different in UTF-16 from u_strncmp() if supplementary characters are present. + * For details, see u_strCompare(). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param n The maximum number of characters to compare. + * @return a negative/zero/positive integer corresponding to whether + * the first string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strncmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t n); + +/** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to u_strcmp(u_strFoldCase(s1, options), u_strFoldCase(s2, options)). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strcasecmp(const UChar *s1, const UChar *s2, uint32_t options); + +/** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to u_strcmp(u_strFoldCase(s1, at most n, options), + * u_strFoldCase(s2, at most n, options)). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param n The maximum number of characters each string to case-fold and then compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strncasecmp(const UChar *s1, const UChar *s2, int32_t n, uint32_t options); + +/** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to u_strcmp(u_strFoldCase(s1, n, options), + * u_strFoldCase(s2, n, options)). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param length The number of characters in each string to case-fold and then compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_memcasecmp(const UChar *s1, const UChar *s2, int32_t length, uint32_t options); + +/** + * Copy a ustring. Adds a null terminator. + * + * @param dst The destination string. + * @param src The source string. + * @return A pointer to <code>dst</code>. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strcpy(UChar *dst, + const UChar *src); + +/** + * Copy a ustring. + * Copies at most <code>n</code> characters. The result will be null terminated + * if the length of <code>src</code> is less than <code>n</code>. + * + * @param dst The destination string. + * @param src The source string (can be NULL/invalid if n<=0). + * @param n The maximum number of characters to copy; no-op if <=0. + * @return A pointer to <code>dst</code>. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strncpy(UChar *dst, + const UChar *src, + int32_t n); + +#if !UCONFIG_NO_CONVERSION + +/** + * Copy a byte string encoded in the default codepage to a ustring. + * Adds a null terminator. + * Performs a host byte to UChar conversion + * + * @param dst The destination string. + * @param src The source string. + * @return A pointer to <code>dst</code>. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 u_uastrcpy(UChar *dst, + const char *src ); + +/** + * Copy a byte string encoded in the default codepage to a ustring. + * Copies at most <code>n</code> characters. The result will be null terminated + * if the length of <code>src</code> is less than <code>n</code>. + * Performs a host byte to UChar conversion + * + * @param dst The destination string. + * @param src The source string. + * @param n The maximum number of characters to copy. + * @return A pointer to <code>dst</code>. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 u_uastrncpy(UChar *dst, + const char *src, + int32_t n); + +/** + * Copy ustring to a byte string encoded in the default codepage. + * Adds a null terminator. + * Performs a UChar to host byte conversion + * + * @param dst The destination string. + * @param src The source string. + * @return A pointer to <code>dst</code>. + * @stable ICU 2.0 + */ +U_CAPI char* U_EXPORT2 u_austrcpy(char *dst, + const UChar *src ); + +/** + * Copy ustring to a byte string encoded in the default codepage. + * Copies at most <code>n</code> characters. The result will be null terminated + * if the length of <code>src</code> is less than <code>n</code>. + * Performs a UChar to host byte conversion + * + * @param dst The destination string. + * @param src The source string. + * @param n The maximum number of characters to copy. + * @return A pointer to <code>dst</code>. + * @stable ICU 2.0 + */ +U_CAPI char* U_EXPORT2 u_austrncpy(char *dst, + const UChar *src, + int32_t n ); + +#endif + +/** + * Synonym for memcpy(), but with UChars only. + * @param dest The destination string + * @param src The source string (can be NULL/invalid if count<=0) + * @param count The number of characters to copy; no-op if <=0 + * @return A pointer to <code>dest</code> + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_memcpy(UChar *dest, const UChar *src, int32_t count); + +/** + * Synonym for memmove(), but with UChars only. + * @param dest The destination string + * @param src The source string (can be NULL/invalid if count<=0) + * @param count The number of characters to move; no-op if <=0 + * @return A pointer to <code>dest</code> + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_memmove(UChar *dest, const UChar *src, int32_t count); + +/** + * Initialize <code>count</code> characters of <code>dest</code> to <code>c</code>. + * + * @param dest The destination string. + * @param c The character to initialize the string. + * @param count The maximum number of characters to set. + * @return A pointer to <code>dest</code>. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_memset(UChar *dest, UChar c, int32_t count); + +/** + * Compare the first <code>count</code> UChars of each buffer. + * + * @param buf1 The first string to compare. + * @param buf2 The second string to compare. + * @param count The maximum number of UChars to compare. + * @return When buf1 < buf2, a negative number is returned. + * When buf1 == buf2, 0 is returned. + * When buf1 > buf2, a positive number is returned. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_memcmp(const UChar *buf1, const UChar *buf2, int32_t count); + +/** + * Compare two Unicode strings in code point order. + * This is different in UTF-16 from u_memcmp() if supplementary characters are present. + * For details, see u_strCompare(). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param count The maximum number of characters to compare. + * @return a negative/zero/positive integer corresponding to whether + * the first string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_memcmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t count); + +/** + * Find the first occurrence of a BMP code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (contains <code>count</code> UChars). + * @param c The BMP code point to find. + * @param count The length of the string. + * @return A pointer to the first occurrence of <code>c</code> in <code>s</code> + * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. + * @stable ICU 2.0 + * + * @see u_strchr + * @see u_memchr32 + * @see u_strFindFirst + */ +U_CAPI UChar* U_EXPORT2 +u_memchr(const UChar *s, UChar c, int32_t count); + +/** + * Find the first occurrence of a code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (contains <code>count</code> UChars). + * @param c The code point to find. + * @param count The length of the string. + * @return A pointer to the first occurrence of <code>c</code> in <code>s</code> + * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. + * @stable ICU 2.0 + * + * @see u_strchr32 + * @see u_memchr + * @see u_strFindFirst + */ +U_CAPI UChar* U_EXPORT2 +u_memchr32(const UChar *s, UChar32 c, int32_t count); + +/** + * Find the last occurrence of a BMP code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (contains <code>count</code> UChars). + * @param c The BMP code point to find. + * @param count The length of the string. + * @return A pointer to the last occurrence of <code>c</code> in <code>s</code> + * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. + * @stable ICU 2.4 + * + * @see u_strrchr + * @see u_memrchr32 + * @see u_strFindLast + */ +U_CAPI UChar* U_EXPORT2 +u_memrchr(const UChar *s, UChar c, int32_t count); + +/** + * Find the last occurrence of a code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (contains <code>count</code> UChars). + * @param c The code point to find. + * @param count The length of the string. + * @return A pointer to the last occurrence of <code>c</code> in <code>s</code> + * or <code>NULL</code> if <code>c</code> is not in <code>s</code>. + * @stable ICU 2.4 + * + * @see u_strrchr32 + * @see u_memrchr + * @see u_strFindLast + */ +U_CAPI UChar* U_EXPORT2 +u_memrchr32(const UChar *s, UChar32 c, int32_t count); + +/** + * Unicode String literals in C. + * We need one macro to declare a variable for the string + * and to statically preinitialize it if possible, + * and a second macro to dynamically initialize such a string variable if necessary. + * + * The macros are defined for maximum performance. + * They work only for strings that contain "invariant characters", i.e., + * only latin letters, digits, and some punctuation. + * See utypes.h for details. + * + * A pair of macros for a single string must be used with the same + * parameters. + * The string parameter must be a C string literal. + * The length of the string, not including the terminating + * `NUL`, must be specified as a constant. + * The U_STRING_DECL macro should be invoked exactly once for one + * such string variable before it is used. + * + * Usage: + * + * U_STRING_DECL(ustringVar1, "Quick-Fox 2", 11); + * U_STRING_DECL(ustringVar2, "jumps 5%", 8); + * static UBool didInit=false; + * + * int32_t function() { + * if(!didInit) { + * U_STRING_INIT(ustringVar1, "Quick-Fox 2", 11); + * U_STRING_INIT(ustringVar2, "jumps 5%", 8); + * didInit=true; + * } + * return u_strcmp(ustringVar1, ustringVar2); + * } + * + * Note that the macros will NOT consistently work if their argument is another #`define`. + * The following will not work on all platforms, don't use it. + * + * #define GLUCK "Mr. Gluck" + * U_STRING_DECL(var, GLUCK, 9) + * U_STRING_INIT(var, GLUCK, 9) + * + * Instead, use the string literal "Mr. Gluck" as the argument to both macro + * calls. + * + * + * @stable ICU 2.0 + */ +#if defined(U_DECLARE_UTF16) +# define U_STRING_DECL(var, cs, length) static const UChar *var=(const UChar *)U_DECLARE_UTF16(cs) + /**@stable ICU 2.0 */ +# define U_STRING_INIT(var, cs, length) +#elif U_SIZEOF_WCHAR_T==U_SIZEOF_UCHAR && (U_CHARSET_FAMILY==U_ASCII_FAMILY || (U_SIZEOF_UCHAR == 2 && defined(U_WCHAR_IS_UTF16))) +# define U_STRING_DECL(var, cs, length) static const UChar var[(length)+1]=L ## cs + /**@stable ICU 2.0 */ +# define U_STRING_INIT(var, cs, length) +#elif U_SIZEOF_UCHAR==1 && U_CHARSET_FAMILY==U_ASCII_FAMILY +# define U_STRING_DECL(var, cs, length) static const UChar var[(length)+1]=cs + /**@stable ICU 2.0 */ +# define U_STRING_INIT(var, cs, length) +#else +# define U_STRING_DECL(var, cs, length) static UChar var[(length)+1] + /**@stable ICU 2.0 */ +# define U_STRING_INIT(var, cs, length) u_charsToUChars(cs, var, length+1) +#endif + +/** + * Unescape a string of characters and write the resulting + * Unicode characters to the destination buffer. The following escape + * sequences are recognized: + * + * \\uhhhh 4 hex digits; h in [0-9A-Fa-f] + * \\Uhhhhhhhh 8 hex digits + * \\xhh 1-2 hex digits + * \\x{h...} 1-8 hex digits + * \\ooo 1-3 octal digits; o in [0-7] + * \\cX control-X; X is masked with 0x1F + * + * as well as the standard ANSI C escapes: + * + * \\a => U+0007, \\b => U+0008, \\t => U+0009, \\n => U+000A, + * \\v => U+000B, \\f => U+000C, \\r => U+000D, \\e => U+001B, + * \\" => U+0022, \\' => U+0027, \\? => U+003F, \\\\ => U+005C + * + * Anything else following a backslash is generically escaped. For + * example, "[a\\-z]" returns "[a-z]". + * + * If an escape sequence is ill-formed, this method returns an empty + * string. An example of an ill-formed sequence is "\\u" followed by + * fewer than 4 hex digits. + * + * The above characters are recognized in the compiler's codepage, + * that is, they are coded as 'u', '\\', etc. Characters that are + * not parts of escape sequences are converted using u_charsToUChars(). + * + * This function is similar to UnicodeString::unescape() but not + * identical to it. The latter takes a source UnicodeString, so it + * does escape recognition but no conversion. + * + * @param src a zero-terminated string of invariant characters + * @param dest pointer to buffer to receive converted and unescaped + * text and, if there is room, a zero terminator. May be NULL for + * preflighting, in which case no UChars will be written, but the + * return value will still be valid. On error, an empty string is + * stored here (if possible). + * @param destCapacity the number of UChars that may be written at + * dest. Ignored if dest == NULL. + * @return the length of unescaped string. + * @see u_unescapeAt + * @see UnicodeString#unescape() + * @see UnicodeString#unescapeAt() + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_unescape(const char *src, + UChar *dest, int32_t destCapacity); + +U_CDECL_BEGIN +/** + * Callback function for u_unescapeAt() that returns a character of + * the source text given an offset and a context pointer. The context + * pointer will be whatever is passed into u_unescapeAt(). + * + * @param offset pointer to the offset that will be passed to u_unescapeAt(). + * @param context an opaque pointer passed directly into u_unescapeAt() + * @return the character represented by the escape sequence at + * offset + * @see u_unescapeAt + * @stable ICU 2.0 + */ +typedef UChar (U_CALLCONV *UNESCAPE_CHAR_AT)(int32_t offset, void *context); +U_CDECL_END + +/** + * Unescape a single sequence. The character at offset-1 is assumed + * (without checking) to be a backslash. This method takes a callback + * pointer to a function that returns the UChar at a given offset. By + * varying this callback, ICU functions are able to unescape char* + * strings, UnicodeString objects, and UFILE pointers. + * + * If offset is out of range, or if the escape sequence is ill-formed, + * (UChar32)0xFFFFFFFF is returned. See documentation of u_unescape() + * for a list of recognized sequences. + * + * @param charAt callback function that returns a UChar of the source + * text given an offset and a context pointer. + * @param offset pointer to the offset that will be passed to charAt. + * The offset value will be updated upon return to point after the + * last parsed character of the escape sequence. On error the offset + * is unchanged. + * @param length the number of characters in the source text. The + * last character of the source text is considered to be at offset + * length-1. + * @param context an opaque pointer passed directly into charAt. + * @return the character represented by the escape sequence at + * offset, or (UChar32)0xFFFFFFFF on error. + * @see u_unescape() + * @see UnicodeString#unescape() + * @see UnicodeString#unescapeAt() + * @stable ICU 2.0 + */ +U_CAPI UChar32 U_EXPORT2 +u_unescapeAt(UNESCAPE_CHAR_AT charAt, + int32_t *offset, + int32_t length, + void *context); + +/** + * Uppercase the characters in a string. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer are allowed to overlap. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string. It may be greater than destCapacity. In that case, + * only some of the result was written to the destination buffer. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strToUpper(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + const char *locale, + UErrorCode *pErrorCode); + +/** + * Lowercase the characters in a string. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer are allowed to overlap. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string. It may be greater than destCapacity. In that case, + * only some of the result was written to the destination buffer. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strToLower(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + const char *locale, + UErrorCode *pErrorCode); + +#if !UCONFIG_NO_BREAK_ITERATION + +/** + * Titlecase a string. + * Casing is locale-dependent and context-sensitive. + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. + * + * The titlecase break iterator can be provided to customize for arbitrary + * styles, using rules and dictionaries beyond the standard iterators. + * It may be more efficient to always provide an iterator to avoid + * opening and closing one for each string. + * The standard titlecase iterator for the root locale implements the + * algorithm of Unicode TR 21. + * + * This function uses only the setText(), first() and next() methods of the + * provided break iterator. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer are allowed to overlap. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param titleIter A break iterator to find the first characters of words + * that are to be titlecased. + * If none is provided (NULL), then a standard titlecase + * break iterator is opened. + * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string. It may be greater than destCapacity. In that case, + * only some of the result was written to the destination buffer. + * @stable ICU 2.1 + */ +U_CAPI int32_t U_EXPORT2 +u_strToTitle(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + UBreakIterator *titleIter, + const char *locale, + UErrorCode *pErrorCode); + +#endif + +/** + * Case-folds the characters in a string. + * + * Case-folding is locale-independent and not context-sensitive, + * but there is an option for whether to include or exclude mappings for dotted I + * and dotless i that are marked with 'T' in CaseFolding.txt. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer are allowed to overlap. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string. It may be greater than destCapacity. In that case, + * only some of the result was written to the destination buffer. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strFoldCase(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + uint32_t options, + UErrorCode *pErrorCode); + +#if defined(U_WCHAR_IS_UTF16) || defined(U_WCHAR_IS_UTF32) || !UCONFIG_NO_CONVERSION +/** + * Convert a UTF-16 string to a wchar_t string. + * If it is known at compile time that wchar_t strings are in UTF-16 or UTF-32, then + * this function simply calls the fast, dedicated function for that. + * Otherwise, two conversions UTF-16 -> default charset -> wchar_t* are performed. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of wchar_t's). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The pointer to destination buffer. + * @stable ICU 2.0 + */ +U_CAPI wchar_t* U_EXPORT2 +u_strToWCS(wchar_t *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UErrorCode *pErrorCode); +/** + * Convert a wchar_t string to UTF-16. + * If it is known at compile time that wchar_t strings are in UTF-16 or UTF-32, then + * this function simply calls the fast, dedicated function for that. + * Otherwise, two conversions wchar_t* -> default charset -> UTF-16 are performed. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The pointer to destination buffer. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strFromWCS(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const wchar_t *src, + int32_t srcLength, + UErrorCode *pErrorCode); +#endif /* defined(U_WCHAR_IS_UTF16) || defined(U_WCHAR_IS_UTF32) || !UCONFIG_NO_CONVERSION */ + +/** + * Convert a UTF-16 string to UTF-8. + * If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of chars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The pointer to destination buffer. + * @stable ICU 2.0 + * @see u_strToUTF8WithSub + * @see u_strFromUTF8 + */ +U_CAPI char* U_EXPORT2 +u_strToUTF8(char *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-8 string to UTF-16. + * If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The pointer to destination buffer. + * @stable ICU 2.0 + * @see u_strFromUTF8WithSub + * @see u_strFromUTF8Lenient + */ +U_CAPI UChar* U_EXPORT2 +u_strFromUTF8(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const char *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-16 string to UTF-8. + * + * Same as u_strToUTF8() except for the additional subchar which is output for + * illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code. + * With subchar==U_SENTINEL, this function behaves exactly like u_strToUTF8(). + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of chars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param subchar The substitution character to use in place of an illegal input sequence, + * or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead. + * A substitution character can be any valid Unicode code point (up to U+10FFFF) + * except for surrogate code points (U+D800..U+DFFF). + * The recommended value is U+FFFD "REPLACEMENT CHARACTER". + * @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strToUTF8 + * @see u_strFromUTF8WithSub + * @stable ICU 3.6 + */ +U_CAPI char* U_EXPORT2 +u_strToUTF8WithSub(char *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-8 string to UTF-16. + * + * Same as u_strFromUTF8() except for the additional subchar which is output for + * illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code. + * With subchar==U_SENTINEL, this function behaves exactly like u_strFromUTF8(). + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param subchar The substitution character to use in place of an illegal input sequence, + * or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead. + * A substitution character can be any valid Unicode code point (up to U+10FFFF) + * except for surrogate code points (U+D800..U+DFFF). + * The recommended value is U+FFFD "REPLACEMENT CHARACTER". + * @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strFromUTF8 + * @see u_strFromUTF8Lenient + * @see u_strToUTF8WithSub + * @stable ICU 3.6 + */ +U_CAPI UChar* U_EXPORT2 +u_strFromUTF8WithSub(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const char *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-8 string to UTF-16. + * + * Same as u_strFromUTF8() except that this function is designed to be very fast, + * which it achieves by being lenient about malformed UTF-8 sequences. + * This function is intended for use in environments where UTF-8 text is + * expected to be well-formed. + * + * Its semantics are: + * - Well-formed UTF-8 text is correctly converted to well-formed UTF-16 text. + * - The function will not read beyond the input string, nor write beyond + * the destCapacity. + * - Malformed UTF-8 results in "garbage" 16-bit Unicode strings which may not + * be well-formed UTF-16. + * The function will resynchronize to valid code point boundaries + * within a small number of code points after an illegal sequence. + * - Non-shortest forms are not detected and will result in "spoofing" output. + * + * For further performance improvement, if srcLength is given (>=0), + * then it must be destCapacity>=srcLength. + * + * There is no inverse u_strToUTF8Lenient() function because there is practically + * no performance gain from not checking that a UTF-16 string is well-formed. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * Unlike for other ICU functions, if srcLength>=0 then it + * must be destCapacity>=srcLength. + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * Unlike for other ICU functions, if srcLength>=0 but + * destCapacity<srcLength, then *pDestLength will be set to srcLength + * (and U_BUFFER_OVERFLOW_ERROR will be set) + * regardless of the actual result length. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strFromUTF8 + * @see u_strFromUTF8WithSub + * @see u_strToUTF8WithSub + * @stable ICU 3.6 + */ +U_CAPI UChar * U_EXPORT2 +u_strFromUTF8Lenient(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const char *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-16 string to UTF-32. + * If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChar32s). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The pointer to destination buffer. + * @see u_strToUTF32WithSub + * @see u_strFromUTF32 + * @stable ICU 2.0 + */ +U_CAPI UChar32* U_EXPORT2 +u_strToUTF32(UChar32 *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-32 string to UTF-16. + * If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The pointer to destination buffer. + * @see u_strFromUTF32WithSub + * @see u_strToUTF32 + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strFromUTF32(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar32 *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-16 string to UTF-32. + * + * Same as u_strToUTF32() except for the additional subchar which is output for + * illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code. + * With subchar==U_SENTINEL, this function behaves exactly like u_strToUTF32(). + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChar32s). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param subchar The substitution character to use in place of an illegal input sequence, + * or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead. + * A substitution character can be any valid Unicode code point (up to U+10FFFF) + * except for surrogate code points (U+D800..U+DFFF). + * The recommended value is U+FFFD "REPLACEMENT CHARACTER". + * @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strToUTF32 + * @see u_strFromUTF32WithSub + * @stable ICU 4.2 + */ +U_CAPI UChar32* U_EXPORT2 +u_strToUTF32WithSub(UChar32 *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-32 string to UTF-16. + * + * Same as u_strFromUTF32() except for the additional subchar which is output for + * illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code. + * With subchar==U_SENTINEL, this function behaves exactly like u_strFromUTF32(). + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param subchar The substitution character to use in place of an illegal input sequence, + * or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead. + * A substitution character can be any valid Unicode code point (up to U+10FFFF) + * except for surrogate code points (U+D800..U+DFFF). + * The recommended value is U+FFFD "REPLACEMENT CHARACTER". + * @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strFromUTF32 + * @see u_strToUTF32WithSub + * @stable ICU 4.2 + */ +U_CAPI UChar* U_EXPORT2 +u_strFromUTF32WithSub(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar32 *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + +/** + * Convert a 16-bit Unicode string to Java Modified UTF-8. + * See http://java.sun.com/javase/6/docs/api/java/io/DataInput.html#modified-utf-8 + * + * This function behaves according to the documentation for Java DataOutput.writeUTF() + * except that it does not encode the output length in the destination buffer + * and does not have an output length restriction. + * See http://java.sun.com/javase/6/docs/api/java/io/DataOutput.html#writeUTF(java.lang.String) + * + * The input string need not be well-formed UTF-16. + * (Therefore there is no subchar parameter.) + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of chars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @stable ICU 4.4 + * @see u_strToUTF8WithSub + * @see u_strFromJavaModifiedUTF8WithSub + */ +U_CAPI char* U_EXPORT2 +u_strToJavaModifiedUTF8( + char *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a Java Modified UTF-8 string to a 16-bit Unicode string. + * If the input string is not well-formed and no substitution char is specified, + * then the U_INVALID_CHAR_FOUND error code is set. + * + * This function behaves according to the documentation for Java DataInput.readUTF() + * except that it takes a length parameter rather than + * interpreting the first two input bytes as the length. + * See http://java.sun.com/javase/6/docs/api/java/io/DataInput.html#readUTF() + * + * The output string may not be well-formed UTF-16. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param subchar The substitution character to use in place of an illegal input sequence, + * or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead. + * A substitution character can be any valid Unicode code point (up to U+10FFFF) + * except for surrogate code points (U+D800..U+DFFF). + * The recommended value is U+FFFD "REPLACEMENT CHARACTER". + * @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strFromUTF8WithSub + * @see u_strFromUTF8Lenient + * @see u_strToJavaModifiedUTF8 + * @stable ICU 4.4 + */ +U_CAPI UChar* U_EXPORT2 +u_strFromJavaModifiedUTF8WithSub( + UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const char *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + +#endif diff --git a/thirdparty/icu4c/common/unicode/ustringtrie.h b/thirdparty/icu4c/common/unicode/ustringtrie.h new file mode 100644 index 0000000000..fd85648225 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/ustringtrie.h @@ -0,0 +1,97 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2010-2012, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* file name: udicttrie.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2010dec17 +* created by: Markus W. Scherer +*/ + +#ifndef __USTRINGTRIE_H__ +#define __USTRINGTRIE_H__ + +/** + * \file + * \brief C API: Helper definitions for dictionary trie APIs. + */ + +#include "unicode/utypes.h" + + +/** + * Return values for BytesTrie::next(), UCharsTrie::next() and similar methods. + * @see USTRINGTRIE_MATCHES + * @see USTRINGTRIE_HAS_VALUE + * @see USTRINGTRIE_HAS_NEXT + * @stable ICU 4.8 + */ +enum UStringTrieResult { + /** + * The input unit(s) did not continue a matching string. + * Once current()/next() return USTRINGTRIE_NO_MATCH, + * all further calls to current()/next() will also return USTRINGTRIE_NO_MATCH, + * until the trie is reset to its original state or to a saved state. + * @stable ICU 4.8 + */ + USTRINGTRIE_NO_MATCH, + /** + * The input unit(s) continued a matching string + * but there is no value for the string so far. + * (It is a prefix of a longer string.) + * @stable ICU 4.8 + */ + USTRINGTRIE_NO_VALUE, + /** + * The input unit(s) continued a matching string + * and there is a value for the string so far. + * This value will be returned by getValue(). + * No further input byte/unit can continue a matching string. + * @stable ICU 4.8 + */ + USTRINGTRIE_FINAL_VALUE, + /** + * The input unit(s) continued a matching string + * and there is a value for the string so far. + * This value will be returned by getValue(). + * Another input byte/unit can continue a matching string. + * @stable ICU 4.8 + */ + USTRINGTRIE_INTERMEDIATE_VALUE +}; + +/** + * Same as (result!