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 #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) 140 141 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) 165 166 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) 189 190 ILCID_POSIX_SUBTABLE(bn) { 191 {0x45, "bn"}, 192 {0x0845, "bn_BD"}, 193 {0x0445, "bn_IN"} 194 }; 195 196 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) 203 204 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) 212 213 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) 227 228 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) 241 242 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 }; 270 271 ILCID_POSIX_SUBTABLE(en_US_POSIX) { 272 {0x007f, "en_US_POSIX"} /* duplicate for roundtripping */ 273 }; 274 275 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.*/ 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 */ 313 ILCID_POSIX_SUBTABLE(fa_AF) { 314 {0x8c, "fa_AF"}, /* Persian/Dari (Afghanistan) */ 315 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */ 316 }; 317 318 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) 327 328 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) 352 353 ILCID_POSIX_SUBTABLE(ga) { /* Gaelic (Ireland) */ 354 {0x3c, "ga"}, 355 {0x083c, "ga_IE"}, 356 {0x043c, "gd_GB"} 357 }; 358 359 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) 368 369 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.*/ 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 }; 402 403 ILCID_POSIX_ELEMENT_ARRAY(0x040e, hu, hu_HU) 404 ILCID_POSIX_ELEMENT_ARRAY(0x042b, hy, hy_AM) 405 ILCID_POSIX_ELEMENT_ARRAY(0x0469, ibb, ibb_NG) 406 ILCID_POSIX_ELEMENT_ARRAY(0x0421, id, id_ID) 407 ILCID_POSIX_ELEMENT_ARRAY(0x0470, ig, ig_NG) 408 ILCID_POSIX_ELEMENT_ARRAY(0x0478, ii, ii_CN) 409 ILCID_POSIX_ELEMENT_ARRAY(0x040f, is, is_IS) 410 411 ILCID_POSIX_SUBTABLE(it) { 412 {0x10, "it"}, 413 {0x0810, "it_CH"}, 414 {0x0410, "it_IT"} 415 }; 416 417 ILCID_POSIX_SUBTABLE(iu) { 418 {0x5d, "iu"}, 419 {0x045d, "iu_Cans_CA"}, 420 {0x785d, "iu_Cans"}, 421 {0x085d, "iu_Latn_CA"}, 422 {0x7c5d, "iu_Latn"} 423 }; 424 425 ILCID_POSIX_ELEMENT_ARRAY(0x040d, iw, iw_IL) /*Left in for compatibility*/ 426 ILCID_POSIX_ELEMENT_ARRAY(0x0411, ja, ja_JP) 427 ILCID_POSIX_ELEMENT_ARRAY(0x0437, ka, ka_GE) 428 ILCID_POSIX_ELEMENT_ARRAY(0x043f, kk, kk_KZ) 429 ILCID_POSIX_ELEMENT_ARRAY(0x046f, kl, kl_GL) 430 ILCID_POSIX_ELEMENT_ARRAY(0x0453, km, km_KH) 431 ILCID_POSIX_ELEMENT_ARRAY(0x044b, kn, kn_IN) 432 433 ILCID_POSIX_SUBTABLE(ko) { 434 {0x12, "ko"}, 435 {0x0812, "ko_KP"}, 436 {0x0412, "ko_KR"} 437 }; 438 439 ILCID_POSIX_ELEMENT_ARRAY(0x0457, kok, kok_IN) 440 ILCID_POSIX_ELEMENT_ARRAY(0x0471, kr, kr_NG) 441 442 ILCID_POSIX_SUBTABLE(ks) { /* We could add PK and CN too */ 443 {0x60, "ks"}, 444 {0x0860, "ks_IN"}, /* Documentation doesn't mention script */ 445 {0x0460, "ks_Arab_IN"}, 446 {0x0860, "ks_Deva_IN"} 447 }; 448 449 ILCID_POSIX_ELEMENT_ARRAY(0x0440, ky, ky_KG) /* Kyrgyz is spoken in Kyrgyzstan */ 450 ILCID_POSIX_ELEMENT_ARRAY(0x0476, la, la_IT) /* TODO: Verify the country */ 451 ILCID_POSIX_ELEMENT_ARRAY(0x046e, lb, lb_LU) 