1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/common/locmap.c Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,1137 @@
1.4 +/*
1.5 + **********************************************************************
1.6 + * Copyright (C) 1996-2013, International Business Machines
1.7 + * Corporation and others. All Rights Reserved.
1.8 + **********************************************************************
1.9 + *
1.10 + * Provides functionality for mapping between
1.11 + * LCID and Posix IDs or ICU locale to codepage
1.12 + *
1.13 + * Note: All classes and code in this file are
1.14 + * intended for internal use only.
1.15 + *
1.16 + * Methods of interest:
1.17 + * unsigned long convertToLCID(const char*);
1.18 + * const char* convertToPosix(unsigned long);
1.19 + *
1.20 + * Kathleen Wilson, 4/30/96
1.21 + *
1.22 + * Date Name Description
1.23 + * 3/11/97 aliu Fixed off-by-one bug in assignment operator. Added
1.24 + * setId() method and safety check against
1.25 + * MAX_ID_LENGTH.
1.26 + * 04/23/99 stephen Added C wrapper for convertToPosix.
1.27 + * 09/18/00 george Removed the memory leaks.
1.28 + * 08/23/01 george Convert to C
1.29 + */
1.30 +
1.31 +#include "locmap.h"
1.32 +#include "cstring.h"
1.33 +#include "cmemory.h"
1.34 +
1.35 +#if U_PLATFORM == U_PF_WINDOWS && defined(_MSC_VER) && (_MSC_VER >= 1500)
1.36 +/*
1.37 + * TODO: It seems like we should widen this to
1.38 + * either U_PLATFORM_USES_ONLY_WIN32_API (includes MinGW)
1.39 + * or U_PLATFORM_HAS_WIN32_API (includes MinGW and Cygwin)
1.40 + * but those use gcc and won't have defined(_MSC_VER).
1.41 + * We might need to #include some Windows header and test for some version macro from there.
1.42 + * Or call some Windows function and see what it returns.
1.43 + */
1.44 +#define USE_WINDOWS_LOCALE_API
1.45 +#endif
1.46 +
1.47 +#ifdef USE_WINDOWS_LOCALE_API
1.48 +#include <windows.h>
1.49 +#include <winnls.h>
1.50 +#endif
1.51 +
1.52 +/*
1.53 + * Note:
1.54 + * The mapping from Win32 locale ID numbers to POSIX locale strings should
1.55 + * be the faster one.
1.56 + *
1.57 + * Many LCID values come from winnt.h
1.58 + * Some also come from http://www.microsoft.com/globaldev/reference/lcid-all.mspx
1.59 + */
1.60 +
1.61 +/*
1.62 +////////////////////////////////////////////////
1.63 +//
1.64 +// Internal Classes for LCID <--> POSIX Mapping
1.65 +//
1.66 +/////////////////////////////////////////////////
1.67 +*/
1.68 +
1.69 +typedef struct ILcidPosixElement
1.70 +{
1.71 + const uint32_t hostID;
1.72 + const char * const posixID;
1.73 +} ILcidPosixElement;
1.74 +
1.75 +typedef struct ILcidPosixMap
1.76 +{
1.77 + const uint32_t numRegions;
1.78 + const struct ILcidPosixElement* const regionMaps;
1.79 +} ILcidPosixMap;
1.80 +
1.81 +
1.82 +/*
1.83 +/////////////////////////////////////////////////
1.84 +//
1.85 +// Easy macros to make the LCID <--> POSIX Mapping
1.86 +//
1.87 +/////////////////////////////////////////////////
1.88 +*/
1.89 +
1.90 +/**
1.91 + * The standard one language/one country mapping for LCID.
1.92 + * The first element must be the language, and the following
1.93 + * elements are the language with the country.
