1/* 2 ********************************************************************** 3 * Copyright (C) 1996-2013, 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/** 33 * Chromium has its own implementation to determine the default locale that uses 34 * Windows locale API where available and falls back to the old API at run-time. 35 */ 36#if 0 37#if U_PLATFORM == U_PF_WINDOWS && defined(_MSC_VER) && (_MSC_VER >= 1500) 38/* 39 * TODO: It seems like we should widen this to 40 * either U_PLATFORM_USES_ONLY_WIN32_API (includes MinGW) 41 * or U_PLATFORM_HAS_WIN32_API (includes MinGW and Cygwin) 42 * but those use gcc and won't have defined(_MSC_VER). 43 * We might need to #include some Windows header and test for some version macro from there. 44 * Or call some Windows function and see what it returns. 45 */ 46#define USE_WINDOWS_LOCALE_API 47#endif 48#endif 49 50#ifdef USE_WINDOWS_LOCALE_API 51#include <windows.h> 52#include <winnls.h> 53#endif 54 55/* 56 * Note: 57 * The mapping from Win32 locale ID numbers to POSIX locale strings should 58 * be the faster one. 59 * 60 * Many LCID values come from winnt.h 61 * Some also come from http://www.microsoft.com/globaldev/reference/lcid-all.mspx 62 */ 63 64/* 65//////////////////////////////////////////////// 66// 67// Internal Classes for LCID <--> POSIX Mapping 68// 69///////////////////////////////////////////////// 70*/ 71 72typedef struct ILcidPosixElement 73{ 74 const uint32_t hostID; 75 const char * const posixID; 76} ILcidPosixElement; 77 78typedef struct ILcidPosixMap 79{ 80 const uint32_t numRegions; 81 const struct ILcidPosixElement* const regionMaps; 82} ILcidPosixMap; 83 84 85/* 86///////////////////////////////////////////////// 87// 88// Easy macros to make the LCID <--> POSIX Mapping 89// 90///////////////////////////////////////////////// 91*/ 92 93/** 94 * The standard one language/one country mapping for LCID. 95 * The first element must be the language, and the following 96 * elements are the language with the country. 97 * @param hostID LCID in host format such as 0x044d 98 * @param languageID posix ID of just the language such as 'de' 99 * @param posixID posix ID of the language_TERRITORY such as 'de_CH' 100 */ 101#define ILCID_POSIX_ELEMENT_ARRAY(hostID, languageID, posixID) \ 102static const ILcidPosixElement locmap_ ## languageID [] = { \ 103 {LANGUAGE_LCID(hostID), #languageID}, /* parent locale */ \ 104 {hostID, #posixID}, \ 105}; 106 107/** 108 * Define a subtable by ID 109 * @param id the POSIX ID, either a language or language_TERRITORY 110 */ 111#define ILCID_POSIX_SUBTABLE(id) \ 112static const ILcidPosixElement locmap_ ## id [] = 113 114 115/** 116 * Create the map for the posixID. This macro supposes that the language string 117 * name is the same as the global variable name, and that the first element 118 * in the ILcidPosixElement is just the language. 119 * @param _posixID the full POSIX ID for this entry. 120 */ 121#define ILCID_POSIX_MAP(_posixID) \ 122 {sizeof(locmap_ ## _posixID)/sizeof(ILcidPosixElement), locmap_ ## _posixID} 123 124/* 125//////////////////////////////////////////// 126// 127// Create the table of LCID to POSIX Mapping 128// None of it should be dynamically created. 129// 130// Keep static locale variables inside the function so that 131// it can be created properly during static init. 132// 133// Note: This table should be updated periodically. Check the National Lanaguage Support API Reference Website. 134// Microsoft is moving away from LCID in favor of locale name as of Vista. This table needs to be 135// maintained for support of older Windows version. 136// Update: Windows 7 (091130) 137// 138// Note: Microsoft assign a different LCID if a locale has a sorting variant. POSIX IDs below may contain 139// @collation=XXX, but no other keywords are allowed (at least for now). When uprv_convertToLCID() is 140// called from uloc_getLCID(), keywords other than collation are already removed. If we really need 141// to support other keywords in this mapping data, we must update the implementation. 