=USTRINGTRIE_NO_MATCH). + * @param result A result from BytesTrie::first(), UCharsTrie::next() etc. + * @return true if the input bytes/units so far are part of a matching string/byte sequence. + * @stable ICU 4.8 + */ +#define USTRINGTRIE_MATCHES(result) ((result)!=USTRINGTRIE_NO_MATCH) + +/** + * Equivalent to (result==USTRINGTRIE_INTERMEDIATE_VALUE || result==USTRINGTRIE_FINAL_VALUE) but + * this macro evaluates result exactly once. + * @param result A result from BytesTrie::first(), UCharsTrie::next() etc. + * @return true if there is a value for the input bytes/units so far. + * @see BytesTrie::getValue + * @see UCharsTrie::getValue + * @stable ICU 4.8 + */ +#define USTRINGTRIE_HAS_VALUE(result) ((result)>=USTRINGTRIE_FINAL_VALUE) + +/** + * Equivalent to (result==USTRINGTRIE_NO_VALUE || result==USTRINGTRIE_INTERMEDIATE_VALUE) but + * this macro evaluates result exactly once. + * @param result A result from BytesTrie::first(), UCharsTrie::next() etc. + * @return true if another input byte/unit can continue a matching string. + * @stable ICU 4.8 + */ +#define USTRINGTRIE_HAS_NEXT(result) ((result)&1) + +#endif /* __USTRINGTRIE_H__ */ diff --git a/thirdparty/icu4c/common/unicode/utext.h b/thirdparty/icu4c/common/unicode/utext.h new file mode 100644 index 0000000000..c6d1e53a8c --- /dev/null +++ b/thirdparty/icu4c/common/unicode/utext.h @@ -0,0 +1,1603 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2004-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utext.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2004oct06 +* created by: Markus W. Scherer +*/ + +#ifndef __UTEXT_H__ +#define __UTEXT_H__ + +/** + * \file + * \brief C API: Abstract Unicode Text API + * + * The Text Access API provides a means to allow text that is stored in alternative + * formats to work with ICU services. ICU normally operates on text that is + * stored in UTF-16 format, in (UChar *) arrays for the C APIs or as type + * UnicodeString for C++ APIs. + * + * ICU Text Access allows other formats, such as UTF-8 or non-contiguous + * UTF-16 strings, to be placed in a UText wrapper and then passed to ICU services. + * + * There are three general classes of usage for UText: + * + * Application Level Use. This is the simplest usage - applications would + * use one of the utext_open() functions on their input text, and pass + * the resulting UText to the desired ICU service. + * + * Second is usage in ICU Services, such as break iteration, that will need to + * operate on input presented to them as a UText. These implementations + * will need to use the iteration and related UText functions to gain + * access to the actual text. + * + * The third class of UText users are "text providers." These are the + * UText implementations for the various text storage formats. An application + * or system with a unique text storage format can implement a set of + * UText provider functions for that format, which will then allow + * ICU services to operate on that format. + * + * + * <em>Iterating over text</em> + * + * Here is sample code for a forward iteration over the contents of a UText + * + * \code + * UChar32 c; + * UText *ut = whatever(); + * + * for (c=utext_next32From(ut, 0); c>=0; c=utext_next32(ut)) { + * // do whatever with the codepoint c here. + * } + * \endcode + * + * And here is similar code to iterate in the reverse direction, from the end + * of the text towards the beginning. + * + * \code + * UChar32 c; + * UText *ut = whatever(); + * int textLength = utext_nativeLength(ut); + * for (c=utext_previous32From(ut, textLength); c>=0; c=utext_previous32(ut)) { + * // do whatever with the codepoint c here. + * } + * \endcode + * + * <em>Characters and Indexing</em> + * + * Indexing into text by UText functions is nearly always in terms of the native + * indexing of the underlying text storage. The storage format could be UTF-8 + * or UTF-32, for example. When coding to the UText access API, no assumptions + * can be made regarding the size of characters, or how far an index + * may move when iterating between characters. + * + * All indices supplied to UText functions are pinned to the length of the + * text. An out-of-bounds index is not considered to be an error, but is + * adjusted to be in the range 0 <= index <= length of input text. + * + * + * When an index position is returned from a UText function, it will be + * a native index to the underlying text. In the case of multi-unit characters, + * it will always refer to the first position of the character, + * never to the interior. This is essentially the same thing as saying that + * a returned index will always point to a boundary between characters. + * + * When a native index is supplied to a UText function, all indices that + * refer to any part of a multi-unit character representation are considered + * to be equivalent. In the case of multi-unit characters, an incoming index + * will be logically normalized to refer to the start of the character. + * + * It is possible to test whether a native index is on a code point boundary + * by doing a utext_setNativeIndex() followed by a utext_getNativeIndex(). + * If the index is returned unchanged, it was on a code point boundary. If + * an adjusted index is returned, the original index referred to the + * interior of a character. + * + * <em>Conventions for calling UText functions</em> + * + * Most UText access functions have as their first parameter a (UText *) pointer, + * which specifies the UText to be used. Unless otherwise noted, the + * pointer must refer to a valid, open UText. Attempting to + * use a closed UText or passing a NULL pointer is a programming error and + * will produce undefined results or NULL pointer exceptions. + * + * The UText_Open family of functions can either open an existing (closed) + * UText, or heap allocate a new UText. Here is sample code for creating + * a stack-allocated UText. + * + * \code + * char *s = whatever(); // A utf-8 string + * U_ErrorCode status = U_ZERO_ERROR; + * UText ut = UTEXT_INITIALIZER; + * utext_openUTF8(ut, s, -1, &status); + * if (U_FAILURE(status)) { + * // error handling + * } else { + * // work with the UText + * } + * \endcode + * + * Any existing UText passed to an open function _must_ have been initialized, + * either by the UTEXT_INITIALIZER, or by having been originally heap-allocated + * by an open function. Passing NULL will cause the open function to + * heap-allocate and fully initialize a new UText. + * + */ + + + +#include "unicode/utypes.h" +#include "unicode/uchar.h" +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#include "unicode/rep.h" +#include "unicode/unistr.h" +#include "unicode/chariter.h" +#endif + + +U_CDECL_BEGIN + +struct UText; +typedef struct UText UText; /**< C typedef for struct UText. @stable ICU 3.6 */ + + +/*************************************************************************************** + * + * C Functions for creating UText wrappers around various kinds of text strings. + * + ****************************************************************************************/ + + +/** + * Close function for UText instances. + * Cleans up, releases any resources being held by an open UText. + * <p> + * If the UText was originally allocated by one of the utext_open functions, + * the storage associated with the utext will also be freed. + * If the UText storage originated with the application, as it would with + * a local or static instance, the storage will not be deleted. + * + * An open UText can be reset to refer to new string by using one of the utext_open() + * functions without first closing the UText. + * + * @param ut The UText to be closed. + * @return NULL if the UText struct was deleted by the close. If the UText struct + * was originally provided by the caller to the open function, it is + * returned by this function, and may be safely used again in + * a subsequent utext_open. + * + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_close(UText *ut); + +/** + * Open a read-only UText implementation for UTF-8 strings. + * + * \htmlonly + * Any invalid UTF-8 in the input will be handled in this way: + * a sequence of bytes that has the form of a truncated, but otherwise valid, + * UTF-8 sequence will be replaced by a single unicode replacement character, \uFFFD. + * Any other illegal bytes will each be replaced by a \uFFFD. + * \endhtmlonly + * + * @param ut Pointer to a UText struct. If NULL, a new UText will be created. + * If non-NULL, must refer to an initialized UText struct, which will then + * be reset to reference the specified UTF-8 string. + * @param s A UTF-8 string. Must not be NULL. + * @param length The length of the UTF-8 string in bytes, or -1 if the string is + * zero terminated. + * @param status Errors are returned here. + * @return A pointer to the UText. If a pre-allocated UText was provided, it + * will always be used and returned. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_openUTF8(UText *ut, const char *s, int64_t length, UErrorCode *status); + + +/** + * Open a read-only UText for UChar * string. + * + * @param ut Pointer to a UText struct. If NULL, a new UText will be created. + * If non-NULL, must refer to an initialized UText struct, which will then + * be reset to reference the specified UChar string. + * @param s A UChar (UTF-16) string + * @param length The number of UChars in the input string, or -1 if the string is + * zero terminated. + * @param status Errors are returned here. + * @return A pointer to the UText. If a pre-allocated UText was provided, it + * will always be used and returned. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_openUChars(UText *ut, const UChar *s, int64_t length, UErrorCode *status); + + +#if U_SHOW_CPLUSPLUS_API +/** + * Open a writable UText for a non-const UnicodeString. + * + * @param ut Pointer to a UText struct. If NULL, a new UText will be created. + * If non-NULL, must refer to an initialized UText struct, which will then + * be reset to reference the specified input string. + * @param s A UnicodeString. + * @param status Errors are returned here. + * @return Pointer to the UText. If a UText was supplied as input, this + * will always be used and returned. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_openUnicodeString(UText *ut, icu::UnicodeString *s, UErrorCode *status); + + +/** + * Open a UText for a const UnicodeString. The resulting UText will not be writable. + * + * @param ut Pointer to a UText struct. If NULL, a new UText will be created. + * If non-NULL, must refer to an initialized UText struct, which will then + * be reset to reference the specified input string. + * @param s A const UnicodeString to be wrapped. + * @param status Errors are returned here. + * @return Pointer to the UText. If a UText was supplied as input, this + * will always be used and returned. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_openConstUnicodeString(UText *ut, const icu::UnicodeString *s, UErrorCode *status); + + +/** + * Open a writable UText implementation for an ICU Replaceable object. + * @param ut Pointer to a UText struct. If NULL, a new UText will be created. + * If non-NULL, must refer to an already existing UText, which will then + * be reset to reference the specified replaceable text. + * @param rep A Replaceable text object. + * @param status Errors are returned here. + * @return Pointer to the UText. If a UText was supplied as input, this + * will always be used and returned. + * @see Replaceable + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_openReplaceable(UText *ut, icu::Replaceable *rep, UErrorCode *status); + +/** + * Open a UText implementation over an ICU CharacterIterator. + * @param ut Pointer to a UText struct. If NULL, a new UText will be created. + * If non-NULL, must refer to an already existing UText, which will then + * be reset to reference the specified replaceable text. + * @param ci A Character Iterator. + * @param status Errors are returned here. + * @return Pointer to the UText. If a UText was supplied as input, this + * will always be used and returned. + * @see Replaceable + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_openCharacterIterator(UText *ut, icu::CharacterIterator *ci, UErrorCode *status); + +#endif + + +/** + * Clone a UText. This is much like opening a UText where the source text is itself + * another UText. + * + * A deep clone will copy both the UText data structures and the underlying text. + * The original and cloned UText will operate completely independently; modifications + * made to the text in one will not affect the other. Text providers are not + * required to support deep clones. The user of clone() must check the status return + * and be prepared to handle failures. + * + * The standard UText implementations for UTF8, UChar *, UnicodeString and + * Replaceable all support deep cloning. + * + * The UText returned from a deep clone will be writable, assuming that the text + * provider is able to support writing, even if the source UText had been made + * non-writable by means of UText_freeze(). + * + * A shallow clone replicates only the UText data structures; it does not make + * a copy of the underlying text. Shallow clones can be used as an efficient way to + * have multiple iterators active in a single text string that is not being + * modified. + * + * A shallow clone operation will not fail, barring truly exceptional conditions such + * as memory allocation failures. + * + * Shallow UText clones should be avoided if the UText functions that modify the + * text are expected to be used, either on the original or the cloned UText. + * Any such modifications can cause unpredictable behavior. Read Only + * shallow clones provide some protection against errors of this type by + * disabling text modification via the cloned UText. + * + * A shallow clone made with the readOnly parameter == false will preserve the + * utext_isWritable() state of the source object. Note, however, that + * write operations must be avoided while more than one UText exists that refer + * to the same underlying text. + * + * A UText and its clone may be safely concurrently accessed by separate threads. + * This is true for read access only with shallow clones, and for both read and + * write access with deep clones. + * It is the responsibility of the Text Provider to ensure that this thread safety + * constraint is met. + * + * @param dest A UText struct to be filled in with the result of the clone operation, + * or NULL if the clone function should heap-allocate a new UText struct. + * If non-NULL, must refer to an already existing UText, which will then + * be reset to become the clone. + * @param src The UText to be cloned. + * @param deep true to request a deep clone, false for a shallow clone. + * @param readOnly true to request that the cloned UText have read only access to the + * underlying text. + + * @param status Errors are returned here. For deep clones, U_UNSUPPORTED_ERROR + * will be returned if the text provider is unable to clone the + * original text. + * @return The newly created clone, or NULL if the clone operation failed. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_clone(UText *dest, const UText *src, UBool deep, UBool readOnly, UErrorCode *status); + + +/** + * Compare two UText objects for equality. + * UTexts are equal if they are iterating over the same text, and + * have the same iteration position within the text. + * If either or both of the parameters are NULL, the comparison is false. + * + * @param a The first of the two UTexts to compare. + * @param b The other UText to be compared. + * @return true if the two UTexts are equal. + * @stable ICU 3.6 + */ +U_CAPI UBool U_EXPORT2 +utext_equals(const UText *a, const UText *b); + + +/***************************************************************************** + * + * Functions to work with the text represented by a UText wrapper + * + *****************************************************************************/ + +/** + * Get the length of the text. Depending on the characteristics + * of the underlying text representation, this may be expensive. + * @see utext_isLengthExpensive() + * + * + * @param ut the text to be accessed. + * @return the length of the text, expressed in native units. + * + * @stable ICU 3.4 + */ +U_CAPI int64_t U_EXPORT2 +utext_nativeLength(UText *ut); + +/** + * Return true if calculating the length of the text could be expensive. + * Finding the length of NUL terminated strings is considered to be expensive. + * + * Note that the value of this function may change + * as the result of other operations on a UText. + * Once the length of a string has been discovered, it will no longer + * be expensive to report it. + * + * @param ut the text to be accessed. + * @return true if determining the length of the text could be time consuming. + * @stable ICU 3.4 + */ +U_CAPI UBool U_EXPORT2 +utext_isLengthExpensive(const UText *ut); + +/** + * Returns the code point at the requested index, + * or U_SENTINEL (-1) if it is out of bounds. + * + * If the specified index points to the interior of a multi-unit + * character - one of the trail bytes of a UTF-8 sequence, for example - + * the complete code point will be returned. + * + * The iteration position will be set to the start of the returned code point. + * + * This function is roughly equivalent to the sequence + * utext_setNativeIndex(index); + * utext_current32(); + * (There is a subtle difference if the index is out of bounds by being less than zero - + * utext_setNativeIndex(negative value) sets the index to zero, after which utext_current() + * will return the char at zero. utext_char32At(negative index), on the other hand, will + * return the U_SENTINEL value of -1.) + * + * @param ut the text to be accessed + * @param nativeIndex the native index of the character to be accessed. If the index points + * to other than the first unit of a multi-unit character, it will be adjusted + * to the start of the character. + * @return the code point at the specified index. + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_char32At(UText *ut, int64_t nativeIndex); + + +/** + * + * Get the code point at the current iteration position, + * or U_SENTINEL (-1) if the iteration has reached the end of + * the input text. + * + * @param ut the text to be accessed. + * @return the Unicode code point at the current iterator position. + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_current32(UText *ut); + + +/** + * Get the code point at the current iteration position of the UText, and + * advance the position to the first index following the character. + * + * If the position is at the end of the text (the index following + * the last character, which is also the length of the text), + * return U_SENTINEL (-1) and do not advance the index. + * + * This is a post-increment operation. + * + * An inline macro version of this function, UTEXT_NEXT32(), + * is available for performance critical use. + * + * @param ut the text to be accessed. + * @return the Unicode code point at the iteration position. + * @see UTEXT_NEXT32 + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_next32(UText *ut); + + +/** + * Move the iterator position to the character (code point) whose + * index precedes the current position, and return that character. + * This is a pre-decrement operation. + * + * If the initial position is at the start of the text (index of 0) + * return U_SENTINEL (-1), and leave the position unchanged. + * + * An inline macro version of this function, UTEXT_PREVIOUS32(), + * is available for performance critical use. + * + * @param ut the text to be accessed. + * @return the previous UChar32 code point, or U_SENTINEL (-1) + * if the iteration has reached the start of the text. + * @see UTEXT_PREVIOUS32 + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_previous32(UText *ut); + + +/** + * Set the iteration index and return the code point at that index. + * Leave the iteration index at the start of the following code point. + * + * This function is the most efficient and convenient way to + * begin a forward iteration. The results are identical to the those + * from the sequence + * \code + * utext_setIndex(); + * utext_next32(); + * \endcode + * + * @param ut the text to be accessed. + * @param nativeIndex Iteration index, in the native units of the text provider. + * @return Code point which starts at or before index, + * or U_SENTINEL (-1) if it is out of bounds. + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_next32From(UText *ut, int64_t nativeIndex); + + + +/** + * Set the iteration index, and return the code point preceding the + * one specified by the initial index. Leave the iteration position + * at the start of the returned code point. + * + * This function is the most efficient and convenient way to + * begin a backwards iteration. + * + * @param ut the text to be accessed. + * @param nativeIndex Iteration index in the native units of the text provider. + * @return Code point preceding the one at the initial index, + * or U_SENTINEL (-1) if it is out of bounds. + * + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_previous32From(UText *ut, int64_t nativeIndex); + +/** + * Get the current iterator position, which can range from 0 to + * the length of the text. + * The position is a native index into the input text, in whatever format it + * may have (possibly UTF-8 for example), and may not always be the same as + * the corresponding UChar (UTF-16) index. + * The returned position will always be aligned to a code point boundary. + * + * @param ut the text to be accessed. + * @return the current index position, in the native units of the text provider. + * @stable ICU 3.4 + */ +U_CAPI int64_t U_EXPORT2 +utext_getNativeIndex(const UText *ut); + +/** + * Set the current iteration position to the nearest code point + * boundary at or preceding the specified index. + * The index is in the native units of the original input text. + * If the index is out of range, it will be pinned to be within + * the range of the input text. + * <p> + * It will usually be more efficient to begin an iteration + * using the functions utext_next32From() or utext_previous32From() + * rather than setIndex(). + * <p> + * Moving the index position to an adjacent character is best done + * with utext_next32(), utext_previous32() or utext_moveIndex32(). + * Attempting to do direct arithmetic on the index position is + * complicated by the fact that the size (in native units) of a + * character depends on the underlying representation of the character + * (UTF-8, UTF-16, UTF-32, arbitrary codepage), and is not + * easily knowable. + * + * @param ut the text to be accessed. + * @param nativeIndex the native unit index of the new iteration position. + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +utext_setNativeIndex(UText *ut, int64_t nativeIndex); + +/** + * Move the iterator position by delta code points. The number of code points + * is a signed number; a negative delta will move the iterator backwards, + * towards the start of the text. + * <p> + * The index is moved by <code>delta</code> code points + * forward or backward, but no further backward than to 0 and + * no further forward than to utext_nativeLength(). + * The resulting index value will be in between 0 and length, inclusive. + * + * @param ut the text to be accessed. + * @param delta the signed number of code points to move the iteration position. + * @return true if the position could be moved the requested number of positions while + * staying within the range [0 - text length]. + * @stable ICU 3.4 + */ +U_CAPI UBool U_EXPORT2 +utext_moveIndex32(UText *ut, int32_t delta); + +/** + * Get the native index of the character preceding the current position. + * If the iteration position is already at the start of the text, zero + * is returned. + * The value returned is the same as that obtained from the following sequence, + * but without the side effect of changing the iteration position. + * + * \code + * UText *ut = whatever; + * ... + * utext_previous(ut) + * utext_getNativeIndex(ut); + * \endcode + * + * This function is most useful during forwards iteration, where it will get the + * native index of the character most recently returned from utext_next(). + * + * @param ut the text to be accessed + * @return the native index of the character preceding the current index position, + * or zero if the current position is at the start of the text. + * @stable ICU 3.6 + */ +U_CAPI int64_t U_EXPORT2 +utext_getPreviousNativeIndex(UText *ut); + + +/** + * + * Extract text from a UText into a UChar buffer. The range of text to be extracted + * is specified in the native indices of the UText provider. These may not necessarily + * be UTF-16 indices. + * <p> + * The size (number of 16 bit UChars) of the data to be extracted is returned. The + * full number of UChars is returned, even when the extracted text is truncated + * because the specified buffer size is too small. + * <p> + * The extracted string will (if you are a user) / must (if you are a text provider) + * be NUL-terminated if there is sufficient space in the destination buffer. This + * terminating NUL is not included in the returned length. + * <p> + * The iteration index is left at the position following the last extracted character. + * + * @param ut the UText from which to extract data. + * @param nativeStart the native index of the first character to extract.\ + * If the specified index is out of range, + * it will be pinned to be within 0 <= index <= textLength + * @param nativeLimit the native string index of the position following the last + * character to extract. If the specified index is out of range, + * it will be pinned to be within 0 <= index <= textLength. + * nativeLimit must be >= nativeStart. + * @param dest the UChar (UTF-16) buffer into which the extracted text is placed + * @param destCapacity The size, in UChars, of the destination buffer. May be zero + * for precomputing the required size. + * @param status receives any error status. + * U_BUFFER_OVERFLOW_ERROR: the extracted text was truncated because the + * buffer was too small. Returns number of UChars for preflighting. + * @return Number of UChars in the data to be extracted. Does not include a trailing NUL. + * + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +utext_extract(UText *ut, + int64_t nativeStart, int64_t nativeLimit, + UChar *dest, int32_t destCapacity, + UErrorCode *status); + + + +/************************************************************************************ + * + * #define inline versions of selected performance-critical text access functions + * Caution: do not use auto increment++ or decrement-- expressions + * as parameters to these macros. + * + * For most use, where there is no extreme performance constraint, the + * normal, non-inline functions are a better choice. The resulting code + * will be smaller, and, if the need ever arises, easier to debug. + * + * These are implemented as #defines rather than real functions + * because there is no fully portable way to do inline functions in plain C. + * + ************************************************************************************/ + +#ifndef U_HIDE_INTERNAL_API +/** + * inline version of utext_current32(), for performance-critical situations. + * + * Get the code point at the current iteration position of the UText. + * Returns U_SENTINEL (-1) if the position is at the end of the + * text. + * + * @internal ICU 4.4 technology preview + */ +#define UTEXT_CURRENT32(ut) \ + ((ut)->chunkOffset < (ut)->chunkLength && ((ut)->chunkContents)[(ut)->chunkOffset]<0xd800 ? \ + ((ut)->chunkContents)[((ut)->chunkOffset)] : utext_current32(ut)) +#endif /* U_HIDE_INTERNAL_API */ + +/** + * inline version of utext_next32(), for performance-critical situations. + * + * Get the code point at the current iteration position of the UText, and + * advance the position to the first index following the character. + * This is a post-increment operation. + * Returns U_SENTINEL (-1) if the position is at the end of the + * text. + * + * @stable ICU 3.4 + */ +#define UTEXT_NEXT32(ut) \ + ((ut)->chunkOffset < (ut)->chunkLength && ((ut)->chunkContents)[(ut)->chunkOffset]<0xd800 ? \ + ((ut)->chunkContents)[((ut)->chunkOffset)++] : utext_next32(ut)) + +/** + * inline version of utext_previous32(), for performance-critical situations. + * + * Move the iterator position to the character (code point) whose + * index precedes the current position, and return that character. + * This is a pre-decrement operation. + * Returns U_SENTINEL (-1) if the position is at the start of the text. + * + * @stable ICU 3.4 + */ +#define UTEXT_PREVIOUS32(ut) \ + ((ut)->chunkOffset > 0 && \ + (ut)->chunkContents[(ut)->chunkOffset-1] < 0xd800 ? \ + (ut)->chunkContents[--((ut)->chunkOffset)] : utext_previous32(ut)) + +/** + * inline version of utext_getNativeIndex(), for performance-critical situations. + * + * Get the current iterator position, which can range from 0 to + * the length of the text. + * The position is a native index into the input text, in whatever format it + * may have (possibly UTF-8 for example), and may not always be the same as + * the corresponding UChar (UTF-16) index. + * The returned position will always be aligned to a code point boundary. + * + * @stable ICU 3.6 + */ +#define UTEXT_GETNATIVEINDEX(ut) \ + ((ut)->chunkOffset <= (ut)->nativeIndexingLimit? \ + (ut)->chunkNativeStart+(ut)->chunkOffset : \ + (ut)->pFuncs->mapOffsetToNative(ut)) + +/** + * inline version of utext_setNativeIndex(), for performance-critical situations. + * + * Set the current iteration position to the nearest code point + * boundary at or preceding the specified index. + * The index is in the native units of the original input text. + * If the index is out of range, it will be pinned to be within + * the range of the input text. + * + * @stable ICU 3.8 + */ +#define UTEXT_SETNATIVEINDEX(ut, ix) UPRV_BLOCK_MACRO_BEGIN { \ + int64_t __offset = (ix) - (ut)->chunkNativeStart; \ + if (__offset>=0 && __offset<(int64_t)(ut)->nativeIndexingLimit && (ut)->chunkContents[__offset]<0xdc00) { \ + (ut)->chunkOffset=(int32_t)__offset; \ + } else { \ + utext_setNativeIndex((ut), (ix)); \ + } \ +} UPRV_BLOCK_MACRO_END + + + +/************************************************************************************ + * + * Functions related to writing or modifying the text. + * These will work only with modifiable UTexts. Attempting to + * modify a read-only UText will return an error status. + * + ************************************************************************************/ + + +/** + * Return true if the text can be written (modified) with utext_replace() or + * utext_copy(). For the text to be writable, the text provider must + * be of a type that supports writing and the UText must not be frozen. + * + * Attempting to modify text when utext_isWriteable() is false will fail - + * the text will not be modified, and an error will be returned from the function + * that attempted the modification. + * + * @param ut the UText to be tested. + * @return true if the text is modifiable. + * + * @see utext_freeze() + * @see utext_replace() + * @see utext_copy() + * @stable ICU 3.4 + * + */ +U_CAPI UBool U_EXPORT2 +utext_isWritable(const UText *ut); + + +/** + * Test whether there is meta data associated with the text. + * @see Replaceable::hasMetaData() + * + * @param ut The UText to be tested + * @return true if the underlying text includes meta data. + * @stable ICU 3.4 + */ +U_CAPI UBool U_EXPORT2 +utext_hasMetaData(const UText *ut); + + +/** + * Replace a range of the original text with a replacement text. + * + * Leaves the current iteration position at the position following the + * newly inserted replacement text. + * + * This function is only available on UText types that support writing, + * that is, ones where utext_isWritable() returns true. + * + * When using this function, there should be only a single UText opened onto the + * underlying native text string. Behavior after a replace operation + * on a UText is undefined for any other additional UTexts that refer to the + * modified string. + * + * @param ut the UText representing the text to be operated on. + * @param nativeStart the native index of the start of the region to be replaced + * @param nativeLimit the native index of the character following the region to be replaced. + * @param replacementText pointer to the replacement text + * @param replacementLength length of the replacement text, or -1 if the text is NUL terminated. + * @param status receives any error status. Possible errors include + * U_NO_WRITE_PERMISSION + * + * @return The signed number of (native) storage units by which + * the length of the text expanded or contracted. + * + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +utext_replace(UText *ut, + int64_t nativeStart, int64_t nativeLimit, + const UChar *replacementText, int32_t replacementLength, + UErrorCode *status); + + + +/** + * + * Copy or move a substring from one position to another within the text, + * while retaining any metadata associated with the text. + * This function is used to duplicate or reorder substrings. + * The destination index must not overlap the source range. + * + * The text to be copied or moved is inserted at destIndex; + * it does not replace or overwrite any existing text. + * + * The iteration position is left following the newly inserted text + * at the destination position. + * + * This function is only available on UText types that support writing, + * that is, ones where utext_isWritable() returns true. + * + * When using this function, there should be only a single UText opened onto the + * underlying native text string. Behavior after a copy operation + * on a UText is undefined in any other additional UTexts that refer to the + * modified string. + * + * @param ut The UText representing the text to be operated on. + * @param nativeStart The native index of the start of the region to be copied or moved + * @param nativeLimit The native index of the character position following the region + * to be copied. + * @param destIndex The native destination index to which the source substring is + * copied or moved. + * @param move If true, then the substring is moved, not copied/duplicated. + * @param status receives any error status. Possible errors include U_NO_WRITE_PERMISSION + * + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +utext_copy(UText *ut, + int64_t nativeStart, int64_t nativeLimit, + int64_t destIndex, + UBool move, + UErrorCode *status); + + +/** + * <p> + * Freeze a UText. This prevents any modification to the underlying text itself + * by means of functions operating on this UText. + * </p> + * <p> + * Once frozen, a UText can not be unfrozen. The intent is to ensure + * that a the text underlying a frozen UText wrapper cannot be modified via that UText. + * </p> + * <p> + * Caution: freezing a UText will disable changes made via the specific + * frozen UText wrapper only; it will not have any effect on the ability to + * directly modify the text by bypassing the UText. Any such backdoor modifications + * are always an error while UText access is occurring because the underlying + * text can get out of sync with UText's buffering. + * </p> + * + * @param ut The UText to be frozen. + * @see utext_isWritable() + * @stable ICU 3.6 + */ +U_CAPI void U_EXPORT2 +utext_freeze(UText *ut); + + +/** + * UText provider properties (bit field indexes). + * + * @see UText + * @stable ICU 3.4 + */ +enum { + /** + * It is potentially time consuming for the provider to determine the length of the text. + * @stable ICU 3.4 + */ + UTEXT_PROVIDER_LENGTH_IS_EXPENSIVE = 1, + /** + * Text chunks remain valid and usable until the text object is modified or + * deleted, not just until the next time the access() function is called + * (which is the default). + * @stable ICU 3.4 + */ + UTEXT_PROVIDER_STABLE_CHUNKS = 2, + /** + * The provider supports modifying the text via the replace() and copy() + * functions. + * @see Replaceable + * @stable ICU 3.4 + */ + UTEXT_PROVIDER_WRITABLE = 3, + /** + * There is meta data associated with the text. + * @see Replaceable::hasMetaData() + * @stable ICU 3.4 + */ + UTEXT_PROVIDER_HAS_META_DATA = 4, + /** + * Text provider owns the text storage. + * Generally occurs as the result of a deep clone of the UText. + * When closing the UText, the associated text must + * also be closed/deleted/freed/ whatever is appropriate. + * @stable ICU 3.6 + */ + UTEXT_PROVIDER_OWNS_TEXT = 5 +}; + +/** + * Function type declaration for UText.clone(). + * + * clone a UText. Much like opening a UText where the source text is itself + * another UText. + * + * A deep clone will copy both the UText data structures and the underlying text. + * The original and cloned UText will operate completely independently; modifications + * made to the text in one will not effect the other. Text providers are not + * required to support deep clones. The user of clone() must check the status return + * and be prepared to handle failures. + * + * A shallow clone replicates only the UText data structures; it does not make + * a copy of the underlying text. Shallow clones can be used as an efficient way to + * have multiple iterators active in a single text string that is not being + * modified. + * + * A shallow clone operation must not fail except for truly exceptional conditions such + * as memory allocation failures. + * + * A UText and its clone may be safely concurrently accessed by separate threads. + * This is true for both shallow and deep clones. + * It is the responsibility of the Text Provider to ensure that this thread safety + * constraint is met. + + * + * @param dest A UText struct to be filled in with the result of the clone operation, + * or NULL if the clone function should heap-allocate a new UText struct. + * @param src The UText to be cloned. + * @param deep true to request a deep clone, false for a shallow clone. + * @param status Errors are returned here. For deep clones, U_UNSUPPORTED_ERROR + * should be returned if the text provider is unable to clone the + * original text. + * @return The newly created clone, or NULL if the clone operation failed. + * + * @stable ICU 3.4 + */ +typedef UText * U_CALLCONV +UTextClone(UText *dest, const UText *src, UBool deep, UErrorCode *status); + + +/** + * Function type declaration for UText.nativeLength(). + * + * @param ut the UText to get the length of. + * @return the length, in the native units of the original text string. + * @see UText + * @stable ICU 3.4 + */ +typedef int64_t U_CALLCONV +UTextNativeLength(UText *ut); + +/** + * Function type declaration for UText.access(). Get the description of the text chunk + * containing the text at a requested native index. The UText's iteration + * position will be left at the requested index. If the index is out + * of bounds, the iteration position will be left at the start or end + * of the string, as appropriate. + * + * Chunks must begin and end on code point boundaries. A single code point + * comprised of multiple storage units must never span a chunk boundary. + * + * + * @param ut the UText being accessed. + * @param nativeIndex Requested index of the text to be accessed. + * @param forward If true, then the returned chunk must contain text + * starting from the index, so that start<=index<limit. + * If false, then the returned chunk must contain text + * before the index, so that start<index<=limit. + * @return True if the requested index could be accessed. The chunk + * will contain the requested text. + * False value if a chunk cannot be accessed + * (the requested index is out of bounds). + * + * @see UText + * @stable ICU 3.4 + */ +typedef UBool U_CALLCONV +UTextAccess(UText *ut, int64_t nativeIndex, UBool forward); + +/** + * Function type declaration for UText.extract(). + * + * Extract text from a UText into a UChar buffer. The range of text to be extracted + * is specified in the native indices of the UText provider. These may not necessarily + * be UTF-16 indices. + * <p> + * The size (number of 16 bit UChars) in the data to be extracted is returned. The + * full amount is returned, even when the specified buffer size is smaller. + * <p> + * The extracted string will (if you are a user) / must (if you are a text provider) + * be NUL-terminated if there is sufficient space in the destination buffer. + * + * @param ut the UText from which to extract data. + * @param nativeStart the native index of the first character to extract. + * @param nativeLimit the native string index of the position following the last + * character to extract. + * @param dest the UChar (UTF-16) buffer into which the extracted text is placed + * @param destCapacity The size, in UChars, of the destination buffer. May be zero + * for precomputing the required size. + * @param status receives any error status. + * If U_BUFFER_OVERFLOW_ERROR: Returns number of UChars for + * preflighting. + * @return Number of UChars in the data. Does not include a trailing NUL. + * + * @stable ICU 3.4 + */ +typedef int32_t U_CALLCONV +UTextExtract(UText *ut, + int64_t nativeStart, int64_t nativeLimit, + UChar *dest, int32_t destCapacity, + UErrorCode *status); + +/** + * Function type declaration for UText.replace(). + * + * Replace a range of the original text with a replacement text. + * + * Leaves the current iteration position at the position following the + * newly inserted replacement text. + * + * This function need only be implemented on UText types that support writing. + * + * When using this function, there should be only a single UText opened onto the + * underlying native text string. The function is responsible for updating the + * text chunk within the UText to reflect the updated iteration position, + * taking into account any changes to the underlying string's structure caused + * by the replace operation. + * + * @param ut the UText representing the text to be operated on. + * @param nativeStart the index of the start of the region to be replaced + * @param nativeLimit the index of the character following the region to be replaced. + * @param replacementText pointer to the replacement text + * @param replacmentLength length of the replacement text in UChars, or -1 if the text is NUL terminated. + * @param status receives any error status. Possible errors include + * U_NO_WRITE_PERMISSION + * + * @return The signed number of (native) storage units by which + * the length of the text expanded or contracted. + * + * @stable ICU 3.4 + */ +typedef int32_t U_CALLCONV +UTextReplace(UText *ut, + int64_t nativeStart, int64_t nativeLimit, + const UChar *replacementText, int32_t replacmentLength, + UErrorCode *status); + +/** + * Function type declaration for UText.copy(). + * + * Copy or move a substring from one position to another within the text, + * while retaining any metadata associated with the text. + * This function is used to duplicate or reorder substrings. + * The destination index must not overlap the source range. + * + * The text to be copied or moved is inserted at destIndex; + * it does not replace or overwrite any existing text. + * + * This function need only be implemented for UText types that support writing. + * + * When using this function, there should be only a single UText opened onto the + * underlying native text string. The function is responsible for updating the + * text chunk within the UText to reflect the updated iteration position, + * taking into account any changes to the underlying string's structure caused + * by the replace operation. + * + * @param ut The UText representing the text to be operated on. + * @param nativeStart The index of the start of the region to be copied or moved + * @param nativeLimit The index of the character following the region to be replaced. + * @param nativeDest The destination index to which the source substring is copied or moved. + * @param move If true, then the substring is moved, not copied/duplicated. + * @param status receives any error status. Possible errors include U_NO_WRITE_PERMISSION + * + * @stable ICU 3.4 + */ +typedef void U_CALLCONV +UTextCopy(UText *ut, + int64_t nativeStart, int64_t nativeLimit, + int64_t nativeDest, + UBool move, + UErrorCode *status); + +/** + * Function type declaration for UText.mapOffsetToNative(). + * Map from the current UChar offset within the current text chunk to + * the corresponding native index in the original source text. + * + * This is required only for text providers that do not use native UTF-16 indexes. + * + * @param ut the UText. + * @return Absolute (native) index corresponding to chunkOffset in the current chunk. + * The returned native index should always be to a code point boundary. + * + * @stable ICU 3.4 + */ +typedef int64_t U_CALLCONV +UTextMapOffsetToNative(const UText *ut); + +/** + * Function type declaration for UText.mapIndexToUTF16(). + * Map from a native index to a UChar offset within a text chunk. + * Behavior is undefined if the native index does not fall within the + * current chunk. + * + * This function is required only for text providers that do not use native UTF-16 indexes. + * + * @param ut The UText containing the text chunk. + * @param nativeIndex Absolute (native) text index, chunk->start<=index<=chunk->limit. + * @return Chunk-relative UTF-16 offset corresponding to the specified native + * index. + * + * @stable ICU 3.4 + */ +typedef int32_t U_CALLCONV +UTextMapNativeIndexToUTF16(const UText *ut, int64_t nativeIndex); + + +/** + * Function type declaration for UText.utextClose(). + * + * A Text Provider close function is only required for provider types that make + * allocations in their open function (or other functions) that must be + * cleaned when the UText is closed. + * + * The allocation of the UText struct itself and any "extra" storage + * associated with the UText is handled by the common UText implementation + * and does not require provider specific cleanup in a close function. + * + * Most UText provider implementations do not need to implement this function. + * + * @param ut A UText object to be closed. + * + * @stable ICU 3.4 + */ +typedef void U_CALLCONV +UTextClose(UText *ut); + + +/** + * (public) Function dispatch table for UText. + * Conceptually very much like a C++ Virtual Function Table. + * This struct defines the organization of the table. + * Each text provider implementation must provide an + * actual table that is initialized with the appropriate functions + * for the type of text being handled. + * @stable ICU 3.6 + */ +struct UTextFuncs { + /** + * (public) Function table size, sizeof(UTextFuncs) + * Intended for use should the table grow to accommodate added + * functions in the future, to allow tests for older format + * function tables that do not contain the extensions. + * + * Fields are placed for optimal alignment on + * 32/64/128-bit-pointer machines, by normally grouping together + * 4 32-bit fields, + * 4 pointers, + * 2 64-bit fields + * in sequence. + * @stable ICU 3.6 + */ + int32_t tableSize; + + /** + * (private) Alignment padding. + * Do not use, reserved for use by the UText framework only. + * @internal + */ + int32_t reserved1, /** @internal */ reserved2, /** @internal */ reserved3; + + + /** + * (public) Function pointer for UTextClone + * + * @see UTextClone + * @stable ICU 3.6 + */ + UTextClone *clone; + + /** + * (public) function pointer for UTextLength + * May be expensive to compute! + * + * @see UTextLength + * @stable ICU 3.6 + */ + UTextNativeLength *nativeLength; + + /** + * (public) Function pointer for UTextAccess. + * + * @see UTextAccess + * @stable ICU 3.6 + */ + UTextAccess *access; + + /** + * (public) Function pointer for UTextExtract. + * + * @see UTextExtract + * @stable ICU 3.6 + */ + UTextExtract *extract; + + /** + * (public) Function pointer for UTextReplace. + * + * @see UTextReplace + * @stable ICU 3.6 + */ + UTextReplace *replace; + + /** + * (public) Function pointer for UTextCopy. + * + * @see UTextCopy + * @stable ICU 3.6 + */ + UTextCopy *copy; + + /** + * (public) Function pointer for UTextMapOffsetToNative. + * + * @see UTextMapOffsetToNative + * @stable ICU 3.6 + */ + UTextMapOffsetToNative *mapOffsetToNative; + + /** + * (public) Function pointer for UTextMapNativeIndexToUTF16. + * + * @see UTextMapNativeIndexToUTF16 + * @stable ICU 3.6 + */ + UTextMapNativeIndexToUTF16 *mapNativeIndexToUTF16; + + /** + * (public) Function pointer for UTextClose. + * + * @see UTextClose + * @stable ICU 3.6 + */ + UTextClose *close; + + /** + * (private) Spare function pointer + * @internal + */ + UTextClose *spare1; + + /** + * (private) Spare function pointer + * @internal + */ + UTextClose *spare2; + + /** + * (private) Spare function pointer + * @internal + */ + UTextClose *spare3; + +}; +/** + * Function dispatch table for UText + * @see UTextFuncs + */ +typedef struct UTextFuncs UTextFuncs; + + /** + * UText struct. Provides the interface between the generic UText access code + * and the UText provider code that works on specific kinds of + * text (UTF-8, noncontiguous UTF-16, whatever.) + * + * Applications that are using predefined types of text providers + * to pass text data to ICU services will have no need to view the + * internals of the UText structs that they open. + * + * @stable ICU 3.6 + */ +struct UText { + /** + * (private) Magic. Used to help detect when UText functions are handed + * invalid or uninitialized UText structs. + * utext_openXYZ() functions take an initialized, + * but not necessarily open, UText struct as an + * optional fill-in parameter. This magic field + * is used to check for that initialization. + * Text provider close functions must NOT clear + * the magic field because that would prevent + * reuse of the UText struct. + * @internal + */ + uint32_t magic; + + + /** + * (private) Flags for managing the allocation and freeing of + * memory associated with this UText. + * @internal + */ + int32_t flags; + + + /** + * Text provider properties. This set of flags is maintained by the + * text provider implementation. + * @stable ICU 3.4 + */ + int32_t providerProperties; + + /** + * (public) sizeOfStruct=sizeof(UText) + * Allows possible backward compatible extension. + * + * @stable ICU 3.4 + */ + int32_t sizeOfStruct; + + /* ------ 16 byte alignment boundary ----------- */ + + + /** + * (protected) Native index of the first character position following + * the current chunk. + * @stable ICU 3.6 + */ + int64_t chunkNativeLimit; + + /** + * (protected) Size in bytes of the extra space (pExtra). + * @stable ICU 3.4 + */ + int32_t extraSize; + + /** + * (protected) The highest chunk offset where native indexing and + * chunk (UTF-16) indexing correspond. For UTF-16 sources, value + * will be equal to chunkLength. + * + * @stable ICU 3.6 + */ + int32_t nativeIndexingLimit; + + /* ---- 16 byte alignment boundary------ */ + + /** + * (protected) Native index of the first character in the text chunk. + * @stable ICU 3.6 + */ + int64_t chunkNativeStart; + + /** + * (protected) Current iteration position within the text chunk (UTF-16 buffer). + * This is the index to the character that will be returned by utext_next32(). + * @stable ICU 3.6 + */ + int32_t chunkOffset; + + /** + * (protected) Length the text chunk (UTF-16 buffer), in UChars. + * @stable ICU 3.6 + */ + int32_t chunkLength; + + /* ---- 16 byte alignment boundary-- */ + + + /** + * (protected) pointer to a chunk of text in UTF-16 format. + * May refer either to original storage of the source of the text, or + * if conversion was required, to a buffer owned by the UText. + * @stable ICU 3.6 + */ + const UChar *chunkContents; + + /** + * (public) Pointer to Dispatch table for accessing functions for this UText. + * @stable ICU 3.6 + */ + const UTextFuncs *pFuncs; + + /** + * (protected) Pointer to additional space requested by the + * text provider during the utext_open operation. + * @stable ICU 3.4 + */ + void *pExtra; + + /** + * (protected) Pointer to string or text-containing object or similar. + * This is the source of the text that this UText is wrapping, in a format + * that is known to the text provider functions. + * @stable ICU 3.4 + */ + const void *context; + + /* --- 16 byte alignment boundary--- */ + + /** + * (protected) Pointer fields available for use by the text provider. + * Not used by UText common code. + * @stable ICU 3.6 + */ + const void *p; + /** + * (protected) Pointer fields available for use by the text provider. + * Not used by UText common code. + * @stable ICU 3.6 + */ + const void *q; + /** + * (protected) Pointer fields available for use by the text provider. + * Not used by UText common code. + * @stable ICU 3.6 + */ + const void *r; + + /** + * Private field reserved for future use by the UText framework + * itself. This is not to be touched by the text providers. + * @internal ICU 3.4 + */ + void *privP; + + + /* --- 16 byte alignment boundary--- */ + + + /** + * (protected) Integer field reserved for use by the text provider. + * Not used by the UText framework, or by the client (user) of the UText. + * @stable ICU 3.4 + */ + int64_t a; + + /** + * (protected) Integer field reserved for use by the text provider. + * Not used by the UText framework, or by the client (user) of the UText. + * @stable ICU 3.4 + */ + int32_t b; + + /** + * (protected) Integer field reserved for use by the text provider. + * Not used by the UText framework, or by the client (user) of the UText. + * @stable ICU 3.4 + */ + int32_t c; + + /* ---- 16 byte alignment boundary---- */ + + + /** + * Private field reserved for future use by the UText framework + * itself. This is not to be touched by the text providers. + * @internal ICU 3.4 + */ + int64_t privA; + /** + * Private field reserved for future use by the UText framework + * itself. This is not to be touched by the text providers. + * @internal ICU 3.4 + */ + int32_t privB; + /** + * Private field reserved for future use by the UText framework + * itself. This is not to be touched by the text providers. + * @internal ICU 3.4 + */ + int32_t privC; +}; + + +/** + * Common function for use by Text Provider implementations to allocate and/or initialize + * a new UText struct. To be called in the implementation of utext_open() functions. + * If the supplied UText parameter is null, a new UText struct will be allocated on the heap. + * If the supplied UText is already open, the provider's close function will be called + * so that the struct can be reused by the open that is in progress. + * + * @param ut pointer to a UText struct to be re-used, or null if a new UText + * should be allocated. + * @param extraSpace The amount of additional space to be allocated as part + * of this UText, for use by types of providers that require + * additional storage. + * @param status Errors are returned here. + * @return pointer to the UText, allocated if necessary, with extra space set up if requested. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_setup(UText *ut, int32_t extraSpace, UErrorCode *status); + +// do not use #ifndef U_HIDE_INTERNAL_API around the following! +/** + * @internal + * Value used to help identify correctly initialized UText structs. + * Note: must be publicly visible so that UTEXT_INITIALIZER can access it. + */ +enum { + UTEXT_MAGIC = 0x345ad82c +}; + +/** + * initializer to be used with local (stack) instances of a UText + * struct. UText structs must be initialized before passing + * them to one of the utext_open functions. + * + * @stable ICU 3.6 + */ +#define UTEXT_INITIALIZER { \ + UTEXT_MAGIC, /* magic */ \ + 0, /* flags */ \ + 0, /* providerProps */ \ + sizeof(UText), /* sizeOfStruct */ \ + 0, /* chunkNativeLimit */ \ + 0, /* extraSize */ \ + 0, /* nativeIndexingLimit */ \ + 0, /* chunkNativeStart */ \ + 0, /* chunkOffset */ \ + 0, /* chunkLength */ \ + NULL, /* chunkContents */ \ + NULL, /* pFuncs */ \ + NULL, /* pExtra */ \ + NULL, /* context */ \ + NULL, NULL, NULL, /* p, q, r */ \ + NULL, /* privP */ \ + 0, 0, 0, /* a, b, c */ \ + 0, 0, 0 /* privA,B,C, */ \ + } + + +U_CDECL_END + + +#if U_SHOW_CPLUSPLUS_API + +U_NAMESPACE_BEGIN + +/** + * \class LocalUTextPointer + * "Smart pointer" class, closes a UText via utext_close(). + * For most methods see the LocalPointerBase base class. + * + * @see LocalPointerBase + * @see LocalPointer + * @stable ICU 4.4 + */ +U_DEFINE_LOCAL_OPEN_POINTER(LocalUTextPointer, UText, utext_close); + +U_NAMESPACE_END + +#endif + + +#endif diff --git a/thirdparty/icu4c/common/unicode/utf.h b/thirdparty/icu4c/common/unicode/utf.h new file mode 100644 index 0000000000..c9d5f5785c --- /dev/null +++ b/thirdparty/icu4c/common/unicode/utf.h @@ -0,0 +1,225 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 1999-2011, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utf.