1.94 + * @param hostID LCID in host format such as 0x044d
1.95 + * @param languageID posix ID of just the language such as 'de'
1.96 + * @param posixID posix ID of the language_TERRITORY such as 'de_CH'
1.97 + */
1.98 +#define ILCID_POSIX_ELEMENT_ARRAY(hostID, languageID, posixID) \
1.99 +static const ILcidPosixElement locmap_ ## languageID [] = { \
1.100 + {LANGUAGE_LCID(hostID), #languageID}, /* parent locale */ \
1.101 + {hostID, #posixID}, \
1.102 +};
1.103 +
1.104 +/**
1.105 + * Define a subtable by ID
1.106 + * @param id the POSIX ID, either a language or language_TERRITORY
1.107 + */
1.108 +#define ILCID_POSIX_SUBTABLE(id) \
1.109 +static const ILcidPosixElement locmap_ ## id [] =
1.110 +
1.111 +
1.112 +/**
1.113 + * Create the map for the posixID. This macro supposes that the language string
1.114 + * name is the same as the global variable name, and that the first element
1.115 + * in the ILcidPosixElement is just the language.
1.116 + * @param _posixID the full POSIX ID for this entry.
1.117 + */
1.118 +#define ILCID_POSIX_MAP(_posixID) \
1.119 + {sizeof(locmap_ ## _posixID)/sizeof(ILcidPosixElement), locmap_ ## _posixID}
1.120 +
1.121 +/*
1.122 +////////////////////////////////////////////
1.123 +//
1.124 +// Create the table of LCID to POSIX Mapping
1.125 +// None of it should be dynamically created.
1.126 +//
1.127 +// Keep static locale variables inside the function so that
1.128 +// it can be created properly during static init.
1.129 +//
1.130 +// Note: This table should be updated periodically. Check the National Lanaguage Support API Reference Website.
1.131 +// Microsoft is moving away from LCID in favor of locale name as of Vista. This table needs to be
1.132 +// maintained for support of older Windows version.
1.133 +// Update: Windows 7 (091130)
1.134 +//
1.135 +// Note: Microsoft assign a different LCID if a locale has a sorting variant. POSIX IDs below may contain
1.136 +// @collation=XXX, but no other keywords are allowed (at least for now). When uprv_convertToLCID() is
1.137 +// called from uloc_getLCID(), keywords other than collation are already removed. If we really need
1.138 +// to support other keywords in this mapping data, we must update the implementation.
1.139 +////////////////////////////////////////////
1.140 +*/
1.141 +
1.142 +ILCID_POSIX_ELEMENT_ARRAY(0x0436, af, af_ZA)
1.143 +
1.144 +ILCID_POSIX_SUBTABLE(ar) {
1.145 + {0x01, "ar"},
