1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 2011, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: uniset_closure.cpp
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
* created on: 2011may30
* created by: Markus W. Scherer
*
* UnicodeSet::closeOver() and related methods moved here from uniset_props.cpp
* to simplify dependencies.
* In particular, this depends on the BreakIterator, but the BreakIterator
* code also builds UnicodeSets from patterns and needs uniset_props.
*/
#include "unicode/brkiter.h"
#include "unicode/locid.h"
#include "unicode/parsepos.h"
#include "unicode/uniset.h"
#include "cmemory.h"
#include "ruleiter.h"
#include "ucase.h"
#include "util.h"
#include "uvector.h"
U_NAMESPACE_BEGIN
// TODO memory debugging provided inside uniset.cpp
// could be made available here but probably obsolete with use of modern
// memory leak checker tools
#define _dbgct(me)
//----------------------------------------------------------------
// Constructors &c
//----------------------------------------------------------------
UnicodeSet::UnicodeSet(const UnicodeString& pattern,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status) {
applyPattern(pattern, options, symbols, status);
_dbgct(this);
}
UnicodeSet::UnicodeSet(const UnicodeString& pattern, ParsePosition& pos,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status) {
applyPattern(pattern, pos, options, symbols, status);
_dbgct(this);
}
//----------------------------------------------------------------
// Public API
//----------------------------------------------------------------
UnicodeSet& UnicodeSet::applyPattern(const UnicodeString& pattern,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status) {
ParsePosition pos(0);
applyPattern(pattern, pos, options, symbols, status);
if (U_FAILURE(status)) return *this;
int32_t i = pos.getIndex();
if (options & USET_IGNORE_SPACE) {
// Skip over trailing whitespace
ICU_Utility::skipWhitespace(pattern, i, true);
}
if (i != pattern.length()) {
status = U_ILLEGAL_ARGUMENT_ERROR;
}
return *this;
}
UnicodeSet& UnicodeSet::applyPattern(const UnicodeString& pattern,
ParsePosition& pos,
uint32_t options,
const SymbolTable* symbols,
UErrorCode& status) {
if (U_FAILURE(status)) {
return *this;
}
if (isFrozen()) {
status = U_NO_WRITE_PERMISSION;
return *this;
}
// Need to build the pattern in a temporary string because
// _applyPattern calls add() etc., which set pat to empty.
UnicodeString rebuiltPat;
RuleCharacterIterator chars(pattern, symbols, pos);
applyPattern(chars, symbols, rebuiltPat, options, &UnicodeSet::closeOver, 0, status);
if (U_FAILURE(status)) return *this;
if (chars.inVariable()) {
// syntaxError(chars, "Extra chars in variable value");
status = U_MALFORMED_SET;
return *this;
}
setPattern(rebuiltPat);
return *this;
}
// USetAdder implementation
// Does not use uset.h to reduce code dependencies
static void U_CALLCONV
_set_add(USet *set, UChar32 c) {
((UnicodeSet *)set)->add(c);
}
static void U_CALLCONV
_set_addRange(USet *set, UChar32 start, UChar32 end) {
((UnicodeSet *)set)->add(start, end);
}
static void U_CALLCONV
_set_addString(USet *set, const UChar *str, int32_t length) {
((UnicodeSet *)set)->add(UnicodeString((UBool)(length<0), str, length));
}
//----------------------------------------------------------------
// Case folding API
//----------------------------------------------------------------
// add the result of a full case mapping to the set
// use str as a temporary string to avoid constructing one
static inline void
addCaseMapping(UnicodeSet &set, int32_t result, const UChar *full, UnicodeString &str) {
if(result >= 0) {
if(result > UCASE_MAX_STRING_LENGTH) {
// add a single-code point case mapping
set.add(result);
} else {
// add a string case mapping from full with length result
str.setTo((UBool)false, full, result);
set.add(str);
}
}
// result < 0: the code point mapped to itself, no need to add it
// see ucase.h
}
UnicodeSet& UnicodeSet::closeOver(int32_t attribute) {
if (isFrozen() || isBogus()) {
return *this;
}
if (attribute & (USET_CASE_INSENSITIVE | USET_ADD_CASE_MAPPINGS)) {
{
UnicodeSet foldSet(*this);
UnicodeString str;
USetAdder sa = {
foldSet.toUSet(),
_set_add,
_set_addRange,
_set_addString,
NULL, // don't need remove()
NULL // don't need removeRange()
};
// start with input set to guarantee inclusion
// USET_CASE: remove strings because the strings will actually be reduced (folded);
// therefore, start with no strings and add only those needed
if ((attribute & USET_CASE_INSENSITIVE) && foldSet.hasStrings()) {
foldSet.strings->removeAllElements();
}
int32_t n = getRangeCount();
UChar32 result;
const UChar *full;
for (int32_t i=0; i<n; ++i) {
UChar32 start = getRangeStart(i);
UChar32 end = getRangeEnd(i);
if (attribute & USET_CASE_INSENSITIVE) {
// full case closure
for (UChar32 cp=start; cp<=end; ++cp) {
ucase_addCaseClosure(cp, &sa);
}
} else {
// add case mappings
// (does not add long s for regular s, or Kelvin for k, for example)
for (UChar32 cp=start; cp<=end; ++cp) {
result = ucase_toFullLower(cp, NULL, NULL, &full, UCASE_LOC_ROOT);
addCaseMapping(foldSet, result, full, str);
result = ucase_toFullTitle(cp, NULL, NULL, &full, UCASE_LOC_ROOT);
addCaseMapping(foldSet, result, full, str);
result = ucase_toFullUpper(cp, NULL, NULL, &full, UCASE_LOC_ROOT);
addCaseMapping(foldSet, result, full, str);
result = ucase_toFullFolding(cp, &full, 0);
addCaseMapping(foldSet, result, full, str);
}
}
}
if (hasStrings()) {
if (attribute & USET_CASE_INSENSITIVE) {
for (int32_t j=0; j<strings->size(); ++j) {
str = *(const UnicodeString *) strings->elementAt(j);
str.foldCase();
if(!ucase_addStringCaseClosure(str.getBuffer(), str.length(), &sa)) {
foldSet.add(str); // does not map to code points: add the folded string itself
}
}
} else {
Locale root("");
#if !UCONFIG_NO_BREAK_ITERATION
UErrorCode status = U_ZERO_ERROR;
BreakIterator *bi = BreakIterator::createWordInstance(root, status);
if (U_SUCCESS(status)) {
#endif
const UnicodeString *pStr;
for (int32_t j=0; j<strings->size(); ++j) {
pStr = (const UnicodeString *) strings->elementAt(j);
(str = *pStr).toLower(root);
foldSet.add(str);
#if !UCONFIG_NO_BREAK_ITERATION
(str = *pStr).toTitle(bi, root);
foldSet.add(str);
#endif
(str = *pStr).toUpper(root);
foldSet.add(str);
(str = *pStr).foldCase();
foldSet.add(str);
}
#if !UCONFIG_NO_BREAK_ITERATION
}
delete bi;
#endif
}
}
*this = foldSet;
}
}
return *this;
}
U_NAMESPACE_END
|