1 /*
2 **********************************************************************
3 * Copyright (C) 1996-2014, International Business Machines
4 * Corporation and others. All Rights Reserved.
5 **********************************************************************
6 *
7 * Provides functionality for mapping between
8 * LCID and Posix IDs or ICU locale to codepage
9 *
10 * Note: All classes and code in this file are
11 * intended for internal use only.
12 *
13 * Methods of interest:
14 * unsigned long convertToLCID(const char*);
15 * const char* convertToPosix(unsigned long);
16 *
17 * Kathleen Wilson, 4/30/96
18 *
19 * Date Name Description
20 * 3/11/97 aliu Fixed off-by-one bug in assignment operator. Added
21 * setId() method and safety check against
22 * MAX_ID_LENGTH.
23 * 04/23/99 stephen Added C wrapper for convertToPosix.
24 * 09/18/00 george Removed the memory leaks.
25 * 08/23/01 george Convert to C
26 */
27
28 #include "locmap.h"
29 #include "cstring.h"
30 #include "cmemory.h"
31
32 #if U_PLATFORM == U_PF_WINDOWS && defined(_MSC_VER) && (_MSC_VER >= 1500)
33 /*
34 * TODO: It seems like we should widen this to
35 * either U_PLATFORM_USES_ONLY_WIN32_API (includes MinGW)
36 * or U_PLATFORM_HAS_WIN32_API (includes MinGW and Cygwin)
37 * but those use gcc and won't have defined(_MSC_VER).
38 * We might need to #include some Windows header and test for some version macro from there.
39 * Or call some Windows function and see what it returns.
40 */
41 #define USE_WINDOWS_LOCALE_API
42 #endif
43
44 #ifdef USE_WINDOWS_LOCALE_API
45 #include <windows.h>
46 #include <winnls.h>
47 #endif
48
49 /*
50 * Note:
51 * The mapping from Win32 locale ID numbers to POSIX locale strings should
52 * be the faster one.
53 *
54 * Many LCID values come from winnt.h
55 * Some also come from http://www.microsoft.com/globaldev/reference/lcid-all.mspx
56 */
57
58 /*
59 ////////////////////////////////////////////////
60 //
61 // Internal Classes for LCID <--> POSIX Mapping
62 //
63 /////////////////////////////////////////////////
64 */
65
66 typedef struct ILcidPosixElement
67 {
68 const uint32_t hostID;
69 const char * const posixID;
70 } ILcidPosixElement;
71
72 typedef struct ILcidPosixMap
73 {
74 const uint32_t numRegions;
75 const struct ILcidPosixElement* const regionMaps;
76 } ILcidPosixMap;
77
78
79 /*
80 /////////////////////////////////////////////////
81 //
82 // Easy macros to make the LCID <--> POSIX Mapping
83 //
84 /////////////////////////////////////////////////
85 */
86
87 /**
88 * The standard one language/one country mapping for LCID.
89 * The first element must be the language, and the following
90 * elements are the language with the country.
91 * @param hostID LCID in host format such as 0x044d
92 * @param languageID posix ID of just the language such as 'de'
93 * @param posixID posix ID of the language_TERRITORY such as 'de_CH'
94 */
95 #define ILCID_POSIX_ELEMENT_ARRAY(hostID, languageID, posixID) \
96 static const ILcidPosixElement locmap_ ## languageID [] = { \
97 {LANGUAGE_LCID(hostID), #languageID}, /* parent locale */ \
98 {hostID, #posixID}, \
99 };
100
101 /**
102 * Define a subtable by ID
103 * @param id the POSIX ID, either a language or language_TERRITORY
104 */
105 #define ILCID_POSIX_SUBTABLE(id) \
106 static const ILcidPosixElement locmap_ ## id [] =
107
108
109 /**
110 * Create the map for the posixID. This macro supposes that the language string
111 * name is the same as the global variable name, and that the first element
112 * in the ILcidPosixElement is just the language.
113 * @param _posixID the full POSIX ID for this entry.
114 */
115 #define ILCID_POSIX_MAP(_posixID) \
116 {sizeof(locmap_ ## _posixID)/sizeof(ILcidPosixElement), locmap_ ## _posixID}
117
118 /*
119 ////////////////////////////////////////////
120 //
121 // Create the table of LCID to POSIX Mapping
122 // None of it should be dynamically created.
123 //
124 // Keep static locale variables inside the function so that
125 // it can be created properly during static init.
126 //
127 // Note: This table should be updated periodically. Check the National Lanaguage Support API Reference Website.
128 // Microsoft is moving away from LCID in favor of locale name as of Vista. This table needs to be
129 // maintained for support of older Windows version.