452 ILCID_POSIX_ELEMENT_ARRAY(0x0454, lo, lo_LA) 453 ILCID_POSIX_ELEMENT_ARRAY(0x0427, lt, lt_LT) 454 ILCID_POSIX_ELEMENT_ARRAY(0x0426, lv, lv_LV) 455 ILCID_POSIX_ELEMENT_ARRAY(0x0481, mi, mi_NZ) 456 ILCID_POSIX_ELEMENT_ARRAY(0x042f, mk, mk_MK) 457 ILCID_POSIX_ELEMENT_ARRAY(0x044c, ml, ml_IN) 458 459 ILCID_POSIX_SUBTABLE(mn) { 460 {0x50, "mn"}, 461 {0x0450, "mn_MN"}, 462 {0x7c50, "mn_Mong"}, 463 {0x0850, "mn_Mong_CN"}, 464 {0x0850, "mn_CN"}, 465 {0x7850, "mn_Cyrl"}, 466 {0x0c50, "mn_Mong_MN"} 467 }; 468 469 ILCID_POSIX_ELEMENT_ARRAY(0x0458, mni,mni_IN) 470 ILCID_POSIX_ELEMENT_ARRAY(0x047c, moh,moh_CA) 471 ILCID_POSIX_ELEMENT_ARRAY(0x044e, mr, mr_IN) 472 473 ILCID_POSIX_SUBTABLE(ms) { 474 {0x3e, "ms"}, 475 {0x083e, "ms_BN"}, /* Brunei Darussalam*/ 476 {0x043e, "ms_MY"} /* Malaysia*/ 477 }; 478 479 ILCID_POSIX_ELEMENT_ARRAY(0x043a, mt, mt_MT) 480 ILCID_POSIX_ELEMENT_ARRAY(0x0455, my, my_MM) 481 482 ILCID_POSIX_SUBTABLE(ne) { 483 {0x61, "ne"}, 484 {0x0861, "ne_IN"}, /* India*/ 485 {0x0461, "ne_NP"} /* Nepal*/ 486 }; 487 488 ILCID_POSIX_SUBTABLE(nl) { 489 {0x13, "nl"}, 490 {0x0813, "nl_BE"}, 491 {0x0413, "nl_NL"} 492 }; 493 494 /* The "no" locale split into nb and nn. By default in ICU, "no" is nb.*/ 495 ILCID_POSIX_SUBTABLE(no) { 496 {0x14, "no"}, /* really nb_NO */ 497 {0x7c14, "nb"}, /* really nb */ 498 {0x0414, "nb_NO"}, /* really nb_NO. Keep first in the 414 list. */ 499 {0x0414, "no_NO"}, /* really nb_NO */ 500 {0x0814, "nn_NO"}, /* really nn_NO. Keep first in the 814 list. */ 501 {0x7814, "nn"}, /* It's 0x14 or 0x814, pick one to make the test program happy. */ 502 {0x0814, "no_NO_NY"}/* really nn_NO */ 503 }; 504 505 ILCID_POSIX_ELEMENT_ARRAY(0x046c, nso,nso_ZA) /* TODO: Verify the ISO-639 code */ 506 ILCID_POSIX_ELEMENT_ARRAY(0x0482, oc, oc_FR) 507 508 ILCID_POSIX_SUBTABLE(om) { /* TODO: Verify the country */ 509 {0x72, "om"}, 510 {0x0472, "om_ET"}, 511 {0x0472, "gaz_ET"} 512 }; 513 514 /* Declared as or_IN to get around compiler errors*/ 515 ILCID_POSIX_SUBTABLE(or_IN) { 516 {0x48, "or"}, 517 {0x0448, "or_IN"}, 518 }; 519 520 521 ILCID_POSIX_SUBTABLE(pa) { 522 {0x46, "pa"}, 523 {0x0446, "pa_IN"}, 524 {0x0846, "pa_PK"}, 525 {0x0846, "pa_Arab_PK"} 526 }; 527 528 ILCID_POSIX_ELEMENT_ARRAY(0x0479, pap, pap_AN) 529 ILCID_POSIX_ELEMENT_ARRAY(0x0415, pl, pl_PL) 530 ILCID_POSIX_ELEMENT_ARRAY(0x0463, ps, ps_AF) 531 532 ILCID_POSIX_SUBTABLE(pt) { 533 {0x16, "pt"}, 534 {0x0416, "pt_BR"}, 535 {0x0816, "pt_PT"} 536 }; 537 538 ILCID_POSIX_SUBTABLE(qu) { 539 {0x6b, "qu"}, 540 {0x046b, "qu_BO"}, 541 {0x086b, "qu_EC"}, 542 {0x0C6b, "qu_PE"}, 543 {0x046b, "quz_BO"}, 544 {0x086b, "quz_EC"}, 545 {0x0C6b, "quz_PE"} 546 }; 547 548 ILCID_POSIX_ELEMENT_ARRAY(0x0486, qut, qut_GT) /* qut is an ISO-639-3 code */ 549 ILCID_POSIX_ELEMENT_ARRAY(0x0417, rm, rm_CH) 550 551 ILCID_POSIX_SUBTABLE(ro) { 552 {0x18, "ro"}, 553 {0x0418, "ro_RO"}, 554 {0x0818, "ro_MD"} 555 }; 556 557 ILCID_POSIX_SUBTABLE(root) { 558 {0x00, "root"} 559 }; 560 561 ILCID_POSIX_SUBTABLE(ru) { 562 {0x19, "ru"}, 563 {0x0419, "ru_RU"}, 564 {0x0819, "ru_MD"} 565 }; 566 567 ILCID_POSIX_ELEMENT_ARRAY(0x0487, rw, rw_RW) 