142//////////////////////////////////////////// 143*/ 144 145ILCID_POSIX_ELEMENT_ARRAY(0x0436, af, af_ZA) 146 147ILCID_POSIX_SUBTABLE(ar) { 148 {0x01, "ar"}, 149 {0x3801, "ar_AE"}, 150 {0x3c01, "ar_BH"}, 151 {0x1401, "ar_DZ"}, 152 {0x0c01, "ar_EG"}, 153 {0x0801, "ar_IQ"}, 154 {0x2c01, "ar_JO"}, 155 {0x3401, "ar_KW"}, 156 {0x3001, "ar_LB"}, 157 {0x1001, "ar_LY"}, 158 {0x1801, "ar_MA"}, 159 {0x1801, "ar_MO"}, 160 {0x2001, "ar_OM"}, 161 {0x4001, "ar_QA"}, 162 {0x0401, "ar_SA"}, 163 {0x2801, "ar_SY"}, 164 {0x1c01, "ar_TN"}, 165 {0x2401, "ar_YE"} 166}; 167 168ILCID_POSIX_ELEMENT_ARRAY(0x044d, as, as_IN) 169ILCID_POSIX_ELEMENT_ARRAY(0x045e, am, am_ET) 170ILCID_POSIX_ELEMENT_ARRAY(0x047a, arn,arn_CL) 171 172ILCID_POSIX_SUBTABLE(az) { 173 {0x2c, "az"}, 174 {0x082c, "az_Cyrl_AZ"}, /* Cyrillic based */ 175 {0x742c, "az_Cyrl"}, /* Cyrillic based */ 176 {0x042c, "az_Latn_AZ"}, /* Latin based */ 177 {0x782c, "az_Latn"}, /* Latin based */ 178 {0x042c, "az_AZ"} /* Latin based */ 179}; 180 181ILCID_POSIX_ELEMENT_ARRAY(0x046d, ba, ba_RU) 182ILCID_POSIX_ELEMENT_ARRAY(0x0423, be, be_BY) 183 184/*ILCID_POSIX_SUBTABLE(ber) { 185 {0x5f, "ber"}, 186 {0x045f, "ber_Arab_DZ"}, 187 {0x045f, "ber_Arab"}, 188 {0x085f, "ber_Latn_DZ"}, 189 {0x085f, "ber_Latn"} 190};*/ 191 192ILCID_POSIX_ELEMENT_ARRAY(0x0402, bg, bg_BG) 193 194ILCID_POSIX_ELEMENT_ARRAY(0x0466, bin, bin_NG) 195 196ILCID_POSIX_SUBTABLE(bn) { 197 {0x45, "bn"}, 198 {0x0845, "bn_BD"}, 199 {0x0445, "bn_IN"} 200}; 201 202ILCID_POSIX_SUBTABLE(bo) { 203 {0x51, "bo"}, 204 {0x0851, "bo_BT"}, 205 {0x0451, "bo_CN"} 206}; 207 208ILCID_POSIX_ELEMENT_ARRAY(0x047e, br, br_FR) 209 210ILCID_POSIX_SUBTABLE(ca) { 211 {0x03, "ca"}, 212 {0x0403, "ca_ES"}, 213 {0x0803, "ca_ES_VALENCIA"} 214}; 215 216ILCID_POSIX_ELEMENT_ARRAY(0x0483, co, co_FR) 217ILCID_POSIX_ELEMENT_ARRAY(0x045c, chr,chr_US) 218 219ILCID_POSIX_SUBTABLE(ckb) { 220 {0x92, "ckb"}, 221 {0x92, "ku"}, 222 {0x7c92, "ckb_Arab"}, 223 {0x7c92, "ku_Arab"}, 224 {0x0492, "ckb_Arab_IQ"}, 225 {0x0492, "ku_Arab_IQ"} 226}; 227 228/* Declared as cs_CZ to get around compiler errors on z/OS, which defines cs as a function */ 229ILCID_POSIX_ELEMENT_ARRAY(0x0405, cs, cs_CZ) 230 231ILCID_POSIX_ELEMENT_ARRAY(0x0452, cy, cy_GB) 232ILCID_POSIX_ELEMENT_ARRAY(0x0406, da, da_DK) 233 234ILCID_POSIX_SUBTABLE(de) { 235 {0x07, "de"}, 236 {0x0c07, "de_AT"}, 237 {0x0807, "de_CH"}, 238 {0x0407, "de_DE"}, 239 {0x1407, "de_LI"}, 240 {0x1007, "de_LU"}, 241 {0x10407,"de_DE@collation=phonebook"}, /*This is really de_DE_PHONEBOOK on Windows*/ 242 {0x10407,"de@collation=phonebook"} /*This is really de_DE_PHONEBOOK on Windows*/ 243}; 244 245ILCID_POSIX_ELEMENT_ARRAY(0x0465, dv, dv_MV) 246ILCID_POSIX_ELEMENT_ARRAY(0x0408, el, el_GR) 247 248ILCID_POSIX_SUBTABLE(en) { 249 {0x09, "en"}, 250 {0x0c09, "en_AU"}, 251 {0x2809, "en_BZ"}, 252 {0x1009, "en_CA"}, 253 {0x0809, "en_GB"}, 254 {0x3c09, "en_HK"}, 255 {0x3809, "en_ID"}, 256 {0x1809, "en_IE"}, 257 {0x4009, "en_IN"}, 258 {0x2009, "en_JM"}, 259 {0x4409, "en_MY"}, 260 {0x1409, "en_NZ"}, 261 {0x3409, "en_PH"}, 262 {0x4809, "en_SG"}, 263 {0x2C09, "en_TT"}, 264 {0x0409, "en_US"}, 265 {0x007f, "en_US_POSIX"}, /* duplicate for roundtripping */ 266 {0x2409, "en_VI"}, /* Virgin Islands AKA Caribbean Islands (en_CB). */ 267 {0x1c09, "en_ZA"}, 268 {0x3009, "en_ZW"}, 269 {0x2409, "en_029"}, 270 {0x0409, "en_AS"}, /* Alias for en_US. Leave last. */ 271 {0x0409, "en_GU"}, /* Alias for en_US. Leave last. */ 272 {0x0409, "en_MH"}, /* Alias for en_US. Leave last. */ 273 {0x0409, "en_MP"}, /* Alias for en_US. Leave last. */ 274 {0x0409, "en_UM"} /* Alias for en_US. Leave last. */ 275}; 276 277ILCID_POSIX_SUBTABLE(en_US_POSIX) { 278 {0x007f, "en_US_POSIX"} /* duplicate for roundtripping */ 279}; 280 281ILCID_POSIX_SUBTABLE(es) { 282 {0x0a, "es"}, 283 {0x2c0a, "es_AR"}, 284 {0x400a, "es_BO"}, 285 {0x340a, "es_CL"}, 286 {0x240a, "es_CO"}, 287 {0x140a, "es_CR"}, 288 {0x1c0a, "es_DO"}, 289 {0x300a, "es_EC"}, 290 {0x0c0a, "es_ES"}, /*Modern sort.*/ 291 {0x100a, "es_GT"}, 292 {0x480a, "es_HN"}, 293 {0x080a, "es_MX"}, 294 {0x4c0a, "es_NI"}, 295 {0x180a, "es_PA"}, 296 {0x280a, "es_PE"}, 297 {0x500a, "es_PR"}, 298 {0x3c0a, "es_PY"}, 299 {0x440a, "es_SV"}, 300 {0x540a, "es_US"}, 301 {0x380a, "es_UY"}, 302 {0x200a, "es_VE"}, 303 {0xe40a, "es_419"}, 304 {0x040a, "es_ES@collation=traditional"}, 305 {0x040a, "es@collation=traditional"} 306}; 307 308ILCID_POSIX_ELEMENT_ARRAY(0x0425, et, et_EE) 309ILCID_POSIX_ELEMENT_ARRAY(0x042d, eu, eu_ES) 310 311/* ISO-639 doesn't distinguish between Persian and Dari.