130 // Update: Windows 7 (091130)
131 //
132 // Note: Microsoft assign a different LCID if a locale has a sorting variant. POSIX IDs below may contain
133 // @collation=XXX, but no other keywords are allowed (at least for now). When uprv_convertToLCID() is
134 // called from uloc_getLCID(), keywords other than collation are already removed. If we really need
135 // to support other keywords in this mapping data, we must update the implementation.
136 ////////////////////////////////////////////
137 */
138
139 ILCID_POSIX_ELEMENT_ARRAY(0x0436, af, af_ZA)
140
ILCID_POSIX_SUBTABLE(ar)141 ILCID_POSIX_SUBTABLE(ar) {
142 {0x01, "ar"},
143 {0x3801, "ar_AE"},
144 {0x3c01, "ar_BH"},
145 {0x1401, "ar_DZ"},
146 {0x0c01, "ar_EG"},
147 {0x0801, "ar_IQ"},
148 {0x2c01, "ar_JO"},
149 {0x3401, "ar_KW"},
150 {0x3001, "ar_LB"},
151 {0x1001, "ar_LY"},
152 {0x1801, "ar_MA"},
153 {0x1801, "ar_MO"},
154 {0x2001, "ar_OM"},
155 {0x4001, "ar_QA"},
156 {0x0401, "ar_SA"},
157 {0x2801, "ar_SY"},
158 {0x1c01, "ar_TN"},
159 {0x2401, "ar_YE"}
160 };
161
162 ILCID_POSIX_ELEMENT_ARRAY(0x044d, as, as_IN)
163 ILCID_POSIX_ELEMENT_ARRAY(0x045e, am, am_ET)
164 ILCID_POSIX_ELEMENT_ARRAY(0x047a, arn,arn_CL)
165
ILCID_POSIX_SUBTABLE(az)166 ILCID_POSIX_SUBTABLE(az) {
167 {0x2c, "az"},
168 {0x082c, "az_Cyrl_AZ"}, /* Cyrillic based */
169 {0x742c, "az_Cyrl"}, /* Cyrillic based */
170 {0x042c, "az_Latn_AZ"}, /* Latin based */
171 {0x782c, "az_Latn"}, /* Latin based */
172 {0x042c, "az_AZ"} /* Latin based */
173 };
174
175 ILCID_POSIX_ELEMENT_ARRAY(0x046d, ba, ba_RU)
176 ILCID_POSIX_ELEMENT_ARRAY(0x0423, be, be_BY)
177
178 /*ILCID_POSIX_SUBTABLE(ber) {
179 {0x5f, "ber"},
180 {0x045f, "ber_Arab_DZ"},
181 {0x045f, "ber_Arab"},
182 {0x085f, "ber_Latn_DZ"},
183 {0x085f, "ber_Latn"}
184 };*/
185
186 ILCID_POSIX_ELEMENT_ARRAY(0x0402, bg, bg_BG)
187
188 ILCID_POSIX_ELEMENT_ARRAY(0x0466, bin, bin_NG)
189
ILCID_POSIX_SUBTABLE(bn)190 ILCID_POSIX_SUBTABLE(bn) {
191 {0x45, "bn"},
192 {0x0845, "bn_BD"},
193 {0x0445, "bn_IN"}
194 };
195
ILCID_POSIX_SUBTABLE(bo)196 ILCID_POSIX_SUBTABLE(bo) {
197 {0x51, "bo"},
198 {0x0851, "bo_BT"},
199 {0x0451, "bo_CN"}
200 };
201
202 ILCID_POSIX_ELEMENT_ARRAY(0x047e, br, br_FR)
203
ILCID_POSIX_SUBTABLE(ca)204 ILCID_POSIX_SUBTABLE(ca) {
205 {0x03, "ca"},
206 {0x0403, "ca_ES"},
207 {0x0803, "ca_ES_VALENCIA"}
208 };
209
210 ILCID_POSIX_ELEMENT_ARRAY(0x0483, co, co_FR)
211 ILCID_POSIX_ELEMENT_ARRAY(0x045c, chr,chr_US)
212
ILCID_POSIX_SUBTABLE(ckb)213 ILCID_POSIX_SUBTABLE(ckb) {
214 {0x92, "ckb"},
215 {0x92, "ku"},
216 {0x7c92, "ckb_Arab"},
217 {0x7c92, "ku_Arab"},
218 {0x0492, "ckb_Arab_IQ"},
219 {0x0492, "ku_Arab_IQ"}
220 };
221
222 /* Declared as cs_CZ to get around compiler errors on z/OS, which defines cs as a function */
223 ILCID_POSIX_ELEMENT_ARRAY(0x0405, cs, cs_CZ)
224
225 ILCID_POSIX_ELEMENT_ARRAY(0x0452, cy, cy_GB)
226 ILCID_POSIX_ELEMENT_ARRAY(0x0406, da, da_DK)
227
ILCID_POSIX_SUBTABLE(de)228 ILCID_POSIX_SUBTABLE(de) {
229 {0x07, "de"},
230 {0x0c07, "de_AT"},
231 {0x0807, "de_CH"},
232 {0x0407, "de_DE"},
233 {0x1407, "de_LI"},
234 {0x1007, "de_LU"},
235 {0x10407,"de_DE@collation=phonebook"}, /*This is really de_DE_PHONEBOOK on Windows*/
236 {0x10407,"de@collation=phonebook"} /*This is really de_DE_PHONEBOOK on Windows*/
237 };
238
239 ILCID_POSIX_ELEMENT_ARRAY(0x0465, dv, dv_MV)
240 ILCID_POSIX_ELEMENT_ARRAY(0x0408, el, el_GR)
241
ILCID_POSIX_SUBTABLE(en)242 ILCID_POSIX_SUBTABLE(en) {
243 {0x09, "en"},
244 {0x0c09, "en_AU"},
245 {0x2809, "en_BZ"},
246 {0x1009, "en_CA"},
247 {0x0809, "en_GB"},
248 {0x3c09, "en_HK"},
249 {0x3809, "en_ID"},
250 {0x1809, "en_IE"},
251 {0x4009, "en_IN"},
252 {0x2009, "en_JM"},
253 {0x4409, "en_MY"},
254 {0x1409, "en_NZ"},
255 {0x3409, "en_PH"},
256 {0x4809, "en_SG"},
257 {0x2C09, "en_TT"},
258 {0x0409, "en_US"},
259 {0x007f, "en_US_POSIX"}, /* duplicate for roundtripping */
260 {0x2409, "en_VI"}, /* Virgin Islands AKA Caribbean Islands (en_CB). */
261 {0x1c09, "en_ZA"},
262 {0x3009, "en_ZW"},
263 {0x2409, "en_029"},
264 {0x0409, "en_AS"}, /* Alias for en_US. Leave last. */
265 {0x0409, "en_GU"}, /* Alias for en_US. Leave last. */
266 {0x0409, "en_MH"}, /* Alias for en_US. Leave last. */
267 {0x0409, "en_MP"}, /* Alias for en_US. Leave last. */
268 {0x0409, "en_UM"} /* Alias for en_US. Leave last. */
269 };
270