568 ILCID_POSIX_ELEMENT_ARRAY(0x044f, sa, sa_IN) 569 ILCID_POSIX_ELEMENT_ARRAY(0x0485, sah,sah_RU) 570 571 ILCID_POSIX_SUBTABLE(sd) { 572 {0x59, "sd"}, 573 {0x0459, "sd_IN"}, 574 {0x0859, "sd_PK"} 575 }; 576 577 ILCID_POSIX_SUBTABLE(se) { 578 {0x3b, "se"}, 579 {0x0c3b, "se_FI"}, 580 {0x043b, "se_NO"}, 581 {0x083b, "se_SE"}, 582 {0x783b, "sma"}, 583 {0x183b, "sma_NO"}, 584 {0x1c3b, "sma_SE"}, 585 {0x7c3b, "smj"}, 586 {0x703b, "smn"}, 587 {0x743b, "sms"}, 588 {0x103b, "smj_NO"}, 589 {0x143b, "smj_SE"}, 590 {0x243b, "smn_FI"}, 591 {0x203b, "sms_FI"}, 592 }; 593 594 ILCID_POSIX_ELEMENT_ARRAY(0x045b, si, si_LK) 595 ILCID_POSIX_ELEMENT_ARRAY(0x041b, sk, sk_SK) 596 ILCID_POSIX_ELEMENT_ARRAY(0x0424, sl, sl_SI) 597 598 ILCID_POSIX_SUBTABLE(so) { /* TODO: Verify the country */ 599 {0x77, "so"}, 600 {0x0477, "so_ET"}, 601 {0x0477, "so_SO"} 602 }; 603 604 ILCID_POSIX_ELEMENT_ARRAY(0x041c, sq, sq_AL) 605 ILCID_POSIX_ELEMENT_ARRAY(0x0430, st, st_ZA) 606 607 ILCID_POSIX_SUBTABLE(sv) { 608 {0x1d, "sv"}, 609 {0x081d, "sv_FI"}, 610 {0x041d, "sv_SE"} 611 }; 612 613 ILCID_POSIX_ELEMENT_ARRAY(0x0441, sw, sw_KE) 614 ILCID_POSIX_ELEMENT_ARRAY(0x045A, syr, syr_SY) 615 616 ILCID_POSIX_SUBTABLE(ta) { 617 {0x49, "ta"}, 618 {0x0449, "ta_IN"}, 619 {0x0849, "ta_LK"} 620 }; 621 622 ILCID_POSIX_ELEMENT_ARRAY(0x044a, te, te_IN) 623 624 /* Cyrillic based by default */ 625 ILCID_POSIX_SUBTABLE(tg) { 626 {0x28, "tg"}, 627 {0x7c28, "tg_Cyrl"}, 628 {0x0428, "tg_Cyrl_TJ"} 629 }; 630 631 ILCID_POSIX_ELEMENT_ARRAY(0x041e, th, th_TH) 632 633 ILCID_POSIX_SUBTABLE(ti) { 634 {0x73, "ti"}, 635 {0x0873, "ti_ER"}, 636 {0x0473, "ti_ET"} 637 }; 638 639 ILCID_POSIX_ELEMENT_ARRAY(0x0442, tk, tk_TM) 640 641 ILCID_POSIX_SUBTABLE(tn) { 642 {0x32, "tn"}, 643 {0x0832, "tn_BW"}, 644 {0x0432, "tn_ZA"} 645 }; 646 647 ILCID_POSIX_ELEMENT_ARRAY(0x041f, tr, tr_TR) 648 ILCID_POSIX_ELEMENT_ARRAY(0x0431, ts, ts_ZA) 649 ILCID_POSIX_ELEMENT_ARRAY(0x0444, tt, tt_RU) 650 651 ILCID_POSIX_SUBTABLE(tzm) { 652 {0x5f, "tzm"}, 653 {0x7c5f, "tzm_Latn"}, 654 {0x085f, "tzm_Latn_DZ"}, 655 {0x105f, "tzm_Tfng_MA"}, 656 {0x045f, "tmz"} 657 }; 658 659 ILCID_POSIX_SUBTABLE(ug) { 660 {0x80, "ug"}, 661 {0x0480, "ug_CN"}, 662 {0x0480, "ug_Arab_CN"} 663 }; 664 665 ILCID_POSIX_ELEMENT_ARRAY(0x0422, uk, uk_UA) 666 667 ILCID_POSIX_SUBTABLE(ur) { 668 {0x20, "ur"}, 669 {0x0820, "ur_IN"}, 670 {0x0420, "ur_PK"} 671 }; 672 673 ILCID_POSIX_SUBTABLE(uz) { 674 {0x43, "uz"}, 675 {0x0843, "uz_Cyrl_UZ"}, /* Cyrillic based */ 676 {0x7843, "uz_Cyrl"}, /* Cyrillic based */ 677 {0x0843, "uz_UZ"}, /* Cyrillic based */ 678 {0x0443, "uz_Latn_UZ"}, /* Latin based */ 679 {0x7c43, "uz_Latn"} /* Latin based */ 680 }; 681 682 ILCID_POSIX_SUBTABLE(ve) { /* TODO: Verify the country */ 683 {0x33, "ve"}, 684 {0x0433, "ve_ZA"}, 685 {0x0433, "ven_ZA"} 686 }; 687 688 ILCID_POSIX_ELEMENT_ARRAY(0x042a, vi, vi_VN) 689 690 ILCID_POSIX_SUBTABLE(wen) { 691 {0x2E, "wen"}, 692 {0x042E, "wen_DE"}, 693 {0x042E, "hsb_DE"}, 694 {0x082E, "dsb_DE"}, 695 {0x7C2E, "dsb"}, 696 {0x2E, "hsb"} 697 }; 698 699 ILCID_POSIX_ELEMENT_ARRAY(0x0488, wo, wo_SN) 700 ILCID_POSIX_ELEMENT_ARRAY(0x0434, xh, xh_ZA) 