From b56241f22f96826ef9ef38cf7e4312b899f8e241 Mon Sep 17 00:00:00 2001 From: bruvzg <7645683+bruvzg@users.noreply.github.com> Date: Thu, 22 Apr 2021 15:08:59 +0300 Subject: ICU: Update to version 69.1, improve ICU data export process. --- thirdparty/icu4c/common/unicode/bytestream.h | 6 +- thirdparty/icu4c/common/unicode/bytestrie.h | 3 + thirdparty/icu4c/common/unicode/bytestriebuilder.h | 5 ++ thirdparty/icu4c/common/unicode/docmain.h | 8 +- thirdparty/icu4c/common/unicode/icuplug.h | 7 +- thirdparty/icu4c/common/unicode/localematcher.h | 16 ++-- thirdparty/icu4c/common/unicode/locid.h | 4 +- thirdparty/icu4c/common/unicode/normalizer2.h | 28 +++---- thirdparty/icu4c/common/unicode/platform.h | 2 +- thirdparty/icu4c/common/unicode/stringpiece.h | 26 ++---- thirdparty/icu4c/common/unicode/ubrk.h | 21 ++++- thirdparty/icu4c/common/unicode/ucnv.h | 4 +- thirdparty/icu4c/common/unicode/ucnvsel.h | 4 +- thirdparty/icu4c/common/unicode/unifilt.h | 4 +- thirdparty/icu4c/common/unicode/uniset.h | 66 +++++++++------ thirdparty/icu4c/common/unicode/unistr.h | 8 +- thirdparty/icu4c/common/unicode/urename.h | 16 ++++ thirdparty/icu4c/common/unicode/uset.h | 95 ++++++++++++++++++++-- thirdparty/icu4c/common/unicode/ushape.h | 2 +- thirdparty/icu4c/common/unicode/utrace.h | 17 ++-- thirdparty/icu4c/common/unicode/uvernum.h | 12 +-- 21 files changed, 232 insertions(+), 122 deletions(-) (limited to 'thirdparty/icu4c/common/unicode') diff --git a/thirdparty/icu4c/common/unicode/bytestream.h b/thirdparty/icu4c/common/unicode/bytestream.h index 044f7a77e7..9735ee0bf8 100644 --- a/thirdparty/icu4c/common/unicode/bytestream.h +++ b/thirdparty/icu4c/common/unicode/bytestream.h @@ -71,7 +71,6 @@ public: */ 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 @@ -81,7 +80,7 @@ public: * * @param bytes the pointer to the bytes * @param n the number of bytes; must be non-negative - * @draft ICU 67 + * @stable ICU 67 */ inline void AppendU8(const char* bytes, int32_t n) { Append(bytes, n); @@ -97,13 +96,12 @@ public: * * @param bytes the pointer to the bytes * @param n the number of bytes; must be non-negative - * @draft ICU 67 + * @stable ICU 67 */ inline void AppendU8(const char8_t* bytes, int32_t n) { Append(reinterpret_cast(bytes), n); } #endif -#endif // U_HIDE_DRAFT_API /** * Returns a writable buffer for appending and writes the buffer's capacity to diff --git a/thirdparty/icu4c/common/unicode/bytestrie.h b/thirdparty/icu4c/common/unicode/bytestrie.h index 85f802df42..271a81d1b4 100644 --- a/thirdparty/icu4c/common/unicode/bytestrie.h +++ b/thirdparty/icu4c/common/unicode/bytestrie.h @@ -30,6 +30,8 @@ #include "unicode/uobject.h" #include "unicode/ustringtrie.h" +class BytesTrieTest; + U_NAMESPACE_BEGIN class ByteSink; @@ -378,6 +380,7 @@ public: private: friend class BytesTrieBuilder; + friend class ::BytesTrieTest; /** * Constructs a BytesTrie reader instance. diff --git a/thirdparty/icu4c/common/unicode/bytestriebuilder.h b/thirdparty/icu4c/common/unicode/bytestriebuilder.h index cae16e48b4..3cff89e443 100644 --- a/thirdparty/icu4c/common/unicode/bytestriebuilder.h +++ b/thirdparty/icu4c/common/unicode/bytestriebuilder.h @@ -30,6 +30,8 @@ #include "unicode/stringpiece.h" #include "unicode/stringtriebuilder.h" +class BytesTrieTest; + U_NAMESPACE_BEGIN class BytesTrieElement; @@ -125,6 +127,8 @@ public: BytesTrieBuilder &clear(); private: + friend class ::BytesTrieTest; + BytesTrieBuilder(const BytesTrieBuilder &other); // no copy constructor BytesTrieBuilder &operator=(const BytesTrieBuilder &other); // no assignment operator @@ -168,6 +172,7 @@ private: 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); + static int32_t internalEncodeDelta(int32_t i, char intBytes[]); CharString *strings; // Pointer not object so we need not #include internal