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999sep09 +* created by: Markus W. Scherer +*/ + +/** + * \file + * \brief C API: Code point macros + * + * This file defines macros for checking whether a code point is + * a surrogate or a non-character etc. + * + * If U_NO_DEFAULT_INCLUDE_UTF_HEADERS is 0 then utf.h is included by utypes.h + * and itself includes utf8.h and utf16.h after some + * common definitions. + * If U_NO_DEFAULT_INCLUDE_UTF_HEADERS is 1 then each of these headers must be + * included explicitly if their definitions are used. + * + * utf8.h and utf16.h define macros for efficiently getting code points + * in and out of UTF-8/16 strings. + * utf16.h macros have "U16_" prefixes. + * utf8.h defines similar macros with "U8_" prefixes for UTF-8 string handling. + * + * ICU mostly processes 16-bit Unicode strings. + * Most of the time, such strings are well-formed UTF-16. + * Single, unpaired surrogates must be handled as well, and are treated in ICU + * like regular code points where possible. + * (Pairs of surrogate code points are indistinguishable from supplementary + * code points encoded as pairs of supplementary code units.) + * + * In fact, almost all Unicode code points in normal text (>99%) + * are on the BMP (<=U+ffff) and even <=U+d7ff. + * ICU functions handle supplementary code points (U+10000..U+10ffff) + * but are optimized for the much more frequently occurring BMP code points. + * + * umachine.h defines UChar to be an unsigned 16-bit integer. + * Since ICU 59, ICU uses char16_t in C++, UChar only in C, + * and defines UChar=char16_t by default. See the UChar API docs for details. + * + * UChar32 is defined to be a signed 32-bit integer (int32_t), large enough for a 21-bit + * Unicode code point (Unicode scalar value, 0..0x10ffff) and U_SENTINEL (-1). + * Before ICU 2.4, the definition of UChar32 was similarly platform-dependent as + * the definition of UChar. For details see the documentation for UChar32 itself. + * + * utf.h defines a small number of C macros for single Unicode code points. + * These are simple checks for surrogates and non-characters. + * For actual Unicode character properties see uchar.h. + * + * By default, string operations must be done with error checking in case + * a string is not well-formed UTF-16 or UTF-8. + * + * The U16_ macros detect if a surrogate code unit is unpaired + * (lead unit without trail unit or vice versa) and just return the unit itself + * as the code point. + * + * The U8_ macros detect illegal byte sequences and return a negative value. + * Starting with ICU 60, the observable length of a single illegal byte sequence + * skipped by one of these macros follows the Unicode 6+ recommendation + * which is consistent with the W3C Encoding Standard. + * + * There are ..._OR_FFFD versions of both U16_ and U8_ macros + * that return U+FFFD for illegal code unit sequences. + * + * The regular "safe" macros require that the initial, passed-in string index + * is within bounds. They only check the index when they read more than one + * code unit. This is usually done with code similar to the following loop: + * <pre>while(i<length) { + * U16_NEXT(s, i, length, c); + * // use c + * }</pre> + * + * When it is safe to assume that text is well-formed UTF-16 + * (does not contain single, unpaired surrogates), then one can use + * U16_..._UNSAFE macros. + * These do not check for proper code unit sequences or truncated text and may + * yield wrong results or even cause a crash if they are used with "malformed" + * text. + * In practice, U16_..._UNSAFE macros will produce slightly less code but + * should not be faster because the processing is only different when a + * surrogate code unit is detected, which will be rare. + * + * Similarly for UTF-8, there are "safe" macros without a suffix, + * and U8_..._UNSAFE versions. + * The performance differences are much larger here because UTF-8 provides so + * many opportunities for malformed sequences. + * The unsafe UTF-8 macros are entirely implemented inside the macro definitions + * and are fast, while the safe UTF-8 macros call functions for some complicated cases. + * + * Unlike with UTF-16, malformed sequences cannot be expressed with distinct + * code point values (0..U+10ffff). They are indicated with negative values instead. + * + * For more information see the ICU User Guide Strings chapter + * (https://unicode-org.github.io/icu/userguide/strings). + * + * <em>Usage:</em> + * ICU coding guidelines for if() statements should be followed when using these macros. + * Compound statements (curly braces {}) must be used for if-else-while... + * bodies and all macro statements should be terminated with semicolon. + * + * @stable ICU 2.4 + */ + +#ifndef __UTF_H__ +#define __UTF_H__ + +#include "unicode/umachine.h" +/* include the utfXX.h after the following definitions */ + +/* single-code point definitions -------------------------------------------- */ + +/** + * Is this code point a Unicode noncharacter? + * @param c 32-bit code point + * @return true or false + * @stable ICU 2.4 + */ +#define U_IS_UNICODE_NONCHAR(c) \ + ((c)>=0xfdd0 && \ + ((c)<=0xfdef || ((c)&0xfffe)==0xfffe) && (c)<=0x10ffff) + +/** + * Is c a Unicode code point value (0..U+10ffff) + * that can be assigned a character? + * + * Code points that are not characters include: + * - single surrogate code points (U+d800..U+dfff, 2048 code points) + * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points) + * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points) + * - the highest Unicode code point value is U+10ffff + * + * This means that all code points below U+d800 are character code points, + * and that boundary is tested first for performance. + * + * @param c 32-bit code point + * @return true or false + * @stable ICU 2.4 + */ +#define U_IS_UNICODE_CHAR(c) \ + ((uint32_t)(c)<0xd800 || \ + (0xdfff<(c) && (c)<=0x10ffff && !U_IS_UNICODE_NONCHAR(c))) + +/** + * Is this code point a BMP code point (U+0000..U+ffff)? + * @param c 32-bit code point + * @return true or false + * @stable ICU 2.8 + */ +#define U_IS_BMP(c) ((uint32_t)(c)<=0xffff) + +/** + * Is this code point a supplementary code point (U+10000..U+10ffff)? + * @param c 32-bit code point + * @return true or false + * @stable ICU 2.8 + */ +#define U_IS_SUPPLEMENTARY(c) ((uint32_t)((c)-0x10000)<=0xfffff) + +/** + * Is this code point a lead surrogate (U+d800..U+dbff)? + * @param c 32-bit code point + * @return true or false + * @stable ICU 2.4 + */ +#define U_IS_LEAD(c) (((c)&0xfffffc00)==0xd800) + +/** + * Is this code point a trail surrogate (U+dc00..U+dfff)? + * @param c 32-bit code point + * @return true or false + * @stable ICU 2.4 + */ +#define U_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00) + +/** + * Is this code point a surrogate (U+d800..U+dfff)? + * @param c 32-bit code point + * @return true or false + * @stable ICU 2.4 + */ +#define U_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800) + +/** + * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), + * is it a lead surrogate? + * @param c 32-bit code point + * @return true or false + * @stable ICU 2.4 + */ +#define U_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) + +/** + * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), + * is it a trail surrogate? + * @param c 32-bit code point + * @return true or false + * @stable ICU 4.2 + */ +#define U_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0) + +/* include the utfXX.h ------------------------------------------------------ */ + +#if !U_NO_DEFAULT_INCLUDE_UTF_HEADERS + +#include "unicode/utf8.h" +#include "unicode/utf16.h" + +/* utf_old.h contains deprecated, pre-ICU 2.4 definitions */ +#include "unicode/utf_old.h" + +#endif /* !U_NO_DEFAULT_INCLUDE_UTF_HEADERS */ + +#endif /* __UTF_H__ */ diff --git a/thirdparty/icu4c/common/unicode/utf16.h b/thirdparty/icu4c/common/unicode/utf16.h new file mode 100644 index 0000000000..3902c60e95 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/utf16.h @@ -0,0 +1,734 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 1999-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utf16.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999sep09 +* created by: Markus W. Scherer +*/ + +/** + * \file + * \brief C API: 16-bit Unicode handling macros + * + * This file defines macros to deal with 16-bit Unicode (UTF-16) code units and strings. + * + * For more information see utf.h and the ICU User Guide Strings chapter + * (https://unicode-org.github.io/icu/userguide/strings). + * + * <em>Usage:</em> + * ICU coding guidelines for if() statements should be followed when using these macros. + * Compound statements (curly braces {}) must be used for if-else-while... + * bodies and all macro statements should be terminated with semicolon. + */ + +#ifndef __UTF16_H__ +#define __UTF16_H__ + +#include <stdbool.h> +#include "unicode/umachine.h" +#ifndef __UTF_H__ +# include "unicode/utf.h" +#endif + +/* single-code point definitions -------------------------------------------- */ + +/** + * Does this code unit alone encode a code point (BMP, not a surrogate)? + * @param c 16-bit code unit + * @return true or false + * @stable ICU 2.4 + */ +#define U16_IS_SINGLE(c) !U_IS_SURROGATE(c) + +/** + * Is this code unit a lead surrogate (U+d800..U+dbff)? + * @param c 16-bit code unit + * @return true or false + * @stable ICU 2.4 + */ +#define U16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800) + +/** + * Is this code unit a trail surrogate (U+dc00..U+dfff)? + * @param c 16-bit code unit + * @return true or false + * @stable ICU 2.4 + */ +#define U16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00) + +/** + * Is this code unit a surrogate (U+d800..U+dfff)? + * @param c 16-bit code unit + * @return true or false + * @stable ICU 2.4 + */ +#define U16_IS_SURROGATE(c) U_IS_SURROGATE(c) + +/** + * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)), + * is it a lead surrogate? + * @param c 16-bit code unit + * @return true or false + * @stable ICU 2.4 + */ +#define U16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) + +/** + * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)), + * is it a trail surrogate? + * @param c 16-bit code unit + * @return true or false + * @stable ICU 4.2 + */ +#define U16_IS_SURROGATE_TRAIL(c) (((c)&0x400)!=0) + +/** + * Helper constant for U16_GET_SUPPLEMENTARY. + * @internal + */ +#define U16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000) + +/** + * Get a supplementary code point value (U+10000..U+10ffff) + * from its lead and trail surrogates. + * The result is undefined if the input values are not + * lead and trail surrogates. + * + * @param lead lead surrogate (U+d800..U+dbff) + * @param trail trail surrogate (U+dc00..U+dfff) + * @return supplementary code point (U+10000..U+10ffff) + * @stable ICU 2.4 + */ +#define U16_GET_SUPPLEMENTARY(lead, trail) \ + (((UChar32)(lead)<<10UL)+(UChar32)(trail)-U16_SURROGATE_OFFSET) + + +/** + * Get the lead surrogate (0xd800..0xdbff) for a + * supplementary code point (0x10000..0x10ffff). + * @param supplementary 32-bit code point (U+10000..U+10ffff) + * @return lead surrogate (U+d800..U+dbff) for supplementary + * @stable ICU 2.4 + */ +#define U16_LEAD(supplementary) (UChar)(((supplementary)>>10)+0xd7c0) + +/** + * Get the trail surrogate (0xdc00..0xdfff) for a + * supplementary code point (0x10000..0x10ffff). + * @param supplementary 32-bit code point (U+10000..U+10ffff) + * @return trail surrogate (U+dc00..U+dfff) for supplementary + * @stable ICU 2.4 + */ +#define U16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00) + +/** + * How many 16-bit code units are used to encode this Unicode code point? (1 or 2) + * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff). + * @param c 32-bit code point + * @return 1 or 2 + * @stable ICU 2.4 + */ +#define U16_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2) + +/** + * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff). + * @return 2 + * @stable ICU 2.4 + */ +#define U16_MAX_LENGTH 2 + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * The offset may point to either the lead or trail surrogate unit + * for a supplementary code point, in which case the macro will read + * the adjacent matching surrogate as well. + * The result is undefined if the offset points to a single, unpaired surrogate. + * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT. + * + * @param s const UChar * string + * @param i string offset + * @param c output UChar32 variable + * @see U16_GET + * @stable ICU 2.4 + */ +#define U16_GET_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(U16_IS_SURROGATE(c)) { \ + if(U16_IS_SURROGATE_LEAD(c)) { \ + (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)+1]); \ + } else { \ + (c)=U16_GET_SUPPLEMENTARY((s)[(i)-1], (c)); \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The offset may point to either the lead or trail surrogate unit + * for a supplementary code point, in which case the macro will read + * the adjacent matching surrogate as well. + * + * The length can be negative for a NUL-terminated string. + * + * If the offset points to a single, unpaired surrogate, then + * c is set to that unpaired surrogate. + * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<=i<length + * @param length string length + * @param c output UChar32 variable + * @see U16_GET_UNSAFE + * @stable ICU 2.4 + */ +#define U16_GET(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(U16_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(U16_IS_SURROGATE_LEAD(c)) { \ + if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \ + (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ + } \ + } else { \ + if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ + (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The offset may point to either the lead or trail surrogate unit + * for a supplementary code point, in which case the macro will read + * the adjacent matching surrogate as well. + * + * The length can be negative for a NUL-terminated string. + * + * If the offset points to a single, unpaired surrogate, then + * c is set to U+FFFD. + * Iteration through a string is more efficient with U16_NEXT_UNSAFE or U16_NEXT_OR_FFFD. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<=i<length + * @param length string length + * @param c output UChar32 variable + * @see U16_GET_UNSAFE + * @stable ICU 60 + */ +#define U16_GET_OR_FFFD(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(U16_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(U16_IS_SURROGATE_LEAD(c)) { \ + if((i)+1!=(length) && U16_IS_TRAIL(__c2=(s)[(i)+1])) { \ + (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ + } else { \ + (c)=0xfffd; \ + } \ + } else { \ + if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ + (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ + } else { \ + (c)=0xfffd; \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/* definitions with forward iteration --------------------------------------- */ + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Unsafe" macro, assumes well-formed UTF-16. + * + * The offset may point to the lead surrogate unit + * for a supplementary code point, in which case the macro will read + * the following trail surrogate as well. + * If the offset points to a trail surrogate, then that itself + * will be returned as the code point. + * The result is undefined if the offset points to a single, unpaired lead surrogate. + * + * @param s const UChar * string + * @param i string offset + * @param c output UChar32 variable + * @see U16_NEXT + * @stable ICU 2.4 + */ +#define U16_NEXT_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(U16_IS_LEAD(c)) { \ + (c)=U16_GET_SUPPLEMENTARY((c), (s)[(i)++]); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * The offset may point to the lead surrogate unit + * for a supplementary code point, in which case the macro will read + * the following trail surrogate as well. + * If the offset points to a trail surrogate or + * to a single, unpaired lead surrogate, then c is set to that unpaired surrogate. + * + * @param s const UChar * string + * @param i string offset, must be i<length + * @param length string length + * @param c output UChar32 variable + * @see U16_NEXT_UNSAFE + * @stable ICU 2.4 + */ +#define U16_NEXT(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(U16_IS_LEAD(c)) { \ + uint16_t __c2; \ + if((i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \ + ++(i); \ + (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * The offset may point to the lead surrogate unit + * for a supplementary code point, in which case the macro will read + * the following trail surrogate as well. + * If the offset points to a trail surrogate or + * to a single, unpaired lead surrogate, then c is set to U+FFFD. + * + * @param s const UChar * string + * @param i string offset, must be i<length + * @param length string length + * @param c output UChar32 variable + * @see U16_NEXT_UNSAFE + * @stable ICU 60 + */ +#define U16_NEXT_OR_FFFD(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(U16_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(U16_IS_SURROGATE_LEAD(c) && (i)!=(length) && U16_IS_TRAIL(__c2=(s)[(i)])) { \ + ++(i); \ + (c)=U16_GET_SUPPLEMENTARY((c), __c2); \ + } else { \ + (c)=0xfffd; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Append a code point to a string, overwriting 1 or 2 code units. + * The offset points to the current end of the string contents + * and is advanced (post-increment). + * "Unsafe" macro, assumes a valid code point and sufficient space in the string. + * Otherwise, the result is undefined. + * + * @param s const UChar * string buffer + * @param i string offset + * @param c code point to append + * @see U16_APPEND + * @stable ICU 2.4 + */ +#define U16_APPEND_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0xffff) { \ + (s)[(i)++]=(uint16_t)(c); \ + } else { \ + (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ + (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Append a code point to a string, overwriting 1 or 2 code units. + * The offset points to the current end of the string contents + * and is advanced (post-increment). + * "Safe" macro, checks for a valid code point. + * If a surrogate pair is written, checks for sufficient space in the string. + * If the code point is not valid or a trail surrogate does not fit, + * then isError is set to true. + * + * @param s const UChar * string buffer + * @param i string offset, must be i<capacity + * @param capacity size of the string buffer + * @param c code point to append + * @param isError output UBool set to true if an error occurs, otherwise not modified + * @see U16_APPEND_UNSAFE + * @stable ICU 2.4 + */ +#define U16_APPEND(s, i, capacity, c, isError) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0xffff) { \ + (s)[(i)++]=(uint16_t)(c); \ + } else if((uint32_t)(c)<=0x10ffff && (i)+1<(capacity)) { \ + (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ + (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ + } else /* c>0x10ffff or not enough space */ { \ + (isError)=true; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the next. + * (Post-incrementing iteration.) + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @see U16_FWD_1 + * @stable ICU 2.4 + */ +#define U16_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_LEAD((s)[(i)++])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the next. + * (Post-incrementing iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const UChar * string + * @param i string offset, must be i<length + * @param length string length + * @see U16_FWD_1_UNSAFE + * @stable ICU 2.4 + */ +#define U16_FWD_1(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_LEAD((s)[(i)++]) && (i)!=(length) && U16_IS_TRAIL((s)[i])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the n-th next one, + * i.e., move forward by n code points. + * (Post-incrementing iteration.) + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @param n number of code points to skip + * @see U16_FWD_N + * @stable ICU 2.4 + */ +#define U16_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + U16_FWD_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the n-th next one, + * i.e., move forward by n code points. + * (Post-incrementing iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const UChar * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @param n number of code points to skip + * @see U16_FWD_N_UNSAFE + * @stable ICU 2.4 + */ +#define U16_FWD_N(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \ + U16_FWD_1(s, i, length); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary + * at the start of a code point. + * If the offset points to the trail surrogate of a surrogate pair, + * then the offset is decremented. + * Otherwise, it is not modified. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @see U16_SET_CP_START + * @stable ICU 2.4 + */ +#define U16_SET_CP_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_TRAIL((s)[i])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary + * at the start of a code point. + * If the offset points to the trail surrogate of a surrogate pair, + * then the offset is decremented. + * Otherwise, it is not modified. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<=i + * @see U16_SET_CP_START_UNSAFE + * @stable ICU 2.4 + */ +#define U16_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_TRAIL((s)[i]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/* definitions with backward iteration -------------------------------------- */ + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Unsafe" macro, assumes well-formed UTF-16. + * + * The input offset may be the same as the string length. + * If the offset is behind a trail surrogate unit + * for a supplementary code point, then the macro will read + * the preceding lead surrogate as well. + * If the offset is behind a lead surrogate, then that itself + * will be returned as the code point. + * The result is undefined if the offset is behind a single, unpaired trail surrogate. + * + * @param s const UChar * string + * @param i string offset + * @param c output UChar32 variable + * @see U16_PREV + * @stable ICU 2.4 + */ +#define U16_PREV_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(U16_IS_TRAIL(c)) { \ + (c)=U16_GET_SUPPLEMENTARY((s)[--(i)], (c)); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The input offset may be the same as the string length. + * If the offset is behind a trail surrogate unit + * for a supplementary code point, then the macro will read + * the preceding lead surrogate as well. + * If the offset is behind a lead surrogate or behind a single, unpaired + * trail surrogate, then c is set to that unpaired surrogate. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<i + * @param c output UChar32 variable + * @see U16_PREV_UNSAFE + * @stable ICU 2.4 + */ +#define U16_PREV(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(U16_IS_TRAIL(c)) { \ + uint16_t __c2; \ + if((i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ + --(i); \ + (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The input offset may be the same as the string length. + * If the offset is behind a trail surrogate unit + * for a supplementary code point, then the macro will read + * the preceding lead surrogate as well. + * If the offset is behind a lead surrogate or behind a single, unpaired + * trail surrogate, then c is set to U+FFFD. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<i + * @param c output UChar32 variable + * @see U16_PREV_UNSAFE + * @stable ICU 60 + */ +#define U16_PREV_OR_FFFD(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(U16_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(U16_IS_SURROGATE_TRAIL(c) && (i)>(start) && U16_IS_LEAD(__c2=(s)[(i)-1])) { \ + --(i); \ + (c)=U16_GET_SUPPLEMENTARY(__c2, (c)); \ + } else { \ + (c)=0xfffd; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @see U16_BACK_1 + * @stable ICU 2.4 + */ +#define U16_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_TRAIL((s)[--(i)])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * @param s const UChar * string + * @param start starting string offset (usually 0) + * @param i string offset, must be start<i + * @see U16_BACK_1_UNSAFE + * @stable ICU 2.4 + */ +#define U16_BACK_1(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_TRAIL((s)[--(i)]) && (i)>(start) && U16_IS_LEAD((s)[(i)-1])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the n-th one before it, + * i.e., move backward by n code points. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @param n number of code points to skip + * @see U16_BACK_N + * @stable ICU 2.4 + */ +#define U16_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + U16_BACK_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the n-th one before it, + * i.e., move backward by n code points. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * @param s const UChar * string + * @param start start of string + * @param i string offset, must be start<i + * @param n number of code points to skip + * @see U16_BACK_N_UNSAFE + * @stable ICU 2.4 + */ +#define U16_BACK_N(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0 && (i)>(start)) { \ + U16_BACK_1(s, start, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary after a code point. + * If the offset is behind the lead surrogate of a surrogate pair, + * then the offset is incremented. + * Otherwise, it is not modified. + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-16. + * + * @param s const UChar * string + * @param i string offset + * @see U16_SET_CP_LIMIT + * @stable ICU 2.4 + */ +#define U16_SET_CP_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U16_IS_LEAD((s)[(i)-1])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary after a code point. + * If the offset is behind the lead surrogate of a surrogate pair, + * then the offset is incremented. + * Otherwise, it is not modified. + * The input offset may be the same as the string length. + * "Safe" macro, handles unpaired surrogates and checks for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const UChar * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, start<=i<=length + * @param length int32_t string length + * @see U16_SET_CP_LIMIT_UNSAFE + * @stable ICU 2.4 + */ +#define U16_SET_CP_LIMIT(s, start, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + if((start)<(i) && ((i)<(length) || (length)<0) && U16_IS_LEAD((s)[(i)-1]) && U16_IS_TRAIL((s)[i])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +#endif diff --git a/thirdparty/icu4c/common/unicode/utf32.h b/thirdparty/icu4c/common/unicode/utf32.h new file mode 100644 index 0000000000..8822c4dd09 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/utf32.h @@ -0,0 +1,25 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 1999-2001, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utf32.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999sep20 +* created by: Markus W. Scherer +*/ +/** + * \file + * \brief C API: UTF-32 macros + * + * This file is obsolete and its contents moved to utf_old.h. + * See utf_old.h and Jitterbug 2150 and its discussion on the ICU mailing list + * in September 2002. + */ diff --git a/thirdparty/icu4c/common/unicode/utf8.h b/thirdparty/icu4c/common/unicode/utf8.h new file mode 100644 index 0000000000..5a07435fcf --- /dev/null +++ b/thirdparty/icu4c/common/unicode/utf8.h @@ -0,0 +1,882 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 1999-2015, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utf8.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 1999sep13 +* created by: Markus W. Scherer +*/ + +/** + * \file + * \brief C API: 8-bit Unicode handling macros + * + * This file defines macros to deal with 8-bit Unicode (UTF-8) code units (bytes) and strings. + * + * For more information see utf.h and the ICU User Guide Strings chapter + * (https://unicode-org.github.io/icu/userguide/strings). + * + * <em>Usage:</em> + * ICU coding guidelines for if() statements should be followed when using these macros. + * Compound statements (curly braces {}) must be used for if-else-while... + * bodies and all macro statements should be terminated with semicolon. + */ + +#ifndef __UTF8_H__ +#define __UTF8_H__ + +#include <stdbool.h> +#include "unicode/umachine.h" +#ifndef __UTF_H__ +# include "unicode/utf.h" +#endif + +/* internal definitions ----------------------------------------------------- */ + +/** + * Counts the trail bytes for a UTF-8 lead byte. + * Returns 0 for 0..0xc1 as well as for 0xf5..0xff. + * leadByte might be evaluated multiple times. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this file and thus must remain stable. + * + * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. + * @internal + */ +#define U8_COUNT_TRAIL_BYTES(leadByte) \ + (U8_IS_LEAD(leadByte) ? \ + ((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)+1 : 0) + +/** + * Counts the trail bytes for a UTF-8 lead byte of a valid UTF-8 sequence. + * Returns 0 for 0..0xc1. Undefined for 0xf5..0xff. + * leadByte might be evaluated multiple times. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this file and thus must remain stable. + * + * @param leadByte The first byte of a UTF-8 sequence. Must be 0..0xff. + * @internal + */ +#define U8_COUNT_TRAIL_BYTES_UNSAFE(leadByte) \ + (((uint8_t)(leadByte)>=0xc2)+((uint8_t)(leadByte)>=0xe0)+((uint8_t)(leadByte)>=0xf0)) + +/** + * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this file and thus must remain stable. + * @internal + */ +#define U8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1) + +/** + * Internal bit vector for 3-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD3_AND_T1. + * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence. + * Lead byte E0..EF bits 3..0 are used as byte index, + * first trail byte bits 7..5 are used as bit index into that byte. + * @see U8_IS_VALID_LEAD3_AND_T1 + * @internal + */ +#define U8_LEAD3_T1_BITS "\x20\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x10\x30\x30" + +/** + * Internal 3-byte UTF-8 validity check. + * Non-zero if lead byte E0..EF and first trail byte 00..FF start a valid sequence. + * @internal + */ +#define U8_IS_VALID_LEAD3_AND_T1(lead, t1) (U8_LEAD3_T1_BITS[(lead)&0xf]&(1<<((uint8_t)(t1)>>5))) + +/** + * Internal bit vector for 4-byte UTF-8 validity check, for use in U8_IS_VALID_LEAD4_AND_T1. + * Each bit indicates whether one lead byte + first trail byte pair starts a valid sequence. + * First trail byte bits 7..4 are used as byte index, + * lead byte F0..F4 bits 2..0 are used as bit index into that byte. + * @see U8_IS_VALID_LEAD4_AND_T1 + * @internal + */ +#define U8_LEAD4_T1_BITS "\x00\x00\x00\x00\x00\x00\x00\x00\x1E\x0F\x0F\x0F\x00\x00\x00\x00" + +/** + * Internal 4-byte UTF-8 validity check. + * Non-zero if lead byte F0..F4 and first trail byte 00..FF start a valid sequence. + * @internal + */ +#define U8_IS_VALID_LEAD4_AND_T1(lead, t1) (U8_LEAD4_T1_BITS[(uint8_t)(t1)>>4]&(1<<((lead)&7))) + +/** + * Function for handling "next code point" with error-checking. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this + * file and thus must remain stable, and should not be hidden when other internal + * functions are hidden (otherwise public macros would fail to compile). + * @internal + */ +U_CAPI UChar32 U_EXPORT2 +utf8_nextCharSafeBody(const uint8_t *s, int32_t *pi, int32_t length, UChar32 c, UBool strict); + +/** + * Function for handling "append code point" with error-checking. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this + * file and thus must remain stable, and should not be hidden when other internal + * functions are hidden (otherwise public macros would fail to compile). + * @internal + */ +U_CAPI int32_t U_EXPORT2 +utf8_appendCharSafeBody(uint8_t *s, int32_t i, int32_t length, UChar32 c, UBool *pIsError); + +/** + * Function for handling "previous code point" with error-checking. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this + * file and thus must remain stable, and should not be hidden when other internal + * functions are hidden (otherwise public macros would fail to compile). + * @internal + */ +U_CAPI UChar32 U_EXPORT2 +utf8_prevCharSafeBody(const uint8_t *s, int32_t start, int32_t *pi, UChar32 c, UBool strict); + +/** + * Function for handling "skip backward one code point" with error-checking. + * + * This is internal since it is not meant to be called directly by external clients; + * however it is called by public macros in this + * file and thus must remain stable, and should not be hidden when other internal + * functions are hidden (otherwise public macros would fail to compile). + * @internal + */ +U_CAPI int32_t U_EXPORT2 +utf8_back1SafeBody(const uint8_t *s, int32_t start, int32_t i); + +/* single-code point definitions -------------------------------------------- */ + +/** + * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)? + * @param c 8-bit code unit (byte) + * @return true or false + * @stable ICU 2.4 + */ +#define U8_IS_SINGLE(c) (((c)&0x80)==0) + +/** + * Is this code unit (byte) a UTF-8 lead byte? (0xC2..0xF4) + * @param c 8-bit code unit (byte) + * @return true or false + * @stable ICU 2.4 + */ +#define U8_IS_LEAD(c) ((uint8_t)((c)-0xc2)<=0x32) +// 0x32=0xf4-0xc2 + +/** + * Is this code unit (byte) a UTF-8 trail byte? (0x80..0xBF) + * @param c 8-bit code unit (byte) + * @return true or false + * @stable ICU 2.4 + */ +#define U8_IS_TRAIL(c) ((int8_t)(c)<-0x40) + +/** + * How many code units (bytes) are used for the UTF-8 encoding + * of this Unicode code point? + * @param c 32-bit code point + * @return 1..4, or 0 if c is a surrogate or not a Unicode code point + * @stable ICU 2.4 + */ +#define U8_LENGTH(c) \ + ((uint32_t)(c)<=0x7f ? 