701 ILCID_POSIX_ELEMENT_ARRAY(0x043d, yi, yi) 702 ILCID_POSIX_ELEMENT_ARRAY(0x046a, yo, yo_NG) 703 704 ILCID_POSIX_SUBTABLE(zh) { 705 {0x0004, "zh_Hans"}, 706 {0x7804, "zh"}, 707 {0x0804, "zh_CN"}, 708 {0x0804, "zh_Hans_CN"}, 709 {0x0c04, "zh_Hant_HK"}, 710 {0x0c04, "zh_HK"}, 711 {0x1404, "zh_Hant_MO"}, 712 {0x1404, "zh_MO"}, 713 {0x1004, "zh_Hans_SG"}, 714 {0x1004, "zh_SG"}, 715 {0x0404, "zh_Hant_TW"}, 716 {0x7c04, "zh_Hant"}, 717 {0x0404, "zh_TW"}, 718 {0x30404,"zh_Hant_TW"}, /* Bopomofo order */ 719 {0x30404,"zh_TW"}, /* Bopomofo order */ 720 {0x20004,"zh@collation=stroke"}, 721 {0x20404,"zh_Hant@collation=stroke"}, 722 {0x20404,"zh_Hant_TW@collation=stroke"}, 723 {0x20404,"zh_TW@collation=stroke"}, 724 {0x20804,"zh_Hans@collation=stroke"}, 725 {0x20804,"zh_Hans_CN@collation=stroke"}, 726 {0x20804,"zh_CN@collation=stroke"} 727 }; 728 729 ILCID_POSIX_ELEMENT_ARRAY(0x0435, zu, zu_ZA) 730 731 /* This must be static and grouped by LCID. */ 732 static const ILcidPosixMap gPosixIDmap[] = { 733 ILCID_POSIX_MAP(af), /* af Afrikaans 0x36 */ 734 ILCID_POSIX_MAP(am), /* am Amharic 0x5e */ 735 ILCID_POSIX_MAP(ar), /* ar Arabic 0x01 */ 736 ILCID_POSIX_MAP(arn), /* arn Araucanian/Mapudungun 0x7a */ 737 ILCID_POSIX_MAP(as), /* as Assamese 0x4d */ 738 ILCID_POSIX_MAP(az), /* az Azerbaijani 0x2c */ 739 ILCID_POSIX_MAP(ba), /* ba Bashkir 0x6d */ 740 ILCID_POSIX_MAP(be), /* be Belarusian 0x23 */ 741 /* ILCID_POSIX_MAP(ber), ber Berber/Tamazight 0x5f */ 742 ILCID_POSIX_MAP(bg), /* bg Bulgarian 0x02 */ 743 ILCID_POSIX_MAP(bin), /* bin Edo 0x66 */ 744 ILCID_POSIX_MAP(bn), /* bn Bengali; Bangla 0x45 */ 745 ILCID_POSIX_MAP(bo), /* bo Tibetan 0x51 */ 746 ILCID_POSIX_MAP(br), /* br Breton 0x7e */ 747 ILCID_POSIX_MAP(ca), /* ca Catalan 0x03 */ 748 ILCID_POSIX_MAP(chr), /* chr Cherokee 0x5c */ 749 ILCID_POSIX_MAP(ckb), /* ckb Sorani (Central Kurdish) 0x92 */ 750 ILCID_POSIX_MAP(co), /* co Corsican 0x83 */ 751 ILCID_POSIX_MAP(cs), /* cs Czech 0x05 */ 752 ILCID_POSIX_MAP(cy), /* cy Welsh 0x52 */ 753 ILCID_POSIX_MAP(da), /* da Danish 0x06 */ 754 ILCID_POSIX_MAP(de), /* de German 0x07 */ 755 ILCID_POSIX_MAP(dv), /* dv Divehi 0x65 */ 756 ILCID_POSIX_MAP(el), /* el Greek 0x08 */ 757 ILCID_POSIX_MAP(en), /* en English 0x09 */ 758 ILCID_POSIX_MAP(en_US_POSIX), /* invariant 0x7f */ 759 ILCID_POSIX_MAP(es), /* es Spanish 0x0a */ 760 ILCID_POSIX_MAP(et), /* et Estonian 0x25 */ 761 ILCID_POSIX_MAP(eu), /* eu Basque 0x2d */ 762 ILCID_POSIX_MAP(fa), /* fa Persian/Farsi 0x29 */ 763 ILCID_POSIX_MAP(fa_AF), /* fa Persian/Dari 0x8c */ 764 ILCID_POSIX_MAP(ff), /* ff Fula 0x67 */ 765 ILCID_POSIX_MAP(fi), /* fi Finnish 0x0b */ 766 ILCID_POSIX_MAP(fil), /* fil Filipino 0x64 */ 767 ILCID_POSIX_MAP(fo), /* fo Faroese 0x38 */ 768 ILCID_POSIX_MAP(fr), /* fr French 0x0c */ 769 ILCID_POSIX_MAP(fuv), /* fuv Fulfulde - Nigeria 0x67 */ 770 ILCID_POSIX_MAP(fy), /* fy Frisian 0x62 */ 771 ILCID_POSIX_MAP(ga), /* * Gaelic (Ireland,Scotland) 0x3c */ 772 ILCID_POSIX_MAP(gd), /* gd Gaelic (United Kingdom) 0x91 */ 773 ILCID_POSIX_MAP(gl), /* gl Galician 0x56 */ 774 ILCID_POSIX_MAP(gn), /* gn Guarani 0x74 */ 775 