charstr.h. BytesTrieElement *elements; diff --git a/thirdparty/icu4c/common/unicode/docmain.h b/thirdparty/icu4c/common/unicode/docmain.h index edcb5d4e83..e82678c95f 100644 --- a/thirdparty/icu4c/common/unicode/docmain.h +++ b/thirdparty/icu4c/common/unicode/docmain.h @@ -15,7 +15,7 @@ * \file * \brief (Non API- contains Doxygen definitions) * - * This file contains documentation for Doxygen and doesnot have + * This file contains documentation for Doxygen and does not have * any significance with respect to C or C++ API */ @@ -74,7 +74,7 @@ * * * Strings and Character Iteration - * ustring.h, utf8.h, utf16.h, UText, UCharIterator + * ustring.h, utf8.h, utf16.h, icu::StringPiece, UText, UCharIterator, icu::ByteSink * icu::UnicodeString, icu::CharacterIterator, icu::Appendable, icu::StringPiece,icu::ByteSink * * @@ -128,9 +128,9 @@ * icu::Normalizer2 * * - * Calendars + * Calendars and Time Zones * ucal.h - * icu::Calendar + * icu::Calendar, icu::TimeZone * * * Date and Time Formatting diff --git a/thirdparty/icu4c/common/unicode/icuplug.h b/thirdparty/icu4c/common/unicode/icuplug.h index 52f810da57..205af360d4 100644 --- a/thirdparty/icu4c/common/unicode/icuplug.h +++ b/thirdparty/icu4c/common/unicode/icuplug.h @@ -117,14 +117,13 @@ /* === Basic types === */ #ifndef U_HIDE_INTERNAL_API +struct UPlugData; /** * @{ - * Opaque structure passed to/from a plugin. - * use the APIs to access it. + * Typedef for 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; /** @} */ diff --git a/thirdparty/icu4c/common/unicode/localematcher.h b/thirdparty/icu4c/common/unicode/localematcher.h index 63a68b0b7f..0cd068ef32 100644 --- a/thirdparty/icu4c/common/unicode/localematcher.h +++ b/thirdparty/icu4c/common/unicode/localematcher.h @@ -91,8 +91,6 @@ enum ULocMatchDemotion { 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. @@ -108,20 +106,20 @@ typedef enum ULocMatchDemotion ULocMatchDemotion; * but not if it is merely a fallback. * * @see LocaleMatcher::Builder#setDirection(ULocMatchDirection) - * @draft ICU 67 + * @stable ICU 67 */ enum ULocMatchDirection { /** * Locale matching includes one-way matches such as Breton→French. (default) * - * @draft ICU 67 + * @stable 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 + * @stable ICU 67 */ ULOCMATCH_DIRECTION_ONLY_TWO_WAY }; @@ -129,8 +127,6 @@ enum ULocMatchDirection { typedef enum ULocMatchDirection ULocMatchDirection; #endif -#endif // U_FORCE_HIDE_DRAFT_API - struct UHashtable; U_NAMESPACE_BEGIN @@ -463,14 +459,13 @@ public: */ 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 + * @stable ICU 67 */ Builder &setDirection(ULocMatchDirection direction) { if (U_SUCCESS(errorCode_)) { @@ -478,7 +473,6 @@ public: } return *this; } -#endif // U_HIDE_DRAFT_API #ifndef U_HIDE_DRAFT_API /** @@ -704,7 +698,7 @@ private: LSR *lsrs; int32_t supportedLocalesLength; // These are in preference order: 1. Default locale 2. paradigm locales 3. others. - UHashtable *supportedLsrToIndex; // Map stores index+1 because 0 is "not found" + UHashtable *supportedLsrToIndex; // Map // 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; diff --git a/thirdparty/icu4c/common/unicode/locid.h b/thirdparty/icu4c/common/unicode/locid.h index ba858d702a..81f4685d65 100644 --- a/thirdparty/icu4c/common/unicode/locid.h +++ b/thirdparty/icu4c/common/unicode/locid.h @@ -571,15 +571,13 @@ public: */ 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 + * @stable ICU 67 * @see createCanonical */ void canonicalize(UErrorCode& status); -#endif // U_HIDE_DRAFT_API /** * Gets the list of keywords for the specified locale. diff --git a/thirdparty/icu4c/common/unicode/normalizer2.h b/thirdparty/icu4c/common/unicode/normalizer2.h index 5eb1d95caf..2d355250c2 100644 --- a/thirdparty/icu4c/common/unicode/normalizer2.h +++ b/thirdparty/icu4c/common/unicode/normalizer2.h @@ -225,10 +225,8 @@ public: * 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. + * Implemented completely for all built-in modes except for FCD. + * The base class implementation 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. @@ -381,11 +379,9 @@ public: * 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(). + * This works for all normalization modes. + * It is optimized for UTF-8 for all built-in modes except for FCD. + * The base class implementation converts to UTF-16 and calls isNormalized(). * * @param s UTF-8 input string * @param errorCode Standard ICU error code. Its input value must @@ -543,10 +539,8 @@ public: * 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. + * Implemented completely for most built-in modes except for FCD. + * The base class implementation 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. @@ -676,11 +670,9 @@ public: * 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(). + * This works for all normalization modes. + * It is optimized for UTF-8 for all built-in modes except for FCD. + * The base class implementation converts to UTF-16 and calls isNormalized(). * * @param s UTF-8 input string * @param errorCode Standard ICU error code. Its input value must diff --git a/thirdparty/icu4c/common/unicode/platform.h b/thirdparty/icu4c/common/unicode/platform.h index 2bb2f8b318..cb3a833fef 100644 --- a/thirdparty/icu4c/common/unicode/platform.h +++ b/thirdparty/icu4c/common/unicode/platform.h @@ -880,6 +880,6 @@ namespace std { #else # define U_CALLCONV_FPTR #endif -/* @} */ +/** @} */ #endif // _PLATFORM_H diff --git a/thirdparty/icu4c/common/unicode/stringpiece.h b/thirdparty/icu4c/common/unicode/stringpiece.h index 7d7d871e1f..8c96789e73 100644 --- a/thirdparty/icu4c/common/unicode/stringpiece.h +++ b/thirdparty/icu4c/common/unicode/stringpiece.h @@ -75,12 +75,11 @@ class U_COMMON_API StringPiece : public UMemory { * @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 + * @stable ICU 67 */ StringPiece(const char8_t* str) : StringPiece(reinterpret_cast(str)) {} #endif @@ -88,10 +87,9 @@ class U_COMMON_API StringPiece : public UMemory { * Constructs an empty StringPiece. * Needed for type disambiguation from multiple other overloads. * @param p nullptr - * @draft ICU 67 + * @stable ICU 67 */ StringPiece(std::nullptr_t p) : ptr_(p), length_(0) {} -#endif // U_HIDE_DRAFT_API /** * Constructs from a std::string. @@ -99,17 +97,15 @@ class U_COMMON_API StringPiece : public UMemory { */ StringPiece(const std::string& str) : ptr_(str.data()), length_(static_cast(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 + * @stable ICU 67 */ StringPiece(const std::u8string& str) : ptr_(reinterpret_cast(str.data())), length_(static_cast(str.size())) { } #endif -#endif // U_HIDE_DRAFT_API /** * Constructs from some other implementation of a string piece class, from any @@ -152,18 +148,16 @@ class U_COMMON_API StringPiece : public UMemory { * @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 + * @stable ICU 67 */ StringPiece(const char8_t* str, int32_t len) : StringPiece(reinterpret_cast(str), len) {} #endif -#endif // U_HIDE_DRAFT_API /** * Substring of another StringPiece. @@ -233,13 +227,12 @@ class U_COMMON_API StringPiece : public UMemory { */ 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 + * @stable ICU 67 */ inline void set(const char8_t* xdata, int32_t len) { set(reinterpret_cast(xdata), len); @@ -248,13 +241,12 @@ class U_COMMON_API StringPiece : public UMemory { /** * Resets the stringpiece to refer to new data. * @param str a pointer to a NUL-terminated string. - * @draft ICU 67 + * @stable ICU 67 */ inline void set(const char8_t* str) { set(reinterpret_cast(str)); } #endif -#endif // U_HIDE_DRAFT_API /** * Removes the first n string