1 : \ + ((uint32_t)(c)<=0x7ff ? 2 : \ + ((uint32_t)(c)<=0xd7ff ? 3 : \ + ((uint32_t)(c)<=0xdfff || (uint32_t)(c)>0x10ffff ? 0 : \ + ((uint32_t)(c)<=0xffff ? 3 : 4)\ + ) \ + ) \ + ) \ + ) + +/** + * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff). + * @return 4 + * @stable ICU 2.4 + */ +#define U8_MAX_LENGTH 4 + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * The offset may point to either the lead byte or one of the trail bytes + * for a code point, in which case the macro will read all of the bytes + * for the code point. + * The result is undefined if the offset points to an illegal UTF-8 + * byte sequence. + * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT. + * + * @param s const uint8_t * string + * @param i string offset + * @param c output UChar32 variable + * @see U8_GET + * @stable ICU 2.4 + */ +#define U8_GET_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t _u8_get_unsafe_index=(int32_t)(i); \ + U8_SET_CP_START_UNSAFE(s, _u8_get_unsafe_index); \ + U8_NEXT_UNSAFE(s, _u8_get_unsafe_index, c); \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * The offset may point to either the lead byte or one of the trail bytes + * for a code point, in which case the macro will read all of the bytes + * for the code point. + * + * The length can be negative for a NUL-terminated string. + * + * If the offset points to an illegal UTF-8 byte sequence, then + * c is set to a negative value. + * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset + * @param i int32_t string offset, must be start<=i<length + * @param length int32_t string length + * @param c output UChar32 variable, set to <0 in case of an error + * @see U8_GET_UNSAFE + * @stable ICU 2.4 + */ +#define U8_GET(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t _u8_get_index=(i); \ + U8_SET_CP_START(s, start, _u8_get_index); \ + U8_NEXT(s, _u8_get_index, length, c); \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a random-access offset, + * without changing the offset. + * The offset may point to either the lead byte or one of the trail bytes + * for a code point, in which case the macro will read all of the bytes + * for the code point. + * + * The length can be negative for a NUL-terminated string. + * + * If the offset points to an illegal UTF-8 byte sequence, then + * c is set to U+FFFD. + * Iteration through a string is more efficient with U8_NEXT_UNSAFE or U8_NEXT_OR_FFFD. + * + * This macro does not distinguish between a real U+FFFD in the text + * and U+FFFD returned for an ill-formed sequence. + * Use U8_GET() if that distinction is important. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset + * @param i int32_t string offset, must be start<=i<length + * @param length int32_t string length + * @param c output UChar32 variable, set to U+FFFD in case of an error + * @see U8_GET + * @stable ICU 51 + */ +#define U8_GET_OR_FFFD(s, start, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t _u8_get_index=(i); \ + U8_SET_CP_START(s, start, _u8_get_index); \ + U8_NEXT_OR_FFFD(s, _u8_get_index, length, c); \ +} UPRV_BLOCK_MACRO_END + +/* definitions with forward iteration --------------------------------------- */ + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Unsafe" macro, assumes well-formed UTF-8. + * + * The offset may point to the lead byte of a multi-byte sequence, + * in which case the macro will read the whole sequence. + * The result is undefined if the offset points to a trail byte + * or an illegal UTF-8 sequence. + * + * @param s const uint8_t * string + * @param i string offset + * @param c output UChar32 variable + * @see U8_NEXT + * @stable ICU 2.4 + */ +#define U8_NEXT_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[(i)++]; \ + if(!U8_IS_SINGLE(c)) { \ + if((c)<0xe0) { \ + (c)=(((c)&0x1f)<<6)|((s)[(i)++]&0x3f); \ + } else if((c)<0xf0) { \ + /* no need for (c&0xf) because the upper bits are truncated after <<12 in the cast to (UChar) */ \ + (c)=(UChar)(((c)<<12)|(((s)[i]&0x3f)<<6)|((s)[(i)+1]&0x3f)); \ + (i)+=2; \ + } else { \ + (c)=(((c)&7)<<18)|(((s)[i]&0x3f)<<12)|(((s)[(i)+1]&0x3f)<<6)|((s)[(i)+2]&0x3f); \ + (i)+=3; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * The offset may point to the lead byte of a multi-byte sequence, + * in which case the macro will read the whole sequence. + * If the offset points to a trail byte or an illegal UTF-8 sequence, then + * c is set to a negative value. + * + * @param s const uint8_t * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @param c output UChar32 variable, set to <0 in case of an error + * @see U8_NEXT_UNSAFE + * @stable ICU 2.4 + */ +#define U8_NEXT(s, i, length, c) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, U_SENTINEL) + +/** + * Get a code point from a string at a code point boundary offset, + * and advance the offset to the next code point boundary. + * (Post-incrementing forward iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * The offset may point to the lead byte of a multi-byte sequence, + * in which case the macro will read the whole sequence. + * If the offset points to a trail byte or an illegal UTF-8 sequence, then + * c is set to U+FFFD. + * + * This macro does not distinguish between a real U+FFFD in the text + * and U+FFFD returned for an ill-formed sequence. + * Use U8_NEXT() if that distinction is important. + * + * @param s const uint8_t * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @param c output UChar32 variable, set to U+FFFD in case of an error + * @see U8_NEXT + * @stable ICU 51 + */ +#define U8_NEXT_OR_FFFD(s, i, length, c) U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, 0xfffd) + +/** @internal */ +#define U8_INTERNAL_NEXT_OR_SUB(s, i, length, c, sub) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[(i)++]; \ + if(!U8_IS_SINGLE(c)) { \ + uint8_t __t = 0; \ + if((i)!=(length) && \ + /* fetch/validate/assemble all but last trail byte */ \ + ((c)>=0xe0 ? \ + ((c)<0xf0 ? /* U+0800..U+FFFF except surrogates */ \ + U8_LEAD3_T1_BITS[(c)&=0xf]&(1<<((__t=(s)[i])>>5)) && \ + (__t&=0x3f, 1) \ + : /* U+10000..U+10FFFF */ \ + ((c)-=0xf0)<=4 && \ + U8_LEAD4_T1_BITS[(__t=(s)[i])>>4]&(1<<(c)) && \ + ((c)=((c)<<6)|(__t&0x3f), ++(i)!=(length)) && \ + (__t=(s)[i]-0x80)<=0x3f) && \ + /* valid second-to-last trail byte */ \ + ((c)=((c)<<6)|__t, ++(i)!=(length)) \ + : /* U+0080..U+07FF */ \ + (c)>=0xc2 && ((c)&=0x1f, 1)) && \ + /* last trail byte */ \ + (__t=(s)[i]-0x80)<=0x3f && \ + ((c)=((c)<<6)|__t, ++(i), 1)) { \ + } else { \ + (c)=(sub); /* ill-formed*/ \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Append a code point to a string, overwriting 1 to 4 bytes. + * The offset points to the current end of the string contents + * and is advanced (post-increment). + * "Unsafe" macro, assumes a valid code point and sufficient space in the string. + * Otherwise, the result is undefined. + * + * @param s const uint8_t * string buffer + * @param i string offset + * @param c code point to append + * @see U8_APPEND + * @stable ICU 2.4 + */ +#define U8_APPEND_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + uint32_t __uc=(c); \ + if(__uc<=0x7f) { \ + (s)[(i)++]=(uint8_t)__uc; \ + } else { \ + if(__uc<=0x7ff) { \ + (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \ + } else { \ + if(__uc<=0xffff) { \ + (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \ + } else { \ + (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \ + (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \ + } \ + (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ + } \ + (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Append a code point to a string, overwriting 1 to 4 bytes. + * The offset points to the current end of the string contents + * and is advanced (post-increment). + * "Safe" macro, checks for a valid code point. + * If a non-ASCII code point is written, checks for sufficient space in the string. + * If the code point is not valid or trail bytes do not fit, + * then isError is set to true. + * + * @param s const uint8_t * string buffer + * @param i int32_t string offset, must be i<capacity + * @param capacity int32_t size of the string buffer + * @param c UChar32 code point to append + * @param isError output UBool set to true if an error occurs, otherwise not modified + * @see U8_APPEND_UNSAFE + * @stable ICU 2.4 + */ +#define U8_APPEND(s, i, capacity, c, isError) UPRV_BLOCK_MACRO_BEGIN { \ + uint32_t __uc=(c); \ + if(__uc<=0x7f) { \ + (s)[(i)++]=(uint8_t)__uc; \ + } else if(__uc<=0x7ff && (i)+1<(capacity)) { \ + (s)[(i)++]=(uint8_t)((__uc>>6)|0xc0); \ + (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ + } else if((__uc<=0xd7ff || (0xe000<=__uc && __uc<=0xffff)) && (i)+2<(capacity)) { \ + (s)[(i)++]=(uint8_t)((__uc>>12)|0xe0); \ + (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ + (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ + } else if(0xffff<__uc && __uc<=0x10ffff && (i)+3<(capacity)) { \ + (s)[(i)++]=(uint8_t)((__uc>>18)|0xf0); \ + (s)[(i)++]=(uint8_t)(((__uc>>12)&0x3f)|0x80); \ + (s)[(i)++]=(uint8_t)(((__uc>>6)&0x3f)|0x80); \ + (s)[(i)++]=(uint8_t)((__uc&0x3f)|0x80); \ + } else { \ + (isError)=true; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the next. + * (Post-incrementing iteration.) + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @see U8_FWD_1 + * @stable ICU 2.4 + */ +#define U8_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + (i)+=1+U8_COUNT_TRAIL_BYTES_UNSAFE((s)[i]); \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the next. + * (Post-incrementing iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const uint8_t * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @see U8_FWD_1_UNSAFE + * @stable ICU 2.4 + */ +#define U8_FWD_1(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + uint8_t __b=(s)[(i)++]; \ + if(U8_IS_LEAD(__b) && (i)!=(length)) { \ + uint8_t __t1=(s)[i]; \ + if((0xe0<=__b && __b<0xf0)) { \ + if(U8_IS_VALID_LEAD3_AND_T1(__b, __t1) && \ + ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \ + ++(i); \ + } \ + } else if(__b<0xe0) { \ + if(U8_IS_TRAIL(__t1)) { \ + ++(i); \ + } \ + } else /* c>=0xf0 */ { \ + if(U8_IS_VALID_LEAD4_AND_T1(__b, __t1) && \ + ++(i)!=(length) && U8_IS_TRAIL((s)[i]) && \ + ++(i)!=(length) && U8_IS_TRAIL((s)[i])) { \ + ++(i); \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the n-th next one, + * i.e., move forward by n code points. + * (Post-incrementing iteration.) + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @param n number of code points to skip + * @see U8_FWD_N + * @stable ICU 2.4 + */ +#define U8_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + U8_FWD_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Advance the string offset from one code point boundary to the n-th next one, + * i.e., move forward by n code points. + * (Post-incrementing iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const uint8_t * string + * @param i int32_t string offset, must be i<length + * @param length int32_t string length + * @param n number of code points to skip + * @see U8_FWD_N_UNSAFE + * @stable ICU 2.4 + */ +#define U8_FWD_N(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0 && ((i)<(length) || ((length)<0 && (s)[i]!=0))) { \ + U8_FWD_1(s, i, length); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary + * at the start of a code point. + * If the offset points to a UTF-8 trail byte, + * then the offset is moved backward to the corresponding lead byte. + * Otherwise, it is not modified. + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @see U8_SET_CP_START + * @stable ICU 2.4 + */ +#define U8_SET_CP_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + while(U8_IS_TRAIL((s)[i])) { --(i); } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary + * at the start of a code point. + * If the offset points to a UTF-8 trail byte, + * then the offset is moved backward to the corresponding lead byte. + * Otherwise, it is not modified. + * + * "Safe" macro, checks for illegal sequences and for string boundaries. + * Unlike U8_TRUNCATE_IF_INCOMPLETE(), this macro always reads s[i]. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<=i + * @see U8_SET_CP_START_UNSAFE + * @see U8_TRUNCATE_IF_INCOMPLETE + * @stable ICU 2.4 + */ +#define U8_SET_CP_START(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U8_IS_TRAIL((s)[(i)])) { \ + (i)=utf8_back1SafeBody(s, start, (i)); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * If the string ends with a UTF-8 byte sequence that is valid so far + * but incomplete, then reduce the length of the string to end before + * the lead byte of that incomplete sequence. + * For example, if the string ends with E1 80, the length is reduced by 2. + * + * In all other cases (the string ends with a complete sequence, or it is not + * possible for any further trail byte to extend the trailing sequence) + * the length remains unchanged. + * + * Useful for processing text split across multiple buffers + * (save the incomplete sequence for later) + * and for optimizing iteration + * (check for string length only once per character). + * + * "Safe" macro, checks for illegal sequences and for string boundaries. + * Unlike U8_SET_CP_START(), this macro never reads s[length]. + * + * (In UTF-16, simply check for U16_IS_LEAD(last code unit).) + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param length int32_t string length (usually start<=length) + * @see U8_SET_CP_START + * @stable ICU 61 + */ +#define U8_TRUNCATE_IF_INCOMPLETE(s, start, length) UPRV_BLOCK_MACRO_BEGIN { \ + if((length)>(start)) { \ + uint8_t __b1=s[(length)-1]; \ + if(U8_IS_SINGLE(__b1)) { \ + /* common ASCII character */ \ + } else if(U8_IS_LEAD(__b1)) { \ + --(length); \ + } else if(U8_IS_TRAIL(__b1) && ((length)-2)>=(start)) { \ + uint8_t __b2=s[(length)-2]; \ + if(0xe0<=__b2 && __b2<=0xf4) { \ + if(__b2<0xf0 ? U8_IS_VALID_LEAD3_AND_T1(__b2, __b1) : \ + U8_IS_VALID_LEAD4_AND_T1(__b2, __b1)) { \ + (length)-=2; \ + } \ + } else if(U8_IS_TRAIL(__b2) && ((length)-3)>=(start)) { \ + uint8_t __b3=s[(length)-3]; \ + if(0xf0<=__b3 && __b3<=0xf4 && U8_IS_VALID_LEAD4_AND_T1(__b3, __b2)) { \ + (length)-=3; \ + } \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/* definitions with backward iteration -------------------------------------- */ + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Unsafe" macro, assumes well-formed UTF-8. + * + * The input offset may be the same as the string length. + * If the offset is behind a multi-byte sequence, then the macro will read + * the whole sequence. + * If the offset is behind a lead byte, then that itself + * will be returned as the code point. + * The result is undefined if the offset is behind an illegal UTF-8 sequence. + * + * @param s const uint8_t * string + * @param i string offset + * @param c output UChar32 variable + * @see U8_PREV + * @stable ICU 2.4 + */ +#define U8_PREV_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[--(i)]; \ + if(U8_IS_TRAIL(c)) { \ + uint8_t __b, __count=1, __shift=6; \ +\ + /* c is a trail byte */ \ + (c)&=0x3f; \ + for(;;) { \ + __b=(s)[--(i)]; \ + if(__b>=0xc0) { \ + U8_MASK_LEAD_BYTE(__b, __count); \ + (c)|=(UChar32)__b<<__shift; \ + break; \ + } else { \ + (c)|=(UChar32)(__b&0x3f)<<__shift; \ + ++__count; \ + __shift+=6; \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The input offset may be the same as the string length. + * If the offset is behind a multi-byte sequence, then the macro will read + * the whole sequence. + * If the offset is behind a lead byte, then that itself + * will be returned as the code point. + * If the offset is behind an illegal UTF-8 sequence, then c is set to a negative value. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<i + * @param c output UChar32 variable, set to <0 in case of an error + * @see U8_PREV_UNSAFE + * @stable ICU 2.4 + */ +#define U8_PREV(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[--(i)]; \ + if(!U8_IS_SINGLE(c)) { \ + (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -1); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one + * and get the code point between them. + * (Pre-decrementing backward iteration.) + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The input offset may be the same as the string length. + * If the offset is behind a multi-byte sequence, then the macro will read + * the whole sequence. + * If the offset is behind a lead byte, then that itself + * will be returned as the code point. + * If the offset is behind an illegal UTF-8 sequence, then c is set to U+FFFD. + * + * This macro does not distinguish between a real U+FFFD in the text + * and U+FFFD returned for an ill-formed sequence. + * Use U8_PREV() if that distinction is important. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<i + * @param c output UChar32 variable, set to U+FFFD in case of an error + * @see U8_PREV + * @stable ICU 51 + */ +#define U8_PREV_OR_FFFD(s, start, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(uint8_t)(s)[--(i)]; \ + if(!U8_IS_SINGLE(c)) { \ + (c)=utf8_prevCharSafeBody((const uint8_t *)s, start, &(i), c, -3); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @see U8_BACK_1 + * @stable ICU 2.4 + */ +#define U8_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + while(U8_IS_TRAIL((s)[--(i)])) {} \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the previous one. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<i + * @see U8_BACK_1_UNSAFE + * @stable ICU 2.4 + */ +#define U8_BACK_1(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(U8_IS_TRAIL((s)[--(i)])) { \ + (i)=utf8_back1SafeBody(s, start, (i)); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the n-th one before it, + * i.e., move backward by n code points. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @param n number of code points to skip + * @see U8_BACK_N + * @stable ICU 2.4 + */ +#define U8_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + U8_BACK_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Move the string offset from one code point boundary to the n-th one before it, + * i.e., move backward by n code points. + * (Pre-decrementing backward iteration.) + * The input offset may be the same as the string length. + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * @param s const uint8_t * string + * @param start int32_t index of the start of the string + * @param i int32_t string offset, must be start<i + * @param n number of code points to skip + * @see U8_BACK_N_UNSAFE + * @stable ICU 2.4 + */ +#define U8_BACK_N(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0 && (i)>(start)) { \ + U8_BACK_1(s, start, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary after a code point. + * If the offset is behind a partial multi-byte sequence, + * then the offset is incremented to behind the whole sequence. + * Otherwise, it is not modified. + * The input offset may be the same as the string length. + * "Unsafe" macro, assumes well-formed UTF-8. + * + * @param s const uint8_t * string + * @param i string offset + * @see U8_SET_CP_LIMIT + * @stable ICU 2.4 + */ +#define U8_SET_CP_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + U8_BACK_1_UNSAFE(s, i); \ + U8_FWD_1_UNSAFE(s, i); \ +} UPRV_BLOCK_MACRO_END + +/** + * Adjust a random-access offset to a code point boundary after a code point. + * If the offset is behind a partial multi-byte sequence, + * then the offset is incremented to behind the whole sequence. + * Otherwise, it is not modified. + * The input offset may be the same as the string length. + * "Safe" macro, checks for illegal sequences and for string boundaries. + * + * The length can be negative for a NUL-terminated string. + * + * @param s const uint8_t * string + * @param start int32_t starting string offset (usually 0) + * @param i int32_t string offset, must be start<=i<=length + * @param length int32_t string length + * @see U8_SET_CP_LIMIT_UNSAFE + * @stable ICU 2.4 + */ +#define U8_SET_CP_LIMIT(s, start, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + if((start)<(i) && ((i)<(length) || (length)<0)) { \ + U8_BACK_1(s, start, i); \ + U8_FWD_1(s, i, length); \ + } \ +} UPRV_BLOCK_MACRO_END + +#endif diff --git a/thirdparty/icu4c/common/unicode/utf_old.h b/thirdparty/icu4c/common/unicode/utf_old.h new file mode 100644 index 0000000000..160f5ad0a9 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/utf_old.h @@ -0,0 +1,1201 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2002-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utf_old.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2002sep21 +* created by: Markus W. Scherer +*/ + +/** + * \file + * \brief C API: Deprecated macros for Unicode string handling + * + * The macros in utf_old.h are all deprecated and their use discouraged. + * Some of the design principles behind the set of UTF macros + * have changed or proved impractical. + * Almost all of the old "UTF macros" are at least renamed. + * If you are looking for a new equivalent to an old macro, please see the + * comment at the old one. + * + * Brief summary of reasons for deprecation: + * - Switch on UTF_SIZE (selection of UTF-8/16/32 default string processing) + * was impractical. + * - Switch on UTF_SAFE etc. (selection of unsafe/safe/strict default string processing) + * was of little use and impractical. + * - Whole classes of macros became obsolete outside of the UTF_SIZE/UTF_SAFE + * selection framework: UTF32_ macros (all trivial) + * and UTF_ default and intermediate macros (all aliases). + * - The selection framework also caused many macro aliases. + * - Change in Unicode standard: "irregular" sequences (3.0) became illegal (3.2). + * - Change of language in Unicode standard: + * Growing distinction between internal x-bit Unicode strings and external UTF-x + * forms, with the former more lenient. + * Suggests renaming of UTF16_ macros to U16_. + * - The prefix "UTF_" without a width number confused some users. + * - "Safe" append macros needed the addition of an error indicator output. + * - "Safe" UTF-8 macros used legitimate (if rarely used) code point values + * to indicate error conditions. + * - The use of the "_CHAR" infix for code point operations confused some users. + * + * More details: + * + * Until ICU 2.2, utf.h theoretically allowed to choose among UTF-8/16/32 + * for string processing, and among unsafe/safe/strict default macros for that. + * + * It proved nearly impossible to write non-trivial, high-performance code + * that is UTF-generic. + * Unsafe default macros would be dangerous for default string processing, + * and the main reason for the "strict" versions disappeared: + * Between Unicode 3.0 and 3.2 all "irregular" UTF-8 sequences became illegal. + * The only other conditions that "strict" checked for were non-characters, + * which are valid during processing. Only during text input/output should they + * be checked, and at that time other well-formedness checks may be + * necessary or useful as well. + * This can still be done by using U16_NEXT and U_IS_UNICODE_NONCHAR + * or U_IS_UNICODE_CHAR. + * + * The old UTF8_..._SAFE macros also used some normal Unicode code points + * to indicate malformed sequences. + * The new UTF8_ macros without suffix use negative values instead. + * + * The entire contents of utf32.h was moved here without replacement + * because all those macros were trivial and + * were meaningful only in the framework of choosing the UTF size. + * + * See Jitterbug 2150 and its discussion on the ICU mailing list + * in September 2002. + * + * <hr> + * + * <em>Obsolete part</em> of pre-ICU 2.4 utf.h file documentation: + * + * <p>The original concept for these files was for ICU to allow + * in principle to set which UTF (UTF-8/16/32) is used internally + * by defining UTF_SIZE to either 8, 16, or 32. utf.h would then define the UChar type + * accordingly. UTF-16 was the default.</p> + * + * <p>This concept has been abandoned. + * A lot of the ICU source code assumes UChar strings are in UTF-16. + * This is especially true for low-level code like + * conversion, normalization, and collation. + * The utf.h header enforces the default of UTF-16. + * The UTF-8 and UTF-32 macros remain for now for completeness and backward compatibility.</p> + * + * <p>Accordingly, utf.h defines UChar to be an unsigned 16-bit integer. If this matches wchar_t, then + * UChar is defined to be exactly wchar_t, otherwise uint16_t.</p> + * + * <p>UChar32 is defined to be a signed 32-bit integer (int32_t), large enough for a 21-bit + * Unicode code point (Unicode scalar value, 0..0x10ffff). + * Before ICU 2.4, the definition of UChar32 was similarly platform-dependent as + * the definition of UChar. For details see the documentation for UChar32 itself.</p> + * + * <p>utf.h also defines a number of C macros for handling single Unicode code points and + * for using UTF Unicode strings. It includes utf8.h, utf16.h, and utf32.h for the actual + * implementations of those macros and then aliases one set of them (for UTF-16) for general use. + * The UTF-specific macros have the UTF size in the macro name prefixes (UTF16_...), while + * the general alias macros always begin with UTF_...</p> + * + * <p>Many string operations can be done with or without error checking. + * Where such a distinction is useful, there are two versions of the macros, "unsafe" and "safe" + * ones with ..._UNSAFE and ..._SAFE suffixes. The unsafe macros are fast but may cause + * program failures if the strings are not well-formed. The safe macros have an additional, boolean + * parameter "strict". If strict is false, then only illegal sequences are detected. + * Otherwise, irregular sequences and non-characters are detected as well (like single surrogates). + * Safe macros return special error code points for illegal/irregular sequences: + * Typically, U+ffff, or values that would result in a code unit sequence of the same length + * as the erroneous input sequence.<br> + * Note that _UNSAFE macros have fewer parameters: They do not have the strictness parameter, and + * they do not have start/length parameters for boundary checking.</p> + * + * <p>Here, the macros are aliased in two steps: + * In the first step, the UTF-specific macros with UTF16_ prefix and _UNSAFE and _SAFE suffixes are + * aliased according to the UTF_SIZE to macros with UTF_ prefix and the same suffixes and signatures. + * Then, in a second step, the default, general alias macros are set to use either the unsafe or + * the safe/not strict (default) or the safe/strict macro; + * these general macros do not have a strictness parameter.</p> + * + * <p>It is possible to change the default choice for the general alias macros to be unsafe, safe/not strict or safe/strict. + * The default is safe/not strict. It is not recommended to select the unsafe macros as the basis for + * Unicode string handling in ICU! To select this, define UTF_SAFE, UTF_STRICT, or UTF_UNSAFE.</p> + * + * <p>For general use, one should use the default, general macros with UTF_ prefix and no _SAFE/_UNSAFE suffix. + * Only in some cases it may be necessary to control the choice of macro directly and use a less generic alias. + * For example, if it can be assumed that a string is well-formed and the index will stay within the bounds, + * then the _UNSAFE version may be used. + * If a UTF-8 string is to be processed, then the macros with UTF8_ prefixes need to be used.</p> + * + * <hr> + * + * Deprecated ICU 2.4. Use the macros in utf.h, utf16.h, utf8.h instead. + */ + +#ifndef __UTF_OLD_H__ +#define __UTF_OLD_H__ + +#include "unicode/utf.h" +#include "unicode/utf8.h" +#include "unicode/utf16.h" + +/** + * \def U_HIDE_OBSOLETE_UTF_OLD_H + * + * Hides the obsolete definitions in unicode/utf_old.h. + * Recommended to be set to 1 at compile time to make sure + * the long-deprecated macros are no longer used. + * + * For reasons for the deprecation see the utf_old.h file comments. + * + * @internal + */ +#ifndef U_HIDE_OBSOLETE_UTF_OLD_H +# define U_HIDE_OBSOLETE_UTF_OLD_H 0 +#endif + +#if !defined(U_HIDE_DEPRECATED_API) && !U_HIDE_OBSOLETE_UTF_OLD_H + +/* Formerly utf.h, part 1 --------------------------------------------------- */ + +#ifdef U_USE_UTF_DEPRECATES +/** + * Unicode string and array offset and index type. + * ICU always counts Unicode code units (UChars) for + * string offsets, indexes, and lengths, not Unicode code points. + * + * @obsolete ICU 2.6. Use int32_t directly instead since this API will be removed in that release. + */ +typedef int32_t UTextOffset; +#endif + +/** Number of bits in a Unicode string code unit - ICU uses 16-bit Unicode. @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF_SIZE 16 + +/** + * The default choice for general Unicode string macros is to use the ..._SAFE macro implementations + * with strict=false. + * + * @deprecated ICU 2.4. Obsolete, see utf_old.h. + */ +#define UTF_SAFE +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#undef UTF_UNSAFE +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#undef UTF_STRICT + +/** + * UTF8_ERROR_VALUE_1 and UTF8_ERROR_VALUE_2 are special error values for UTF-8, + * which need 1 or 2 bytes in UTF-8: + * \code + * U+0015 = NAK = Negative Acknowledge, C0 control character + * U+009f = highest C1 control character + * \endcode + * + * These are used by UTF8_..._SAFE macros so that they can return an error value + * that needs the same number of code units (bytes) as were seen by + * a macro. They should be tested with UTF_IS_ERROR() or UTF_IS_VALID(). + * + * @deprecated ICU 2.4. Obsolete, see utf_old.h. + */ +#define UTF8_ERROR_VALUE_1 0x15 + +/** + * See documentation on UTF8_ERROR_VALUE_1 for details. + * + * @deprecated ICU 2.4. Obsolete, see utf_old.h. + */ +#define UTF8_ERROR_VALUE_2 0x9f + +/** + * Error value for all UTFs. This code point value will be set by macros with error + * checking if an error is detected. + * + * @deprecated ICU 2.4. Obsolete, see utf_old.h. + */ +#define UTF_ERROR_VALUE 0xffff + +/** + * Is a given 32-bit code an error value + * as returned by one of the macros for any UTF? + * + * @deprecated ICU 2.4. Obsolete, see utf_old.h. + */ +#define UTF_IS_ERROR(c) \ + (((c)&0xfffe)==0xfffe || (c)==UTF8_ERROR_VALUE_1 || (c)==UTF8_ERROR_VALUE_2) + +/** + * This is a combined macro: Is c a valid Unicode value _and_ not an error code? + * + * @deprecated ICU 2.4. Obsolete, see utf_old.h. + */ +#define UTF_IS_VALID(c) \ + (UTF_IS_UNICODE_CHAR(c) && \ + (c)!