ILCID_POSIX_SUBTABLE(en_US_POSIX)271 ILCID_POSIX_SUBTABLE(en_US_POSIX) {
272 {0x007f, "en_US_POSIX"} /* duplicate for roundtripping */
273 };
274
ILCID_POSIX_SUBTABLE(es)275 ILCID_POSIX_SUBTABLE(es) {
276 {0x0a, "es"},
277 {0x2c0a, "es_AR"},
278 {0x400a, "es_BO"},
279 {0x340a, "es_CL"},
280 {0x240a, "es_CO"},
281 {0x140a, "es_CR"},
282 {0x1c0a, "es_DO"},
283 {0x300a, "es_EC"},
284 {0x0c0a, "es_ES"}, /*Modern sort.*/
285 {0x100a, "es_GT"},
286 {0x480a, "es_HN"},
287 {0x080a, "es_MX"},
288 {0x4c0a, "es_NI"},
289 {0x180a, "es_PA"},
290 {0x280a, "es_PE"},
291 {0x500a, "es_PR"},
292 {0x3c0a, "es_PY"},
293 {0x440a, "es_SV"},
294 {0x540a, "es_US"},
295 {0x380a, "es_UY"},
296 {0x200a, "es_VE"},
297 {0x580a, "es_419"},
298 {0x040a, "es_ES@collation=traditional"},
299 {0x040a, "es@collation=traditional"}
300 };
301
302 ILCID_POSIX_ELEMENT_ARRAY(0x0425, et, et_EE)
303 ILCID_POSIX_ELEMENT_ARRAY(0x042d, eu, eu_ES)
304
305 /* ISO-639 doesn't distinguish between Persian and Dari.*/
ILCID_POSIX_SUBTABLE(fa)306 ILCID_POSIX_SUBTABLE(fa) {
307 {0x29, "fa"},
308 {0x0429, "fa_IR"}, /* Persian/Farsi (Iran) */
309 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */
310 };
311
312 /* duplicate for roundtripping */
ILCID_POSIX_SUBTABLE(fa_AF)313 ILCID_POSIX_SUBTABLE(fa_AF) {
314 {0x8c, "fa_AF"}, /* Persian/Dari (Afghanistan) */
315 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */
316 };
317
ILCID_POSIX_SUBTABLE(ff)318 ILCID_POSIX_SUBTABLE(ff) {
319 {0x67, "ff"},
320 {0x7c67, "ff_Latn"},
321 {0x0867, "ff_Latn_SN"}
322 };
323
324 ILCID_POSIX_ELEMENT_ARRAY(0x040b, fi, fi_FI)
325 ILCID_POSIX_ELEMENT_ARRAY(0x0464, fil,fil_PH)
326 ILCID_POSIX_ELEMENT_ARRAY(0x0438, fo, fo_FO)
327
ILCID_POSIX_SUBTABLE(fr)328 ILCID_POSIX_SUBTABLE(fr) {
329 {0x0c, "fr"},
330 {0x080c, "fr_BE"},
331 {0x0c0c, "fr_CA"},
332 {0x240c, "fr_CD"},
333 {0x240c, "fr_CG"},
334 {0x100c, "fr_CH"},
335 {0x300c, "fr_CI"},
336 {0x2c0c, "fr_CM"},
337 {0x040c, "fr_FR"},
338 {0x3c0c, "fr_HT"},
339 {0x140c, "fr_LU"},
340 {0x380c, "fr_MA"},
341 {0x180c, "fr_MC"},
342 {0x340c, "fr_ML"},
343 {0x200c, "fr_RE"},
344 {0x280c, "fr_SN"},
345 {0xe40c, "fr_015"},
346 {0x1c0c, "fr_029"}
347 };
348
349 ILCID_POSIX_ELEMENT_ARRAY(0x0467, fuv, fuv_NG)
350
351 ILCID_POSIX_ELEMENT_ARRAY(0x0462, fy, fy_NL)
352
ILCID_POSIX_SUBTABLE(ga)353 ILCID_POSIX_SUBTABLE(ga) { /* Gaelic (Ireland) */
354 {0x3c, "ga"},
355 {0x083c, "ga_IE"},
356 {0x043c, "gd_GB"}
357 };
358
ILCID_POSIX_SUBTABLE(gd)359 ILCID_POSIX_SUBTABLE(gd) { /* Gaelic (Scotland) */
360 {0x91, "gd"},
361 {0x0491, "gd_GB"}
362 };
363
364 ILCID_POSIX_ELEMENT_ARRAY(0x0456, gl, gl_ES)
365 ILCID_POSIX_ELEMENT_ARRAY(0x0447, gu, gu_IN)
366 ILCID_POSIX_ELEMENT_ARRAY(0x0474, gn, gn_PY)
367 ILCID_POSIX_ELEMENT_ARRAY(0x0484, gsw,gsw_FR)
368
ILCID_POSIX_SUBTABLE(ha)369 ILCID_POSIX_SUBTABLE(ha) {
370 {0x68, "ha"},
371 {0x7c68, "ha_Latn"},
372 {0x0468, "ha_Latn_NG"},
373 };
374
375 ILCID_POSIX_ELEMENT_ARRAY(0x0475, haw,haw_US)
376 ILCID_POSIX_ELEMENT_ARRAY(0x040d, he, he_IL)
377 ILCID_POSIX_ELEMENT_ARRAY(0x0439, hi, hi_IN)
378
379 /* This LCID is really four different locales.*/
ILCID_POSIX_SUBTABLE(hr)380 ILCID_POSIX_SUBTABLE(hr) {
381 {0x1a, "hr"},
382 {0x141a, "bs_Latn_BA"}, /* Bosnian, Bosnia and Herzegovina */
383 {0x681a, "bs_Latn"}, /* Bosnian, Bosnia and Herzegovina */
384 {0x141a, "bs_BA"}, /* Bosnian, Bosnia and Herzegovina */
385 {0x781a, "bs"}, /* Bosnian */
386 {0x201a, "bs_Cyrl_BA"}, /* Bosnian, Bosnia and Herzegovina */
387 {0x641a, "bs_Cyrl"}, /* Bosnian, Bosnia and Herzegovina */
388 {0x101a, "hr_BA"}, /* Croatian in Bosnia */
389 {0x041a, "hr_HR"}, /* Croatian*/
390 {0x2c1a, "sr_Latn_ME"},
391 {0x241a, "sr_Latn_RS"},
392 {0x181a, "sr_Latn_BA"}, /* Serbo-Croatian in Bosnia */
393 {0x081a, "sr_Latn_CS"}, /* Serbo-Croatian*/
394 {0x701a, "sr_Latn"}, /* It's 0x1a or 0x081a, pick one to make the test program happy. */
395 {0x1c1a, "sr_Cyrl_BA"}, /* Serbo-Croatian in Bosnia */
396 {0x0c1a, "sr_Cyrl_CS"}, /* Serbian*/
397 {0x301a, "sr_Cyrl_ME"},
398 {0x281a, "sr_Cyrl_RS"},
399 {0x6c1a, "sr_Cyrl"}, /* It's 0x1a or 0x0c1a, pick one to make the test program happy. */
400 {0x7c1a, "sr"} /* In CLDR sr is sr_Cyrl. */
401 };
402
ILCID_POSIX_SUBTABLE(hsb)403 ILCID_POSIX_SUBTABLE(hsb) {
404 {0x2E, "hsb"},
405 {0x042E, "hsb_DE"},
406 {0x082E, "dsb_DE"},
407 {0x7C2E, "dsb"},
408 };
409