units. @@ -286,13 +278,12 @@ class U_COMMON_API StringPiece : public UMemory { } } -#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 + * @stable ICU 67 */ int32_t find(StringPiece needle, int32_t offset); @@ -301,10 +292,9 @@ class U_COMMON_API StringPiece : public UMemory { * 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 + * @stable ICU 67 */ int32_t compare(StringPiece other); -#endif // U_HIDE_DRAFT_API /** * Maximum integer, used as a default value for substring methods. diff --git a/thirdparty/icu4c/common/unicode/ubrk.h b/thirdparty/icu4c/common/unicode/ubrk.h index 37189a8598..1249b0b160 100644 --- a/thirdparty/icu4c/common/unicode/ubrk.h +++ b/thirdparty/icu4c/common/unicode/ubrk.h @@ -296,6 +296,8 @@ ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength, const UChar * text, int32_t textLength, UErrorCode * status); +#ifndef U_HIDE_DEPRECATED_API + /** * Thread safe cloning operation * @param bi iterator to be cloned @@ -312,7 +314,7 @@ ubrk_openBinaryRules(const uint8_t *binaryRules, int32_t rulesLength, * @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 + * @deprecated ICU 69 Use ubrk_clone() instead. */ U_CAPI UBreakIterator * U_EXPORT2 ubrk_safeClone( @@ -321,6 +323,23 @@ ubrk_safeClone( int32_t *pBufferSize, UErrorCode *status); +#endif /* U_HIDE_DEPRECATED_API */ + +#ifndef U_HIDE_DRAFT_API + +/** + * Thread safe cloning operation. + * @param bi iterator to be cloned + * @param status to indicate whether the operation went on smoothly or there were errors + * @return pointer to the new clone + * @draft ICU 69 + */ +U_CAPI UBreakIterator * U_EXPORT2 +ubrk_clone(const UBreakIterator *bi, + UErrorCode *status); + +#endif // U_HIDE_DRAFT_API + #ifndef U_HIDE_DEPRECATED_API /** diff --git a/thirdparty/icu4c/common/unicode/ucnv.h b/thirdparty/icu4c/common/unicode/ucnv.h index 58f271cfb5..5d784990f2 100644 --- a/thirdparty/icu4c/common/unicode/ucnv.h +++ b/thirdparty/icu4c/common/unicode/ucnv.h @@ -1699,10 +1699,10 @@ 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 + * all available converters contained 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 [0..ucnv_countAvaiable()]) + * @param n the index to a converter available on the system (in the range [0..ucnv_countAvailable()]) * @return a pointer a string (library owned), or NULL if the index is out of bounds. * @see ucnv_countAvailable * @stable ICU 2.0 diff --git a/thirdparty/icu4c/common/unicode/ucnvsel.h b/thirdparty/icu4c/common/unicode/ucnvsel.h index 5e0a71cf35..3d7d3327f7 100644 --- a/thirdparty/icu4c/common/unicode/ucnvsel.h +++ b/thirdparty/icu4c/common/unicode/ucnvsel.h @@ -45,11 +45,11 @@ * from the serialized form. */ +struct UConverterSelector; /** * @{ - * The selector data structure + * Typedef for selector data structure. */ -struct UConverterSelector; typedef struct UConverterSelector UConverterSelector; /** @} */ diff --git a/thirdparty/icu4c/common/unicode/unifilt.h b/thirdparty/icu4c/common/unicode/unifilt.h index 420e1a1905..7870b55939 100644 --- a/thirdparty/icu4c/common/unicode/unifilt.h +++ b/thirdparty/icu4c/common/unicode/unifilt.h @@ -40,8 +40,8 @@ U_NAMESPACE_BEGIN * * UnicodeFilter 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 + * Currently, filters are used in conjunction with classes like + * {@link Transliterator} to only process selected characters through a * transformation. * *

Note: UnicodeFilter currently stubs out two pure virtual methods diff --git a/thirdparty/icu4c/common/unicode/uniset.h b/thirdparty/icu4c/common/unicode/uniset.h index 50b6360f3a..8403c4026c 100644 --- a/thirdparty/icu4c/common/unicode/uniset.h +++ b/thirdparty/icu4c/common/unicode/uniset.h @@ -178,8 +178,6 @@ class RuleCharacterIterator; * Unicode property * * - *

Warning: you cannot add an empty string ("") to a UnicodeSet.

