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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
|
// © 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: loclikely.cpp
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
* created on: 2010feb25
* created by: Markus W. Scherer
*
* Code for likely and minimized locale subtags, separated out from other .cpp files
* that then do not depend on resource bundle code and likely-subtags data.
*/
#include <utility>
#include "unicode/bytestream.h"
#include "unicode/utypes.h"
#include "unicode/locid.h"
#include "unicode/putil.h"
#include "unicode/uchar.h"
#include "unicode/uloc.h"
#include "unicode/ures.h"
#include "unicode/uscript.h"
#include "bytesinkutil.h"
#include "charstr.h"
#include "cmemory.h"
#include "cstring.h"
#include "loclikelysubtags.h"
#include "ulocimp.h"
namespace {
/**
* Create a tag string from the supplied parameters. The lang, script and region
* parameters may be nullptr pointers. If they are, their corresponding length parameters
* must be less than or equal to 0.
*
* If an illegal argument is provided, the function returns the error
* U_ILLEGAL_ARGUMENT_ERROR.
*
* @param lang The language tag to use.
* @param langLength The length of the language tag.
* @param script The script tag to use.
* @param scriptLength The length of the script tag.
* @param region The region tag to use.
* @param regionLength The length of the region tag.
* @param variant The region tag to use.
* @param variantLength The length of the region tag.
* @param trailing Any trailing data to append to the new tag.
* @param trailingLength The length of the trailing data.
* @param sink The output sink receiving the tag string.
* @param err A pointer to a UErrorCode for error reporting.
**/
void U_CALLCONV
createTagStringWithAlternates(
const char* lang,
int32_t langLength,
const char* script,
int32_t scriptLength,
const char* region,
int32_t regionLength,
const char* variant,
int32_t variantLength,
const char* trailing,
int32_t trailingLength,
icu::ByteSink& sink,
UErrorCode& err) {
if (U_FAILURE(err)) {
return;
}
if (langLength >= ULOC_LANG_CAPACITY ||
scriptLength >= ULOC_SCRIPT_CAPACITY ||
regionLength >= ULOC_COUNTRY_CAPACITY) {
err = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
if (langLength > 0) {
sink.Append(lang, langLength);
}
if (scriptLength > 0) {
sink.Append("_", 1);
sink.Append(script, scriptLength);
}
if (regionLength > 0) {
sink.Append("_", 1);
sink.Append(region, regionLength);
}
if (variantLength > 0) {
if (regionLength == 0) {
/* extra separator is required */
sink.Append("_", 1);
}
sink.Append("_", 1);
sink.Append(variant, variantLength);
}
if (trailingLength > 0) {
/*
* Copy the trailing data into the supplied buffer.
*/
sink.Append(trailing, trailingLength);
}
}
bool CHECK_TRAILING_VARIANT_SIZE(const char* variant, int32_t variantLength) {
int32_t count = 0;
for (int32_t i = 0; i < variantLength; i++) {
if (_isIDSeparator(variant[i])) {
count = 0;
} else if (count == 8) {
return false;
} else {
count++;
}
}
return true;
}
void
_uloc_addLikelySubtags(const char* localeID,
icu::ByteSink& sink,
UErrorCode& err) {
if (U_FAILURE(err)) {
return;
}
if (localeID == nullptr) {
err = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
icu::CharString lang;
icu::CharString script;
icu::CharString region;
icu::CharString variant;
const char* trailing = nullptr;
ulocimp_getSubtags(localeID, &lang, &script, ®ion, &variant, &trailing, err);
if (U_FAILURE(err)) {
return;
}
if (!CHECK_TRAILING_VARIANT_SIZE(variant.data(), variant.length())) {
err = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
if (lang.length() == 4) {
if (script.isEmpty()) {
script = std::move(lang);
lang.clear();
} else {
err = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
} else if (lang.length() > 8) {
err = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
int32_t trailingLength = (int32_t)uprv_strlen(trailing);
const icu::LikelySubtags* likelySubtags = icu::LikelySubtags::getSingleton(err);
if (U_FAILURE(err)) {
return;
}
// We need to keep l on the stack because lsr may point into internal
// memory of l.