*/ 312ILCID_POSIX_SUBTABLE(fa) { 313 {0x29, "fa"}, 314 {0x0429, "fa_IR"}, /* Persian/Farsi (Iran) */ 315 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */ 316}; 317 318/* duplicate for roundtripping */ 319ILCID_POSIX_SUBTABLE(fa_AF) { 320 {0x8c, "fa_AF"}, /* Persian/Dari (Afghanistan) */ 321 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */ 322}; 323 324ILCID_POSIX_SUBTABLE(ff) { 325 {0x67, "ff"}, 326 {0x7c67, "ff_Latn"}, 327 {0x0867, "ff_Latn_SN"} 328}; 329 330ILCID_POSIX_ELEMENT_ARRAY(0x040b, fi, fi_FI) 331ILCID_POSIX_ELEMENT_ARRAY(0x0464, fil,fil_PH) 332ILCID_POSIX_ELEMENT_ARRAY(0x0438, fo, fo_FO) 333 334ILCID_POSIX_SUBTABLE(fr) { 335 {0x0c, "fr"}, 336 {0x080c, "fr_BE"}, 337 {0x0c0c, "fr_CA"}, 338 {0x240c, "fr_CD"}, 339 {0x240c, "fr_CG"}, 340 {0x100c, "fr_CH"}, 341 {0x300c, "fr_CI"}, 342 {0x2c0c, "fr_CM"}, 343 {0x040c, "fr_FR"}, 344 {0x3c0c, "fr_HT"}, 345 {0x140c, "fr_LU"}, 346 {0x380c, "fr_MA"}, 347 {0x180c, "fr_MC"}, 348 {0x340c, "fr_ML"}, 349 {0x200c, "fr_RE"}, 350 {0x280c, "fr_SN"}, 351 {0xe40c, "fr_015"}, 352 {0x1c0c, "fr_029"} 353}; 354 355ILCID_POSIX_ELEMENT_ARRAY(0x0467, fuv, fuv_NG) 356 357ILCID_POSIX_ELEMENT_ARRAY(0x0462, fy, fy_NL) 358 359ILCID_POSIX_SUBTABLE(ga) { /* Gaelic (Ireland) */ 360 {0x3c, "ga"}, 361 {0x083c, "ga_IE"}, 362 {0x043c, "gd_GB"} 363}; 364 365ILCID_POSIX_SUBTABLE(gd) { /* Gaelic (Scotland) */ 366 {0x91, "gd"}, 367 {0x0491, "gd_GB"} 368}; 369 370ILCID_POSIX_ELEMENT_ARRAY(0x0456, gl, gl_ES) 371ILCID_POSIX_ELEMENT_ARRAY(0x0447, gu, gu_IN) 372ILCID_POSIX_ELEMENT_ARRAY(0x0474, gn, gn_PY) 373ILCID_POSIX_ELEMENT_ARRAY(0x0484, gsw,gsw_FR) 374 375ILCID_POSIX_SUBTABLE(ha) { 376 {0x68, "ha"}, 377 {0x7c68, "ha_Latn"}, 378 {0x0468, "ha_Latn_NG"}, 379}; 380 381ILCID_POSIX_ELEMENT_ARRAY(0x0475, haw,haw_US) 382ILCID_POSIX_ELEMENT_ARRAY(0x040d, he, he_IL) 383ILCID_POSIX_ELEMENT_ARRAY(0x0439, hi, hi_IN) 384 385/* This LCID is really four different locales.*/ 386ILCID_POSIX_SUBTABLE(hr) { 387 {0x1a, "hr"}, 388 {0x141a, "bs_Latn_BA"}, /* Bosnian, Bosnia and Herzegovina */ 389 {0x681a, "bs_Latn"}, /* Bosnian, Bosnia and Herzegovina */ 390 {0x141a, "bs_BA"}, /* Bosnian, Bosnia and Herzegovina */ 391 {0x781a, "bs"}, /* Bosnian */ 392 {0x201a, "bs_Cyrl_BA"}, /* Bosnian, Bosnia and Herzegovina */ 393 {0x641a, "bs_Cyrl"}, /* Bosnian, Bosnia and Herzegovina */ 394 {0x101a, "hr_BA"}, /* Croatian in Bosnia */ 395 {0x041a, "hr_HR"}, /* Croatian*/ 396 {0x2c1a, "sr_Latn_ME"}, 397 {0x241a, "sr_Latn_RS"}, 398 {0x181a, "sr_Latn_BA"}, /* Serbo-Croatian in Bosnia */ 399 {0x081a, "sr_Latn_CS"}, /* Serbo-Croatian*/ 400 {0x701a, "sr_Latn"}, /* It's 0x1a or 0x081a, pick one to make the test program happy. */ 401 {0x1c1a, "sr_Cyrl_BA"}, /* Serbo-Croatian in Bosnia */ 402 {0x0c1a, "sr_Cyrl_CS"}, /* Serbian*/ 403 {0x301a, "sr_Cyrl_ME"}, 404 {0x281a, "sr_Cyrl_RS"}, 405 {0x6c1a, "sr_Cyrl"}, /* It's 0x1a or 0x0c1a, pick one to make the test program happy. */ 406 {0x7c1a, "sr"} /* In CLDR sr is sr_Cyrl. */ 407}; 408 409ILCID_POSIX_ELEMENT_ARRAY(0x040e, hu, hu_HU) 410ILCID_POSIX_ELEMENT_ARRAY(0x042b, hy, hy_AM) 411ILCID_POSIX_ELEMENT_ARRAY(0x0469, ibb, ibb_NG) 412ILCID_POSIX_ELEMENT_ARRAY(0x0421, id, id_ID) 413ILCID_POSIX_ELEMENT_ARRAY(0x0470, ig, ig_NG) 414ILCID_POSIX_ELEMENT_ARRAY(0x0478, ii, ii_CN) 415ILCID_POSIX_ELEMENT_ARRAY(0x040f, is, is_IS) 416 417ILCID_POSIX_SUBTABLE(it) { 418 {0x10, "it"}, 419 {0x0810, "it_CH"}, 420 {0x0410, "it_IT"} 421}; 422 423ILCID_POSIX_SUBTABLE(iu) { 424 {0x5d, "iu"}, 425 {0x045d, "iu_Cans_CA"}, 426 {0x785d, "iu_Cans"}, 427 {0x085d, "iu_Latn_CA"}, 428 {0x7c5d, "iu_Latn"} 429}; 430 431ILCID_POSIX_ELEMENT_ARRAY(0x040d, iw, iw_IL) /*Left in for compatibility*/ 432ILCID_POSIX_ELEMENT_ARRAY(0x0411, ja, ja_JP) 433ILCID_POSIX_ELEMENT_ARRAY(0x0437, ka, ka_GE) 434ILCID_POSIX_ELEMENT_ARRAY(0x043f, kk, kk_KZ) 435ILCID_POSIX_ELEMENT_ARRAY(0x046f, kl, kl_GL) 436ILCID_POSIX_ELEMENT_ARRAY(0x0453, km, km_KH) 437ILCID_POSIX_ELEMENT_ARRAY(0x044b, kn, kn_IN) 438 439ILCID_POSIX_SUBTABLE(ko) { 440 {0x12, "ko"}, 441 {0x0812, "ko_KP"}, 442 {0x0412, "ko_KR"} 443}; 444 445ILCID_POSIX_ELEMENT_ARRAY(0x0457, kok, kok_IN) 446ILCID_POSIX_ELEMENT_ARRAY(0x0471, kr, kr_NG) 447 448ILCID_POSIX_SUBTABLE(ks) { /* We could add PK and CN too */ 449 {0x60, "ks"}, 450 {0x0860, "ks_IN"}, /* Documentation doesn't mention script */ 451 {0x0460, "ks_Arab_IN"}, 452 {0x0860, "ks_Deva_IN"} 453}; 454 455ILCID_POSIX_ELEMENT_ARRAY(0x0440, ky, ky_KG) /* Kyrgyz is spoken in Kyrgyzstan */ 