- * *

Formal syntax

* * \htmlonly
\endhtmlonly @@ -601,7 +599,7 @@ public: /** * Make this object represent the range `start - end`. - * If `end > start` then this object is set to an empty range. + * If `start > end` then this object is set to an empty range. * A frozen set will not be modified. * * @param start first character in the set, inclusive @@ -1077,7 +1075,7 @@ public: /** * 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 end > start + * the call leaves this set unchanged. If start > end * 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. @@ -1095,6 +1093,9 @@ public: * present. If this set already contains the specified character, * the call leaves this set unchanged. * A frozen set will not be modified. + * + * @param c the character (code point) + * @return this object, for chaining * @stable ICU 2.0 */ UnicodeSet& add(UChar32 c); @@ -1104,8 +1105,8 @@ public: * present. If this set already contains the multicharacter, * the call leaves this set unchanged. * Thus "ch" => {"ch"} - *
Warning: you cannot add an empty string ("") to a UnicodeSet. * A frozen set will not be modified. + * * @param s the source string * @return this object, for chaining * @stable ICU 2.4 @@ -1124,8 +1125,8 @@ public: 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. + * Adds each of the characters in this string to the set. Note: "ch" => {"c", "h"} + * If this set already contains 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 @@ -1135,7 +1136,6 @@ public: /** * 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 @@ -1145,7 +1145,6 @@ public: /** * 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 @@ -1155,7 +1154,6 @@ public: /** * 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 @@ -1165,7 +1163,7 @@ public: /** * Makes a set from a multicharacter string. Thus "ch" => {"ch"} - *
Warning: you cannot add an empty string ("") to a UnicodeSet. + * * @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. @@ -1185,15 +1183,13 @@ public: /** * Retain only the elements in this set that are contained in the - * specified range. If end > start then an empty range is + * specified range. If start > end 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. + * @param start first character, inclusive, of range + * @param end last character, inclusive, of range * @stable ICU 2.0 */ virtual UnicodeSet& retain(UChar32 start, UChar32 end); @@ -1202,14 +1198,31 @@ public: /** * Retain the specified character from this set if it is present. * A frozen set will not be modified. + * + * @param c the character (code point) + * @return this object, for chaining * @stable ICU 2.0 */ UnicodeSet& retain(UChar32 c); +#ifndef U_HIDE_DRAFT_API + /** + * Retains only the specified string from this set if it is present. + * Upon return this set will be empty if it did not contain s, or + * will only contain s if it did contain s. + * A frozen set will not be modified. + * + * @param s the source string + * @return this object, for chaining + * @draft ICU 69 + */ + UnicodeSet& retain(const UnicodeString &s); +#endif // U_HIDE_DRAFT_API + /** * Removes the specified range from this set if it is present. * The set will not contain the specified range once the call - * returns. If end > start then an empty range is + * returns. If start > end then an empty range is * removed, leaving the set unchanged. * A frozen set will not be modified. * @@ -1226,6 +1239,9 @@ public: * The set will not contain the specified range once the call * returns. * A frozen set will not be modified. + * + * @param c the character (code point) + * @return this object, for chaining * @stable ICU 2.0 */ UnicodeSet& remove(UChar32 c); @@ -1253,15 +1269,13 @@ public: /** * 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 end > start + * added if it is not in this set. If start > end * 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. + * @param start first character, inclusive, of range + * @param end last character, inclusive, of range * @stable ICU 2.0 */ virtual UnicodeSet& complement(UChar32 start, UChar32 end); @@ -1271,16 +1285,18 @@ public: * 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 the character (code point) + * @return this object, for chaining * @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. - *