icu::Locale l = icu::Locale::createFromName(localeID);
if (l.isBogus()) {
err = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
icu::LSR lsr = likelySubtags->makeMaximizedLsrFrom(l, true, err);
if (U_FAILURE(err)) {
return;
}
const char* language = lsr.language;
if (uprv_strcmp(language, "und") == 0) {
language = "";
}
createTagStringWithAlternates(
language,
(int32_t)uprv_strlen(language),
lsr.script,
(int32_t)uprv_strlen(lsr.script),
lsr.region,
(int32_t)uprv_strlen(lsr.region),
variant.data(),
variant.length(),
trailing,
trailingLength,
sink,
err);
}
void
_uloc_minimizeSubtags(const char* localeID,
icu::ByteSink& sink,
bool favorScript,
UErrorCode& err) {
if (U_FAILURE(err)) {
return;
}
if (localeID == nullptr) {
err = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
icu::CharString lang;
icu::CharString script;
icu::CharString region;
icu::CharString variant;
const char* trailing = nullptr;
ulocimp_getSubtags(localeID, &lang, &script, ®ion, &variant, &trailing, err);
if (U_FAILURE(err)) {
return;
}
if (!CHECK_TRAILING_VARIANT_SIZE(variant.data(), variant.length())) {
err = U_ILLEGAL_ARGUMENT_ERROR;
return;
}
int32_t trailingLength = (int32_t)uprv_strlen(trailing);
const icu::LikelySubtags* likelySubtags = icu::LikelySubtags::getSingleton(err);
if (U_FAILURE(err)) {
return;
}
icu::LSR lsr = likelySubtags->minimizeSubtags(
lang.toStringPiece(),
script.toStringPiece(),
region.toStringPiece(),
favorScript,
err);
if (U_FAILURE(err)) {
return;
}
const char* language = lsr.language;
if (uprv_strcmp(language, "und") == 0) {
language = "";
}
createTagStringWithAlternates(
language,
(int32_t)uprv_strlen(language),
lsr.script,
(int32_t)uprv_strlen(lsr.script),
lsr.region,
(int32_t)uprv_strlen(lsr.region),
variant.data(),
variant.length(),
trailing,
trailingLength,
sink,
err);
}
} // namespace
U_CAPI int32_t U_EXPORT2
uloc_addLikelySubtags(const char* localeID,
char* maximizedLocaleID,
int32_t maximizedLocaleIDCapacity,
UErrorCode* status) {
return icu::ByteSinkUtil::viaByteSinkToTerminatedChars(
maximizedLocaleID, maximizedLocaleIDCapacity,
[&](icu::ByteSink& sink, UErrorCode& status) {
ulocimp_addLikelySubtags(localeID, sink, status);
},
*status);
}
U_EXPORT icu::CharString
ulocimp_addLikelySubtags(const char* localeID,
UErrorCode& status) {
return icu::ByteSinkUtil::viaByteSinkToCharString(
[&](icu::ByteSink& sink, UErrorCode& status) {
ulocimp_addLikelySubtags(localeID, sink, status);
},
status);
}
U_EXPORT void
ulocimp_addLikelySubtags(const char* localeID,
icu::ByteSink& sink,
UErrorCode& status) {
if (U_FAILURE(status)) { return; }
icu::CharString localeBuffer = ulocimp_canonicalize(localeID, status);
_uloc_addLikelySubtags(localeBuffer.data(), sink, status);
}
U_CAPI int32_t U_EXPORT2
uloc_minimizeSubtags(const char* localeID,
char* minimizedLocaleID,
int32_t minimizedLocaleIDCapacity,
UErrorCode* status) {
return icu::ByteSinkUtil::viaByteSinkToTerminatedChars(
minimizedLocaleID, minimizedLocaleIDCapacity,
[&](icu::ByteSink& sink, UErrorCode& status) {
ulocimp_minimizeSubtags(localeID, sink, false, status);
},
*status);
}
U_EXPORT icu::CharString
ulocimp_minimizeSubtags(const char* localeID,
bool favorScript,
UErrorCode& status) {
return icu::ByteSinkUtil::viaByteSinkToCharString(
[&](icu::ByteSink& sink, UErrorCode& status) {
ulocimp_minimizeSubtags(localeID, sink, favorScript, status);
},
status);
}
U_EXPORT void
ulocimp_minimizeSubtags(const char* localeID,
icu::ByteSink& sink,
bool favorScript,
UErrorCode& status) {
if (U_FAILURE(status)) { return; }
icu::CharString localeBuffer = ulocimp_canonicalize(localeID, status);
_uloc_minimizeSubtags(localeBuffer.data(), sink, favorScript, status);
}
// Pairs of (language subtag, + or -) for finding out fast if common languages
// are LTR (minus) or RTL (plus).