410 ILCID_POSIX_ELEMENT_ARRAY(0x040e, hu, hu_HU)
411 ILCID_POSIX_ELEMENT_ARRAY(0x042b, hy, hy_AM)
412 ILCID_POSIX_ELEMENT_ARRAY(0x0469, ibb, ibb_NG)
413 ILCID_POSIX_ELEMENT_ARRAY(0x0421, id, id_ID)
414 ILCID_POSIX_ELEMENT_ARRAY(0x0470, ig, ig_NG)
415 ILCID_POSIX_ELEMENT_ARRAY(0x0478, ii, ii_CN)
416 ILCID_POSIX_ELEMENT_ARRAY(0x040f, is, is_IS)
417
ILCID_POSIX_SUBTABLE(it)418 ILCID_POSIX_SUBTABLE(it) {
419 {0x10, "it"},
420 {0x0810, "it_CH"},
421 {0x0410, "it_IT"}
422 };
423
ILCID_POSIX_SUBTABLE(iu)424 ILCID_POSIX_SUBTABLE(iu) {
425 {0x5d, "iu"},
426 {0x045d, "iu_Cans_CA"},
427 {0x785d, "iu_Cans"},
428 {0x085d, "iu_Latn_CA"},
429 {0x7c5d, "iu_Latn"}
430 };
431
432 ILCID_POSIX_ELEMENT_ARRAY(0x040d, iw, iw_IL) /*Left in for compatibility*/
433 ILCID_POSIX_ELEMENT_ARRAY(0x0411, ja, ja_JP)
434 ILCID_POSIX_ELEMENT_ARRAY(0x0437, ka, ka_GE)
435 ILCID_POSIX_ELEMENT_ARRAY(0x043f, kk, kk_KZ)
436 ILCID_POSIX_ELEMENT_ARRAY(0x046f, kl, kl_GL)
437 ILCID_POSIX_ELEMENT_ARRAY(0x0453, km, km_KH)
438 ILCID_POSIX_ELEMENT_ARRAY(0x044b, kn, kn_IN)
439
ILCID_POSIX_SUBTABLE(ko)440 ILCID_POSIX_SUBTABLE(ko) {
441 {0x12, "ko"},
442 {0x0812, "ko_KP"},
443 {0x0412, "ko_KR"}
444 };
445
446 ILCID_POSIX_ELEMENT_ARRAY(0x0457, kok, kok_IN)
447 ILCID_POSIX_ELEMENT_ARRAY(0x0471, kr, kr_NG)
448
ILCID_POSIX_SUBTABLE(ks)449 ILCID_POSIX_SUBTABLE(ks) { /* We could add PK and CN too */
450 {0x60, "ks"},
451 {0x0860, "ks_IN"}, /* Documentation doesn't mention script */
452 {0x0460, "ks_Arab_IN"},
453 {0x0860, "ks_Deva_IN"}
454 };
455
456 ILCID_POSIX_ELEMENT_ARRAY(0x0440, ky, ky_KG) /* Kyrgyz is spoken in Kyrgyzstan */
457 ILCID_POSIX_ELEMENT_ARRAY(0x0476, la, la_IT) /* TODO: Verify the country */
458 ILCID_POSIX_ELEMENT_ARRAY(0x046e, lb, lb_LU)
459 ILCID_POSIX_ELEMENT_ARRAY(0x0454, lo, lo_LA)
460 ILCID_POSIX_ELEMENT_ARRAY(0x0427, lt, lt_LT)
461 ILCID_POSIX_ELEMENT_ARRAY(0x0426, lv, lv_LV)
462 ILCID_POSIX_ELEMENT_ARRAY(0x0481, mi, mi_NZ)
463 ILCID_POSIX_ELEMENT_ARRAY(0x042f, mk, mk_MK)
464 ILCID_POSIX_ELEMENT_ARRAY(0x044c, ml, ml_IN)
465
ILCID_POSIX_SUBTABLE(mn)466 ILCID_POSIX_SUBTABLE(mn) {
467 {0x50, "mn"},
468 {0x0450, "mn_MN"},
469 {0x7c50, "mn_Mong"},
470 {0x0850, "mn_Mong_CN"},
471 {0x0850, "mn_CN"},
472 {0x7850, "mn_Cyrl"},
473 {0x0c50, "mn_Mong_MN"}
474 };
475
476 ILCID_POSIX_ELEMENT_ARRAY(0x0458, mni,mni_IN)
477 ILCID_POSIX_ELEMENT_ARRAY(0x047c, moh,moh_CA)
478 ILCID_POSIX_ELEMENT_ARRAY(0x044e, mr, mr_IN)
479
ILCID_POSIX_SUBTABLE(ms)480 ILCID_POSIX_SUBTABLE(ms) {
481 {0x3e, "ms"},
482 {0x083e, "ms_BN"}, /* Brunei Darussalam*/
483 {0x043e, "ms_MY"} /* Malaysia*/
484 };
485
486 ILCID_POSIX_ELEMENT_ARRAY(0x043a, mt, mt_MT)
487 ILCID_POSIX_ELEMENT_ARRAY(0x0455, my, my_MM)
488
ILCID_POSIX_SUBTABLE(ne)489 ILCID_POSIX_SUBTABLE(ne) {
490 {0x61, "ne"},
491 {0x0861, "ne_IN"}, /* India*/
492 {0x0461, "ne_NP"} /* Nepal*/
493 };
494
ILCID_POSIX_SUBTABLE(nl)495 ILCID_POSIX_SUBTABLE(nl) {
496 {0x13, "nl"},
497 {0x0813, "nl_BE"},
498 {0x0413, "nl_NL"}
499 };
500
501 /* The "no" locale split into nb and nn. By default in ICU, "no" is nb.*/
ILCID_POSIX_SUBTABLE(no)502 ILCID_POSIX_SUBTABLE(no) {
503 {0x14, "no"}, /* really nb_NO */
504 {0x7c14, "nb"}, /* really nb */
505 {0x0414, "nb_NO"}, /* really nb_NO. Keep first in the 414 list. */
506 {0x0414, "no_NO"}, /* really nb_NO */
507 {0x0814, "nn_NO"}, /* really nn_NO. Keep first in the 814 list. */
508 {0x7814, "nn"}, /* It's 0x14 or 0x814, pick one to make the test program happy. */
509 {0x0814, "no_NO_NY"}/* really nn_NO */
510 };
511
512 ILCID_POSIX_ELEMENT_ARRAY(0x046c, nso,nso_ZA) /* TODO: Verify the ISO-639 code */
513 ILCID_POSIX_ELEMENT_ARRAY(0x0482, oc, oc_FR)
514
ILCID_POSIX_SUBTABLE(om)515 ILCID_POSIX_SUBTABLE(om) { /* TODO: Verify the country */
516 {0x72, "om"},
517 {0x0472, "om_ET"},
518 {0x0472, "gaz_ET"}
519 };
520
521 /* Declared as or_IN to get around compiler errors*/
ILCID_POSIX_SUBTABLE(or_IN)522 ILCID_POSIX_SUBTABLE(or_IN) {
523 {0x48, "or"},
524 {0x0448, "or_IN"},
525 };
526
527
ILCID_POSIX_SUBTABLE(pa)528 ILCID_POSIX_SUBTABLE(pa) {
529 {0x46, "pa"},
530 {0x0446, "pa_IN"},
531 {0x0846, "pa_PK"},
532 {0x0846, "pa_Arab_PK"}
533 };
534
535 ILCID_POSIX_ELEMENT_ARRAY(0x0479, pap, pap_AN)
536 ILCID_POSIX_ELEMENT_ARRAY(0x0415, pl, pl_PL)
537 ILCID_POSIX_ELEMENT_ARRAY(0x0463, ps, ps_AF)
538
ILCID_POSIX_SUBTABLE(pt)539 ILCID_POSIX_SUBTABLE(pt) {