=UTF8_ERROR_VALUE_1 && (c)!=UTF8_ERROR_VALUE_2) + +/** + * Is this code unit or code point a surrogate (U+d800..U+dfff)? + * @deprecated ICU 2.4. Renamed to U_IS_SURROGATE and U16_IS_SURROGATE, see utf_old.h. + */ +#define UTF_IS_SURROGATE(uchar) (((uchar)&0xfffff800)==0xd800) + +/** + * Is a given 32-bit code point a Unicode noncharacter? + * + * @deprecated ICU 2.4. Renamed to U_IS_UNICODE_NONCHAR, see utf_old.h. + */ +#define UTF_IS_UNICODE_NONCHAR(c) \ + ((c)>=0xfdd0 && \ + ((uint32_t)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \ + (uint32_t)(c)<=0x10ffff) + +/** + * Is a given 32-bit value a Unicode code point value (0..U+10ffff) + * that can be assigned a character? + * + * Code points that are not characters include: + * - single surrogate code points (U+d800..U+dfff, 2048 code points) + * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points) + * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points) + * - the highest Unicode code point value is U+10ffff + * + * This means that all code points below U+d800 are character code points, + * and that boundary is tested first for performance. + * + * @deprecated ICU 2.4. Renamed to U_IS_UNICODE_CHAR, see utf_old.h. + */ +#define UTF_IS_UNICODE_CHAR(c) \ + ((uint32_t)(c)<0xd800 || \ + ((uint32_t)(c)>0xdfff && \ + (uint32_t)(c)<=0x10ffff && \ + !UTF_IS_UNICODE_NONCHAR(c))) + +/* Formerly utf8.h ---------------------------------------------------------- */ + +/** +* \var utf8_countTrailBytes +* Internal array with numbers of trail bytes for any given byte used in +* lead byte position. +* +* This is internal since it is not meant to be called directly by external clients; +* however it is called by public macros in this file and thus must remain stable, +* and should not be hidden when other internal functions are hidden (otherwise +* public macros would fail to compile). +* @internal +*/ +#ifdef U_UTF8_IMPL +// No forward declaration if compiling utf_impl.cpp, which defines utf8_countTrailBytes. +#elif defined(U_STATIC_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) +U_CFUNC const uint8_t utf8_countTrailBytes[]; +#else +U_CFUNC U_IMPORT const uint8_t utf8_countTrailBytes[]; /* U_IMPORT2? */ /*U_IMPORT*/ +#endif + +/** + * Count the trail bytes for a UTF-8 lead byte. + * @deprecated ICU 2.4. Renamed to U8_COUNT_TRAIL_BYTES, see utf_old.h. + */ +#define UTF8_COUNT_TRAIL_BYTES(leadByte) (utf8_countTrailBytes[(uint8_t)leadByte]) + +/** + * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value. + * @deprecated ICU 2.4. Renamed to U8_MASK_LEAD_BYTE, see utf_old.h. + */ +#define UTF8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1) + +/** Is this this code point a single code unit (byte)? @deprecated ICU 2.4. Renamed to U8_IS_SINGLE, see utf_old.h. */ +#define UTF8_IS_SINGLE(uchar) (((uchar)&0x80)==0) +/** Is this this code unit the lead code unit (byte) of a code point? @deprecated ICU 2.4. Renamed to U8_IS_LEAD, see utf_old.h. */ +#define UTF8_IS_LEAD(uchar) ((uint8_t)((uchar)-0xc0)<0x3e) +/** Is this this code unit a trailing code unit (byte) of a code point? @deprecated ICU 2.4. Renamed to U8_IS_TRAIL, see utf_old.h. */ +#define UTF8_IS_TRAIL(uchar) (((uchar)&0xc0)==0x80) + +/** Does this scalar Unicode value need multiple code units for storage? @deprecated ICU 2.4. Use U8_LENGTH or test ((uint32_t)(c)>0x7f) instead, see utf_old.h. */ +#define UTF8_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0x7f) + +/** + * Given the lead character, how many bytes are taken by this code point. + * ICU does not deal with code points >0x10ffff + * unless necessary for advancing in the byte stream. + * + * These length macros take into account that for values >0x10ffff + * the UTF8_APPEND_CHAR_SAFE macros would write the error code point 0xffff + * with 3 bytes. + * Code point comparisons need to be in uint32_t because UChar32 + * may be a signed type, and negative values must be recognized. + * + * @deprecated ICU 2.4. Use U8_LENGTH instead, see utf.h. + */ +#if 1 +# define UTF8_CHAR_LENGTH(c) \ + ((uint32_t)(c)<=0x7f ? 1 : \ + ((uint32_t)(c)<=0x7ff ? 2 : \ + ((uint32_t)((c)-0x10000)>0xfffff ? 3 : 4) \ + ) \ + ) +#else +# define UTF8_CHAR_LENGTH(c) \ + ((uint32_t)(c)<=0x7f ? 1 : \ + ((uint32_t)(c)<=0x7ff ? 2 : \ + ((uint32_t)(c)<=0xffff ? 3 : \ + ((uint32_t)(c)<=0x10ffff ? 4 : \ + ((uint32_t)(c)<=0x3ffffff ? 5 : \ + ((uint32_t)(c)<=0x7fffffff ? 6 : 3) \ + ) \ + ) \ + ) \ + ) \ + ) +#endif + +/** The maximum number of bytes per code point. @deprecated ICU 2.4. Renamed to U8_MAX_LENGTH, see utf_old.h. */ +#define UTF8_MAX_CHAR_LENGTH 4 + +/** Average number of code units compared to UTF-16. @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF8_ARRAY_SIZE(size) ((5*(size))/2) + +/** @deprecated ICU 2.4. Renamed to U8_GET_UNSAFE, see utf_old.h. */ +#define UTF8_GET_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t _utf8_get_char_unsafe_index=(int32_t)(i); \ + UTF8_SET_CHAR_START_UNSAFE(s, _utf8_get_char_unsafe_index); \ + UTF8_NEXT_CHAR_UNSAFE(s, _utf8_get_char_unsafe_index, c); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Use U8_GET instead, see utf_old.h. */ +#define UTF8_GET_CHAR_SAFE(s, start, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t _utf8_get_char_safe_index=(int32_t)(i); \ + UTF8_SET_CHAR_START_SAFE(s, start, _utf8_get_char_safe_index); \ + UTF8_NEXT_CHAR_SAFE(s, _utf8_get_char_safe_index, length, c, strict); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_NEXT_UNSAFE, see utf_old.h. */ +#define UTF8_NEXT_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if((uint8_t)((c)-0xc0)<0x35) { \ + uint8_t __count=UTF8_COUNT_TRAIL_BYTES(c); \ + UTF8_MASK_LEAD_BYTE(c, __count); \ + switch(__count) { \ + /* each following branch falls through to the next one */ \ + case 3: \ + (c)=((c)<<6)|((s)[(i)++]&0x3f); \ + case 2: \ + (c)=((c)<<6)|((s)[(i)++]&0x3f); \ + case 1: \ + (c)=((c)<<6)|((s)[(i)++]&0x3f); \ + /* no other branches to optimize switch() */ \ + break; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_APPEND_UNSAFE, see utf_old.h. */ +#define UTF8_APPEND_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0x7f) { \ + (s)[(i)++]=(uint8_t)(c); \ + } else { \ + if((uint32_t)(c)<=0x7ff) { \ + (s)[(i)++]=(uint8_t)(((c)>>6)|0xc0); \ + } else { \ + if((uint32_t)(c)<=0xffff) { \ + (s)[(i)++]=(uint8_t)(((c)>>12)|0xe0); \ + } else { \ + (s)[(i)++]=(uint8_t)(((c)>>18)|0xf0); \ + (s)[(i)++]=(uint8_t)((((c)>>12)&0x3f)|0x80); \ + } \ + (s)[(i)++]=(uint8_t)((((c)>>6)&0x3f)|0x80); \ + } \ + (s)[(i)++]=(uint8_t)(((c)&0x3f)|0x80); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_FWD_1_UNSAFE, see utf_old.h. */ +#define UTF8_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + (i)+=1+UTF8_COUNT_TRAIL_BYTES((s)[i]); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_FWD_N_UNSAFE, see utf_old.h. */ +#define UTF8_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + UTF8_FWD_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_SET_CP_START_UNSAFE, see utf_old.h. */ +#define UTF8_SET_CHAR_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + while(UTF8_IS_TRAIL((s)[i])) { --(i); } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Use U8_NEXT instead, see utf_old.h. */ +#define UTF8_NEXT_CHAR_SAFE(s, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if((c)>=0x80) { \ + if(UTF8_IS_LEAD(c)) { \ + (c)=utf8_nextCharSafeBody(s, &(i), (int32_t)(length), c, strict); \ + } else { \ + (c)=UTF8_ERROR_VALUE_1; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Use U8_APPEND instead, see utf_old.h. */ +#define UTF8_APPEND_CHAR_SAFE(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0x7f) { \ + (s)[(i)++]=(uint8_t)(c); \ + } else { \ + (i)=utf8_appendCharSafeBody(s, (int32_t)(i), (int32_t)(length), c, NULL); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_FWD_1, see utf_old.h. */ +#define UTF8_FWD_1_SAFE(s, i, length) U8_FWD_1(s, i, length) + +/** @deprecated ICU 2.4. Renamed to U8_FWD_N, see utf_old.h. */ +#define UTF8_FWD_N_SAFE(s, i, length, n) U8_FWD_N(s, i, length, n) + +/** @deprecated ICU 2.4. Renamed to U8_SET_CP_START, see utf_old.h. */ +#define UTF8_SET_CHAR_START_SAFE(s, start, i) U8_SET_CP_START(s, start, i) + +/** @deprecated ICU 2.4. Renamed to U8_PREV_UNSAFE, see utf_old.h. */ +#define UTF8_PREV_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(UTF8_IS_TRAIL(c)) { \ + uint8_t __b, __count=1, __shift=6; \ +\ + /* c is a trail byte */ \ + (c)&=0x3f; \ + for(;;) { \ + __b=(s)[--(i)]; \ + if(__b>=0xc0) { \ + UTF8_MASK_LEAD_BYTE(__b, __count); \ + (c)|=(UChar32)__b<<__shift; \ + break; \ + } else { \ + (c)|=(UChar32)(__b&0x3f)<<__shift; \ + ++__count; \ + __shift+=6; \ + } \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_BACK_1_UNSAFE, see utf_old.h. */ +#define UTF8_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + while(UTF8_IS_TRAIL((s)[--(i)])) {} \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_BACK_N_UNSAFE, see utf_old.h. */ +#define UTF8_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + UTF8_BACK_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_SET_CP_LIMIT_UNSAFE, see utf_old.h. */ +#define UTF8_SET_CHAR_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + UTF8_BACK_1_UNSAFE(s, i); \ + UTF8_FWD_1_UNSAFE(s, i); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Use U8_PREV instead, see utf_old.h. */ +#define UTF8_PREV_CHAR_SAFE(s, start, i, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if((c)>=0x80) { \ + if((c)<=0xbf) { \ + (c)=utf8_prevCharSafeBody(s, start, &(i), c, strict); \ + } else { \ + (c)=UTF8_ERROR_VALUE_1; \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U8_BACK_1, see utf_old.h. */ +#define UTF8_BACK_1_SAFE(s, start, i) U8_BACK_1(s, start, i) + +/** @deprecated ICU 2.4. Renamed to U8_BACK_N, see utf_old.h. */ +#define UTF8_BACK_N_SAFE(s, start, i, n) U8_BACK_N(s, start, i, n) + +/** @deprecated ICU 2.4. Renamed to U8_SET_CP_LIMIT, see utf_old.h. */ +#define UTF8_SET_CHAR_LIMIT_SAFE(s, start, i, length) U8_SET_CP_LIMIT(s, start, i, length) + +/* Formerly utf16.h --------------------------------------------------------- */ + +/** Is uchar a first/lead surrogate? @deprecated ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h. */ +#define UTF_IS_FIRST_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xd800) + +/** Is uchar a second/trail surrogate? @deprecated ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h. */ +#define UTF_IS_SECOND_SURROGATE(uchar) (((uchar)&0xfffffc00)==0xdc00) + +/** Assuming c is a surrogate, is it a first/lead surrogate? @deprecated ICU 2.4. Renamed to U_IS_SURROGATE_LEAD and U16_IS_SURROGATE_LEAD, see utf_old.h. */ +#define UTF_IS_SURROGATE_FIRST(c) (((c)&0x400)==0) + +/** Helper constant for UTF16_GET_PAIR_VALUE. @deprecated ICU 2.4. Renamed to U16_SURROGATE_OFFSET, see utf_old.h. */ +#define UTF_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000) + +/** Get the UTF-32 value from the surrogate code units. @deprecated ICU 2.4. Renamed to U16_GET_SUPPLEMENTARY, see utf_old.h. */ +#define UTF16_GET_PAIR_VALUE(first, second) \ + (((first)<<10UL)+(second)-UTF_SURROGATE_OFFSET) + +/** @deprecated ICU 2.4. Renamed to U16_LEAD, see utf_old.h. */ +#define UTF_FIRST_SURROGATE(supplementary) (UChar)(((supplementary)>>10)+0xd7c0) + +/** @deprecated ICU 2.4. Renamed to U16_TRAIL, see utf_old.h. */ +#define UTF_SECOND_SURROGATE(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00) + +/** @deprecated ICU 2.4. Renamed to U16_LEAD, see utf_old.h. */ +#define UTF16_LEAD(supplementary) UTF_FIRST_SURROGATE(supplementary) + +/** @deprecated ICU 2.4. Renamed to U16_TRAIL, see utf_old.h. */ +#define UTF16_TRAIL(supplementary) UTF_SECOND_SURROGATE(supplementary) + +/** @deprecated ICU 2.4. Renamed to U16_IS_SINGLE, see utf_old.h. */ +#define UTF16_IS_SINGLE(uchar) !UTF_IS_SURROGATE(uchar) + +/** @deprecated ICU 2.4. Renamed to U16_IS_LEAD, see utf_old.h. */ +#define UTF16_IS_LEAD(uchar) UTF_IS_FIRST_SURROGATE(uchar) + +/** @deprecated ICU 2.4. Renamed to U16_IS_TRAIL, see utf_old.h. */ +#define UTF16_IS_TRAIL(uchar) UTF_IS_SECOND_SURROGATE(uchar) + +/** Does this scalar Unicode value need multiple code units for storage? @deprecated ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead, see utf_old.h. */ +#define UTF16_NEED_MULTIPLE_UCHAR(c) ((uint32_t)(c)>0xffff) + +/** @deprecated ICU 2.4. Renamed to U16_LENGTH, see utf_old.h. */ +#define UTF16_CHAR_LENGTH(c) ((uint32_t)(c)<=0xffff ? 1 : 2) + +/** @deprecated ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h. */ +#define UTF16_MAX_CHAR_LENGTH 2 + +/** Average number of code units compared to UTF-16. @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF16_ARRAY_SIZE(size) (size) + +/** + * Get a single code point from an offset that points to any + * of the code units that belong to that code point. + * Assume 0<=i<length. + * + * This could be used for iteration together with + * UTF16_CHAR_LENGTH() and UTF_IS_ERROR(), + * but the use of UTF16_NEXT_CHAR[_UNSAFE]() and + * UTF16_PREV_CHAR[_UNSAFE]() is more efficient for that. + * @deprecated ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h. + */ +#define UTF16_GET_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(UTF_IS_SURROGATE(c)) { \ + if(UTF_IS_SURROGATE_FIRST(c)) { \ + (c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)+1]); \ + } else { \ + (c)=UTF16_GET_PAIR_VALUE((s)[(i)-1], (c)); \ + } \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Use U16_GET instead, see utf_old.h. */ +#define UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(UTF_IS_SURROGATE(c)) { \ + uint16_t __c2; \ + if(UTF_IS_SURROGATE_FIRST(c)) { \ + if((i)+1<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)+1])) { \ + (c)=UTF16_GET_PAIR_VALUE((c), __c2); \ + /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \ + } else if(strict) {\ + /* unmatched first surrogate */ \ + (c)=UTF_ERROR_VALUE; \ + } \ + } else { \ + if((i)-1>=(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \ + (c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \ + /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \ + } else if(strict) {\ + /* unmatched second surrogate */ \ + (c)=UTF_ERROR_VALUE; \ + } \ + } \ + } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \ + (c)=UTF_ERROR_VALUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_NEXT_UNSAFE, see utf_old.h. */ +#define UTF16_NEXT_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(UTF_IS_FIRST_SURROGATE(c)) { \ + (c)=UTF16_GET_PAIR_VALUE((c), (s)[(i)++]); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_APPEND_UNSAFE, see utf_old.h. */ +#define UTF16_APPEND_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0xffff) { \ + (s)[(i)++]=(uint16_t)(c); \ + } else { \ + (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ + (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_FWD_1_UNSAFE, see utf_old.h. */ +#define UTF16_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(UTF_IS_FIRST_SURROGATE((s)[(i)++])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_FWD_N_UNSAFE, see utf_old.h. */ +#define UTF16_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + UTF16_FWD_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h. */ +#define UTF16_SET_CHAR_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(UTF_IS_SECOND_SURROGATE((s)[i])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Use U16_NEXT instead, see utf_old.h. */ +#define UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(UTF_IS_FIRST_SURROGATE(c)) { \ + uint16_t __c2; \ + if((i)<(length) && UTF_IS_SECOND_SURROGATE(__c2=(s)[(i)])) { \ + ++(i); \ + (c)=UTF16_GET_PAIR_VALUE((c), __c2); \ + /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \ + } else if(strict) {\ + /* unmatched first surrogate */ \ + (c)=UTF_ERROR_VALUE; \ + } \ + } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \ + /* unmatched second surrogate or other non-character */ \ + (c)=UTF_ERROR_VALUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */ +#define UTF16_APPEND_CHAR_SAFE(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0xffff) { \ + (s)[(i)++]=(uint16_t)(c); \ + } else if((uint32_t)(c)<=0x10ffff) { \ + if((i)+1<(length)) { \ + (s)[(i)++]=(uint16_t)(((c)>>10)+0xd7c0); \ + (s)[(i)++]=(uint16_t)(((c)&0x3ff)|0xdc00); \ + } else /* not enough space */ { \ + (s)[(i)++]=UTF_ERROR_VALUE; \ + } \ + } else /* c>0x10ffff, write error value */ { \ + (s)[(i)++]=UTF_ERROR_VALUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */ +#define UTF16_FWD_1_SAFE(s, i, length) U16_FWD_1(s, i, length) + +/** @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */ +#define UTF16_FWD_N_SAFE(s, i, length, n) U16_FWD_N(s, i, length, n) + +/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */ +#define UTF16_SET_CHAR_START_SAFE(s, start, i) U16_SET_CP_START(s, start, i) + +/** @deprecated ICU 2.4. Renamed to U16_PREV_UNSAFE, see utf_old.h. */ +#define UTF16_PREV_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(UTF_IS_SECOND_SURROGATE(c)) { \ + (c)=UTF16_GET_PAIR_VALUE((s)[--(i)], (c)); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_BACK_1_UNSAFE, see utf_old.h. */ +#define UTF16_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(UTF_IS_SECOND_SURROGATE((s)[--(i)])) { \ + --(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_BACK_N_UNSAFE, see utf_old.h. */ +#define UTF16_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + int32_t __N=(n); \ + while(__N>0) { \ + UTF16_BACK_1_UNSAFE(s, i); \ + --__N; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h. */ +#define UTF16_SET_CHAR_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + if(UTF_IS_FIRST_SURROGATE((s)[(i)-1])) { \ + ++(i); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Use U16_PREV instead, see utf_old.h. */ +#define UTF16_PREV_CHAR_SAFE(s, start, i, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(UTF_IS_SECOND_SURROGATE(c)) { \ + uint16_t __c2; \ + if((i)>(start) && UTF_IS_FIRST_SURROGATE(__c2=(s)[(i)-1])) { \ + --(i); \ + (c)=UTF16_GET_PAIR_VALUE(__c2, (c)); \ + /* strict: ((c)&0xfffe)==0xfffe is caught by UTF_IS_ERROR() and UTF_IS_UNICODE_CHAR() */ \ + } else if(strict) {\ + /* unmatched second surrogate */ \ + (c)=UTF_ERROR_VALUE; \ + } \ + } else if((strict) && !UTF_IS_UNICODE_CHAR(c)) { \ + /* unmatched first surrogate or other non-character */ \ + (c)=UTF_ERROR_VALUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */ +#define UTF16_BACK_1_SAFE(s, start, i) U16_BACK_1(s, start, i) + +/** @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */ +#define UTF16_BACK_N_SAFE(s, start, i, n) U16_BACK_N(s, start, i, n) + +/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */ +#define UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length) + +/* Formerly utf32.h --------------------------------------------------------- */ + +/* +* Old documentation: +* +* This file defines macros to deal with UTF-32 code units and code points. +* Signatures and semantics are the same as for the similarly named macros +* in utf16.h. +* utf32.h is included by utf.h after unicode/umachine.h</p> +* and some common definitions. +* <p><b>Usage:</b> ICU coding guidelines for if() statements should be followed when using these macros. +* Compound statements (curly braces {}) must be used for if-else-while... +* bodies and all macro statements should be terminated with semicolon.</p> +*/ + +/* internal definitions ----------------------------------------------------- */ + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_IS_SAFE(c, strict) \ + (!(strict) ? \ + (uint32_t)(c)<=0x10ffff : \ + UTF_IS_UNICODE_CHAR(c)) + +/* + * For the semantics of all of these macros, see utf16.h. + * The UTF-32 versions are trivial because any code point is + * encoded using exactly one code unit. + */ + +/* single-code point definitions -------------------------------------------- */ + +/* classes of code unit values */ + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_IS_SINGLE(uchar) 1 +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_IS_LEAD(uchar) 0 +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_IS_TRAIL(uchar) 0 + +/* number of code units per code point */ + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_NEED_MULTIPLE_UCHAR(c) 0 +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_CHAR_LENGTH(c) 1 +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_MAX_CHAR_LENGTH 1 + +/* average number of code units compared to UTF-16 */ + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_ARRAY_SIZE(size) (size) + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_GET_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_GET_CHAR_SAFE(s, start, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[i]; \ + if(!UTF32_IS_SAFE(c, strict)) { \ + (c)=UTF_ERROR_VALUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/* definitions with forward iteration --------------------------------------- */ + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_NEXT_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_APPEND_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (s)[(i)++]=(c); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_FWD_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + ++(i); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_FWD_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + (i)+=(n); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_SET_CHAR_START_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_NEXT_CHAR_SAFE(s, i, length, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[(i)++]; \ + if(!UTF32_IS_SAFE(c, strict)) { \ + (c)=UTF_ERROR_VALUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_APPEND_CHAR_SAFE(s, i, length, c) UPRV_BLOCK_MACRO_BEGIN { \ + if((uint32_t)(c)<=0x10ffff) { \ + (s)[(i)++]=(c); \ + } else /* c>0x10ffff, write 0xfffd */ { \ + (s)[(i)++]=0xfffd; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_FWD_1_SAFE(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ + ++(i); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_FWD_N_SAFE(s, i, length, n) UPRV_BLOCK_MACRO_BEGIN { \ + if(((i)+=(n))>(length)) { \ + (i)=(length); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_SET_CHAR_START_SAFE(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ +} UPRV_BLOCK_MACRO_END + +/* definitions with backward iteration -------------------------------------- */ + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_PREV_CHAR_UNSAFE(s, i, c) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_BACK_1_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ + --(i); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_BACK_N_UNSAFE(s, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + (i)-=(n); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_SET_CHAR_LIMIT_UNSAFE(s, i) UPRV_BLOCK_MACRO_BEGIN { \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_PREV_CHAR_SAFE(s, start, i, c, strict) UPRV_BLOCK_MACRO_BEGIN { \ + (c)=(s)[--(i)]; \ + if(!UTF32_IS_SAFE(c, strict)) { \ + (c)=UTF_ERROR_VALUE; \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_BACK_1_SAFE(s, start, i) UPRV_BLOCK_MACRO_BEGIN { \ + --(i); \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_BACK_N_SAFE(s, start, i, n) UPRV_BLOCK_MACRO_BEGIN { \ + (i)-=(n); \ + if((i)<(start)) { \ + (i)=(start); \ + } \ +} UPRV_BLOCK_MACRO_END + +/** @deprecated ICU 2.4. Obsolete, see utf_old.h. */ +#define UTF32_SET_CHAR_LIMIT_SAFE(s, i, length) UPRV_BLOCK_MACRO_BEGIN { \ +} UPRV_BLOCK_MACRO_END + +/* Formerly utf.h, part 2 --------------------------------------------------- */ + +/** + * Estimate the number of code units for a string based on the number of UTF-16 code units. + * + * @deprecated ICU 2.4. Obsolete, see utf_old.h. + */ +#define UTF_ARRAY_SIZE(size) UTF16_ARRAY_SIZE(size) + +/** @deprecated ICU 2.4. Renamed to U16_GET_UNSAFE, see utf_old.h. */ +#define UTF_GET_CHAR_UNSAFE(s, i, c) UTF16_GET_CHAR_UNSAFE(s, i, c) + +/** @deprecated ICU 2.4. Use U16_GET instead, see utf_old.h. */ +#define UTF_GET_CHAR_SAFE(s, start, i, length, c, strict) UTF16_GET_CHAR_SAFE(s, start, i, length, c, strict) + + +/** @deprecated ICU 2.4. Renamed to U16_NEXT_UNSAFE, see utf_old.h. */ +#define UTF_NEXT_CHAR_UNSAFE(s, i, c) UTF16_NEXT_CHAR_UNSAFE(s, i, c) + +/** @deprecated ICU 2.4. Use U16_NEXT instead, see utf_old.h. */ +#define UTF_NEXT_CHAR_SAFE(s, i, length, c, strict) UTF16_NEXT_CHAR_SAFE(s, i, length, c, strict) + + +/** @deprecated ICU 2.4. Renamed to U16_APPEND_UNSAFE, see utf_old.h. */ +#define UTF_APPEND_CHAR_UNSAFE(s, i, c) UTF16_APPEND_CHAR_UNSAFE(s, i, c) + +/** @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. */ +#define UTF_APPEND_CHAR_SAFE(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c) + + +/** @deprecated ICU 2.4. Renamed to U16_FWD_1_UNSAFE, see utf_old.h. */ +#define UTF_FWD_1_UNSAFE(s, i) UTF16_FWD_1_UNSAFE(s, i) + +/** @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. */ +#define UTF_FWD_1_SAFE(s, i, length) UTF16_FWD_1_SAFE(s, i, length) + + +/** @deprecated ICU 2.4. Renamed to U16_FWD_N_UNSAFE, see utf_old.h. */ +#define UTF_FWD_N_UNSAFE(s, i, n) UTF16_FWD_N_UNSAFE(s, i, n) + +/** @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. */ +#define UTF_FWD_N_SAFE(s, i, length, n) UTF16_FWD_N_SAFE(s, i, length, n) + + +/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START_UNSAFE, see utf_old.h. */ +#define UTF_SET_CHAR_START_UNSAFE(s, i) UTF16_SET_CHAR_START_UNSAFE(s, i) + +/** @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. */ +#define UTF_SET_CHAR_START_SAFE(s, start, i) UTF16_SET_CHAR_START_SAFE(s, start, i) + + +/** @deprecated ICU 2.4. Renamed to U16_PREV_UNSAFE, see utf_old.h. */ +#define UTF_PREV_CHAR_UNSAFE(s, i, c) UTF16_PREV_CHAR_UNSAFE(s, i, c) + +/** @deprecated ICU 2.4. Use U16_PREV instead, see utf_old.h. */ +#define UTF_PREV_CHAR_SAFE(s, start, i, c, strict) UTF16_PREV_CHAR_SAFE(s, start, i, c, strict) + + +/** @deprecated ICU 2.4. Renamed to U16_BACK_1_UNSAFE, see utf_old.h. */ +#define UTF_BACK_1_UNSAFE(s, i) UTF16_BACK_1_UNSAFE(s, i) + +/** @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. */ +#define UTF_BACK_1_SAFE(s, start, i) UTF16_BACK_1_SAFE(s, start, i) + + +/** @deprecated ICU 2.4. Renamed to U16_BACK_N_UNSAFE, see utf_old.h. */ +#define UTF_BACK_N_UNSAFE(s, i, n) UTF16_BACK_N_UNSAFE(s, i, n) + +/** @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. */ +#define UTF_BACK_N_SAFE(s, start, i, n) UTF16_BACK_N_SAFE(s, start, i, n) + + +/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT_UNSAFE, see utf_old.h. */ +#define UTF_SET_CHAR_LIMIT_UNSAFE(s, i) UTF16_SET_CHAR_LIMIT_UNSAFE(s, i) + +/** @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. */ +#define UTF_SET_CHAR_LIMIT_SAFE(s, start, i, length) UTF16_SET_CHAR_LIMIT_SAFE(s, start, i, length) + +/* Define default macros (UTF-16 "safe") ------------------------------------ */ + +/** + * Does this code unit alone encode a code point (BMP, not a surrogate)? + * Same as UTF16_IS_SINGLE. + * @deprecated ICU 2.4. Renamed to U_IS_SINGLE and U16_IS_SINGLE, see utf_old.h. + */ +#define UTF_IS_SINGLE(uchar) U16_IS_SINGLE(uchar) + +/** + * Is this code unit the first one of several (a lead surrogate)? + * Same as UTF16_IS_LEAD. + * @deprecated ICU 2.4. Renamed to U_IS_LEAD and U16_IS_LEAD, see utf_old.h. + */ +#define UTF_IS_LEAD(uchar) U16_IS_LEAD(uchar) + +/** + * Is this code unit one of several but not the first one (a trail surrogate)? + * Same as UTF16_IS_TRAIL. + * @deprecated ICU 2.4. Renamed to U_IS_TRAIL and U16_IS_TRAIL, see utf_old.h. + */ +#define UTF_IS_TRAIL(uchar) U16_IS_TRAIL(uchar) + +/** + * Does this code point require multiple code units (is it a supplementary code point)? + * Same as UTF16_NEED_MULTIPLE_UCHAR. + * @deprecated ICU 2.4. Use U16_LENGTH or test ((uint32_t)(c)>0xffff) instead. + */ +#define UTF_NEED_MULTIPLE_UCHAR(c) UTF16_NEED_MULTIPLE_UCHAR(c) + +/** + * How many code units are used to encode this code point (1 or 2)? + * Same as UTF16_CHAR_LENGTH. + * @deprecated ICU 2.4. Renamed to U16_LENGTH, see utf_old.h. + */ +#define UTF_CHAR_LENGTH(c) U16_LENGTH(c) + +/** + * How many code units are used at most for any Unicode code point (2)? + * Same as UTF16_MAX_CHAR_LENGTH. + * @deprecated ICU 2.4. Renamed to U16_MAX_LENGTH, see utf_old.h. + */ +#define UTF_MAX_CHAR_LENGTH U16_MAX_LENGTH + +/** + * Set c to the code point that contains the code unit i. + * i could point to the lead or the trail surrogate for the code point. + * i is not modified. + * Same as UTF16_GET_CHAR. + * \pre 0<=i<length + * + * @deprecated ICU 2.4. Renamed to U16_GET, see utf_old.h. + */ +#define UTF_GET_CHAR(s, start, i, length, c) U16_GET(s, start, i, length, c) + +/** + * Set c to the code point that starts at code unit i + * and advance i to beyond the code units of this code point (post-increment). + * i must point to the first code unit of a code point. + * Otherwise c is set to the trail unit (surrogate) itself. + * Same as UTF16_NEXT_CHAR. + * \pre 0<=i<length + * \post 0<i<=length + * + * @deprecated ICU 2.4. Renamed to U16_NEXT, see utf_old.h. + */ +#define UTF_NEXT_CHAR(s, i, length, c) U16_NEXT(s, i, length, c) + +/** + * Append the code units of code point c to the string at index i + * and advance i to beyond the new code units (post-increment). + * The code units beginning at index i will be overwritten. + * Same as UTF16_APPEND_CHAR. + * \pre 0<=c<=0x10ffff + * \pre 0<=i<length + * \post 0<i<=length + * + * @deprecated ICU 2.4. Use U16_APPEND instead, see utf_old.h. + */ +#define UTF_APPEND_CHAR(s, i, length, c) UTF16_APPEND_CHAR_SAFE(s, i, length, c) + +/** + * Advance i to beyond the code units of the code point that begins at i. + * I.e., advance i by one code point. + * Same as UTF16_FWD_1. + * \pre 0<=i<length + * \post 0<i<=length + * + * @deprecated ICU 2.4. Renamed to U16_FWD_1, see utf_old.h. + */ +#define UTF_FWD_1(s, i, length) U16_FWD_1(s, i, length) + +/** + * Advance i to beyond the code units of the n code points where the first one begins at i. + * I.e., advance i by n code points. + * Same as UT16_FWD_N. + * \pre 0<=i<length + * \post 0<i<=length + * + * @deprecated ICU 2.4. Renamed to U16_FWD_N, see utf_old.h. + */ +#define UTF_FWD_N(s, i, length, n) U16_FWD_N(s, i, length, n) + +/** + * Take the random-access index i and adjust it so that it points to the beginning + * of a code point. + * The input index points to any code unit of a code point and is moved to point to + * the first code unit of the same code point. i is never incremented. + * In other words, if i points to a trail surrogate that is preceded by a matching + * lead surrogate, then i is decremented. Otherwise it is not modified. + * This can be used to start an iteration with UTF_NEXT_CHAR() from a random index. + * Same as UTF16_SET_CHAR_START. + * \pre start<=i<length + * \post start<=i<length + * + * @deprecated ICU 2.4. Renamed to U16_SET_CP_START, see utf_old.h. + */ +#define UTF_SET_CHAR_START(s, start, i) U16_SET_CP_START(s, start, i) + +/** + * Set c to the code point that has code units before i + * and move i backward (towards the beginning of the string) + * to the first code unit of this code point (pre-increment). + * i must point to the first code unit after the last unit of a code point (i==length is allowed). + * Same as UTF16_PREV_CHAR. + * \pre start<i<=length + * \post start<=i<length + * + * @deprecated ICU 2.4. Renamed to U16_PREV, see utf_old.h. + */ +#define UTF_PREV_CHAR(s, start, i, c) U16_PREV(s, start, i, c) + +/** + * Move i backward (towards the beginning of the string) + * to the first code unit of the code point that has code units before i. + * I.e., move i backward by one code point. + * i must point to the first code unit after the last unit of a code point (i==length is allowed). + * Same as UTF16_BACK_1. + * \pre start<i<=length + * \post start<=i<length + * + * @deprecated ICU 2.4. Renamed to U16_BACK_1, see utf_old.h. + */ +#define UTF_BACK_1(s, start, i) U16_BACK_1(s, start, i) + +/** + * Move i backward (towards the beginning of the string) + * to the first code unit of the n code points that have code units before i. + * I.e., move i backward by n code points. + * i must point to the first code unit after the last unit of a code point (i==length is allowed). + * Same as UTF16_BACK_N. + * \pre start<i<=length + * \post start<=i<length + * + * @deprecated ICU 2.4. Renamed to U16_BACK_N, see utf_old.h. + */ +#define UTF_BACK_N(s, start, i, n) U16_BACK_N(s, start, i, n) + +/** + * Take the random-access index i and adjust it so that it points beyond + * a code point. The input index points beyond any code unit + * of a code point and is moved to point beyond the last code unit of the same + * code point. i is never decremented. + * In other words, if i points to a trail surrogate that is preceded by a matching + * lead surrogate, then i is incremented. Otherwise it is not modified. + * This can be used to start an iteration with UTF_PREV_CHAR() from a random index. + * Same as UTF16_SET_CHAR_LIMIT. + * \pre start<i<=length + * \post start<i<=length + * + * @deprecated ICU 2.4. Renamed to U16_SET_CP_LIMIT, see utf_old.h. + */ +#define UTF_SET_CHAR_LIMIT(s, start, i, length) U16_SET_CP_LIMIT(s, start, i, length) + +#endif // !U_HIDE_DEPRECATED_API && !U_HIDE_OBSOLETE_UTF_OLD_H + +#endif diff --git a/thirdparty/icu4c/common/unicode/utrace.h b/thirdparty/icu4c/common/unicode/utrace.h new file mode 100644 index 0000000000..28c313c582 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/utrace.h @@ -0,0 +1,509 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2003-2013, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utrace.