1.146 + {0x3801, "ar_AE"},
1.147 + {0x3c01, "ar_BH"},
1.148 + {0x1401, "ar_DZ"},
1.149 + {0x0c01, "ar_EG"},
1.150 + {0x0801, "ar_IQ"},
1.151 + {0x2c01, "ar_JO"},
1.152 + {0x3401, "ar_KW"},
1.153 + {0x3001, "ar_LB"},
1.154 + {0x1001, "ar_LY"},
1.155 + {0x1801, "ar_MA"},
1.156 + {0x1801, "ar_MO"},
1.157 + {0x2001, "ar_OM"},
1.158 + {0x4001, "ar_QA"},
1.159 + {0x0401, "ar_SA"},
1.160 + {0x2801, "ar_SY"},
1.161 + {0x1c01, "ar_TN"},
1.162 + {0x2401, "ar_YE"}
1.163 +};
1.164 +
1.165 +ILCID_POSIX_ELEMENT_ARRAY(0x044d, as, as_IN)
1.166 +ILCID_POSIX_ELEMENT_ARRAY(0x045e, am, am_ET)
1.167 +ILCID_POSIX_ELEMENT_ARRAY(0x047a, arn,arn_CL)
1.168 +
1.169 +ILCID_POSIX_SUBTABLE(az) {
1.170 + {0x2c, "az"},
1.171 + {0x082c, "az_Cyrl_AZ"}, /* Cyrillic based */
1.172 + {0x742c, "az_Cyrl"}, /* Cyrillic based */
1.173 + {0x042c, "az_Latn_AZ"}, /* Latin based */
1.174 + {0x782c, "az_Latn"}, /* Latin based */
1.175 + {0x042c, "az_AZ"} /* Latin based */
1.176 +};
1.177 +
1.178 +ILCID_POSIX_ELEMENT_ARRAY(0x046d, ba, ba_RU)
1.179 +ILCID_POSIX_ELEMENT_ARRAY(0x0423, be, be_BY)
1.180 +
1.181 +/*ILCID_POSIX_SUBTABLE(ber) {
1.182 + {0x5f, "ber"},
1.183 + {0x045f, "ber_Arab_DZ"},
1.184 + {0x045f, "ber_Arab"},
1.185 + {0x085f, "ber_Latn_DZ"},
1.186 + {0x085f, "ber_Latn"}
1.187 +};*/
1.188 +
1.189 +ILCID_POSIX_ELEMENT_ARRAY(0x0402, bg, bg_BG)
1.190 +
1.191 +ILCID_POSIX_ELEMENT_ARRAY(0x0466, bin, bin_NG)
1.192 +
1.193 +ILCID_POSIX_SUBTABLE(bn) {
1.194 + {0x45, "bn"},
1.195 + {0x0845, "bn_BD"},
1.196 + {0x0445, "bn_IN"}
1.197 +};
1.198 +
1.199 +ILCID_POSIX_SUBTABLE(bo) {
1.200 + {0x51, "bo"},
1.201 + {0x0851, "bo_BT"},
1.202 + {0x0451, "bo_CN"}
1.203 +};
1.204 +
1.205 +ILCID_POSIX_ELEMENT_ARRAY(0x047e, br, br_FR)
1.206 +
1.207 +ILCID_POSIX_SUBTABLE(ca) {
1.208 + {0x03, "ca"},
1.209 + {0x0403, "ca_ES"},
1.210 + {0x0803, "ca_ES_VALENCIA"}
1.211 +};
1.212 +
1.213 +ILCID_POSIX_ELEMENT_ARRAY(0x0483, co, co_FR)
1.214 +ILCID_POSIX_ELEMENT_ARRAY(0x045c, chr,chr_US)
1.215 +
1.216 +ILCID_POSIX_SUBTABLE(ckb) {
1.217 + {0x92, "ckb"},
1.218 + {0x92, "ku"},
1.219 + {0x7c92, "ckb_Arab"},
1.220 + {0x7c92, "ku_Arab"},
1.221 + {0x0492, "ckb_Arab_IQ"},
1.222 + {0x0492, "ku_Arab_IQ"}
1.223 +};
1.224 +
1.225 +/* Declared as cs_CZ to get around compiler errors on z/OS, which defines cs as a function */
1.226 +ILCID_POSIX_ELEMENT_ARRAY(0x0405, cs, cs_CZ)
1.227 +
1.228 +ILCID_POSIX_ELEMENT_ARRAY(0x0452, cy, cy_GB)