540 {0x16, "pt"},
541 {0x0416, "pt_BR"},
542 {0x0816, "pt_PT"}
543 };
544
ILCID_POSIX_SUBTABLE(qu)545 ILCID_POSIX_SUBTABLE(qu) {
546 {0x6b, "qu"},
547 {0x046b, "qu_BO"},
548 {0x086b, "qu_EC"},
549 {0x0C6b, "qu_PE"},
550 {0x046b, "quz_BO"},
551 {0x086b, "quz_EC"},
552 {0x0C6b, "quz_PE"}
553 };
554
555 ILCID_POSIX_ELEMENT_ARRAY(0x0486, qut, qut_GT) /* qut is an ISO-639-3 code */
556 ILCID_POSIX_ELEMENT_ARRAY(0x0417, rm, rm_CH)
557
ILCID_POSIX_SUBTABLE(ro)558 ILCID_POSIX_SUBTABLE(ro) {
559 {0x18, "ro"},
560 {0x0418, "ro_RO"},
561 {0x0818, "ro_MD"}
562 };
563
ILCID_POSIX_SUBTABLE(root)564 ILCID_POSIX_SUBTABLE(root) {
565 {0x00, "root"}
566 };
567
ILCID_POSIX_SUBTABLE(ru)568 ILCID_POSIX_SUBTABLE(ru) {
569 {0x19, "ru"},
570 {0x0419, "ru_RU"},
571 {0x0819, "ru_MD"}
572 };
573
574 ILCID_POSIX_ELEMENT_ARRAY(0x0487, rw, rw_RW)
575 ILCID_POSIX_ELEMENT_ARRAY(0x044f, sa, sa_IN)
576 ILCID_POSIX_ELEMENT_ARRAY(0x0485, sah,sah_RU)
577
ILCID_POSIX_SUBTABLE(sd)578 ILCID_POSIX_SUBTABLE(sd) {
579 {0x59, "sd"},
580 {0x0459, "sd_IN"},
581 {0x0859, "sd_PK"}
582 };
583
ILCID_POSIX_SUBTABLE(se)584 ILCID_POSIX_SUBTABLE(se) {
585 {0x3b, "se"},
586 {0x0c3b, "se_FI"},
587 {0x043b, "se_NO"},
588 {0x083b, "se_SE"},
589 {0x783b, "sma"},
590 {0x183b, "sma_NO"},
591 {0x1c3b, "sma_SE"},
592 {0x7c3b, "smj"},
593 {0x703b, "smn"},
594 {0x743b, "sms"},
595 {0x103b, "smj_NO"},
596 {0x143b, "smj_SE"},
597 {0x243b, "smn_FI"},
598 {0x203b, "sms_FI"},
599 };
600
601 ILCID_POSIX_ELEMENT_ARRAY(0x045b, si, si_LK)
602 ILCID_POSIX_ELEMENT_ARRAY(0x041b, sk, sk_SK)
603 ILCID_POSIX_ELEMENT_ARRAY(0x0424, sl, sl_SI)
604
ILCID_POSIX_SUBTABLE(so)605 ILCID_POSIX_SUBTABLE(so) { /* TODO: Verify the country */
606 {0x77, "so"},
607 {0x0477, "so_ET"},
608 {0x0477, "so_SO"}
609 };
610
611 ILCID_POSIX_ELEMENT_ARRAY(0x041c, sq, sq_AL)
612 ILCID_POSIX_ELEMENT_ARRAY(0x0430, st, st_ZA)
613
ILCID_POSIX_SUBTABLE(sv)614 ILCID_POSIX_SUBTABLE(sv) {
615 {0x1d, "sv"},
616 {0x081d, "sv_FI"},
617 {0x041d, "sv_SE"}
618 };
619
620 ILCID_POSIX_ELEMENT_ARRAY(0x0441, sw, sw_KE)
621 ILCID_POSIX_ELEMENT_ARRAY(0x045A, syr, syr_SY)
622
ILCID_POSIX_SUBTABLE(ta)623 ILCID_POSIX_SUBTABLE(ta) {
624 {0x49, "ta"},
625 {0x0449, "ta_IN"},
626 {0x0849, "ta_LK"}
627 };
628
629 ILCID_POSIX_ELEMENT_ARRAY(0x044a, te, te_IN)
630
631 /* Cyrillic based by default */
ILCID_POSIX_SUBTABLE(tg)632 ILCID_POSIX_SUBTABLE(tg) {
633 {0x28, "tg"},
634 {0x7c28, "tg_Cyrl"},
635 {0x0428, "tg_Cyrl_TJ"}
636 };
637
638 ILCID_POSIX_ELEMENT_ARRAY(0x041e, th, th_TH)
639
ILCID_POSIX_SUBTABLE(ti)640 ILCID_POSIX_SUBTABLE(ti) {
641 {0x73, "ti"},
642 {0x0873, "ti_ER"},
643 {0x0473, "ti_ET"}
644 };
645
646 ILCID_POSIX_ELEMENT_ARRAY(0x0442, tk, tk_TM)
647
ILCID_POSIX_SUBTABLE(tn)648 ILCID_POSIX_SUBTABLE(tn) {
649 {0x32, "tn"},
650 {0x0832, "tn_BW"},
651 {0x0432, "tn_ZA"}
652 };
653
654 ILCID_POSIX_ELEMENT_ARRAY(0x041f, tr, tr_TR)
655 ILCID_POSIX_ELEMENT_ARRAY(0x0431, ts, ts_ZA)
656 ILCID_POSIX_ELEMENT_ARRAY(0x0444, tt, tt_RU)
657
ILCID_POSIX_SUBTABLE(tzm)658 ILCID_POSIX_SUBTABLE(tzm) {
659 {0x5f, "tzm"},
660 {0x7c5f, "tzm_Latn"},
661 {0x085f, "tzm_Latn_DZ"},
662 {0x105f, "tzm_Tfng_MA"},
663 {0x045f, "tmz"}
664 };
665
ILCID_POSIX_SUBTABLE(ug)666 ILCID_POSIX_SUBTABLE(ug) {
667 {0x80, "ug"},
668 {0x0480, "ug_CN"},
669 {0x0480, "ug_Arab_CN"}
670 };
671
672 ILCID_POSIX_ELEMENT_ARRAY(0x0422, uk, uk_UA)
673
ILCID_POSIX_SUBTABLE(ur)674 ILCID_POSIX_SUBTABLE(ur) {
675 {0x20, "ur"},
676 {0x0820, "ur_IN"},
677 {0x0420, "ur_PK"}
678 };
679
ILCID_POSIX_SUBTABLE(uz)680 ILCID_POSIX_SUBTABLE(uz) {
681 {0x43, "uz"},
682 {0x0843, "uz_Cyrl_UZ"}, /* Cyrillic based */
683 {0x7843, "uz_Cyrl"}, /* Cyrillic based */
684 {0x0843, "uz_UZ"}, /* Cyrillic based */
685 {0x0443, "uz_Latn_UZ"}, /* Latin based */
686 {0x7c43, "uz_Latn"} /* Latin based */
687 };
688
ILCID_POSIX_SUBTABLE(ve)689 ILCID_POSIX_SUBTABLE(ve) { /* TODO: Verify the country */
690 {0x33, "ve"},
691 {0x0433, "ve_ZA"},
692 {0x0433, "ven_ZA"}
693 };
694
695 ILCID_POSIX_ELEMENT_ARRAY(0x042a, vi, vi_VN)
696 ILCID_POSIX_ELEMENT_ARRAY(0x0488, wo, wo_SN)
697 ILCID_POSIX_ELEMENT_ARRAY(0x0434, xh, xh_ZA)
698 ILCID_POSIX_ELEMENT_ARRAY(0x043d, yi, yi)
699 ILCID_POSIX_ELEMENT_ARRAY(0x046a, yo, yo_NG)
700
ILCID_POSIX_SUBTABLE(zh)701 ILCID_POSIX_SUBTABLE(zh) {
702 {0x0004, "zh_Hans"},
703 {0x7804, "zh"},
704 {0x0804, "zh_CN"},