456ILCID_POSIX_ELEMENT_ARRAY(0x0476, la, la_IT) /* TODO: Verify the country */ 457ILCID_POSIX_ELEMENT_ARRAY(0x046e, lb, lb_LU) 458ILCID_POSIX_ELEMENT_ARRAY(0x0454, lo, lo_LA) 459ILCID_POSIX_ELEMENT_ARRAY(0x0427, lt, lt_LT) 460ILCID_POSIX_ELEMENT_ARRAY(0x0426, lv, lv_LV) 461ILCID_POSIX_ELEMENT_ARRAY(0x0481, mi, mi_NZ) 462ILCID_POSIX_ELEMENT_ARRAY(0x042f, mk, mk_MK) 463ILCID_POSIX_ELEMENT_ARRAY(0x044c, ml, ml_IN) 464 465ILCID_POSIX_SUBTABLE(mn) { 466 {0x50, "mn"}, 467 {0x0450, "mn_MN"}, 468 {0x7c50, "mn_Mong"}, 469 {0x0850, "mn_Mong_CN"}, 470 {0x0850, "mn_CN"}, 471 {0x7850, "mn_Cyrl"} 472}; 473 474ILCID_POSIX_ELEMENT_ARRAY(0x0458, mni,mni_IN) 475ILCID_POSIX_ELEMENT_ARRAY(0x047c, moh,moh_CA) 476ILCID_POSIX_ELEMENT_ARRAY(0x044e, mr, mr_IN) 477 478ILCID_POSIX_SUBTABLE(ms) { 479 {0x3e, "ms"}, 480 {0x083e, "ms_BN"}, /* Brunei Darussalam*/ 481 {0x043e, "ms_MY"} /* Malaysia*/ 482}; 483 484ILCID_POSIX_ELEMENT_ARRAY(0x043a, mt, mt_MT) 485ILCID_POSIX_ELEMENT_ARRAY(0x0455, my, my_MM) 486 487ILCID_POSIX_SUBTABLE(ne) { 488 {0x61, "ne"}, 489 {0x0861, "ne_IN"}, /* India*/ 490 {0x0461, "ne_NP"} /* Nepal*/ 491}; 492 493ILCID_POSIX_SUBTABLE(nl) { 494 {0x13, "nl"}, 495 {0x0813, "nl_BE"}, 496 {0x0413, "nl_NL"} 497}; 498 499/* The "no" locale split into nb and nn. By default in ICU, "no" is nb.*/ 500ILCID_POSIX_SUBTABLE(no) { 501 {0x14, "no"}, /* really nb_NO */ 502 {0x7c14, "nb"}, /* really nb */ 503 {0x0414, "nb_NO"}, /* really nb_NO. Keep first in the 414 list. */ 504 {0x0414, "no_NO"}, /* really nb_NO */ 505 {0x0814, "nn_NO"}, /* really nn_NO. Keep first in the 814 list. */ 506 {0x7814, "nn"}, /* It's 0x14 or 0x814, pick one to make the test program happy. */ 507 {0x0814, "no_NO_NY"}/* really nn_NO */ 508}; 509 510ILCID_POSIX_ELEMENT_ARRAY(0x046c, nso,nso_ZA) /* TODO: Verify the ISO-639 code */ 511ILCID_POSIX_ELEMENT_ARRAY(0x0482, oc, oc_FR) 512 513ILCID_POSIX_SUBTABLE(om) { /* TODO: Verify the country */ 514 {0x72, "om"}, 515 {0x0472, "om_ET"}, 516 {0x0472, "gaz_ET"} 517}; 518 519/* Declared as or_IN to get around compiler errors*/ 520ILCID_POSIX_SUBTABLE(or_IN) { 521 {0x48, "or"}, 522 {0x0448, "or_IN"}, 523}; 524 525 526ILCID_POSIX_SUBTABLE(pa) { 527 {0x46, "pa"}, 528 {0x0446, "pa_IN"}, 529 {0x0846, "pa_PK"}, 530 {0x0846, "pa_Arab_PK"} 531}; 532 533ILCID_POSIX_ELEMENT_ARRAY(0x0479, pap, pap_AN) 534ILCID_POSIX_ELEMENT_ARRAY(0x0415, pl, pl_PL) 535ILCID_POSIX_ELEMENT_ARRAY(0x0463, ps, ps_AF) 536 537ILCID_POSIX_SUBTABLE(pt) { 538 {0x16, "pt"}, 539 {0x0416, "pt_BR"}, 540 {0x0816, "pt_PT"} 541}; 542 543ILCID_POSIX_SUBTABLE(qu) { 544 {0x6b, "qu"}, 545 {0x046b, "qu_BO"}, 546 {0x086b, "qu_EC"}, 547 {0x0C6b, "qu_PE"}, 548 {0x046b, "quz_BO"}, 549 {0x086b, "quz_EC"}, 550 {0x0C6b, "quz_PE"} 551}; 552 553ILCID_POSIX_ELEMENT_ARRAY(0x0486, qut, qut_GT) /* qut is an ISO-639-3 code */ 554ILCID_POSIX_ELEMENT_ARRAY(0x0417, rm, rm_CH) 555 556ILCID_POSIX_SUBTABLE(ro) { 557 {0x18, "ro"}, 558 {0x0418, "ro_RO"}, 559 {0x0818, "ro_MD"} 560}; 561 562ILCID_POSIX_SUBTABLE(root) { 563 {0x00, "root"} 564}; 565 566ILCID_POSIX_SUBTABLE(ru) { 567 {0x19, "ru"}, 568 {0x0419, "ru_RU"}, 569 {0x0819, "ru_MD"} 570}; 571 572ILCID_POSIX_ELEMENT_ARRAY(0x0487, rw, rw_RW) 573ILCID_POSIX_ELEMENT_ARRAY(0x044f, sa, sa_IN) 574ILCID_POSIX_ELEMENT_ARRAY(0x0485, sah,sah_RU) 575 576ILCID_POSIX_SUBTABLE(sd) { 577 {0x59, "sd"}, 578 {0x0459, "sd_IN"}, 579 {0x0859, "sd_PK"} 580}; 581 582ILCID_POSIX_SUBTABLE(se) { 583 {0x3b, "se"}, 584 {0x0c3b, "se_FI"}, 585 {0x043b, "se_NO"}, 586 {0x083b, "se_SE"}, 587 {0x783b, "sma"}, 588 {0x183b, "sma_NO"}, 589 {0x1c3b, "sma_SE"}, 590 {0x7c3b, "smj"}, 591 {0x703b, "smn"}, 592 {0x743b, "sms"}, 593 {0x103b, "smj_NO"}, 594 {0x143b, "smj_SE"}, 595 {0x243b, "smn_FI"}, 596 {0x203b, "sms_FI"}, 597}; 598 599ILCID_POSIX_ELEMENT_ARRAY(0x045b, si, si_LK) 600ILCID_POSIX_ELEMENT_ARRAY(0x041b, sk, sk_SK) 601ILCID_POSIX_ELEMENT_ARRAY(0x0424, sl, sl_SI) 602 603ILCID_POSIX_SUBTABLE(so) { /* TODO: Verify the country */ 604 {0x77, "so"}, 605 {0x0477, "so_ET"}, 606 {0x0477, "so_SO"} 607}; 608 609ILCID_POSIX_ELEMENT_ARRAY(0x041c, sq, sq_AL) 610ILCID_POSIX_ELEMENT_ARRAY(0x0430, st, st_ZA) 611 612ILCID_POSIX_SUBTABLE(sv) { 613 {0x1d, "sv"}, 614 {0x081d, "sv_FI"}, 615 {0x041d, "sv_SE"} 616}; 617 618ILCID_POSIX_ELEMENT_ARRAY(0x0441, sw, sw_KE) 619ILCID_POSIX_ELEMENT_ARRAY(0x045A, syr, syr_SY) 620 621ILCID_POSIX_SUBTABLE(ta) { 622 {0x49, "ta"}, 