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2003aug06 +* created by: Markus W. Scherer +* +* Definitions for ICU tracing/logging. +* +*/ + +#ifndef __UTRACE_H__ +#define __UTRACE_H__ + +#include <stdarg.h> +#include "unicode/utypes.h" + +/** + * \file + * \brief C API: Definitions for ICU tracing/logging. + * + * This provides API for debugging the internals of ICU without the use of + * a traditional debugger. + * + * By default, tracing is disabled in ICU. If you need to debug ICU with + * tracing, please compile ICU with the --enable-tracing configure option. + */ + +U_CDECL_BEGIN + +/** + * Trace severity levels. Higher levels increase the verbosity of the trace output. + * @see utrace_setLevel + * @stable ICU 2.8 + */ +typedef enum UTraceLevel { + /** Disable all tracing @stable ICU 2.8*/ + UTRACE_OFF=-1, + /** Trace error conditions only @stable ICU 2.8*/ + UTRACE_ERROR=0, + /** Trace errors and warnings @stable ICU 2.8*/ + UTRACE_WARNING=3, + /** Trace opens and closes of ICU services @stable ICU 2.8*/ + UTRACE_OPEN_CLOSE=5, + /** Trace an intermediate number of ICU operations @stable ICU 2.8*/ + UTRACE_INFO=7, + /** Trace the maximum number of ICU operations @stable ICU 2.8*/ + UTRACE_VERBOSE=9 +} UTraceLevel; + +/** + * These are the ICU functions that will be traced when tracing is enabled. + * @stable ICU 2.8 + */ +typedef enum UTraceFunctionNumber { + UTRACE_FUNCTION_START=0, + UTRACE_U_INIT=UTRACE_FUNCTION_START, + UTRACE_U_CLEANUP, + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal collation trace location. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UTRACE_FUNCTION_LIMIT, +#endif // U_HIDE_DEPRECATED_API + + UTRACE_CONVERSION_START=0x1000, + UTRACE_UCNV_OPEN=UTRACE_CONVERSION_START, + UTRACE_UCNV_OPEN_PACKAGE, + UTRACE_UCNV_OPEN_ALGORITHMIC, + UTRACE_UCNV_CLONE, + UTRACE_UCNV_CLOSE, + UTRACE_UCNV_FLUSH_CACHE, + UTRACE_UCNV_LOAD, + UTRACE_UCNV_UNLOAD, + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal collation trace location. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UTRACE_CONVERSION_LIMIT, +#endif // U_HIDE_DEPRECATED_API + + UTRACE_COLLATION_START=0x2000, + UTRACE_UCOL_OPEN=UTRACE_COLLATION_START, + UTRACE_UCOL_CLOSE, + UTRACE_UCOL_STRCOLL, + UTRACE_UCOL_GET_SORTKEY, + UTRACE_UCOL_GETLOCALE, + UTRACE_UCOL_NEXTSORTKEYPART, + UTRACE_UCOL_STRCOLLITER, + UTRACE_UCOL_OPEN_FROM_SHORT_STRING, + UTRACE_UCOL_STRCOLLUTF8, /**< @stable ICU 50 */ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal collation trace location. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + UTRACE_COLLATION_LIMIT, +#endif // U_HIDE_DEPRECATED_API + + /** + * The lowest resource/data location. + * @stable ICU 65 + */ + UTRACE_UDATA_START=0x3000, + + /** + * Indicates that a value was read from a resource bundle. Provides three + * C-style strings to UTraceData: type, file name, and resource path. The + * possible types are: + * + * - "string" (a string value was accessed) + * - "binary" (a binary value was accessed) + * - "intvector" (a integer vector value was accessed) + * - "int" (a signed integer value was accessed) + * - "uint" (a unsigned integer value was accessed) + * - "get" (a path was loaded, but the value was not accessed) + * - "getalias" (a path was loaded, and an alias was resolved) + * + * @stable ICU 65 + */ + UTRACE_UDATA_RESOURCE=UTRACE_UDATA_START, + + /** + * Indicates that a resource bundle was opened. + * + * Provides one C-style string to UTraceData: file name. + * @stable ICU 65 + */ + UTRACE_UDATA_BUNDLE, + + /** + * Indicates that a data file was opened, but not *.res files. + * + * Provides one C-style string to UTraceData: file name. + * + * @stable ICU 65 + */ + UTRACE_UDATA_DATA_FILE, + + /** + * Indicates that a *.res file was opened. + * + * This differs from UTRACE_UDATA_BUNDLE because a res file is typically + * opened only once per application runtime, but the bundle corresponding + * to that res file may be opened many times. + * + * Provides one C-style string to UTraceData: file name. + * + * @stable ICU 65 + */ + UTRACE_UDATA_RES_FILE, + +#ifndef U_HIDE_INTERNAL_API + /** + * One more than the highest normal resource/data trace location. + * @internal The numeric value may change over time, see ICU ticket #12420. + */ + UTRACE_RES_DATA_LIMIT, +#endif // U_HIDE_INTERNAL_API + +#ifndef U_HIDE_DRAFT_API + /** + * The lowest break iterator location. + * @draft ICU 67 + */ + UTRACE_UBRK_START=0x4000, + + /** + * Indicates that a character instance of break iterator was created. + * + * @draft ICU 67 + */ + UTRACE_UBRK_CREATE_CHARACTER = UTRACE_UBRK_START, + + /** + * Indicates that a word instance of break iterator was created. + * + * @draft ICU 67 + */ + UTRACE_UBRK_CREATE_WORD, + + /** + * Indicates that a line instance of break iterator was created. + * + * Provides one C-style string to UTraceData: the lb value ("", + * "loose", "strict", or "normal"). + * + * @draft ICU 67 + */ + UTRACE_UBRK_CREATE_LINE, + + /** + * Indicates that a sentence instance of break iterator was created. + * + * @draft ICU 67 + */ + UTRACE_UBRK_CREATE_SENTENCE, + + /** + * Indicates that a title instance of break iterator was created. + * + * @draft ICU 67 + */ + UTRACE_UBRK_CREATE_TITLE, + + /** + * Indicates that an internal dictionary break engine was created. + * + * Provides one C-style string to UTraceData: the script code of what + * the break engine cover ("Hani", "Khmr", "Laoo", "Mymr", or "Thai"). + * + * @draft ICU 67 + */ + UTRACE_UBRK_CREATE_BREAK_ENGINE, + +#endif // U_HIDE_DRAFT_API + +#ifndef U_HIDE_INTERNAL_API + /** + * One more than the highest normal break iterator trace location. + * @internal The numeric value may change over time, see ICU ticket #12420. + */ + UTRACE_UBRK_LIMIT, +#endif // U_HIDE_INTERNAL_API + +} UTraceFunctionNumber; + +/** + * Setter for the trace level. + * @param traceLevel A UTraceLevel value. + * @stable ICU 2.8 + */ +U_CAPI void U_EXPORT2 +utrace_setLevel(int32_t traceLevel); + +/** + * Getter for the trace level. + * @return The UTraceLevel value being used by ICU. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +utrace_getLevel(void); + +/* Trace function pointers types ----------------------------- */ + +/** + * Type signature for the trace function to be called when entering a function. + * @param context value supplied at the time the trace functions are set. + * @param fnNumber Enum value indicating the ICU function being entered. + * @stable ICU 2.8 + */ +typedef void U_CALLCONV +UTraceEntry(const void *context, int32_t fnNumber); + +/** + * Type signature for the trace function to be called when exiting from a function. + * @param context value supplied at the time the trace functions are set. + * @param fnNumber Enum value indicating the ICU function being exited. + * @param fmt A formatting string that describes the number and types + * of arguments included with the variable args. The fmt + * string has the same form as the utrace_vformat format + * string. + * @param args A variable arguments list. Contents are described by + * the fmt parameter. + * @see utrace_vformat + * @stable ICU 2.8 + */ +typedef void U_CALLCONV +UTraceExit(const void *context, int32_t fnNumber, + const char *fmt, va_list args); + +/** + * Type signature for the trace function to be called from within an ICU function + * to display data or messages. + * @param context value supplied at the time the trace functions are set. + * @param fnNumber Enum value indicating the ICU function being exited. + * @param level The current tracing level + * @param fmt A format string describing the tracing data that is supplied + * as variable args + * @param args The data being traced, passed as variable args. + * @stable ICU 2.8 + */ +typedef void U_CALLCONV +UTraceData(const void *context, int32_t fnNumber, int32_t level, + const char *fmt, va_list args); + +/** + * Set ICU Tracing functions. Installs application-provided tracing + * functions into ICU. After doing this, subsequent ICU operations + * will call back to the installed functions, providing a trace + * of the use of ICU. Passing a NULL pointer for a tracing function + * is allowed, and inhibits tracing action at points where that function + * would be called. + * <p> + * Tracing and Threads: Tracing functions are global to a process, and + * will be called in response to ICU operations performed by any + * thread. If tracing of an individual thread is desired, the + * tracing functions must themselves filter by checking that the + * current thread is the desired thread. + * + * @param context an uninterpreted pointer. Whatever is passed in + * here will in turn be passed to each of the tracing + * functions UTraceEntry, UTraceExit and UTraceData. + * ICU does not use or alter this pointer. + * @param e Callback function to be called on entry to a + * a traced ICU function. + * @param x Callback function to be called on exit from a + * traced ICU function. + * @param d Callback function to be called from within a + * traced ICU function, for the purpose of providing + * data to the trace. + * + * @stable ICU 2.8 + */ +U_CAPI void U_EXPORT2 +utrace_setFunctions(const void *context, + UTraceEntry *e, UTraceExit *x, UTraceData *d); + +/** + * Get the currently installed ICU tracing functions. Note that a null function + * pointer will be returned if no trace function has been set. + * + * @param context The currently installed tracing context. + * @param e The currently installed UTraceEntry function. + * @param x The currently installed UTraceExit function. + * @param d The currently installed UTraceData function. + * @stable ICU 2.8 + */ +U_CAPI void U_EXPORT2 +utrace_getFunctions(const void **context, + UTraceEntry **e, UTraceExit **x, UTraceData **d); + + + +/* + * + * ICU trace format string syntax + * + * Format Strings are passed to UTraceData functions, and define the + * number and types of the trace data being passed on each call. + * + * The UTraceData function, which is supplied by the application, + * not by ICU, can either forward the trace data (passed via + * varargs) and the format string back to ICU for formatting into + * a displayable string, or it can interpret the format itself, + * and do as it wishes with the trace data. + * + * + * Goals for the format string + * - basic data output + * - easy to use for trace programmer + * - sufficient provision for data types for trace output readability + * - well-defined types and binary portable APIs + * + * Non-goals + * - printf compatibility + * - fancy formatting + * - argument reordering and other internationalization features + * + * ICU trace format strings contain plain text with argument inserts, + * much like standard printf format strings. + * Each insert begins with a '%', then optionally contains a 'v', + * then exactly one type character. + * Two '%' in a row represent a '%' instead of an insert. + * The trace format strings need not have \n at the end. + * + * + * Types + * ----- + * + * Type characters: + * - c A char character in the default codepage. + * - s A NUL-terminated char * string in the default codepage. + * - S A UChar * string. Requires two params, (ptr, length). Length=-1 for nul term. + * - b A byte (8-bit integer). + * - h A 16-bit integer. Also a 16 bit Unicode code unit. + * - d A 32-bit integer. Also a 20 bit Unicode code point value. + * - l A 64-bit integer. + * - p A data pointer. + * + * Vectors + * ------- + * + * If the 'v' is not specified, then one item of the specified type + * is passed in. + * If the 'v' (for "vector") is specified, then a vector of items of the + * specified type is passed in, via a pointer to the first item + * and an int32_t value for the length of the vector. + * Length==-1 means zero or NUL termination. Works for vectors of all types. + * + * Note: %vS is a vector of (UChar *) strings. The strings must + * be nul terminated as there is no way to provide a + * separate length parameter for each string. The length + * parameter (required for all vectors) is the number of + * strings, not the length of the strings. + * + * Examples + * -------- + * + * These examples show the parameters that will be passed to an application's + * UTraceData() function for various formats. + * + * - the precise formatting is up to the application! + * - the examples use type casts for arguments only to _show_ the types of + * arguments without needing variable declarations in the examples; + * the type casts will not be necessary in actual code + * + * UTraceDataFunc(context, fnNumber, level, + * "There is a character %c in the string %s.", // Format String + * (char)c, (const char *)s); // varargs parameters + * -> There is a character 0x42 'B' in the string "Bravo". + * + * UTraceDataFunc(context, fnNumber, level, + * "Vector of bytes %vb vector of chars %vc", + * (const uint8_t *)bytes, (int32_t)bytesLength, + * (const char *)chars, (int32_t)charsLength); + * -> Vector of bytes + * 42 63 64 3f [4] + * vector of chars + * "Bcd?"[4] + * + * UTraceDataFunc(context, fnNumber, level, + * "An int32_t %d and a whole bunch of them %vd", + * (int32_t)-5, (const int32_t *)ints, (int32_t)intsLength); + * -> An int32_t 0xfffffffb and a whole bunch of them + * fffffffb 00000005 0000010a [3] + * + */ + + + +/** + * Trace output Formatter. An application's UTraceData tracing functions may call + * back to this function to format the trace output in a + * human readable form. Note that a UTraceData function may choose + * to not format the data; it could, for example, save it in + * in the raw form it was received (more compact), leaving + * formatting for a later trace analysis tool. + * @param outBuf pointer to a buffer to receive the formatted output. Output + * will be nul terminated if there is space in the buffer - + * if the length of the requested output < the output buffer size. + * @param capacity Length of the output buffer. + * @param indent Number of spaces to indent the output. Intended to allow + * data displayed from nested functions to be indented for readability. + * @param fmt Format specification for the data to output + * @param args Data to be formatted. + * @return Length of formatted output, including the terminating NUL. + * If buffer capacity is insufficient, the required capacity is returned. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +utrace_vformat(char *outBuf, int32_t capacity, + int32_t indent, const char *fmt, va_list args); + +/** + * Trace output Formatter. An application's UTraceData tracing functions may call + * this function to format any additional trace data, beyond that + * provided by default, in human readable form with the same + * formatting conventions used by utrace_vformat(). + * @param outBuf pointer to a buffer to receive the formatted output. Output + * will be nul terminated if there is space in the buffer - + * if the length of the requested output < the output buffer size. + * @param capacity Length of the output buffer. + * @param indent Number of spaces to indent the output. Intended to allow + * data displayed from nested functions to be indented for readability. + * @param fmt Format specification for the data to output + * @param ... Data to be formatted. + * @return Length of formatted output, including the terminating NUL. + * If buffer capacity is insufficient, the required capacity is returned. + * @stable ICU 2.8 + */ +U_CAPI int32_t U_EXPORT2 +utrace_format(char *outBuf, int32_t capacity, + int32_t indent, const char *fmt, ...); + + + +/* Trace function numbers --------------------------------------------------- */ + +/** + * Get the name of a function from its trace function number. + * + * @param fnNumber The trace number for an ICU function. + * @return The name string for the function. + * + * @see UTraceFunctionNumber + * @stable ICU 2.8 + */ +U_CAPI const char * U_EXPORT2 +utrace_functionName(int32_t fnNumber); + +U_CDECL_END + +#endif diff --git a/thirdparty/icu4c/common/unicode/utypes.h b/thirdparty/icu4c/common/unicode/utypes.h new file mode 100644 index 0000000000..7c4ea7ac28 --- /dev/null +++ b/thirdparty/icu4c/common/unicode/utypes.h @@ -0,0 +1,732 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1996-2016, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* +* FILE NAME : UTYPES.H (formerly ptypes.h) +* +* Date Name Description +* 12/11/96 helena Creation. +* 02/27/97 aliu Added typedefs for UClassID, int8, int16, int32, +* uint8, uint16, and uint32. +* 04/01/97 aliu Added XP_CPLUSPLUS and modified to work under C as +* well as C++. +* Modified to use memcpy() for uprv_arrayCopy() fns. +* 04/14/97 aliu Added TPlatformUtilities. +* 05/07/97 aliu Added import/export specifiers (replacing the old +* broken EXT_CLASS). Added version number for our +* code. Cleaned up header. +* 6/20/97 helena Java class name change. +* 08/11/98 stephen UErrorCode changed from typedef to enum +* 08/12/98 erm Changed T_ANALYTIC_PACKAGE_VERSION to 3 +* 08/14/98 stephen Added uprv_arrayCopy() for int8_t, int16_t, int32_t +* 12/09/98 jfitz Added BUFFER_OVERFLOW_ERROR (bug 1100066) +* 04/20/99 stephen Cleaned up & reworked for autoconf. +* Renamed to utypes.h. +* 05/05/99 stephen Changed to use <inttypes.h> +* 12/07/99 helena Moved copyright notice string from ucnv_bld.h here. +******************************************************************************* +*/ + +#ifndef UTYPES_H +#define UTYPES_H + + +#include "unicode/umachine.h" +#include "unicode/uversion.h" +#include "unicode/uconfig.h" +#include <float.h> + +#if !U_NO_DEFAULT_INCLUDE_UTF_HEADERS +# include "unicode/utf.h" +#endif + +/*! + * \file + * \brief Basic definitions for ICU, for both C and C++ APIs + * + * This file defines basic types, constants, and enumerations directly or + * indirectly by including other header files, especially utf.h for the + * basic character and string definitions and umachine.h for consistent + * integer and other types. + */ + + +/** + * \def U_SHOW_CPLUSPLUS_API + * @internal + */ +#ifdef __cplusplus +# ifndef U_SHOW_CPLUSPLUS_API +# define U_SHOW_CPLUSPLUS_API 1 +# endif +#else +# undef U_SHOW_CPLUSPLUS_API +# define U_SHOW_CPLUSPLUS_API 0 +#endif + +/** @{ API visibility control */ + +/** + * \def U_HIDE_DRAFT_API + * Define this to 1 to request that draft API be "hidden" + * @internal + */ +/** + * \def U_HIDE_INTERNAL_API + * Define this to 1 to request that internal API be "hidden" + * @internal + */ +#if !U_DEFAULT_SHOW_DRAFT && !defined(U_SHOW_DRAFT_API) +#define U_HIDE_DRAFT_API 1 +#endif +#if !U_DEFAULT_SHOW_DRAFT && !defined(U_SHOW_INTERNAL_API) +#define U_HIDE_INTERNAL_API 1 +#endif + +/** @} */ + +/*===========================================================================*/ +/* ICUDATA naming scheme */ +/*===========================================================================*/ + +/** + * \def U_ICUDATA_TYPE_LETTER + * + * This is a platform-dependent string containing one letter: + * - b for big-endian, ASCII-family platforms + * - l for little-endian, ASCII-family platforms + * - e for big-endian, EBCDIC-family platforms + * This letter is part of the common data file name. + * @stable ICU 2.0 + */ + +/** + * \def U_ICUDATA_TYPE_LITLETTER + * The non-string form of U_ICUDATA_TYPE_LETTER + * @stable ICU 2.0 + */ +#if U_CHARSET_FAMILY +# if U_IS_BIG_ENDIAN + /* EBCDIC - should always be BE */ +# define U_ICUDATA_TYPE_LETTER "e" +# define U_ICUDATA_TYPE_LITLETTER e +# else +# error "Don't know what to do with little endian EBCDIC!" +# define U_ICUDATA_TYPE_LETTER "x" +# define U_ICUDATA_TYPE_LITLETTER x +# endif +#else +# if U_IS_BIG_ENDIAN + /* Big-endian ASCII */ +# define U_ICUDATA_TYPE_LETTER "b" +# define U_ICUDATA_TYPE_LITLETTER b +# else + /* Little-endian ASCII */ +# define U_ICUDATA_TYPE_LETTER "l" +# define U_ICUDATA_TYPE_LITLETTER l +# endif +#endif + +/** + * A single string literal containing the icudata stub name. i.e. 'icudt18e' for + * ICU 1.8.x on EBCDIC, etc.. + * @stable ICU 2.0 + */ +#define U_ICUDATA_NAME "icudt" U_ICU_VERSION_SHORT U_ICUDATA_TYPE_LETTER +#ifndef U_HIDE_INTERNAL_API +#define U_USRDATA_NAME "usrdt" U_ICU_VERSION_SHORT U_ICUDATA_TYPE_LETTER /**< @internal */ +#define U_USE_USRDATA 0 /**< @internal */ +#endif /* U_HIDE_INTERNAL_API */ + +/** + * U_ICU_ENTRY_POINT is the name of the DLL entry point to the ICU data library. + * Defined as a literal, not a string. + * Tricky Preprocessor use - ## operator replaces macro parameters with the literal string + * from the corresponding macro invocation, _before_ other macro substitutions. + * Need a nested \#defines to get the actual version numbers rather than + * the literal text U_ICU_VERSION_MAJOR_NUM into the name. + * The net result will be something of the form + * \#define U_ICU_ENTRY_POINT icudt19_dat + * @stable ICU 2.4 + */ +#define U_ICUDATA_ENTRY_POINT U_DEF2_ICUDATA_ENTRY_POINT(U_ICU_VERSION_MAJOR_NUM,U_LIB_SUFFIX_C_NAME) + +#ifndef U_HIDE_INTERNAL_API +/** + * Do not use. Note that it's OK for the 2nd argument to be undefined (literal). + * @internal + */ +#define U_DEF2_ICUDATA_ENTRY_POINT(major,suff) U_DEF_ICUDATA_ENTRY_POINT(major,suff) + +/** + * Do not use. + * @internal + */ +#ifndef U_DEF_ICUDATA_ENTRY_POINT +/* affected by symbol renaming. See platform.h */ +#ifndef U_LIB_SUFFIX_C_NAME +#define U_DEF_ICUDATA_ENTRY_POINT(major, suff) icudt##major##_dat +#else +#define U_DEF_ICUDATA_ENTRY_POINT(major, suff) icudt##suff ## major##_dat +#endif +#endif +#endif /* U_HIDE_INTERNAL_API */ + +/** + * \def NULL + * Define NULL if necessary, to nullptr for C++ and to ((void *)0) for C. + * @stable ICU 2.0 + */ +#ifndef NULL +#ifdef __cplusplus +#define NULL nullptr +#else +#define NULL ((void *)0) +#endif +#endif + +/*===========================================================================*/ +/* Calendar/TimeZone data types */ +/*===========================================================================*/ + +/** + * Date and Time data type. + * This is a primitive data type that holds the date and time + * as the number of milliseconds since 1970-jan-01, 00:00 UTC. + * UTC leap seconds are ignored. + * @stable ICU 2.0 + */ +typedef double UDate; + +/** The number of milliseconds per second @stable ICU 2.0 */ +#define U_MILLIS_PER_SECOND (1000) +/** The number of milliseconds per minute @stable ICU 2.0 */ +#define U_MILLIS_PER_MINUTE (60000) +/** The number of milliseconds per hour @stable ICU 2.0 */ +#define U_MILLIS_PER_HOUR (3600000) +/** The number of milliseconds per day @stable ICU 2.0 */ +#define U_MILLIS_PER_DAY (86400000) + +/** + * Maximum UDate value + * @stable ICU 4.8 + */ +#define U_DATE_MAX DBL_MAX + +/** + * Minimum UDate value + * @stable ICU 4.8 + */ +#define U_DATE_MIN -U_DATE_MAX + +/*===========================================================================*/ +/* Shared library/DLL import-export API control */ +/*===========================================================================*/ + +/* + * Control of symbol import/export. + * ICU is separated into three libraries. + */ + +/** + * \def U_COMBINED_IMPLEMENTATION + * Set to export library symbols from inside the ICU library + * when all of ICU is in a single library. + * This can be set as a compiler option while building ICU, and it + * needs to be the first one tested to override U_COMMON_API, U_I18N_API, etc. + * @stable ICU 2.0 + */ + +/** + * \def U_DATA_API + * Set to export library symbols from inside the stubdata library, + * and to import them from outside. + * @stable ICU 3.0 + */ + +/** + * \def U_COMMON_API + * Set to export library symbols from inside the common library, + * and to import them from outside. + * @stable ICU 2.0 + */ + +/** + * \def U_I18N_API + * Set to export library symbols from inside the i18n library, + * and to import them from outside. + * @stable ICU 2.0 + */ + +/** + * \def U_LAYOUT_API + * Set to export library symbols from inside the layout engine library, + * and to import them from outside. + * @stable ICU 2.0 + */ + +/** + * \def U_LAYOUTEX_API + * Set to export library symbols from inside the layout extensions library, + * and to import them from outside. + * @stable ICU 2.6 + */ + +/** + * \def U_IO_API + * Set to export library symbols from inside the ustdio library, + * and to import them from outside. + * @stable ICU 2.0 + */ + +/** + * \def U_TOOLUTIL_API + * Set to export library symbols from inside the toolutil library, + * and to import them from outside. + * @stable ICU 3.4 + */ + +#ifdef U_IN_DOXYGEN +// This definition is required when generating the API docs. +#define U_COMBINED_IMPLEMENTATION 1 +#endif + +#if defined(U_COMBINED_IMPLEMENTATION) +#define U_DATA_API U_EXPORT +#define U_COMMON_API U_EXPORT +#define U_I18N_API U_EXPORT +#define U_LAYOUT_API U_EXPORT +#define U_LAYOUTEX_API U_EXPORT +#define U_IO_API U_EXPORT +#define U_TOOLUTIL_API U_EXPORT +#elif defined(U_STATIC_IMPLEMENTATION) +#define U_DATA_API +#define U_COMMON_API +#define U_I18N_API +#define U_LAYOUT_API +#define U_LAYOUTEX_API +#define U_IO_API +#define U_TOOLUTIL_API +#elif defined(U_COMMON_IMPLEMENTATION) +#define U_DATA_API U_IMPORT +#define U_COMMON_API U_EXPORT +#define U_I18N_API U_IMPORT +#define U_LAYOUT_API U_IMPORT +#define U_LAYOUTEX_API U_IMPORT +#define U_IO_API U_IMPORT +#define U_TOOLUTIL_API U_IMPORT +#elif defined(U_I18N_IMPLEMENTATION) +#define U_DATA_API U_IMPORT +#define U_COMMON_API U_IMPORT +#define U_I18N_API U_EXPORT +#define U_LAYOUT_API U_IMPORT +#define U_LAYOUTEX_API U_IMPORT +#define U_IO_API U_IMPORT +#define U_TOOLUTIL_API U_IMPORT +#elif defined(U_LAYOUT_IMPLEMENTATION) +#define U_DATA_API U_IMPORT +#define U_COMMON_API U_IMPORT +#define U_I18N_API U_IMPORT +#define U_LAYOUT_API U_EXPORT +#define U_LAYOUTEX_API U_IMPORT +#define U_IO_API U_IMPORT +#define U_TOOLUTIL_API U_IMPORT +#elif defined(U_LAYOUTEX_IMPLEMENTATION) +#define U_DATA_API U_IMPORT +#define U_COMMON_API U_IMPORT +#define U_I18N_API U_IMPORT +#define U_LAYOUT_API U_IMPORT +#define U_LAYOUTEX_API U_EXPORT +#define U_IO_API U_IMPORT +#define U_TOOLUTIL_API U_IMPORT +#elif defined(U_IO_IMPLEMENTATION) +#define U_DATA_API U_IMPORT +#define U_COMMON_API U_IMPORT +#define U_I18N_API U_IMPORT +#define U_LAYOUT_API U_IMPORT +#define U_LAYOUTEX_API U_IMPORT +#define U_IO_API U_EXPORT +#define U_TOOLUTIL_API U_IMPORT +#elif defined(U_TOOLUTIL_IMPLEMENTATION) +#define U_DATA_API U_IMPORT +#define U_COMMON_API U_IMPORT +#define U_I18N_API U_IMPORT +#define U_LAYOUT_API U_IMPORT +#define U_LAYOUTEX_API U_IMPORT +#define U_IO_API U_IMPORT +#define U_TOOLUTIL_API U_EXPORT +#else +#define U_DATA_API U_IMPORT +#define U_COMMON_API U_IMPORT +#define U_I18N_API U_IMPORT +#define U_LAYOUT_API U_IMPORT +#define U_LAYOUTEX_API U_IMPORT +#define U_IO_API U_IMPORT +#define U_TOOLUTIL_API U_IMPORT +#endif + +/** + * \def U_STANDARD_CPP_NAMESPACE + * Control of C++ Namespace + * @stable ICU 2.0 + */ +#ifdef __cplusplus +#define U_STANDARD_CPP_NAMESPACE :: +#else +#define U_STANDARD_CPP_NAMESPACE +#endif + +/*===========================================================================*/ +/* UErrorCode */ +/*===========================================================================*/ + +/** + * Standard ICU4C error code type, a substitute for exceptions. + * + * Initialize the UErrorCode with U_ZERO_ERROR, and check for success or + * failure using U_SUCCESS() or U_FAILURE(): + * + * UErrorCode errorCode = U_ZERO_ERROR; + * // call ICU API that needs an error code parameter. + * if (U_FAILURE(errorCode)) { + * // An error occurred. Handle it here. + * } + * + * C++ code should use icu::ErrorCode, available in unicode/errorcode.h, or a + * suitable subclass. + * + * For more information, see: + * http://icu-project.org/userguide/conventions + * + * Note: By convention, ICU functions that take a reference (C++) or a pointer + * (C) to a UErrorCode first test: + * + * if (U_FAILURE(errorCode)) { return immediately; } + * + * so that in a chain of such functions the first one that sets an error code + * causes the following ones to not perform any operations. + * + * @stable ICU 2.0 + */ +typedef enum UErrorCode { + /* The ordering of U_ERROR_INFO_START Vs U_USING_FALLBACK_WARNING looks weird + * and is that way because VC++ debugger displays first encountered constant, + * which is not the what the code is used for + */ + + U_USING_FALLBACK_WARNING = -128, /**< A resource bundle lookup returned a fallback result (not an error) */ + + U_ERROR_WARNING_START = -128, /**< Start of information results (semantically successful) */ + + U_USING_DEFAULT_WARNING = -127, /**< A resource bundle lookup returned a result from the root locale (not an error) */ + + U_SAFECLONE_ALLOCATED_WARNING = -126, /**< A SafeClone operation required allocating memory (informational only) */ + + U_STATE_OLD_WARNING = -125, /**< ICU has to use compatibility layer to construct the service. Expect performance/memory usage degradation. Consider upgrading */ + + U_STRING_NOT_TERMINATED_WARNING = -124,/**< An output string could not be NUL-terminated because output length==destCapacity. */ + + U_SORT_KEY_TOO_SHORT_WARNING = -123, /**< Number of levels requested in getBound is higher than the number of levels in the sort key */ + + U_AMBIGUOUS_ALIAS_WARNING = -122, /**< This converter alias can go to different converter implementations */ + + U_DIFFERENT_UCA_VERSION = -121, /**< ucol_open encountered a mismatch between UCA version and collator image version, so the collator was constructed from rules. No impact to further function */ + + U_PLUGIN_CHANGED_LEVEL_WARNING = -120, /**< A plugin caused a level change. May not be an error, but later plugins may not load. */ + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal UErrorCode warning value. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_ERROR_WARNING_LIMIT, +#endif // U_HIDE_DEPRECATED_API + + U_ZERO_ERROR = 0, /**< No error, no warning. */ + + U_ILLEGAL_ARGUMENT_ERROR = 1, /**< Start of codes indicating failure */ + U_MISSING_RESOURCE_ERROR = 2, /**< The requested resource cannot be found */ + U_INVALID_FORMAT_ERROR = 3, /**< Data format is not what is expected */ + U_FILE_ACCESS_ERROR = 4, /**< The requested file cannot be found */ + U_INTERNAL_PROGRAM_ERROR = 5, /**< Indicates a bug in the library code */ + U_MESSAGE_PARSE_ERROR = 6, /**< Unable to parse a message (message format) */ + U_MEMORY_ALLOCATION_ERROR = 7, /**< Memory allocation error */ + U_INDEX_OUTOFBOUNDS_ERROR = 8, /**< Trying to access the index that is out of bounds */ + U_PARSE_ERROR = 9, /**< Equivalent to Java ParseException */ + U_INVALID_CHAR_FOUND = 10, /**< Character conversion: Unmappable input sequence. In other APIs: Invalid character. */ + U_TRUNCATED_CHAR_FOUND = 11, /**< Character conversion: Incomplete input sequence. */ + U_ILLEGAL_CHAR_FOUND = 12, /**< Character conversion: Illegal input sequence/combination of input units. */ + U_INVALID_TABLE_FORMAT = 13, /**< Conversion table file found, but corrupted */ + U_INVALID_TABLE_FILE = 14, /**< Conversion table file not found */ + U_BUFFER_OVERFLOW_ERROR = 15, /**< A result would not fit in the supplied buffer */ + U_UNSUPPORTED_ERROR = 16, /**< Requested operation not supported in current context */ + U_RESOURCE_TYPE_MISMATCH = 17, /**< an operation is requested over a resource that does not support it */ + U_ILLEGAL_ESCAPE_SEQUENCE = 18, /**< ISO-2022 illegal escape sequence */ + U_UNSUPPORTED_ESCAPE_SEQUENCE = 19, /**< ISO-2022 unsupported escape sequence */ + U_NO_SPACE_AVAILABLE = 20, /**< No space available for in-buffer expansion for Arabic shaping */ + U_CE_NOT_FOUND_ERROR = 21, /**< Currently used only while setting variable top, but can be used generally */ + U_PRIMARY_TOO_LONG_ERROR = 22, /**< User tried to set variable top to a primary that is longer than two bytes */ + U_STATE_TOO_OLD_ERROR = 23, /**< ICU cannot construct a service from this state, as it is no longer supported */ + U_TOO_MANY_ALIASES_ERROR = 24, /**< There are too many aliases in the path to the requested resource. + It is very possible that a circular alias definition has occurred */ + U_ENUM_OUT_OF_SYNC_ERROR = 25, /**< UEnumeration out of sync with underlying collection */ + U_INVARIANT_CONVERSION_ERROR = 26, /**< Unable to convert a UChar* string to char* with the invariant converter. */ + U_INVALID_STATE_ERROR = 27, /**< Requested operation can not be completed with ICU in its current state */ + U_COLLATOR_VERSION_MISMATCH = 28, /**< Collator version is not compatible with the base version */ + U_USELESS_COLLATOR_ERROR = 29, /**< Collator is options only and no base is specified */ + U_NO_WRITE_PERMISSION = 30, /**< Attempt to modify read-only or constant data. */ +#ifndef U_HIDE_DRAFT_API + /** + * The input is impractically long for an operation. + * It is rejected because it may lead to problems such as excessive + * processing time, stack depth, or heap memory requirements. + * + * @draft ICU 68 + */ + U_INPUT_TOO_LONG_ERROR = 31, +#endif // U_HIDE_DRAFT_API + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest standard error code. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_STANDARD_ERROR_LIMIT = 32, +#endif // U_HIDE_DEPRECATED_API + + /* + * Error codes in the range 0x10000 0x10100 are reserved for Transliterator. + */ + U_BAD_VARIABLE_DEFINITION=0x10000,/**< Missing '$' or duplicate variable name */ + U_PARSE_ERROR_START = 0x10000, /**< Start of Transliterator errors */ + U_MALFORMED_RULE, /**< Elements of a rule are misplaced */ + U_MALFORMED_SET, /**< A UnicodeSet pattern is invalid*/ + U_MALFORMED_SYMBOL_REFERENCE, /**< UNUSED as of ICU 2.4 */ + U_MALFORMED_UNICODE_ESCAPE, /**< A Unicode escape pattern is invalid*/ + U_MALFORMED_VARIABLE_DEFINITION, /**< A variable definition is invalid */ + U_MALFORMED_VARIABLE_REFERENCE, /**< A variable reference is invalid */ + U_MISMATCHED_SEGMENT_DELIMITERS, /**< UNUSED as of ICU 2.4 */ + U_MISPLACED_ANCHOR_START, /**< A start anchor appears at an illegal position */ + U_MISPLACED_CURSOR_OFFSET, /**< A cursor offset occurs at an illegal position */ + U_MISPLACED_QUANTIFIER, /**< A quantifier appears after a segment close delimiter */ + U_MISSING_OPERATOR, /**< A rule contains no operator */ + U_MISSING_SEGMENT_CLOSE, /**< UNUSED as of ICU 2.4 */ + U_MULTIPLE_ANTE_CONTEXTS, /**< More than one ante context */ + U_MULTIPLE_CURSORS, /**< More than one cursor */ + U_MULTIPLE_POST_CONTEXTS, /**< More than one post context */ + U_TRAILING_BACKSLASH, /**< A dangling backslash */ + U_UNDEFINED_SEGMENT_REFERENCE, /**< A segment reference does not correspond to a defined segment */ + U_UNDEFINED_VARIABLE, /**< A variable reference does not correspond to a defined variable */ + U_UNQUOTED_SPECIAL, /**< A special character was not quoted or escaped */ + U_UNTERMINATED_QUOTE, /**< A closing single quote is missing */ + U_RULE_MASK_ERROR, /**< A rule is hidden by an earlier more general rule */ + U_MISPLACED_COMPOUND_FILTER, /**< A compound filter is in an invalid location */ + U_MULTIPLE_COMPOUND_FILTERS, /**< More than one compound filter */ + U_INVALID_RBT_SYNTAX, /**< A "::id" rule was passed to the RuleBasedTransliterator parser */ + U_INVALID_PROPERTY_PATTERN, /**< UNUSED as of ICU 2.4 */ + U_MALFORMED_PRAGMA, /**< A 'use' pragma is invalid */ + U_UNCLOSED_SEGMENT, /**< A closing ')' is missing */ + U_ILLEGAL_CHAR_IN_SEGMENT, /**< UNUSED as of ICU 2.4 */ + U_VARIABLE_RANGE_EXHAUSTED, /**< Too many stand-ins generated for the given variable range */ + U_VARIABLE_RANGE_OVERLAP, /**< The variable range overlaps characters used in rules */ + U_ILLEGAL_CHARACTER, /**< A special character is outside its allowed context */ + U_INTERNAL_TRANSLITERATOR_ERROR, /**< Internal transliterator system error */ + U_INVALID_ID, /**< A "::id" rule specifies an unknown transliterator */ + U_INVALID_FUNCTION, /**< A "&fn()" rule specifies an unknown transliterator */ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal Transliterator error code. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_PARSE_ERROR_LIMIT, +#endif // U_HIDE_DEPRECATED_API + + /* + * Error codes in the range 0x10100 0x10200 are reserved for the formatting API. + */ + U_UNEXPECTED_TOKEN=0x10100, /**< Syntax error in format pattern */ + U_FMT_PARSE_ERROR_START=0x10100, /**< Start of format library errors */ + U_MULTIPLE_DECIMAL_SEPARATORS, /**< More than one decimal separator in number pattern */ + U_MULTIPLE_DECIMAL_SEPERATORS = U_MULTIPLE_DECIMAL_SEPARATORS, /**< Typo: kept for backward compatibility. Use U_MULTIPLE_DECIMAL_SEPARATORS */ + U_MULTIPLE_EXPONENTIAL_SYMBOLS, /**< More than one exponent symbol in number pattern */ + U_MALFORMED_EXPONENTIAL_PATTERN, /**< Grouping symbol in exponent pattern */ + U_MULTIPLE_PERCENT_SYMBOLS, /**< More than one percent symbol in number pattern */ + U_MULTIPLE_PERMILL_SYMBOLS, /**< More than one permill symbol in number pattern */ + U_MULTIPLE_PAD_SPECIFIERS, /**< More than one pad symbol in number pattern */ + U_PATTERN_SYNTAX_ERROR, /**< Syntax error in format pattern */ + U_ILLEGAL_PAD_POSITION, /**< Pad symbol misplaced in number pattern */ + U_UNMATCHED_BRACES, /**< Braces do not match in message pattern */ + U_UNSUPPORTED_PROPERTY, /**< UNUSED as of ICU 2.4 */ + U_UNSUPPORTED_ATTRIBUTE, /**< UNUSED as of ICU 2.4 */ + U_ARGUMENT_TYPE_MISMATCH, /**< Argument name and argument index mismatch in MessageFormat functions */ + U_DUPLICATE_KEYWORD, /**< Duplicate keyword in PluralFormat */ + U_UNDEFINED_KEYWORD, /**< Undefined Plural keyword */ + U_DEFAULT_KEYWORD_MISSING, /**< Missing DEFAULT rule in plural rules */ + U_DECIMAL_NUMBER_SYNTAX_ERROR, /**< Decimal number syntax error */ + U_FORMAT_INEXACT_ERROR, /**< Cannot format a number exactly and rounding mode is ROUND_UNNECESSARY @stable ICU 4.8 */ + U_NUMBER_ARG_OUTOFBOUNDS_ERROR, /**< The argument to a NumberFormatter helper method was out of bounds; the bounds are usually 0 to 999. @stable ICU 61 */ + U_NUMBER_SKELETON_SYNTAX_ERROR, /**< The number skeleton passed to C++ NumberFormatter or C UNumberFormatter was invalid or contained a syntax error. @stable ICU 62 */ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal formatting API error code. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_FMT_PARSE_ERROR_LIMIT = 0x10114, +#endif // U_HIDE_DEPRECATED_API + + /* + * Error codes in the range 0x10200 0x102ff are reserved for BreakIterator. + */ + U_BRK_INTERNAL_ERROR=0x10200, /**< An internal error (bug) was detected. */ + U_BRK_ERROR_START=0x10200, /**< Start of codes indicating Break Iterator failures */ + U_BRK_HEX_DIGITS_EXPECTED, /**< Hex digits expected as part of a escaped char in a rule. */ + U_BRK_SEMICOLON_EXPECTED, /**< Missing ';' at the end of a RBBI rule. */ + U_BRK_RULE_SYNTAX, /**< Syntax error in RBBI rule. */ + U_BRK_UNCLOSED_SET, /**< UnicodeSet writing an RBBI rule missing a closing ']'. */ + U_BRK_ASSIGN_ERROR, /**< Syntax error in RBBI rule assignment statement. */ + U_BRK_VARIABLE_REDFINITION, /**< RBBI rule $Variable redefined. */ + U_BRK_MISMATCHED_PAREN, /**< Mis-matched parentheses in an RBBI rule. */ + U_BRK_NEW_LINE_IN_QUOTED_STRING, /**< Missing closing quote in an RBBI rule. */ + U_BRK_UNDEFINED_VARIABLE, /**< Use of an undefined $Variable in an RBBI rule. */ + U_BRK_INIT_ERROR, /**< Initialization failure. Probable missing ICU Data. */ + U_BRK_RULE_EMPTY_SET, /**< Rule contains an empty Unicode Set. */ + U_BRK_UNRECOGNIZED_OPTION, /**< !!option in RBBI rules not recognized. */ + U_BRK_MALFORMED_RULE_TAG, /**< The {nnn} tag on a rule is malformed */ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal BreakIterator error code. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_BRK_ERROR_LIMIT, +#endif // U_HIDE_DEPRECATED_API + + /* + * Error codes in the range 0x10300-0x103ff are reserved for regular expression related errors. + */ + U_REGEX_INTERNAL_ERROR=0x10300, /**< An internal error (bug) was detected. */ + U_REGEX_ERROR_START=0x10300, /**< Start of codes indicating Regexp failures */ + U_REGEX_RULE_SYNTAX, /**< Syntax error in regexp pattern. */ + U_REGEX_INVALID_STATE, /**< RegexMatcher in invalid state for requested operation */ + U_REGEX_BAD_ESCAPE_SEQUENCE, /**< Unrecognized backslash escape sequence in pattern */ + U_REGEX_PROPERTY_SYNTAX, /**< Incorrect Unicode property */ + U_REGEX_UNIMPLEMENTED, /**< Use of regexp feature that is not yet implemented. */ + U_REGEX_MISMATCHED_PAREN, /**< Incorrectly nested parentheses in regexp pattern. */ + U_REGEX_NUMBER_TOO_BIG, /**< Decimal number is too large. */ + U_REGEX_BAD_INTERVAL, /**< Error in {min,max} interval */ + U_REGEX_MAX_LT_MIN, /**< In {min,max}, max is less than min. */ + U_REGEX_INVALID_BACK_REF, /**< Back-reference to a non-existent capture group. */ + U_REGEX_INVALID_FLAG, /**< Invalid value for match mode flags. */ + U_REGEX_LOOK_BEHIND_LIMIT, /**< Look-Behind pattern matches must have a bounded maximum length. */ + U_REGEX_SET_CONTAINS_STRING, /**< Regexps cannot have UnicodeSets containing strings.*/ +#ifndef U_HIDE_DEPRECATED_API + U_REGEX_OCTAL_TOO_BIG, /**< Octal character constants must be <= 0377. @deprecated ICU 54. This error cannot occur. */ +#endif /* U_HIDE_DEPRECATED_API */ + U_REGEX_MISSING_CLOSE_BRACKET=U_REGEX_SET_CONTAINS_STRING+2, /**< Missing closing bracket on a bracket expression. */ + U_REGEX_INVALID_RANGE, /**< In a character range [x-y], x is greater than y. */ + U_REGEX_STACK_OVERFLOW, /**< Regular expression backtrack stack overflow. */ + U_REGEX_TIME_OUT, /**< Maximum allowed match time exceeded */ + U_REGEX_STOPPED_BY_CALLER, /**< Matching operation aborted by user callback fn. */ + U_REGEX_PATTERN_TOO_BIG, /**< Pattern exceeds limits on size or complexity. @stable ICU 55 */ + U_REGEX_INVALID_CAPTURE_GROUP_NAME, /**< Invalid capture group name. @stable ICU 55 */ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal regular expression error code. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_REGEX_ERROR_LIMIT=U_REGEX_STOPPED_BY_CALLER+3, +#endif // U_HIDE_DEPRECATED_API + + /* + * Error codes in the range 0x10400-0x104ff are reserved for IDNA related error codes. + */ + U_IDNA_PROHIBITED_ERROR=0x10400, + U_IDNA_ERROR_START=0x10400, + U_IDNA_UNASSIGNED_ERROR, + U_IDNA_CHECK_BIDI_ERROR, + U_IDNA_STD3_ASCII_RULES_ERROR, + U_IDNA_ACE_PREFIX_ERROR, + U_IDNA_VERIFICATION_ERROR, + U_IDNA_LABEL_TOO_LONG_ERROR, + U_IDNA_ZERO_LENGTH_LABEL_ERROR, + U_IDNA_DOMAIN_NAME_TOO_LONG_ERROR, +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal IDNA error code. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_IDNA_ERROR_LIMIT, +#endif // U_HIDE_DEPRECATED_API + /* + * Aliases for StringPrep + */ + U_STRINGPREP_PROHIBITED_ERROR = U_IDNA_PROHIBITED_ERROR, + U_STRINGPREP_UNASSIGNED_ERROR = U_IDNA_UNASSIGNED_ERROR, + U_STRINGPREP_CHECK_BIDI_ERROR = U_IDNA_CHECK_BIDI_ERROR, + + /* + * Error codes in the range 0x10500-0x105ff are reserved for Plugin related error codes. + */ + U_PLUGIN_ERROR_START=0x10500, /**< Start of codes indicating plugin failures */ + U_PLUGIN_TOO_HIGH=0x10500, /**< The plugin's level is too high to be loaded right now. */ + U_PLUGIN_DIDNT_SET_LEVEL, /**< The plugin didn't call uplug_setPlugLevel in response to a QUERY */ +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal plug-in error code. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_PLUGIN_ERROR_LIMIT, +#endif // U_HIDE_DEPRECATED_API + +#ifndef U_HIDE_DEPRECATED_API + /** + * One more than the highest normal error code. + * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. + */ + U_ERROR_LIMIT=U_PLUGIN_ERROR_LIMIT +#endif // U_HIDE_DEPRECATED_API +} UErrorCode; + +/* Use the following to determine if an UErrorCode represents */ +/* operational success or failure. */ + +#ifdef __cplusplus + /** + * Does the error code indicate success? + * @stable ICU 2.0 + */ + static + inline UBool U_SUCCESS(UErrorCode code) { return (UBool)(code<=U_ZERO_ERROR); } + /** + * Does the error code indicate a failure? + * @stable ICU 2.0 + */ + static + inline UBool U_FAILURE(UErrorCode code) { return (UBool)(code>U_ZERO_ERROR); } +#else + /** + * Does the error code indicate success? + * @stable ICU 2.0 + */ +# define U_SUCCESS(x) ((x)<=U_ZERO_ERROR) + /** + * Does the error code indicate a failure? + * @stable ICU 2.0 + */ +# define U_FAILURE(x) ((x)>U_ZERO_ERROR) +#endif + +/** + * Return a string for a UErrorCode value. + * The string will be the same as the name of the error code constant + * in the UErrorCode enum above. + * @stable ICU 2.0 + */ +U_CAPI const char * U_EXPORT2 +u_errorName(UErrorCode code); + + +#endif /* _UTYPES */ diff --git a/thirdparty/icu4c/common/unicode/uvernum.h b/thirdparty/icu4c/common/unicode/uvernum.h new file mode 100644 index 0000000000..a4cbb9e0fe --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uvernum.h @@ -0,0 +1,198 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2000-2016, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* +* file name: uvernum.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* Created by: Vladimir Weinstein +* Updated by: Steven R. Loomis +* +*/ + +/** + * \file + * \brief C API: definitions of ICU version numbers + * + * This file is included by uversion.h and other files. This file contains only + * macros and definitions. The actual version numbers are defined here. + */ + + /* + * IMPORTANT: When updating version, the following things need to be done: + * source/common/unicode/uvernum.h - this file: update major, minor, + * patchlevel, suffix, version, short version constants, namespace, + * renaming macro, and copyright + * + * The following files need to be updated as well, which can be done + * by running the UNIX makefile target 'update-windows-makefiles' in icu/source. + * + * + * source/common/common_uwp.vcxproj + * source/common/common.vcxproj - update 'Output file name' on the link tab so + * that it contains the new major/minor combination + * source/i18n/i18n.vcxproj - same as for the common.vcxproj + * source/i18n/i18n_uwp.vcxproj - same as for the common_uwp.vcxproj + * source/layoutex/layoutex.vcproj - same + * source/stubdata/stubdata.vcproj - same as for the common.vcxproj + * source/io/io.vcproj - same as for the common.vcxproj + * source/data/makedata.mak - change U_ICUDATA_NAME so that it contains + * the new major/minor combination and the Unicode version. + */ + +#ifndef UVERNUM_H +#define UVERNUM_H + +/** The standard copyright notice that gets compiled into each library. + * This value will change in the subsequent releases of ICU + * @stable ICU 2.4 + */ +#define U_COPYRIGHT_STRING \ + " Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.unicode.org/copyright.html " + +/** The current ICU major version as an integer. + * This value will change in the subsequent releases of ICU + * @stable ICU 2.4 + */ +#define U_ICU_VERSION_MAJOR_NUM 68 + +/** The current ICU minor version as an integer. + * This value will change in the subsequent releases of ICU + * @stable ICU 2.6 + */ +#define U_ICU_VERSION_MINOR_NUM 1 + +/** The current ICU patchlevel version as an integer. + * This value will change in the subsequent releases of ICU + * @stable ICU 2.4 + */ +#define U_ICU_VERSION_PATCHLEVEL_NUM 0 + +/** The current ICU build level version as an integer. + * This value is for use by ICU clients. It defaults to 0. + * @stable ICU 4.0 + */ +#ifndef U_ICU_VERSION_BUILDLEVEL_NUM +#define U_ICU_VERSION_BUILDLEVEL_NUM 0 +#endif + +/** Glued version suffix for renamers + * This value will change in the subsequent releases of ICU + * @stable ICU 2.6 + */ +#define U_ICU_VERSION_SUFFIX _68 + +/** + * \def U_DEF2_ICU_ENTRY_POINT_RENAME + * @internal + */ +/** + * \def U_DEF_ICU_ENTRY_POINT_RENAME + * @internal + */ +/** Glued version suffix function for renamers + * This value will change in the subsequent releases of ICU. + * If a custom suffix (such as matching library suffixes) is desired, this can be modified. + * Note that if present, platform.h may contain an earlier definition of this macro. + * \def U_ICU_ENTRY_POINT_RENAME + * @stable ICU 4.2 + */ +/** + * Disable the version suffix. Use the custom suffix if exists. + * \def U_DISABLE_VERSION_SUFFIX + * @internal + */ +#ifndef U_DISABLE_VERSION_SUFFIX +#define U_DISABLE_VERSION_SUFFIX 0 +#endif + +#ifndef U_ICU_ENTRY_POINT_RENAME +#ifdef U_HAVE_LIB_SUFFIX +# if !U_DISABLE_VERSION_SUFFIX +# define U_DEF_ICU_ENTRY_POINT_RENAME(x,y,z) x ## y ## z +# define U_DEF2_ICU_ENTRY_POINT_RENAME(x,y,z) U_DEF_ICU_ENTRY_POINT_RENAME(x,y,z) +# define U_ICU_ENTRY_POINT_RENAME(x) U_DEF2_ICU_ENTRY_POINT_RENAME(x,U_ICU_VERSION_SUFFIX,U_LIB_SUFFIX_C_NAME) +# else +# define U_DEF_ICU_ENTRY_POINT_RENAME(x,y) x ## y +# define U_DEF2_ICU_ENTRY_POINT_RENAME(x,y) U_DEF_ICU_ENTRY_POINT_RENAME(x,y) +# define U_ICU_ENTRY_POINT_RENAME(x) U_DEF2_ICU_ENTRY_POINT_RENAME(x,U_LIB_SUFFIX_C_NAME) +# endif +#else +# if !U_DISABLE_VERSION_SUFFIX +# define U_DEF_ICU_ENTRY_POINT_RENAME(x,y) x ## y +# define U_DEF2_ICU_ENTRY_POINT_RENAME(x,y) U_DEF_ICU_ENTRY_POINT_RENAME(x,y) +# define U_ICU_ENTRY_POINT_RENAME(x) U_DEF2_ICU_ENTRY_POINT_RENAME(x,U_ICU_VERSION_SUFFIX) +# else +# define U_ICU_ENTRY_POINT_RENAME(x) x +# endif +#endif +#endif + +/** The current ICU library version as a dotted-decimal string. The patchlevel + * only appears in this string if it non-zero. + * This value will change in the subsequent releases of ICU + * @stable ICU 2.4 + */ +#define U_ICU_VERSION "68.1" + +/** + * The current ICU library major version number as a string, for library name suffixes. + * This value will change in subsequent releases of ICU. + * + * Until ICU 4.8, this was the combination of the single-digit major and minor ICU version numbers + * into one string without dots ("48"). + * Since ICU 49, it is the double-digit major ICU version number. + * See https://unicode-org.github.io/icu/userguide/design#version-numbers-in-icu + * + * @stable ICU 2.6 + */ +#define U_ICU_VERSION_SHORT "68" + +#ifndef U_HIDE_INTERNAL_API +/** Data version in ICU4C. + * @internal ICU 4.4 Internal Use Only + **/ +#define U_ICU_DATA_VERSION "68.1" +#endif /* U_HIDE_INTERNAL_API */ + +/*=========================================================================== + * ICU collation framework version information + * Version info that can be obtained from a collator is affected by these + * numbers in a secret and magic way. Please use collator version as whole + *=========================================================================== + */ + +/** + * Collation runtime version (sort key generator, strcoll). + * If the version is different, sort keys for the same string could be different. + * This value may change in subsequent releases of ICU. + * @stable ICU 2.4 + */ +#define UCOL_RUNTIME_VERSION 9 + +/** + * Collation builder code version. + * When this is different, the same tailoring might result + * in assigning different collation elements to code points. + * This value may change in subsequent releases of ICU. + * @stable ICU 2.4 + */ +#define UCOL_BUILDER_VERSION 9 + +#ifndef U_HIDE_DEPRECATED_API +/** + * Constant 1. + * This was intended to be the version of collation tailorings, + * but instead the tailoring data carries a version number. + * @deprecated ICU 54 + */ +#define UCOL_TAILORINGS_VERSION 1 +#endif /* U_HIDE_DEPRECATED_API */ + +#endif diff --git a/thirdparty/icu4c/common/unicode/uversion.h b/thirdparty/icu4c/common/unicode/uversion.h new file mode 100644 index 0000000000..113568df8c --- /dev/null +++ b/thirdparty/icu4c/common/unicode/uversion.h @@ -0,0 +1,187 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* Copyright (C) 2000-2011, International Business Machines +* Corporation and others. All Rights Reserved. +******************************************************************************* +* +* file name: uversion.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* Created by: Vladimir Weinstein +* +* Gets included by utypes.h and Windows .rc files +*/ + +/** + * \file + * \brief C API: API for accessing ICU version numbers. + */ +/*===========================================================================*/ +/* Main ICU version information */ +/*===========================================================================*/ + +#ifndef UVERSION_H +#define UVERSION_H + +#include "unicode/umachine.h" + +/* Actual version info lives in uvernum.h */ +#include "unicode/uvernum.h" + +/** Maximum length of the copyright string. + * @stable ICU 2.4 + */ +#define U_COPYRIGHT_STRING_LENGTH 128 + +/** An ICU version consists of up to 4 numbers from 0..255. + * @stable ICU 2.4 + */ +#define U_MAX_VERSION_LENGTH 4 + +/** In a string, ICU version fields are delimited by dots. + * @stable ICU 2.4 + */ +#define U_VERSION_DELIMITER '.' + +/** The maximum length of an ICU version string. + * @stable ICU 2.4 + */ +#define U_MAX_VERSION_STRING_LENGTH 20 + +/** The binary form of a version on ICU APIs is an array of 4 uint8_t. + * To compare two versions, use memcmp(v1,v2,sizeof(UVersionInfo)). + * @stable ICU 2.4 + */ +typedef uint8_t UVersionInfo[U_MAX_VERSION_LENGTH]; + +/*===========================================================================*/ +/* C++ namespace if supported. Versioned unless versioning is disabled. */ +/*===========================================================================*/ + +/* Define C++ namespace symbols. */ +#ifdef __cplusplus + +/** + * \def U_NAMESPACE_BEGIN + * This is used to begin a declaration of a public ICU C++ API within + * versioned-ICU-namespace block. + * + * @stable ICU 2.4 + */ + +/** + * \def U_NAMESPACE_END + * This is used to end a declaration of a public ICU C++ API. + * It ends the versioned-ICU-namespace block begun by U_NAMESPACE_BEGIN. + * + * @stable ICU 2.4 + */ + +/** + * \def U_NAMESPACE_USE + * This is used to specify that the rest of the code uses the + * public ICU C++ API namespace. + * @stable ICU 2.4 + */ + +/** + * \def U_NAMESPACE_QUALIFIER + * This is used to qualify that a function or class is part of + * the public ICU C++ API namespace. + * + * This macro is unnecessary since ICU 49 requires namespace support. + * You can just use "icu::" instead. + * @stable ICU 2.4 + */ + +# if U_DISABLE_RENAMING +# define U_ICU_NAMESPACE icu + namespace U_ICU_NAMESPACE { } +# else +# define U_ICU_NAMESPACE U_ICU_ENTRY_POINT_RENAME(icu) + namespace U_ICU_NAMESPACE { } + namespace icu = U_ICU_NAMESPACE; +# endif + +# define U_NAMESPACE_BEGIN namespace U_ICU_NAMESPACE { +# define U_NAMESPACE_END } +# define U_NAMESPACE_USE using namespace U_ICU_NAMESPACE; +# define U_NAMESPACE_QUALIFIER U_ICU_NAMESPACE:: + +# ifndef U_USING_ICU_NAMESPACE +# if defined(U_COMBINED_IMPLEMENTATION) || defined(U_COMMON_IMPLEMENTATION) || \ + defined(U_I18N_IMPLEMENTATION) || defined(U_IO_IMPLEMENTATION) || \ + defined(U_LAYOUTEX_IMPLEMENTATION) || defined(U_TOOLUTIL_IMPLEMENTATION) +# define U_USING_ICU_NAMESPACE 0 +# else +# define U_USING_ICU_NAMESPACE 0 +# endif +# endif +# if U_USING_ICU_NAMESPACE + U_NAMESPACE_USE +# endif +#endif /* __cplusplus */ + +/*===========================================================================*/ +/* General version helper functions. Definitions in putil.c */ +/*===========================================================================*/ + +/** + * Parse a string with dotted-decimal version information and + * fill in a UVersionInfo structure with the result. + * Definition of this function lives in putil.c + * + * @param versionArray The destination structure for the version information. + * @param versionString A string with dotted-decimal version information, + * with up to four non-negative number fields with + * values of up to 255 each. + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +u_versionFromString(UVersionInfo versionArray, const char *versionString); + +/** + * Parse a Unicode string with dotted-decimal version information and + * fill in a UVersionInfo structure with the result. + * Definition of this function lives in putil.c + * + * @param versionArray The destination structure for the version information. + * @param versionString A Unicode string with dotted-decimal version + * information, with up to four non-negative number + * fields with values of up to 255 each. + * @stable ICU 4.2 + */ +U_CAPI void U_EXPORT2 +u_versionFromUString(UVersionInfo versionArray, const UChar *versionString); + + +/** + * Write a string with dotted-decimal version information according + * to the input UVersionInfo. + * Definition of this function lives in putil.c + * + * @param versionArray The version information to be written as a string. + * @param versionString A string buffer that will be filled in with + * a string corresponding to the numeric version + * information in versionArray. + * The buffer size must be at least U_MAX_VERSION_STRING_LENGTH. + * @stable ICU 2.4 + */ +U_CAPI void U_EXPORT2 +u_versionToString(const UVersionInfo versionArray, char *versionString); + +/** + * Gets the ICU release version. The version array stores the version information + * for ICU. For example, release "1.3.31.2" is then represented as 0x01031F02. + * Definition of this function lives in putil.c + * + * @param versionArray the version # information, the result will be filled in + * @stable ICU 2.0 + */ +U_CAPI void U_EXPORT2 +u_getVersion(UVersionInfo versionArray); +#endif |