ILCID_POSIX_MAP(gsw), /* gsw Alemanic/Alsatian/Swiss German 0x84 */ 776 ILCID_POSIX_MAP(gu), /* gu Gujarati 0x47 */ 777 ILCID_POSIX_MAP(ha), /* ha Hausa 0x68 */ 778 ILCID_POSIX_MAP(haw), /* haw Hawaiian 0x75 */ 779 ILCID_POSIX_MAP(he), /* he Hebrew (formerly iw) 0x0d */ 780 ILCID_POSIX_MAP(hi), /* hi Hindi 0x39 */ 781 ILCID_POSIX_MAP(hr), /* * Croatian and others 0x1a */ 782 ILCID_POSIX_MAP(hu), /* hu Hungarian 0x0e */ 783 ILCID_POSIX_MAP(hy), /* hy Armenian 0x2b */ 784 ILCID_POSIX_MAP(ibb), /* ibb Ibibio - Nigeria 0x69 */ 785 ILCID_POSIX_MAP(id), /* id Indonesian (formerly in) 0x21 */ 786 ILCID_POSIX_MAP(ig), /* ig Igbo 0x70 */ 787 ILCID_POSIX_MAP(ii), /* ii Sichuan Yi 0x78 */ 788 ILCID_POSIX_MAP(is), /* is Icelandic 0x0f */ 789 ILCID_POSIX_MAP(it), /* it Italian 0x10 */ 790 ILCID_POSIX_MAP(iu), /* iu Inuktitut 0x5d */ 791 ILCID_POSIX_MAP(iw), /* iw Hebrew 0x0d */ 792 ILCID_POSIX_MAP(ja), /* ja Japanese 0x11 */ 793 ILCID_POSIX_MAP(ka), /* ka Georgian 0x37 */ 794 ILCID_POSIX_MAP(kk), /* kk Kazakh 0x3f */ 795 ILCID_POSIX_MAP(kl), /* kl Kalaallisut 0x6f */ 796 ILCID_POSIX_MAP(km), /* km Khmer 0x53 */ 797 ILCID_POSIX_MAP(kn), /* kn Kannada 0x4b */ 798 ILCID_POSIX_MAP(ko), /* ko Korean 0x12 */ 799 ILCID_POSIX_MAP(kok), /* kok Konkani 0x57 */ 800 ILCID_POSIX_MAP(kr), /* kr Kanuri 0x71 */ 801 ILCID_POSIX_MAP(ks), /* ks Kashmiri 0x60 */ 802 ILCID_POSIX_MAP(ky), /* ky Kyrgyz 0x40 */ 803 ILCID_POSIX_MAP(lb), /* lb Luxembourgish 0x6e */ 804 ILCID_POSIX_MAP(la), /* la Latin 0x76 */ 805 ILCID_POSIX_MAP(lo), /* lo Lao 0x54 */ 806 ILCID_POSIX_MAP(lt), /* lt Lithuanian 0x27 */ 807 ILCID_POSIX_MAP(lv), /* lv Latvian, Lettish 0x26 */ 808 ILCID_POSIX_MAP(mi), /* mi Maori 0x81 */ 809 ILCID_POSIX_MAP(mk), /* mk Macedonian 0x2f */ 810 ILCID_POSIX_MAP(ml), /* ml Malayalam 0x4c */ 811 ILCID_POSIX_MAP(mn), /* mn Mongolian 0x50 */ 812 ILCID_POSIX_MAP(mni), /* mni Manipuri 0x58 */ 813 ILCID_POSIX_MAP(moh), /* moh Mohawk 0x7c */ 814 ILCID_POSIX_MAP(mr), /* mr Marathi 0x4e */ 815 ILCID_POSIX_MAP(ms), /* ms Malay 0x3e */ 816 ILCID_POSIX_MAP(mt), /* mt Maltese 0x3a */ 817 ILCID_POSIX_MAP(my), /* my Burmese 0x55 */ 818 /* ILCID_POSIX_MAP(nb), // no Norwegian 0x14 */ 819 ILCID_POSIX_MAP(ne), /* ne Nepali 0x61 */ 820 ILCID_POSIX_MAP(nl), /* nl Dutch 0x13 */ 821 /* ILCID_POSIX_MAP(nn), // no Norwegian 0x14 */ 822 ILCID_POSIX_MAP(no), /* * Norwegian 0x14 */ 823 ILCID_POSIX_MAP(nso), /* nso Sotho, Northern (Sepedi dialect) 0x6c */ 824 ILCID_POSIX_MAP(oc), /* oc Occitan 0x82 */ 825 ILCID_POSIX_MAP(om), /* om Oromo 0x72 */ 826 ILCID_POSIX_MAP(or_IN), /* or Oriya 0x48 */ 827 ILCID_POSIX_MAP(pa), /* pa Punjabi 0x46 */ 828 ILCID_POSIX_MAP(pap), /* pap Papiamentu 0x79 */ 829 ILCID_POSIX_MAP(pl), /* pl Polish 0x15 */ 830 ILCID_POSIX_MAP(ps), /* ps Pashto 0x63 */ 831 ILCID_POSIX_MAP(pt), /* pt Portuguese 0x16 */ 832 ILCID_POSIX_MAP(qu), /* qu Quechua 0x6B */ 833 ILCID_POSIX_MAP(qut), /* qut K'iche 0x86 */ 834 ILCID_POSIX_MAP(rm), /* rm Raeto-Romance/Romansh 0x17 */ 835 ILCID_POSIX_MAP(ro), /* ro Romanian 0x18 */ 836 ILCID_POSIX_MAP(root), /* root 0x00 */ 837 ILCID_POSIX_MAP(ru), /* ru Russian 0x19 */ 838 