Warning: you cannot add an empty string ("") to a UnicodeSet. + * The string 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 s the string to complement * @return this object, for chaining * @stable ICU 2.4 diff --git a/thirdparty/icu4c/common/unicode/unistr.h b/thirdparty/icu4c/common/unicode/unistr.h index 456389f265..85bd964951 100644 --- a/thirdparty/icu4c/common/unicode/unistr.h +++ b/thirdparty/icu4c/common/unicode/unistr.h @@ -44,9 +44,10 @@ struct UConverter; // unicode/ucnv.h #ifndef USTRING_H /** * \ingroup ustring_ustrlen + * @param s Pointer to sequence of UChars. + * @return Length of sequence. */ -U_CAPI int32_t U_EXPORT2 -u_strlen(const UChar *s); +U_CAPI int32_t U_EXPORT2 u_strlen(const UChar *s); #endif U_NAMESPACE_BEGIN @@ -2766,7 +2767,6 @@ public: * @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 */ @@ -3614,7 +3614,7 @@ private: // turn a bogus string into an empty one void unBogus(); - // implements assigment operator, copy constructor, and fastCopyFrom() + // implements assignment operator, copy constructor, and fastCopyFrom() UnicodeString ©From(const UnicodeString &src, UBool fastCopy=false); // Copies just the fields without memory management. diff --git a/thirdparty/icu4c/common/unicode/urename.h b/thirdparty/icu4c/common/unicode/urename.h index fe59fdd893..737f4b308e 100644 --- a/thirdparty/icu4c/common/unicode/urename.h +++ b/thirdparty/icu4c/common/unicode/urename.h @@ -482,6 +482,7 @@ #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_clone U_ICU_ENTRY_POINT_RENAME(ubrk_clone) #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) @@ -534,6 +535,7 @@ #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_getTimeZoneOffsetFromLocal U_ICU_ENTRY_POINT_RENAME(ucal_getTimeZoneOffsetFromLocal) #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) @@ -962,6 +964,7 @@ #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_containsKey U_ICU_ENTRY_POINT_RENAME(uhash_containsKey) #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) @@ -970,6 +973,7 @@ #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_getiAndFound U_ICU_ENTRY_POINT_RENAME(uhash_getiAndFound) #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) @@ -977,12 +981,15 @@ #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_icontainsKey U_ICU_ENTRY_POINT_RENAME(uhash_icontainsKey) #define uhash_iget U_ICU_ENTRY_POINT_RENAME(uhash_iget) #define uhash_igeti U_ICU_ENTRY_POINT_RENAME(uhash_igeti) +#define uhash_igetiAndFound U_ICU_ENTRY_POINT_RENAME(uhash_igetiAndFound) #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_iputiAllowZero U_ICU_ENTRY_POINT_RENAME(uhash_iputiAllowZero) #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) @@ -990,6 +997,7 @@ #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_putiAllowZero U_ICU_ENTRY_POINT_RENAME(uhash_putiAllowZero) #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) @@ -1150,6 +1158,8 @@ #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 umeas_getPrefixBase U_ICU_ENTRY_POINT_RENAME(umeas_getPrefixBase) +#define umeas_getPrefixPower U_ICU_ENTRY_POINT_RENAME(umeas_getPrefixPower) #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) @@ -1672,6 +1682,9 @@ #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_complementAllCodePoints U_ICU_ENTRY_POINT_RENAME(uset_complementAllCodePoints) +#define uset_complementRange U_ICU_ENTRY_POINT_RENAME(uset_complementRange) +#define uset_complementString