623 {0x0449, "ta_IN"}, 624 {0x0849, "ta_LK"} 625}; 626 627ILCID_POSIX_ELEMENT_ARRAY(0x044a, te, te_IN) 628 629/* Cyrillic based by default */ 630ILCID_POSIX_SUBTABLE(tg) { 631 {0x28, "tg"}, 632 {0x7c28, "tg_Cyrl"}, 633 {0x0428, "tg_Cyrl_TJ"} 634}; 635 636ILCID_POSIX_ELEMENT_ARRAY(0x041e, th, th_TH) 637 638ILCID_POSIX_SUBTABLE(ti) { 639 {0x73, "ti"}, 640 {0x0873, "ti_ER"}, 641 {0x0473, "ti_ET"} 642}; 643 644ILCID_POSIX_ELEMENT_ARRAY(0x0442, tk, tk_TM) 645 646ILCID_POSIX_SUBTABLE(tn) { 647 {0x32, "tn"}, 648 {0x0832, "tn_BW"}, 649 {0x0432, "tn_ZA"} 650}; 651 652ILCID_POSIX_ELEMENT_ARRAY(0x041f, tr, tr_TR) 653ILCID_POSIX_ELEMENT_ARRAY(0x0431, ts, ts_ZA) 654ILCID_POSIX_ELEMENT_ARRAY(0x0444, tt, tt_RU) 655 656ILCID_POSIX_SUBTABLE(tzm) { 657 {0x5f, "tzm"}, 658 {0x7c5f, "tzm_Latn"}, 659 {0x085f, "tzm_Latn_DZ"}, 660 {0x105f, "tzm_Tfng_MA"}, 661 {0x045f, "tmz"} 662}; 663 664ILCID_POSIX_SUBTABLE(ug) { 665 {0x80, "ug"}, 666 {0x0480, "ug_CN"}, 667 {0x0480, "ug_Arab_CN"} 668}; 669 670ILCID_POSIX_ELEMENT_ARRAY(0x0422, uk, uk_UA) 671 672ILCID_POSIX_SUBTABLE(ur) { 673 {0x20, "ur"}, 674 {0x0820, "ur_IN"}, 675 {0x0420, "ur_PK"} 676}; 677 678ILCID_POSIX_SUBTABLE(uz) { 679 {0x43, "uz"}, 680 {0x0843, "uz_Cyrl_UZ"}, /* Cyrillic based */ 681 {0x7843, "uz_Cyrl"}, /* Cyrillic based */ 682 {0x0843, "uz_UZ"}, /* Cyrillic based */ 683 {0x0443, "uz_Latn_UZ"}, /* Latin based */ 684 {0x7c43, "uz_Latn"} /* Latin based */ 685}; 686 687ILCID_POSIX_SUBTABLE(ve) { /* TODO: Verify the country */ 688 {0x33, "ve"}, 689 {0x0433, "ve_ZA"}, 690 {0x0433, "ven_ZA"} 691}; 692 693ILCID_POSIX_ELEMENT_ARRAY(0x042a, vi, vi_VN) 694 695ILCID_POSIX_SUBTABLE(wen) { 696 {0x2E, "wen"}, 697 {0x042E, "wen_DE"}, 698 {0x042E, "hsb_DE"}, 699 {0x082E, "dsb_DE"}, 700 {0x7C2E, "dsb"}, 701 {0x2E, "hsb"} 702}; 703 704ILCID_POSIX_ELEMENT_ARRAY(0x0488, wo, wo_SN) 705ILCID_POSIX_ELEMENT_ARRAY(0x0434, xh, xh_ZA) 706ILCID_POSIX_ELEMENT_ARRAY(0x043d, yi, yi) 707ILCID_POSIX_ELEMENT_ARRAY(0x046a, yo, yo_NG) 708 709ILCID_POSIX_SUBTABLE(zh) { 710 {0x0004, "zh_Hans"}, 711 {0x7804, "zh"}, 712 {0x0804, "zh_CN"}, 713 {0x0804, "zh_Hans_CN"}, 714 {0x0c04, "zh_Hant_HK"}, 715 {0x0c04, "zh_HK"}, 716 {0x1404, "zh_Hant_MO"}, 717 {0x1404, "zh_MO"}, 718 {0x1004, "zh_Hans_SG"}, 719 {0x1004, "zh_SG"}, 720 {0x0404, "zh_Hant_TW"}, 721 {0x7c04, "zh_Hant"}, 722 {0x0404, "zh_TW"}, 723 {0x30404,"zh_Hant_TW"}, /* Bopomofo order */ 724 {0x30404,"zh_TW"}, /* Bopomofo order */ 725 {0x20004,"zh@collation=stroke"}, 726 {0x20404,"zh_Hant@collation=stroke"}, 727 {0x20404,"zh_Hant_TW@collation=stroke"}, 728 {0x20404,"zh_TW@collation=stroke"}, 729 {0x20804,"zh_Hans@collation=stroke"}, 730 {0x20804,"zh_Hans_CN@collation=stroke"}, 731 {0x20804,"zh_CN@collation=stroke"} 732}; 733 734ILCID_POSIX_ELEMENT_ARRAY(0x0435, zu, zu_ZA) 735 736/* This must be static and grouped by LCID. */ 737static const ILcidPosixMap gPosixIDmap[] = { 738 ILCID_POSIX_MAP(af), /* af Afrikaans 0x36 */ 739 ILCID_POSIX_MAP(am), /* am Amharic 0x5e */ 740 ILCID_POSIX_MAP(ar), /* ar Arabic 0x01 */ 741 ILCID_POSIX_MAP(arn), /* arn Araucanian/Mapudungun 0x7a */ 742 ILCID_POSIX_MAP(as), /* as Assamese 0x4d */ 743 ILCID_POSIX_MAP(az), /* az Azerbaijani 0x2c */ 744 ILCID_POSIX_MAP(ba), /* ba Bashkir 0x6d */ 745 ILCID_POSIX_MAP(be), /* be Belarusian 0x23 */ 746/* ILCID_POSIX_MAP(ber), ber Berber/Tamazight 0x5f */ 747 ILCID_POSIX_MAP(bg), /* bg Bulgarian 0x02 */ 748 ILCID_POSIX_MAP(bin), /* bin Edo 0x66 */ 749 ILCID_POSIX_MAP(bn), /* bn Bengali; Bangla 0x45 */ 750 ILCID_POSIX_MAP(bo), /* bo Tibetan 0x51 */ 751 ILCID_POSIX_MAP(br), /* br Breton 0x7e */ 752 ILCID_POSIX_MAP(ca), /* ca Catalan 0x03 */ 753 ILCID_POSIX_MAP(chr), /* chr Cherokee 0x5c */ 754 ILCID_POSIX_MAP(ckb), /* ckb Sorani (Central Kurdish) 0x92 */ 755 ILCID_POSIX_MAP(co), /* co Corsican 0x83 */ 756 ILCID_POSIX_MAP(cs), /* cs Czech 0x05 */ 757 ILCID_POSIX_MAP(cy), /* cy Welsh 0x52 */ 758 ILCID_POSIX_MAP(da), /* da Danish 0x06 */ 759 ILCID_POSIX_MAP(de), /* de German 0x07 */ 760 ILCID_POSIX_MAP(dv), /* dv Divehi 0x65 */ 761 ILCID_POSIX_MAP(el), /* el Greek 0x08 */ 762 ILCID_POSIX_MAP(en), /* en English 0x09 */ 763 ILCID_POSIX_MAP(en_US_POSIX), /* invariant 0x7f */ 764 ILCID_POSIX_MAP(es), /* es Spanish 0x0a */ 765 ILCID_POSIX_MAP(et), /* et Estonian 0x25 */ 766 ILCID_POSIX_MAP(eu), /* eu Basque 0x2d */ 767 ILCID_POSIX_MAP(fa), /* fa Persian/Farsi 0x29 */ 768 