1.229 +ILCID_POSIX_ELEMENT_ARRAY(0x0406, da, da_DK)
1.230 +
1.231 +ILCID_POSIX_SUBTABLE(de) {
1.232 + {0x07, "de"},
1.233 + {0x0c07, "de_AT"},
1.234 + {0x0807, "de_CH"},
1.235 + {0x0407, "de_DE"},
1.236 + {0x1407, "de_LI"},
1.237 + {0x1007, "de_LU"},
1.238 + {0x10407,"de_DE@collation=phonebook"}, /*This is really de_DE_PHONEBOOK on Windows*/
1.239 + {0x10407,"de@collation=phonebook"} /*This is really de_DE_PHONEBOOK on Windows*/
1.240 +};
1.241 +
1.242 +ILCID_POSIX_ELEMENT_ARRAY(0x0465, dv, dv_MV)
1.243 +ILCID_POSIX_ELEMENT_ARRAY(0x0408, el, el_GR)
1.244 +
1.245 +ILCID_POSIX_SUBTABLE(en) {
1.246 + {0x09, "en"},
1.247 + {0x0c09, "en_AU"},
1.248 + {0x2809, "en_BZ"},
1.249 + {0x1009, "en_CA"},
1.250 + {0x0809, "en_GB"},
1.251 + {0x3c09, "en_HK"},
1.252 + {0x3809, "en_ID"},
1.253 + {0x1809, "en_IE"},
1.254 + {0x4009, "en_IN"},
1.255 + {0x2009, "en_JM"},
1.256 + {0x4409, "en_MY"},
1.257 + {0x1409, "en_NZ"},
1.258 + {0x3409, "en_PH"},
1.259 + {0x4809, "en_SG"},
1.260 + {0x2C09, "en_TT"},
1.261 + {0x0409, "en_US"},
1.262 + {0x007f, "en_US_POSIX"}, /* duplicate for roundtripping */
1.263 + {0x2409, "en_VI"}, /* Virgin Islands AKA Caribbean Islands (en_CB). */
1.264 + {0x1c09, "en_ZA"},
1.265 + {0x3009, "en_ZW"},
1.266 + {0x2409, "en_029"},
1.267 + {0x0409, "en_AS"}, /* Alias for en_US. Leave last. */
1.268 + {0x0409, "en_GU"}, /* Alias for en_US. Leave last. */
1.269 + {0x0409, "en_MH"}, /* Alias for en_US. Leave last. */
1.270 + {0x0409, "en_MP"}, /* Alias for en_US. Leave last. */
1.271 + {0x0409, "en_UM"} /* Alias for en_US. Leave last. */
1.272 +};
1.273 +
1.274 +ILCID_POSIX_SUBTABLE(en_US_POSIX) {
1.275 + {0x007f, "en_US_POSIX"} /* duplicate for roundtripping */
1.276 +};
1.277 +
1.278 +ILCID_POSIX_SUBTABLE(es) {
1.279 + {0x0a, "es"},
1.280 + {0x2c0a, "es_AR"},
1.281 + {0x400a, "es_BO"},
1.282 + {0x340a, "es_CL"},
1.283 + {0x240a, "es_CO"},
1.284 + {0x140a, "es_CR"},
1.285 + {0x1c0a, "es_DO"},
1.286 + {0x300a, "es_EC"},
1.287 + {0x0c0a, "es_ES"}, /*Modern sort.*/
1.288 + {0x100a, "es_GT"},
1.289 + {0x480a, "es_HN"},
1.290 + {0x080a, "es_MX"},
1.291 + {0x4c0a, "es_NI"},
1.292 + {0x180a, "es_PA"},
1.293 + {0x280a, "es_PE"},
1.294 + {0x500a, "es_PR"},
1.295 + {0x3c0a, "es_PY"},
1.296 + {0x440a, "es_SV"},
1.297 + {0x540a, "es_US"},
1.298 + {0x380a, "es_UY"},
1.299 + {0x200a, "es_VE"},
1.300 + {0xe40a, "es_419"},
1.301 + {0x040a, "es_ES@collation=traditional"},