U_ICU_ENTRY_POINT_RENAME(uset_complementString) #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) @@ -1695,12 +1708,15 @@ #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_removeAllCodePoints U_ICU_ENTRY_POINT_RENAME(uset_removeAllCodePoints) #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_retainAllCodePoints U_ICU_ENTRY_POINT_RENAME(uset_retainAllCodePoints) +#define uset_retainString U_ICU_ENTRY_POINT_RENAME(uset_retainString) #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) diff --git a/thirdparty/icu4c/common/unicode/uset.h b/thirdparty/icu4c/common/unicode/uset.h index 502ea8dc14..1d0daf9d09 100644 --- a/thirdparty/icu4c/common/unicode/uset.h +++ b/thirdparty/icu4c/common/unicode/uset.h @@ -582,8 +582,8 @@ 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. + * Adds each of the characters in this string to the set. Note: "ch" => {"c", "h"} + * If this set already contains 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 @@ -628,6 +628,20 @@ uset_removeRange(USet* set, UChar32 start, UChar32 end); U_CAPI void U_EXPORT2 uset_removeString(USet* set, const UChar* str, int32_t strLen); +#ifndef U_HIDE_DRAFT_API +/** + * Removes EACH of the characters in this string. Note: "ch" == {"c", "h"} + * A frozen set will not be modified. + * + * @param set the object to be modified + * @param str the string + * @param length the length of the string, or -1 if NUL-terminated + * @draft ICU 69 + */ +U_CAPI void U_EXPORT2 +uset_removeAllCodePoints(USet *set, const UChar *str, int32_t length); +#endif // U_HIDE_DRAFT_API + /** * Removes from this set all of its elements that are contained in the * specified set. This operation effectively modifies this @@ -650,15 +664,41 @@ uset_removeAll(USet* set, const USet* removeSet); * 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. + * @param start first character, inclusive, of range + * @param end last character, inclusive, of range * @stable ICU 3.2 */ U_CAPI void U_EXPORT2 uset_retain(USet* set, UChar32 start, UChar32 end); +#ifndef U_HIDE_DRAFT_API +/** + * Retains only the specified string from this set if it is present. + * Upon return this set will be empty if it did not contain s, or + * will only contain s if it did contain s. + * A frozen set will not be modified. + * + * @param set the object to be modified + * @param str the string + * @param length the length of the string, or -1 if NUL-terminated + * @draft ICU 69 + */ +U_CAPI void U_EXPORT2 +uset_retainString(USet *set, const UChar *str, int32_t length); + +/** + * Retains EACH of the characters in this string. Note: "ch" == {"c", "h"} + * A frozen set will not be modified. + * + * @param set the object to be modified + * @param str the string + * @param length the length of the string, or -1 if NUL-terminated + * @draft ICU 69 + */ +U_CAPI void U_EXPORT2 +uset_retainAllCodePoints(USet *set, const UChar *str, int32_t length); +#endif // U_HIDE_DRAFT_API + /** * Retains only the elements in this set that are contained in the * specified set. In other words, removes from this set all of @@ -696,6 +736,49 @@ uset_compact(USet* set); U_CAPI void U_EXPORT2 uset_complement(USet* set); +#ifndef U_HIDE_DRAFT_API +/** + * 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 start > end + * 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 set the object to be modified + * @param start first character, inclusive, of range + * @param end last character, inclusive, of range + * @draft ICU 69 + */ +U_CAPI void U_EXPORT2 +uset_complementRange(USet *set, UChar32 start, UChar32 end); + +/** + * Complements the specified string in this set. + * The string 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 object to be modified + * @param str the string + * @param length the length of the string, or -1 if NUL-terminated + * @draft ICU 69 + */ +U_CAPI void U_EXPORT2 +uset_complementString(USet *set, const UChar *str, int32_t