ILCID_POSIX_MAP(rw), /* rw Kinyarwanda 0x87 */ 839 ILCID_POSIX_MAP(sa), /* sa Sanskrit 0x4f */ 840 ILCID_POSIX_MAP(sah), /* sah Yakut 0x85 */ 841 ILCID_POSIX_MAP(sd), /* sd Sindhi 0x59 */ 842 ILCID_POSIX_MAP(se), /* se Sami 0x3b */ 843 /* ILCID_POSIX_MAP(sh), // sh Serbo-Croatian 0x1a */ 844 ILCID_POSIX_MAP(si), /* si Sinhalese 0x5b */ 845 ILCID_POSIX_MAP(sk), /* sk Slovak 0x1b */ 846 ILCID_POSIX_MAP(sl), /* sl Slovenian 0x24 */ 847 ILCID_POSIX_MAP(so), /* so Somali 0x77 */ 848 ILCID_POSIX_MAP(sq), /* sq Albanian 0x1c */ 849 /* ILCID_POSIX_MAP(sr), // sr Serbian 0x1a */ 850 ILCID_POSIX_MAP(st), /* st Sutu 0x30 */ 851 ILCID_POSIX_MAP(sv), /* sv Swedish 0x1d */ 852 ILCID_POSIX_MAP(sw), /* sw Swahili 0x41 */ 853 ILCID_POSIX_MAP(syr), /* syr Syriac 0x5A */ 854 ILCID_POSIX_MAP(ta), /* ta Tamil 0x49 */ 855 ILCID_POSIX_MAP(te), /* te Telugu 0x4a */ 856 ILCID_POSIX_MAP(tg), /* tg Tajik 0x28 */ 857 ILCID_POSIX_MAP(th), /* th Thai 0x1e */ 858 ILCID_POSIX_MAP(ti), /* ti Tigrigna 0x73 */ 859 ILCID_POSIX_MAP(tk), /* tk Turkmen 0x42 */ 860 ILCID_POSIX_MAP(tn), /* tn Tswana 0x32 */ 861 ILCID_POSIX_MAP(tr), /* tr Turkish 0x1f */ 862 ILCID_POSIX_MAP(ts), /* ts Tsonga 0x31 */ 863 ILCID_POSIX_MAP(tt), /* tt Tatar 0x44 */ 864 ILCID_POSIX_MAP(tzm), /* tzm Tamazight 0x5f */ 865 ILCID_POSIX_MAP(ug), /* ug Uighur 0x80 */ 866 ILCID_POSIX_MAP(uk), /* uk Ukrainian 0x22 */ 867 ILCID_POSIX_MAP(ur), /* ur Urdu 0x20 */ 868 ILCID_POSIX_MAP(uz), /* uz Uzbek 0x43 */ 869 ILCID_POSIX_MAP(ve), /* ve Venda 0x33 */ 870 ILCID_POSIX_MAP(vi), /* vi Vietnamese 0x2a */ 871 ILCID_POSIX_MAP(wen), /* wen Sorbian 0x2e */ 872 ILCID_POSIX_MAP(wo), /* wo Wolof 0x88 */ 873 ILCID_POSIX_MAP(xh), /* xh Xhosa 0x34 */ 874 ILCID_POSIX_MAP(yi), /* yi Yiddish 0x3d */ 875 ILCID_POSIX_MAP(yo), /* yo Yoruba 0x6a */ 876 ILCID_POSIX_MAP(zh), /* zh Chinese 0x04 */ 877 ILCID_POSIX_MAP(zu), /* zu Zulu 0x35 */ 878 }; 879 880 static const uint32_t gLocaleCount = sizeof(gPosixIDmap)/sizeof(ILcidPosixMap); 881 882 /** 883 * Do not call this function. It is called by hostID. 884 * The function is not private because this struct must stay as a C struct, 885 * and this is an internal class. 886 */ 887 static int32_t 888 idCmp(const char* id1, const char* id2) 889 { 890 int32_t diffIdx = 0; 891 while (*id1 == *id2 && *id1 != 0) { 892 diffIdx++; 893 id1++; 894 id2++; 895 } 896 return diffIdx; 897 } 898 899 /** 900 * Searches for a Windows LCID 901 * 902 * @param posixid the Posix style locale id. 903 * @param status gets set to U_ILLEGAL_ARGUMENT_ERROR when the Posix ID has 904 * no equivalent Windows LCID. 905 * @return the LCID 906 */ 907 static uint32_t 908 getHostID(const ILcidPosixMap *this_0, const char* posixID, UErrorCode* status) 909 { 910 int32_t bestIdx = 0; 911 int32_t bestIdxDiff = 0; 912 int32_t posixIDlen = (int32_t)uprv_strlen(posixID); 913 uint32_t idx; 914 915 for (idx = 0; idx < this_0->numRegions; idx++ ) { 916 int32_t sameChars = idCmp(posixID, this_0->regionMaps[idx].posixID); 917 if (sameChars > bestIdxDiff && this_0->regionMaps[idx].posixID[sameChars] == 0) { 918 if (posixIDlen == sameChars) { 919 /* Exact match */ 920 return