705 {0x0804, "zh_Hans_CN"},
706 {0x0c04, "zh_Hant_HK"},
707 {0x0c04, "zh_HK"},
708 {0x1404, "zh_Hant_MO"},
709 {0x1404, "zh_MO"},
710 {0x1004, "zh_Hans_SG"},
711 {0x1004, "zh_SG"},
712 {0x0404, "zh_Hant_TW"},
713 {0x7c04, "zh_Hant"},
714 {0x0404, "zh_TW"},
715 {0x30404,"zh_Hant_TW"}, /* Bopomofo order */
716 {0x30404,"zh_TW"}, /* Bopomofo order */
717 {0x20004,"zh@collation=stroke"},
718 {0x20404,"zh_Hant@collation=stroke"},
719 {0x20404,"zh_Hant_TW@collation=stroke"},
720 {0x20404,"zh_TW@collation=stroke"},
721 {0x20804,"zh_Hans@collation=stroke"},
722 {0x20804,"zh_Hans_CN@collation=stroke"},
723 {0x20804,"zh_CN@collation=stroke"}
724 };
725
726 ILCID_POSIX_ELEMENT_ARRAY(0x0435, zu, zu_ZA)
727
728 /* This must be static and grouped by LCID. */
729 static const ILcidPosixMap gPosixIDmap[] = {
730 ILCID_POSIX_MAP(af), /* af Afrikaans 0x36 */
731 ILCID_POSIX_MAP(am), /* am Amharic 0x5e */
732 ILCID_POSIX_MAP(ar), /* ar Arabic 0x01 */
733 ILCID_POSIX_MAP(arn), /* arn Araucanian/Mapudungun 0x7a */
734 ILCID_POSIX_MAP(as), /* as Assamese 0x4d */
735 ILCID_POSIX_MAP(az), /* az Azerbaijani 0x2c */
736 ILCID_POSIX_MAP(ba), /* ba Bashkir 0x6d */
737 ILCID_POSIX_MAP(be), /* be Belarusian 0x23 */
738 /* ILCID_POSIX_MAP(ber), ber Berber/Tamazight 0x5f */
739 ILCID_POSIX_MAP(bg), /* bg Bulgarian 0x02 */
740 ILCID_POSIX_MAP(bin), /* bin Edo 0x66 */
741 ILCID_POSIX_MAP(bn), /* bn Bengali; Bangla 0x45 */
742 ILCID_POSIX_MAP(bo), /* bo Tibetan 0x51 */
743 ILCID_POSIX_MAP(br), /* br Breton 0x7e */
744 ILCID_POSIX_MAP(ca), /* ca Catalan 0x03 */
745 ILCID_POSIX_MAP(chr), /* chr Cherokee 0x5c */
746 ILCID_POSIX_MAP(ckb), /* ckb Sorani (Central Kurdish) 0x92 */
747 ILCID_POSIX_MAP(co), /* co Corsican 0x83 */
748 ILCID_POSIX_MAP(cs), /* cs Czech 0x05 */
749 ILCID_POSIX_MAP(cy), /* cy Welsh 0x52 */
750 ILCID_POSIX_MAP(da), /* da Danish 0x06 */
751 ILCID_POSIX_MAP(de), /* de German 0x07 */
752 ILCID_POSIX_MAP(dv), /* dv Divehi 0x65 */
753 ILCID_POSIX_MAP(el), /* el Greek 0x08 */
754 ILCID_POSIX_MAP(en), /* en English 0x09 */
755 ILCID_POSIX_MAP(en_US_POSIX), /* invariant 0x7f */
756 ILCID_POSIX_MAP(es), /* es Spanish 0x0a */
757 ILCID_POSIX_MAP(et), /* et Estonian 0x25 */
758 ILCID_POSIX_MAP(eu), /* eu Basque 0x2d */
759 ILCID_POSIX_MAP(fa), /* fa Persian/Farsi 0x29 */
760 ILCID_POSIX_MAP(fa_AF), /* fa Persian/Dari 0x8c */
761 ILCID_POSIX_MAP(ff), /* ff Fula 0x67 */
762 ILCID_POSIX_MAP(fi), /* fi Finnish 0x0b */
763 ILCID_POSIX_MAP(fil), /* fil Filipino 0x64 */
764 ILCID_POSIX_MAP(fo), /* fo Faroese 0x38 */
765 ILCID_POSIX_MAP(fr), /* fr French 0x0c */
766 ILCID_POSIX_MAP(fuv), /* fuv Fulfulde - Nigeria 0x67 */
767 ILCID_POSIX_MAP(fy), /* fy Frisian 0x62 */
768 ILCID_POSIX_MAP(ga), /* * Gaelic (Ireland,Scotland) 0x3c */
769 ILCID_POSIX_MAP(gd), /* gd Gaelic (United Kingdom) 0x91 */
770 ILCID_POSIX_MAP(gl), /* gl Galician 0x56 */
771 ILCID_POSIX_MAP(gn), /* gn Guarani 0x74 */
772 ILCID_POSIX_MAP(gsw), /* gsw Alemanic/Alsatian/Swiss German 0x84 */
773 ILCID_POSIX_MAP(gu), /* gu Gujarati 0x47 */
774 ILCID_POSIX_MAP(ha), /* ha Hausa 0x68 */
775 ILCID_POSIX_MAP(haw), /* haw Hawaiian 0x75 */
776 ILCID_POSIX_MAP(he), /* he Hebrew (formerly iw) 0x0d */
777 ILCID_POSIX_MAP(hi), /* hi Hindi 0x39 */
778 ILCID_POSIX_MAP(hr), /* * Croatian and others 0x1a */
779 ILCID_POSIX_MAP(hsb), /* hsb Upper Sorbian 0x2e */
780 ILCID_POSIX_MAP(hu), /* hu Hungarian 0x0e */
781 ILCID_POSIX_MAP(hy), /* hy Armenian 0x2b */
782 ILCID_POSIX_MAP(ibb), /* ibb Ibibio - Nigeria 0x69 */
783 ILCID_POSIX_MAP(id), /* id Indonesian (formerly in) 0x21 */
784 ILCID_POSIX_MAP(ig), /* ig Igbo 0x70 */
785 ILCID_POSIX_MAP(ii), /* ii Sichuan Yi 0x78 */
786 ILCID_POSIX_MAP(is), /* is Icelandic 0x0f */
787 ILCID_POSIX_MAP(it), /* it Italian 0x10 */
788 ILCID_POSIX_MAP(iu), /* iu Inuktitut 0x5d */
789 ILCID_POSIX_MAP(iw), /* iw Hebrew 0x0d */
790 ILCID_POSIX_MAP(ja), /* ja Japanese 0x11 */
791 ILCID_POSIX_MAP(ka), /* ka Georgian 0x37 */
792 ILCID_POSIX_MAP(kk), /* kk Kazakh 0x3f */
793 ILCID_POSIX_MAP(kl), /* kl Kalaallisut 0x6f */
794 ILCID_POSIX_MAP(km), /* km Khmer 0x53 */
795 ILCID_POSIX_MAP(kn), /* kn Kannada 0x4b */
796 ILCID_POSIX_MAP(ko), /* ko Korean 0x12 */
797 ILCID_POSIX_MAP(kok), /* kok Konkani 0x57 */
798 ILCID_POSIX_MAP(kr), /* kr Kanuri 0x71 */
799 ILCID_POSIX_MAP(ks), /* ks Kashmiri 0x60 */