static const char LANG_DIR_STRING[] =
"root-en-es-pt-zh-ja-ko-de-fr-it-ar+he+fa+ru-nl-pl-th-tr-";
// Implemented here because this calls ulocimp_addLikelySubtags().
U_CAPI UBool U_EXPORT2
uloc_isRightToLeft(const char *locale) {
UErrorCode errorCode = U_ZERO_ERROR;
icu::CharString lang;
icu::CharString script;
ulocimp_getSubtags(locale, &lang, &script, nullptr, nullptr, nullptr, errorCode);
if (U_FAILURE(errorCode) || script.isEmpty()) {
// Fastpath: We know the likely scripts and their writing direction
// for some common languages.
if (!lang.isEmpty()) {
const char* langPtr = uprv_strstr(LANG_DIR_STRING, lang.data());
if (langPtr != nullptr) {
switch (langPtr[lang.length()]) {
case '-': return false;
case '+': return true;
default: break; // partial match of a longer code
}
}
}
// Otherwise, find the likely script.
errorCode = U_ZERO_ERROR;
icu::CharString likely = ulocimp_addLikelySubtags(locale, errorCode);
if (U_FAILURE(errorCode)) {
return false;
}
ulocimp_getSubtags(likely.data(), nullptr, &script, nullptr, nullptr, nullptr, errorCode);
if (U_FAILURE(errorCode) || script.isEmpty()) {
return false;
}
}
UScriptCode scriptCode = (UScriptCode)u_getPropertyValueEnum(UCHAR_SCRIPT, script.data());
return uscript_isRightToLeft(scriptCode);
}
U_NAMESPACE_BEGIN
UBool
Locale::isRightToLeft() const {
return uloc_isRightToLeft(getBaseName());
}
U_NAMESPACE_END
namespace {
icu::CharString
GetRegionFromKey(const char* localeID, const char* key, UErrorCode& status) {
icu::CharString result;
// First check for keyword value
icu::CharString kw = ulocimp_getKeywordValue(localeID, key, status);
int32_t len = kw.length();
if (U_SUCCESS(status) && len >= 3 && len <= 7) {
// chop off the subdivision code (which will generally be "zzzz" anyway)
const char* const data = kw.data();
if (uprv_isASCIILetter(data[0])) {
result.append(uprv_toupper(data[0]), status);
result.append(uprv_toupper(data[1]), status);
} else {
// assume three-digit region code
result.append(data, 3, status);
}
}
return result;
}
} // namespace
U_EXPORT icu::CharString
ulocimp_getRegionForSupplementalData(const char *localeID, bool inferRegion,
UErrorCode& status) {
if (U_FAILURE(status)) {
return {};
}
icu::CharString rgBuf = GetRegionFromKey(localeID, "rg", status);
if (U_SUCCESS(status) && rgBuf.isEmpty()) {
// No valid rg keyword value, try for unicode_region_subtag
rgBuf = ulocimp_getRegion(localeID, status);
if (U_SUCCESS(status) && rgBuf.isEmpty() && inferRegion) {
// Second check for sd keyword value
rgBuf = GetRegionFromKey(localeID, "sd", status);
if (U_SUCCESS(status) && rgBuf.isEmpty()) {
// no unicode_region_subtag but inferRegion true, try likely subtags
UErrorCode rgStatus = U_ZERO_ERROR;
icu::CharString locBuf = ulocimp_addLikelySubtags(localeID, rgStatus);
if (U_SUCCESS(rgStatus)) {
rgBuf = ulocimp_getRegion(locBuf.data(), status);
}
}
}
}
return rgBuf;
}
|