this_0->regionMaps[idx].hostID; 921 } 922 bestIdxDiff = sameChars; 923 bestIdx = idx; 924 } 925 } 926 /* We asked for something unusual, like en_ZZ, and we try to return the number for the same language. */ 927 /* We also have to make sure that sid and si and similar string subsets don't match. */ 928 if ((posixID[bestIdxDiff] == '_' || posixID[bestIdxDiff] == '@') 929 && this_0->regionMaps[bestIdx].posixID[bestIdxDiff] == 0) 930 { 931 *status = U_USING_FALLBACK_WARNING; 932 return this_0->regionMaps[bestIdx].hostID; 933 } 934 935 /*no match found */ 936 *status = U_ILLEGAL_ARGUMENT_ERROR; 937 return this_0->regionMaps->hostID; 938 } 939 940 static const char* 941 getPosixID(const ILcidPosixMap *this_0, uint32_t hostID) 942 { 943 uint32_t i; 944 for (i = 0; i <= this_0->numRegions; i++) 945 { 946 if (this_0->regionMaps[i].hostID == hostID) 947 { 948 return this_0->regionMaps[i].posixID; 949 } 950 } 951 952 /* If you get here, then no matching region was found, 953 so return the language id with the wild card region. */ 954 return this_0->regionMaps[0].posixID; 955 } 956 957 /* 958 ////////////////////////////////////// 959 // 960 // LCID --> POSIX 961 // 962 ///////////////////////////////////// 963 */ 964 #ifdef USE_WINDOWS_LOCALE_API 965 /* 966 * Various language tags needs to be changed: 967 * quz -> qu 968 * prs -> fa 969 */ 970 #define FIX_LANGUAGE_ID_TAG(buffer, len) \ 971 if (len >= 3) { \ 972 if (buffer[0] == 'q' && buffer[1] == 'u' && buffer[2] == 'z') {\ 973 buffer[2] = 0; \ 974 uprv_strcat(buffer, buffer+3); \ 975 } else if (buffer[0] == 'p' && buffer[1] == 'r' && buffer[2] == 's') {\ 976 buffer[0] = 'f'; buffer[1] = 'a'; buffer[2] = 0; \ 977 uprv_strcat(buffer, buffer+3); \ 978 } \ 979 } 980 981 #endif 982 U_CAPI int32_t 983 uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UErrorCode* status) 984 { 985 uint16_t langID; 986 uint32_t localeIndex; 987 UBool bLookup = TRUE; 988 const char *pPosixID = NULL; 989 990 #ifdef USE_WINDOWS_LOCALE_API 991 int32_t tmpLen = 0; 992 char locName[157]; /* ULOC_FULLNAME_CAPACITY */ 993 994 tmpLen = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)locName, sizeof(locName)/sizeof(locName[0])); 995 if (tmpLen > 1) { 996 /* Windows locale name may contain sorting variant, such as "es-ES_tradnl". 997 In such case, we need special mapping data found in the hardcoded table 998 in this source file. */ 999 char *p = uprv_strchr(locName, '_'); 1000 if (p) { 1001 /* Keep the base locale, without variant */ 1002 *p = 0; 1003 tmpLen = uprv_strlen(locName); 1004 } else { 1005 /* No hardcoded table lookup necessary */ 1006 bLookup = FALSE; 1007 } 1008 /* Change the tag separator from '-' to '_' */ 1009 p = locName; 1010 while (*p) { 1011 if (*p == '-') { 1012 *p = '_'; 1013 } 1014 p++; 1015 } 1016 FIX_LANGUAGE_ID_TAG(locName, tmpLen); 1017 pPosixID = locName; 1018 } 1019 #endif 1020 if (bLookup) { 1021 const char *pCandidate = NULL; 1022 langID = LANGUAGE_LCID(hostid); 1023 1024 for (localeIndex = 0; localeIndex < gLocaleCount; localeIndex++) { 1025 if (langID == gPosixIDmap[localeIndex].regionMaps->hostID) { 1026 pCandidate = getPosixID(&gPosixIDmap[localeIndex], hostid); 1027 break; 1028 } 1029 } 1030 1031 /* On Windows, when locale name has a variant, we still look up the hardcoded table. 