800 ILCID_POSIX_MAP(ky), /* ky Kyrgyz 0x40 */
801 ILCID_POSIX_MAP(lb), /* lb Luxembourgish 0x6e */
802 ILCID_POSIX_MAP(la), /* la Latin 0x76 */
803 ILCID_POSIX_MAP(lo), /* lo Lao 0x54 */
804 ILCID_POSIX_MAP(lt), /* lt Lithuanian 0x27 */
805 ILCID_POSIX_MAP(lv), /* lv Latvian, Lettish 0x26 */
806 ILCID_POSIX_MAP(mi), /* mi Maori 0x81 */
807 ILCID_POSIX_MAP(mk), /* mk Macedonian 0x2f */
808 ILCID_POSIX_MAP(ml), /* ml Malayalam 0x4c */
809 ILCID_POSIX_MAP(mn), /* mn Mongolian 0x50 */
810 ILCID_POSIX_MAP(mni), /* mni Manipuri 0x58 */
811 ILCID_POSIX_MAP(moh), /* moh Mohawk 0x7c */
812 ILCID_POSIX_MAP(mr), /* mr Marathi 0x4e */
813 ILCID_POSIX_MAP(ms), /* ms Malay 0x3e */
814 ILCID_POSIX_MAP(mt), /* mt Maltese 0x3a */
815 ILCID_POSIX_MAP(my), /* my Burmese 0x55 */
816 /* ILCID_POSIX_MAP(nb), // no Norwegian 0x14 */
817 ILCID_POSIX_MAP(ne), /* ne Nepali 0x61 */
818 ILCID_POSIX_MAP(nl), /* nl Dutch 0x13 */
819 /* ILCID_POSIX_MAP(nn), // no Norwegian 0x14 */
820 ILCID_POSIX_MAP(no), /* * Norwegian 0x14 */
821 ILCID_POSIX_MAP(nso), /* nso Sotho, Northern (Sepedi dialect) 0x6c */
822 ILCID_POSIX_MAP(oc), /* oc Occitan 0x82 */
823 ILCID_POSIX_MAP(om), /* om Oromo 0x72 */
824 ILCID_POSIX_MAP(or_IN), /* or Oriya 0x48 */
825 ILCID_POSIX_MAP(pa), /* pa Punjabi 0x46 */
826 ILCID_POSIX_MAP(pap), /* pap Papiamentu 0x79 */
827 ILCID_POSIX_MAP(pl), /* pl Polish 0x15 */
828 ILCID_POSIX_MAP(ps), /* ps Pashto 0x63 */
829 ILCID_POSIX_MAP(pt), /* pt Portuguese 0x16 */
830 ILCID_POSIX_MAP(qu), /* qu Quechua 0x6B */
831 ILCID_POSIX_MAP(qut), /* qut K'iche 0x86 */
832 ILCID_POSIX_MAP(rm), /* rm Raeto-Romance/Romansh 0x17 */
833 ILCID_POSIX_MAP(ro), /* ro Romanian 0x18 */
834 ILCID_POSIX_MAP(root), /* root 0x00 */
835 ILCID_POSIX_MAP(ru), /* ru Russian 0x19 */
836 ILCID_POSIX_MAP(rw), /* rw Kinyarwanda 0x87 */
837 ILCID_POSIX_MAP(sa), /* sa Sanskrit 0x4f */
838 ILCID_POSIX_MAP(sah), /* sah Yakut 0x85 */
839 ILCID_POSIX_MAP(sd), /* sd Sindhi 0x59 */
840 ILCID_POSIX_MAP(se), /* se Sami 0x3b */
841 /* ILCID_POSIX_MAP(sh), // sh Serbo-Croatian 0x1a */
842 ILCID_POSIX_MAP(si), /* si Sinhalese 0x5b */
843 ILCID_POSIX_MAP(sk), /* sk Slovak 0x1b */
844 ILCID_POSIX_MAP(sl), /* sl Slovenian 0x24 */
845 ILCID_POSIX_MAP(so), /* so Somali 0x77 */
846 ILCID_POSIX_MAP(sq), /* sq Albanian 0x1c */
847 /* ILCID_POSIX_MAP(sr), // sr Serbian 0x1a */
848 ILCID_POSIX_MAP(st), /* st Sutu 0x30 */
849 ILCID_POSIX_MAP(sv), /* sv Swedish 0x1d */
850 ILCID_POSIX_MAP(sw), /* sw Swahili 0x41 */
851 ILCID_POSIX_MAP(syr), /* syr Syriac 0x5A */
852 ILCID_POSIX_MAP(ta), /* ta Tamil 0x49 */
853 ILCID_POSIX_MAP(te), /* te Telugu 0x4a */
854 ILCID_POSIX_MAP(tg), /* tg Tajik 0x28 */
855 ILCID_POSIX_MAP(th), /* th Thai 0x1e */
856 ILCID_POSIX_MAP(ti), /* ti Tigrigna 0x73 */
857 ILCID_POSIX_MAP(tk), /* tk Turkmen 0x42 */
858 ILCID_POSIX_MAP(tn), /* tn Tswana 0x32 */
859 ILCID_POSIX_MAP(tr), /* tr Turkish 0x1f */
860 ILCID_POSIX_MAP(ts), /* ts Tsonga 0x31 */
861 ILCID_POSIX_MAP(tt), /* tt Tatar 0x44 */
862 ILCID_POSIX_MAP(tzm), /* tzm Tamazight 0x5f */
863 ILCID_POSIX_MAP(ug), /* ug Uighur 0x80 */
864 ILCID_POSIX_MAP(uk), /* uk Ukrainian 0x22 */
865 ILCID_POSIX_MAP(ur), /* ur Urdu 0x20 */
866 ILCID_POSIX_MAP(uz), /* uz Uzbek 0x43 */
867 ILCID_POSIX_MAP(ve), /* ve Venda 0x33 */
868 ILCID_POSIX_MAP(vi), /* vi Vietnamese 0x2a */
869 ILCID_POSIX_MAP(wo), /* wo Wolof 0x88 */
870 ILCID_POSIX_MAP(xh), /* xh Xhosa 0x34 */
871 ILCID_POSIX_MAP(yi), /* yi Yiddish 0x3d */
872 ILCID_POSIX_MAP(yo), /* yo Yoruba 0x6a */
873 ILCID_POSIX_MAP(zh), /* zh Chinese 0x04 */
874 ILCID_POSIX_MAP(zu), /* zu Zulu 0x35 */
875 };
876
877 static const uint32_t gLocaleCount = sizeof(gPosixIDmap)/sizeof(ILcidPosixMap);
878
879 /**
880 * Do not call this function. It is called by hostID.
881 * The function is not private because this struct must stay as a C struct,
882 * and this is an internal class.
883 */
884 static int32_t
idCmp(const char * id1,const char * id2)885 idCmp(const char* id1, const char* id2)
886 {
887 int32_t diffIdx = 0;
888 while (*id1 == *id2 && *id1 != 0) {
889 diffIdx++;
890 id1++;
891 id2++;
892 }
893 return diffIdx;
894 }
895
896 /**
897 * Searches for a Windows LCID
898 *
899 * @param posixid the Posix style locale id.
900 * @param status gets set to U_ILLEGAL_ARGUMENT_ERROR when the Posix ID has
901 * no equivalent Windows LCID.