ILCID_POSIX_MAP(fa_AF), /* fa Persian/Dari 0x8c */ 769 ILCID_POSIX_MAP(ff), /* ff Fula 0x67 */ 770 ILCID_POSIX_MAP(fi), /* fi Finnish 0x0b */ 771 ILCID_POSIX_MAP(fil), /* fil Filipino 0x64 */ 772 ILCID_POSIX_MAP(fo), /* fo Faroese 0x38 */ 773 ILCID_POSIX_MAP(fr), /* fr French 0x0c */ 774 ILCID_POSIX_MAP(fuv), /* fuv Fulfulde - Nigeria 0x67 */ 775 ILCID_POSIX_MAP(fy), /* fy Frisian 0x62 */ 776 ILCID_POSIX_MAP(ga), /* * Gaelic (Ireland,Scotland) 0x3c */ 777 ILCID_POSIX_MAP(gd), /* gd Gaelic (United Kingdom) 0x91 */ 778 ILCID_POSIX_MAP(gl), /* gl Galician 0x56 */ 779 ILCID_POSIX_MAP(gn), /* gn Guarani 0x74 */ 780 ILCID_POSIX_MAP(gsw), /* gsw Alemanic/Alsatian/Swiss German 0x84 */ 781 ILCID_POSIX_MAP(gu), /* gu Gujarati 0x47 */ 782 ILCID_POSIX_MAP(ha), /* ha Hausa 0x68 */ 783 ILCID_POSIX_MAP(haw), /* haw Hawaiian 0x75 */ 784 ILCID_POSIX_MAP(he), /* he Hebrew (formerly iw) 0x0d */ 785 ILCID_POSIX_MAP(hi), /* hi Hindi 0x39 */ 786 ILCID_POSIX_MAP(hr), /* * Croatian and others 0x1a */ 787 ILCID_POSIX_MAP(hu), /* hu Hungarian 0x0e */ 788 ILCID_POSIX_MAP(hy), /* hy Armenian 0x2b */ 789 ILCID_POSIX_MAP(ibb), /* ibb Ibibio - Nigeria 0x69 */ 790 ILCID_POSIX_MAP(id), /* id Indonesian (formerly in) 0x21 */ 791 ILCID_POSIX_MAP(ig), /* ig Igbo 0x70 */ 792 ILCID_POSIX_MAP(ii), /* ii Sichuan Yi 0x78 */ 793 ILCID_POSIX_MAP(is), /* is Icelandic 0x0f */ 794 ILCID_POSIX_MAP(it), /* it Italian 0x10 */ 795 ILCID_POSIX_MAP(iu), /* iu Inuktitut 0x5d */ 796 ILCID_POSIX_MAP(iw), /* iw Hebrew 0x0d */ 797 ILCID_POSIX_MAP(ja), /* ja Japanese 0x11 */ 798 ILCID_POSIX_MAP(ka), /* ka Georgian 0x37 */ 799 ILCID_POSIX_MAP(kk), /* kk Kazakh 0x3f */ 800 ILCID_POSIX_MAP(kl), /* kl Kalaallisut 0x6f */ 801 ILCID_POSIX_MAP(km), /* km Khmer 0x53 */ 802 ILCID_POSIX_MAP(kn), /* kn Kannada 0x4b */ 803 ILCID_POSIX_MAP(ko), /* ko Korean 0x12 */ 804 ILCID_POSIX_MAP(kok), /* kok Konkani 0x57 */ 805 ILCID_POSIX_MAP(kr), /* kr Kanuri 0x71 */ 806 ILCID_POSIX_MAP(ks), /* ks Kashmiri 0x60 */ 807 ILCID_POSIX_MAP(ky), /* ky Kyrgyz 0x40 */ 808 ILCID_POSIX_MAP(lb), /* lb Luxembourgish 0x6e */ 809 ILCID_POSIX_MAP(la), /* la Latin 0x76 */ 810 ILCID_POSIX_MAP(lo), /* lo Lao 0x54 */ 811 ILCID_POSIX_MAP(lt), /* lt Lithuanian 0x27 */ 812 ILCID_POSIX_MAP(lv), /* lv Latvian, Lettish 0x26 */ 813 ILCID_POSIX_MAP(mi), /* mi Maori 0x81 */ 814 ILCID_POSIX_MAP(mk), /* mk Macedonian 0x2f */ 815 ILCID_POSIX_MAP(ml), /* ml Malayalam 0x4c */ 816 ILCID_POSIX_MAP(mn), /* mn Mongolian 0x50 */ 817 ILCID_POSIX_MAP(mni), /* mni Manipuri 0x58 */ 818 ILCID_POSIX_MAP(moh), /* moh Mohawk 0x7c */ 819 ILCID_POSIX_MAP(mr), /* mr Marathi 0x4e */ 820 ILCID_POSIX_MAP(ms), /* ms Malay 0x3e */ 821 ILCID_POSIX_MAP(mt), /* mt Maltese 0x3a */ 822 ILCID_POSIX_MAP(my), /* my Burmese 0x55 */ 823/* ILCID_POSIX_MAP(nb), // no Norwegian 0x14 */ 824 ILCID_POSIX_MAP(ne), /* ne Nepali 0x61 */ 825 ILCID_POSIX_MAP(nl), /* nl Dutch 0x13 */ 826/* ILCID_POSIX_MAP(nn), // no Norwegian 0x14 */ 827 ILCID_POSIX_MAP(no), /* * Norwegian 0x14 */ 828 ILCID_POSIX_MAP(nso), /* nso Sotho, Northern (Sepedi dialect) 0x6c */ 829 ILCID_POSIX_MAP(oc), /* oc Occitan 0x82 */ 830 ILCID_POSIX_MAP(om), /* om Oromo 0x72 */ 831 ILCID_POSIX_MAP(or_IN), /* or Oriya 0x48 */ 832 ILCID_POSIX_MAP(pa), /* pa Punjabi 0x46 */ 833 ILCID_POSIX_MAP(pap), /* pap Papiamentu 0x79 */ 834 ILCID_POSIX_MAP(pl), /* pl Polish 0x15 */ 835 ILCID_POSIX_MAP(ps), /* ps Pashto 0x63 */ 836 ILCID_POSIX_MAP(pt), /* pt Portuguese 0x16 */ 837 ILCID_POSIX_MAP(qu), /* qu Quechua 0x6B */ 838 ILCID_POSIX_MAP(qut), /* qut K'iche 0x86 */ 839 ILCID_POSIX_MAP(rm), /* rm Raeto-Romance/Romansh 0x17 */ 840 ILCID_POSIX_MAP(ro), /* ro Romanian 0x18 */ 841 ILCID_POSIX_MAP(root), /* root 0x00 */ 842 ILCID_POSIX_MAP(ru), /* ru Russian 0x19 */ 843 ILCID_POSIX_MAP(rw), /* rw Kinyarwanda 0x87 */ 844 ILCID_POSIX_MAP(sa), /* sa Sanskrit 0x4f */ 845 ILCID_POSIX_MAP(sah), /* sah Yakut 0x85 */ 846 ILCID_POSIX_MAP(sd), /* sd Sindhi 0x59 */ 847 ILCID_POSIX_MAP(se), /* se Sami 0x3b */ 848/* ILCID_POSIX_MAP(sh), // sh Serbo-Croatian 0x1a */ 849 ILCID_POSIX_MAP(si), /* si Sinhalese 0x5b */ 850 ILCID_POSIX_MAP(sk), /* sk Slovak 0x1b */ 851 ILCID_POSIX_MAP(sl), /* sl Slovenian 0x24 */ 852 ILCID_POSIX_MAP(so), /* so Somali 0x77 */ 853 ILCID_POSIX_MAP(sq), /* sq Albanian 0x1c */ 854/* ILCID_POSIX_MAP(sr), // sr Serbian 0x1a */ 855 ILCID_POSIX_MAP(st), /* st Sutu 0x30 */ 856 ILCID_POSIX_MAP(sv), /* sv Swedish 0x1d */ 857 ILCID_POSIX_MAP(sw), /* sw Swahili 0x41 */ 858 ILCID_POSIX_MAP(syr), /* syr Syriac 0x5A */ 859 ILCID_POSIX_MAP(ta), /* ta Tamil 0x49 */ 860 ILCID_POSIX_MAP(te), /* te Telugu 0x4a */ 861 ILCID_POSIX_MAP(tg), /* tg Tajik 0x28 */ 862 ILCID_POSIX_MAP(th), /* th Thai 0x1e */ 863 ILCID_POSIX_MAP(ti), /* ti Tigrigna 0x73 */ 864 ILCID_POSIX_MAP(tk), /* tk Turkmen 0x42 */ 865 ILCID_POSIX_MAP(tn), /* tn Tswana 0x32 */ 866 ILCID_POSIX_MAP(tr), /* tr Turkish 0x1f */ 867 ILCID_POSIX_MAP(ts), /* ts Tsonga 0x31 */ 868 ILCID_POSIX_MAP(tt), /* tt Tatar 0x44 */ 869 ILCID_POSIX_MAP(tzm), /* tzm Tamazight 0x5f */ 870 ILCID_POSIX_MAP(ug), /* ug Uighur 0x80 */ 871 ILCID_POSIX_MAP(uk), /* uk Ukrainian 0x22 */ 872 ILCID_POSIX_MAP(ur), /* ur Urdu 0x20 */ 873 ILCID_POSIX_MAP(uz), /* uz Uzbek 0x43 */ 874 ILCID_POSIX_MAP(ve), /* ve Venda 0x33 */ 875 ILCID_POSIX_MAP(vi), /* vi Vietnamese 0x2a */ 876 ILCID_POSIX_MAP(wen), /* wen Sorbian 0x2e */ 877 ILCID_POSIX_MAP(wo), /* wo Wolof 0x88 */ 878 ILCID_POSIX_MAP(xh), /* xh Xhosa 0x34 */ 879 ILCID_POSIX_MAP(yi), /* yi Yiddish 0x3d */ 880 ILCID_POSIX_MAP(yo), /* yo Yoruba 0x6a */ 881 ILCID_POSIX_MAP(zh), /* zh Chinese 0x04 */ 882 ILCID_POSIX_MAP(zu), /* zu Zulu 0x35 */ 883}; 884 885static const uint32_t gLocaleCount = sizeof(gPosixIDmap)/sizeof(ILcidPosixMap); 886 887/** 888 * Do not call this function. It is called by hostID. 889 * The function is not private because this struct must stay as a C struct, 890 * and this is an internal class. 891 */ 892static int32_t 893idCmp(const char* id1, const char* id2) 894{ 895 int32_t diffIdx = 0; 896 while (*id1 == *id2 && *id1 != 0) { 897 diffIdx++; 898 id1++; 899 id2++; 900 } 901 return diffIdx; 902} 903 904/** 905 * Searches for a Windows LCID 906 * 907 * @param posixid the Posix style locale id. 908 * @param status gets set to U_ILLEGAL_ARGUMENT_ERROR when the Posix ID has 909 * no equivalent Windows LCID. 910 * @return the LCID 911 */ 912static uint32_t 913getHostID(const ILcidPosixMap *this_0, const char* posixID, UErrorCode* status) 914{ 915 int32_t bestIdx = 0; 916 int32_t bestIdxDiff = 0; 917 int32_t posixIDlen = (int32_t)uprv_strlen(posixID); 918 uint32_t idx; 919 920 for (idx = 0; idx < this_0->numRegions; idx++ ) { 921 int32_t sameChars = idCmp(posixID, this_0->regionMaps[idx].posixID); 922 if (sameChars > bestIdxDiff && this_0->regionMaps[idx].posixID[sameChars] == 0) { 923 if (posixIDlen == sameChars) { 924 /* Exact match */ 925 return this_0->regionMaps[idx].hostID; 926 } 927 bestIdxDiff = sameChars; 928 bestIdx = idx; 929 } 930 } 931 /* We asked for something unusual, like en_ZZ, and we try to return the number for the same language. */ 932 /* We also have to make sure that sid and si and similar string subsets don't match. */ 933 if ((posixID[bestIdxDiff] == '_' || posixID[bestIdxDiff] == '@') 934 && this_0->regionMaps[bestIdx].posixID[bestIdxDiff] == 0) 935 { 936 *status = U_USING_FALLBACK_WARNING; 937 return this_0->regionMaps[bestIdx].hostID; 938 } 939 940 /*no match found */ 941 *status = U_ILLEGAL_ARGUMENT_ERROR; 942 return this_0->regionMaps->hostID; 943} 944 945static const char* 946getPosixID(const ILcidPosixMap *this_0, uint32_t hostID) 947{ 948 uint32_t i; 949 for (i = 0; i <= this_0->numRegions; i++) 950 { 951 if (this_0->regionMaps[i].hostID == hostID) 952 { 953 return this_0->regionMaps[i].posixID; 954 } 955 } 956 957 /* If you get here, then no matching region was found, 958 so return the language id with the wild card region. */ 959 return this_0->regionMaps[0].posixID; 960} 961 962/* 963////////////////////////////////////// 964// 965// LCID --> POSIX 966// 967///////////////////////////////////// 968*/ 969#ifdef USE_WINDOWS_LOCALE_API 970/* 971 * Various language tags needs to be changed: 972 * quz -> qu 973 * prs -> fa 974 */ 975#define FIX_LANGUAGE_ID_TAG(buffer, len) \ 976 if (len >= 3) { \ 977 if (buffer[0] == 'q' && buffer[1] == 'u' && buffer[2] == 'z') {\ 978 buffer[2] = 0; \ 979 uprv_strcat(buffer, buffer+3); \ 980 } else if (buffer[0] == 'p' && buffer[1] == 'r' && buffer[2] == 's') {\ 981 buffer[0] = 'f'; buffer[1] = 'a'; buffer[2] = 0; \ 982 uprv_strcat(buffer, buffer+3); \ 983 } \ 984 } 985 986#endif 987U_CAPI int32_t 988uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UErrorCode* status) 989{ 990 uint16_t langID; 991 uint32_t localeIndex; 992 UBool bLookup = TRUE; 993 const char *pPosixID = NULL; 994 995#ifdef USE_WINDOWS_LOCALE_API 996 int32_t tmpLen = 0; 997 char locName[157]; /* ULOC_FULLNAME_CAPACITY */ 998 999 tmpLen = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)locName, sizeof(locName)/sizeof(locName[0])); 1000 if (tmpLen > 1) { 1001 /* Windows locale name may contain sorting variant, such as "es-ES_tradnl". 