1032 If a match in the hardcoded table is longer than the Windows locale name without 1033 variant, we use the one as the result */ 1034 if (pCandidate && (pPosixID == NULL || uprv_strlen(pCandidate) > uprv_strlen(pPosixID))) { 1035 pPosixID = pCandidate; 1036 } 1037 } 1038 1039 if (pPosixID) { 1040 int32_t resLen = uprv_strlen(pPosixID); 1041 int32_t copyLen = resLen <= posixIDCapacity ? resLen : posixIDCapacity; 1042 uprv_memcpy(posixID, pPosixID, copyLen); 1043 if (resLen < posixIDCapacity) { 1044 posixID[resLen] = 0; 1045 if (*status == U_STRING_NOT_TERMINATED_WARNING) { 1046 *status = U_ZERO_ERROR; 1047 } 1048 } else if (resLen == posixIDCapacity) { 1049 *status = U_STRING_NOT_TERMINATED_WARNING; 1050 } else { 1051 *status = U_BUFFER_OVERFLOW_ERROR; 1052 } 1053 return resLen; 1054 } 1055 1056 /* no match found */ 1057 *status = U_ILLEGAL_ARGUMENT_ERROR; 1058 return -1; 1059 } 1060 1061 /* 1062 ////////////////////////////////////// 1063 // 1064 // POSIX --> LCID 1065 // This should only be called from uloc_getLCID. 1066 // The locale ID must be in canonical form. 1067 // langID is separate so that this file doesn't depend on the uloc_* API. 1068 // 1069 ///////////////////////////////////// 1070 */ 1071 1072 U_CAPI uint32_t 1073 uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status) 1074 { 1075 1076 uint32_t low = 0; 1077 uint32_t high = gLocaleCount; 1078 uint32_t mid; 1079 uint32_t oldmid = 0; 1080 int32_t compVal; 1081 1082 uint32_t value = 0; 1083 uint32_t fallbackValue = (uint32_t)-1; 1084 UErrorCode myStatus; 1085 uint32_t idx; 1086 1087 /* Check for incomplete id. */ 1088 if (!langID || !posixID || uprv_strlen(langID) < 2 || uprv_strlen(posixID) < 2) { 1089 return 0; 1090 } 1091 1092 /*Binary search for the map entry for normal cases */ 1093 1094 while (high > low) /*binary search*/{ 1095 1096 mid = (high+low) >> 1; /*Finds median*/ 1097 1098 if (mid == oldmid) 1099 break; 1100 1101 compVal = uprv_strcmp(langID, gPosixIDmap[mid].regionMaps->posixID); 1102 if (compVal < 0){ 1103 high = mid; 1104 } 1105 else if (compVal > 0){ 1106 low = mid; 1107 } 1108 else /*we found it*/{ 1109 return getHostID(&gPosixIDmap[mid], posixID, status); 1110 } 1111 oldmid = mid; 1112 } 1113 1114 /* 1115 * Sometimes we can't do a binary search on posixID because some LCIDs 1116 * go to different locales. We hit one of those special cases. 1117 */ 1118 for (idx = 0; idx < gLocaleCount; idx++ ) { 1119 myStatus = U_ZERO_ERROR; 1120 value = getHostID(&gPosixIDmap[idx], posixID, &myStatus); 1121 if (myStatus == U_ZERO_ERROR) { 1122 return value; 1123 } 1124 else if (myStatus == U_USING_FALLBACK_WARNING) { 1125 fallbackValue = value; 1126 } 1127 } 1128 1129 if (fallbackValue != (uint32_t)-1) { 1130 *status = U_USING_FALLBACK_WARNING; 1131 return fallbackValue; 1132 } 1133 1134 /* no match found */ 1135 *status = U_ILLEGAL_ARGUMENT_ERROR; 1136 return 0; /* return international (root) */ 1137 } 1138 1139