902 * @return the LCID
903 */
904 static uint32_t
getHostID(const ILcidPosixMap * this_0,const char * posixID,UErrorCode * status)905 getHostID(const ILcidPosixMap *this_0, const char* posixID, UErrorCode* status)
906 {
907 int32_t bestIdx = 0;
908 int32_t bestIdxDiff = 0;
909 int32_t posixIDlen = (int32_t)uprv_strlen(posixID);
910 uint32_t idx;
911
912 for (idx = 0; idx < this_0->numRegions; idx++ ) {
913 int32_t sameChars = idCmp(posixID, this_0->regionMaps[idx].posixID);
914 if (sameChars > bestIdxDiff && this_0->regionMaps[idx].posixID[sameChars] == 0) {
915 if (posixIDlen == sameChars) {
916 /* Exact match */
917 return this_0->regionMaps[idx].hostID;
918 }
919 bestIdxDiff = sameChars;
920 bestIdx = idx;
921 }
922 }
923 /* We asked for something unusual, like en_ZZ, and we try to return the number for the same language. */
924 /* We also have to make sure that sid and si and similar string subsets don't match. */
925 if ((posixID[bestIdxDiff] == '_' || posixID[bestIdxDiff] == '@')
926 && this_0->regionMaps[bestIdx].posixID[bestIdxDiff] == 0)
927 {
928 *status = U_USING_FALLBACK_WARNING;
929 return this_0->regionMaps[bestIdx].hostID;
930 }
931
932 /*no match found */
933 *status = U_ILLEGAL_ARGUMENT_ERROR;
934 return this_0->regionMaps->hostID;
935 }
936
937 static const char*
getPosixID(const ILcidPosixMap * this_0,uint32_t hostID)938 getPosixID(const ILcidPosixMap *this_0, uint32_t hostID)
939 {
940 uint32_t i;
941 for (i = 0; i <= this_0->numRegions; i++)
942 {
943 if (this_0->regionMaps[i].hostID == hostID)
944 {
945 return this_0->regionMaps[i].posixID;
946 }
947 }
948
949 /* If you get here, then no matching region was found,
950 so return the language id with the wild card region. */
951 return this_0->regionMaps[0].posixID;
952 }
953
954 /*
955 //////////////////////////////////////
956 //
957 // LCID --> POSIX
958 //
959 /////////////////////////////////////
960 */
961 #ifdef USE_WINDOWS_LOCALE_API
962 /*
963 * Various language tags needs to be changed:
964 * quz -> qu
965 * prs -> fa
966 */
967 #define FIX_LANGUAGE_ID_TAG(buffer, len) \
968 if (len >= 3) { \
969 if (buffer[0] == 'q' && buffer[1] == 'u' && buffer[2] == 'z') {\
970 buffer[2] = 0; \
971 uprv_strcat(buffer, buffer+3); \
972 } else if (buffer[0] == 'p' && buffer[1] == 'r' && buffer[2] == 's') {\
973 buffer[0] = 'f'; buffer[1] = 'a'; buffer[2] = 0; \
974 uprv_strcat(buffer, buffer+3); \
975 } \
976 }
977
978 #endif
979 U_CAPI int32_t
uprv_convertToPosix(uint32_t hostid,char * posixID,int32_t posixIDCapacity,UErrorCode * status)980 uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UErrorCode* status)
981 {
982 uint16_t langID;
983 uint32_t localeIndex;
984 UBool bLookup = TRUE;
985 const char *pPosixID = NULL;
986
987 #ifdef USE_WINDOWS_LOCALE_API
988 int32_t tmpLen = 0;
989 char locName[157]; /* ULOC_FULLNAME_CAPACITY */
990
991 tmpLen = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)locName, sizeof(locName)/sizeof(locName[0]));
992 if (tmpLen > 1) {
993 /* Windows locale name may contain sorting variant, such as "es-ES_tradnl".
994 In such case, we need special mapping data found in the hardcoded table
995 in this source file. */
996 char *p = uprv_strchr(locName, '_');
997 if (p) {
998 /* Keep the base locale, without variant */
999 *p = 0;
1000 tmpLen = uprv_strlen(locName);
1001 } else {
1002 /* No hardcoded table lookup necessary */
1003 bLookup = FALSE;
1004 }
1005 /* Change the tag separator from '-' to '_' */
1006 p = locName;
1007 while (*p) {
1008 if (*p == '-') {
1009 *p = '_';
1010 }
1011 p++;
1012 }
1013 FIX_LANGUAGE_ID_TAG(locName, tmpLen);
1014 pPosixID = locName;
1015 }
1016 #endif
1017 if (bLookup) {
1018 const char *pCandidate = NULL;
1019 langID = LANGUAGE_LCID(hostid);
1020
1021 for (localeIndex = 0; localeIndex < gLocaleCount; localeIndex++) {
1022 if (langID == gPosixIDmap[localeIndex].regionMaps->hostID) {
1023 pCandidate = getPosixID(&gPosixIDmap[localeIndex], hostid);
1024 break;
1025 }
1026 }
1027
1028 /* On Windows, when locale name has a variant, we still look up the hardcoded table.
1029 If a match in the hardcoded table is longer than the Windows locale name without
1030 variant, we use the one as the result */
1031 if (pCandidate && (pPosixID == NULL || uprv_strlen(pCandidate) > uprv_strlen(pPosixID))) {
1032 pPosixID = pCandidate;
1033 }
1034 }
1035
1036 if (pPosixID) {
1037 int32_t resLen = uprv_strlen(pPosixID);
1038 int32_t copyLen = resLen <= posixIDCapacity ? resLen : posixIDCapacity;
1039 uprv_memcpy(posixID, pPosixID, copyLen);
1040 if (resLen < posixIDCapacity) {
1041 posixID[resLen] = 0;
1042 if (*status == U_STRING_NOT_TERMINATED_WARNING) {
1043 *status = U_ZERO_ERROR;
1044 }
1045 } else if (resLen == posixIDCapacity) {
1046 *status = U_STRING_NOT_TERMINATED_WARNING;
1047 } else {
1048 *status = U_BUFFER_OVERFLOW_ERROR;
1049 }
1050 return resLen;
1051 }
1052
1053 /* no match found */
1054 *status = U_ILLEGAL_ARGUMENT_ERROR;
1055 return -1;
1056 }
1057
1058 /*
1059 //////////////////////////////////////
1060 //
1061 // POSIX --> LCID
1062 // This should only be called from uloc_getLCID.
1063 // The locale ID must be in canonical form.
1064 // langID is separate so that this file doesn't depend on the uloc_* API.
1065 //
1066 /////////////////////////////////////
1067 */
1068
1069 U_CAPI uint32_t
uprv_convertToLCID(const char * langID,const char * posixID,UErrorCode * status)1070 uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status)
1071 {
1072
1073 uint32_t low = 0;
1074 uint32_t high = gLocaleCount;
1075 uint32_t mid;
1076 uint32_t oldmid = 0;
1077 int32_t compVal;
1078
1079 uint32_t value = 0;
1080 uint32_t fallbackValue = (uint32_t)-1;
1081 UErrorCode myStatus;
1082 uint32_t idx;
1083
1084 /* Check for incomplete id. */
1085 if (!langID || !posixID || uprv_strlen(langID) < 2 || uprv_strlen(posixID) < 2) {
1086 return 0;
1087 }
1088
1089 /*Binary search for the map entry for normal cases */
1090
1091 while (high > low) /*binary search*/{
1092
1093 mid = (high+low) >> 1; /*Finds median*/
1094
1095 if (mid == oldmid)
1096 break;
1097
1098 compVal = uprv_strcmp(langID, gPosixIDmap[mid].regionMaps->posixID);
1099 if (compVal < 0){
1100 high = mid;
1101 }
1102 else if (compVal > 0){
1103 low = mid;
1104 }
1105 else /*we found it*/{
1106 return getHostID(&gPosixIDmap[mid], posixID, status);
1107 }
1108 oldmid = mid;
1109 }
1110
1111 /*
1112 * Sometimes we can't do a binary search on posixID because some LCIDs
1113 * go to different locales. We hit one of those special cases.
1114 */
1115 for (idx = 0; idx < gLocaleCount; idx++ ) {
1116 myStatus = U_ZERO_ERROR;
1117 value = getHostID(&gPosixIDmap[idx], posixID, &myStatus);
1118 if (myStatus == U_ZERO_ERROR) {
1119 return value;
1120 }
1121 else if (myStatus == U_USING_FALLBACK_WARNING) {
1122 fallbackValue = value;
1123 }
1124 }
1125
1126 if (fallbackValue != (uint32_t)-1) {
1127 *status = U_USING_FALLBACK_WARNING;
1128 return fallbackValue;
1129 }
1130
1131 /* no match found */
1132 *status = U_ILLEGAL_ARGUMENT_ERROR;
1133 return 0; /* return international (root) */
1134 }
1135
1136