1002 In such case, we need special mapping data found in the hardcoded table 1003 in this source file. */ 1004 char *p = uprv_strchr(locName, '_'); 1005 if (p) { 1006 /* Keep the base locale, without variant */ 1007 *p = 0; 1008 tmpLen = uprv_strlen(locName); 1009 } else { 1010 /* No hardcoded table lookup necessary */ 1011 bLookup = FALSE; 1012 } 1013 /* Change the tag separator from '-' to '_' */ 1014 p = locName; 1015 while (*p) { 1016 if (*p == '-') { 1017 *p = '_'; 1018 } 1019 p++; 1020 } 1021 FIX_LANGUAGE_ID_TAG(locName, tmpLen); 1022 pPosixID = locName; 1023 } 1024#endif 1025 if (bLookup) { 1026 const char *pCandidate = NULL; 1027 langID = LANGUAGE_LCID(hostid); 1028 1029 for (localeIndex = 0; localeIndex < gLocaleCount; localeIndex++) { 1030 if (langID == gPosixIDmap[localeIndex].regionMaps->hostID) { 1031 pCandidate = getPosixID(&gPosixIDmap[localeIndex], hostid); 1032 break; 1033 } 1034 } 1035 1036 /* On Windows, when locale name has a variant, we still look up the hardcoded table. 1037 If a match in the hardcoded table is longer than the Windows locale name without 1038 variant, we use the one as the result */ 1039 if (pCandidate && (pPosixID == NULL || uprv_strlen(pCandidate) > uprv_strlen(pPosixID))) { 1040 pPosixID = pCandidate; 1041 } 1042 } 1043 1044 if (pPosixID) { 1045 int32_t resLen = uprv_strlen(pPosixID); 1046 int32_t copyLen = resLen <= posixIDCapacity ? resLen : posixIDCapacity; 1047 uprv_memcpy(posixID, pPosixID, copyLen); 1048 if (resLen < posixIDCapacity) { 1049 posixID[resLen] = 0; 1050 if (*status == U_STRING_NOT_TERMINATED_WARNING) { 1051 *status = U_ZERO_ERROR; 1052 } 1053 } else if (resLen == posixIDCapacity) { 1054 *status = U_STRING_NOT_TERMINATED_WARNING; 1055 } else { 1056 *status = U_BUFFER_OVERFLOW_ERROR; 1057 } 1058 return resLen; 1059 } 1060 1061 /* no match found */ 1062 *status = U_ILLEGAL_ARGUMENT_ERROR; 1063 return -1; 1064} 1065 1066/* 1067////////////////////////////////////// 1068// 1069// POSIX --> LCID 1070// This should only be called from uloc_getLCID. 1071// The locale ID must be in canonical form. 1072// langID is separate so that this file doesn't depend on the uloc_* API. 1073// 1074///////////////////////////////////// 1075*/ 1076 1077U_CAPI uint32_t 1078uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status) 1079{ 1080 1081 uint32_t low = 0; 1082 uint32_t high = gLocaleCount; 1083 uint32_t mid; 1084 uint32_t oldmid = 0; 1085 int32_t compVal; 1086 1087 uint32_t value = 0; 1088 uint32_t fallbackValue = (uint32_t)-1; 1089 UErrorCode myStatus; 1090 uint32_t idx; 1091 1092 /* Check for incomplete id. */ 1093 if (!langID || !posixID || uprv_strlen(langID) < 2 || uprv_strlen(posixID) < 2) { 1094 return 0; 1095 } 1096 1097 /*Binary search for the map entry for normal cases */ 1098 1099 while (high > low) /*binary search*/{ 1100 1101 mid = (high+low) >> 1; /*Finds median*/ 1102 1103 if (mid == oldmid) 1104 break; 1105 1106 compVal = uprv_strcmp(langID, gPosixIDmap[mid].regionMaps->posixID); 1107 if (compVal < 0){ 1108 high = mid; 1109 } 1110 else if (compVal > 0){ 1111 low = mid; 1112 } 1113 else /*we found it*/{ 1114 return getHostID(&gPosixIDmap[mid], posixID, status); 1115 } 1116 oldmid = mid; 1117 } 1118 1119 /* 1120 * Sometimes we can't do a binary search on posixID because some LCIDs 1121 * go to different locales. We hit one of those special cases. 1122 */ 1123 for (idx = 0; idx < gLocaleCount; idx++ ) { 1124 myStatus = U_ZERO_ERROR; 1125 value = getHostID(&gPosixIDmap[idx], posixID, &myStatus); 1126 if (myStatus == U_ZERO_ERROR) { 1127 return value; 1128 } 1129 else if (myStatus == U_USING_FALLBACK_WARNING) { 1130 fallbackValue = value; 1131 } 1132 } 1133 1134 if (fallbackValue != (uint32_t)-1) { 1135 *status = U_USING_FALLBACK_WARNING; 1136 return fallbackValue; 1137 } 1138 1139 /* no match found */ 1140 *status = U_ILLEGAL_ARGUMENT_ERROR; 1141 return 0; /* return international (root) */ 1142} 1143 1144