length); + +/** + * Complements EACH of the characters in this string. Note: "ch" == {"c", "h"} + * A frozen set will not be modified. + * + * @param set the object to be modified + * @param str the string + * @param length the length of the string, or -1 if NUL-terminated + * @draft ICU 69 + */ +U_CAPI void U_EXPORT2 +uset_complementAllCodePoints(USet *set, const UChar *str, int32_t length); +#endif // U_HIDE_DRAFT_API + /** * Complements in this set all elements contained in the specified * set. Any character in the other set will be removed if it is diff --git a/thirdparty/icu4c/common/unicode/ushape.h b/thirdparty/icu4c/common/unicode/ushape.h index fed4869abd..14371edc8f 100644 --- a/thirdparty/icu4c/common/unicode/ushape.h +++ b/thirdparty/icu4c/common/unicode/ushape.h @@ -323,7 +323,7 @@ u_shapeArabic(const UChar *source, int32_t sourceLength, #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. + * their unshaped correspondents in range 0+06xx, before shaping. * @stable ICU 3.6 */ #define U_SHAPE_PRESERVE_PRESENTATION_NOOP 0 diff --git a/thirdparty/icu4c/common/unicode/utrace.h b/thirdparty/icu4c/common/unicode/utrace.h index 28c313c582..677486f473 100644 --- a/thirdparty/icu4c/common/unicode/utrace.h +++ b/thirdparty/icu4c/common/unicode/utrace.h @@ -173,24 +173,23 @@ typedef enum UTraceFunctionNumber { UTRACE_RES_DATA_LIMIT, #endif // U_HIDE_INTERNAL_API -#ifndef U_HIDE_DRAFT_API /** * The lowest break iterator location. - * @draft ICU 67 + * @stable ICU 67 */ UTRACE_UBRK_START=0x4000, /** * Indicates that a character instance of break iterator was created. * - * @draft ICU 67 + * @stable ICU 67 */ UTRACE_UBRK_CREATE_CHARACTER = UTRACE_UBRK_START, /** * Indicates that a word instance of break iterator was created. * - * @draft ICU 67 + * @stable ICU 67 */ UTRACE_UBRK_CREATE_WORD, @@ -200,21 +199,21 @@ typedef enum UTraceFunctionNumber { * Provides one C-style string to UTraceData: the lb value ("", * "loose", "strict", or "normal"). * - * @draft ICU 67 + * @stable ICU 67 */ UTRACE_UBRK_CREATE_LINE, /** * Indicates that a sentence instance of break iterator was created. * - * @draft ICU 67 + * @stable ICU 67 */ UTRACE_UBRK_CREATE_SENTENCE, /** * Indicates that a title instance of break iterator was created. * - * @draft ICU 67 + * @stable ICU 67 */ UTRACE_UBRK_CREATE_TITLE, @@ -224,12 +223,10 @@ typedef enum UTraceFunctionNumber { * 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 + * @stable 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. diff --git a/thirdparty/icu4c/common/unicode/uvernum.h b/thirdparty/icu4c/common/unicode/uvernum.h index a46481a3fe..b09d4943c1 100644 --- a/thirdparty/icu4c/common/unicode/uvernum.h +++ b/thirdparty/icu4c/common/unicode/uvernum.h @@ -60,13 +60,13 @@ * This value will change in the subsequent releases of ICU * @stable ICU 2.4 */ -#define U_ICU_VERSION_MAJOR_NUM 68 +#define U_ICU_VERSION_MAJOR_NUM 69 /** 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 2 +#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 @@ -86,7 +86,7 @@ * This value will change in the subsequent releases of ICU * @stable ICU 2.6 */ -#define U_ICU_VERSION_SUFFIX _68 +#define U_ICU_VERSION_SUFFIX _69 /** * \def U_DEF2_ICU_ENTRY_POINT_RENAME @@ -139,7 +139,7 @@ * This value will change in the subsequent releases of ICU * @stable ICU 2.4 */ -#define U_ICU_VERSION "68.2" +#define U_ICU_VERSION "69.1" /** * The current ICU library major version number as a string, for library name suffixes. @@ -152,13 +152,13 @@ * * @stable ICU 2.6 */ -#define U_ICU_VERSION_SHORT "68" +#define U_ICU_VERSION_SHORT "69" #ifndef U_HIDE_INTERNAL_API /** Data version in ICU4C. * @internal ICU 4.4 Internal Use Only **/ -#define U_ICU_DATA_VERSION "68.2" +#define U_ICU_DATA_VERSION "69.1" #endif /* U_HIDE_INTERNAL_API */ /*=========================================================================== -- cgit v1.2.3