1.302 + {0x040a, "es@collation=traditional"}
1.303 +};
1.304 +
1.305 +ILCID_POSIX_ELEMENT_ARRAY(0x0425, et, et_EE)
1.306 +ILCID_POSIX_ELEMENT_ARRAY(0x042d, eu, eu_ES)
1.307 +
1.308 +/* ISO-639 doesn't distinguish between Persian and Dari.*/
1.309 +ILCID_POSIX_SUBTABLE(fa) {
1.310 + {0x29, "fa"},
1.311 + {0x0429, "fa_IR"}, /* Persian/Farsi (Iran) */
1.312 + {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */
1.313 +};
1.314 +
1.315 +/* duplicate for roundtripping */
1.316 +ILCID_POSIX_SUBTABLE(fa_AF) {
1.317 + {0x8c, "fa_AF"}, /* Persian/Dari (Afghanistan) */
1.318 + {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */
1.319 +};
1.320 +
1.321 +ILCID_POSIX_SUBTABLE(ff) {
1.322 + {0x67, "ff"},
1.323 + {0x7c67, "ff_Latn"},
1.324 + {0x0867, "ff_Latn_SN"}
1.325 +};
1.326 +
1.327 +ILCID_POSIX_ELEMENT_ARRAY(0x040b, fi, fi_FI)
1.328 +ILCID_POSIX_ELEMENT_ARRAY(0x0464, fil,fil_PH)
1.329 +ILCID_POSIX_ELEMENT_ARRAY(0x0438, fo, fo_FO)
1.330 +
1.331 +ILCID_POSIX_SUBTABLE(fr) {
1.332 + {0x0c, "fr"},
1.333 + {0x080c, "fr_BE"},
1.334 + {0x0c0c, "fr_CA"},
1.335 + {0x240c, "fr_CD"},
1.336 + {0x240c, "fr_CG"},
1.337 + {0x100c, "fr_CH"},
1.338 + {0x300c, "fr_CI"},
1.339 + {0x2c0c, "fr_CM"},
1.340 + {0x040c, "fr_FR"},
1.341 + {0x3c0c, "fr_HT"},
1.342 + {0x140c, "fr_LU"},
1.343 + {0x380c, "fr_MA"},
1.344 + {0x180c, "fr_MC"},
1.345 + {0x340c, "fr_ML"},
1.346 + {0x200c, "fr_RE"},
1.347 + {0x280c, "fr_SN"},
1.348 + {0xe40c, "fr_015"},
1.349 + {0x1c0c, "fr_029"}
1.350 +};
1.351 +
1.352 +ILCID_POSIX_ELEMENT_ARRAY(0x0467, fuv, fuv_NG)
1.353 +
1.354 +ILCID_POSIX_ELEMENT_ARRAY(0x0462, fy, fy_NL)
1.355 +
1.356 +ILCID_POSIX_SUBTABLE(ga) { /* Gaelic (Ireland) */
1.357 + {0x3c, "ga"},
1.358 + {0x083c, "ga_IE"},
1.359 + {0x043c, "gd_GB"}
1.360 +};
1.361 +
1.362 +ILCID_POSIX_SUBTABLE(gd) { /* Gaelic (Scotland) */
1.363 + {0x91, "gd"},
1.364 + {0x0491, "gd_GB"}
1.365 +};
1.366 +
1.367 +ILCID_POSIX_ELEMENT_ARRAY(0x0456, gl, gl_ES)
1.368 +ILCID_POSIX_ELEMENT_ARRAY(0x0447, gu, gu_IN)
1.369 +ILCID_POSIX_ELEMENT_ARRAY(0x0474, gn, gn_PY)
1.370 +ILCID_POSIX_ELEMENT_ARRAY(0x0484, gsw,gsw_FR)
1.371 +
1.372 +ILCID_POSIX_SUBTABLE(ha) {
1.373 + {0x68, "ha"},
1.374 + {0x7c68, "ha_Latn"},
1.375 + {0x0468, "ha_Latn_NG"},
1.376 +};
1.377 +
1.378 +ILCID_POSIX_ELEMENT_ARRAY(0x0475, haw,haw_US)
1.379 +ILCID_POSIX_ELEMENT_ARRAY(0x040d, he, he_IL)
1.380 +ILCID_POSIX_ELEMENT_ARRAY(0x0439, hi, hi_IN)
1.381 +
1.382 +/* This LCID is really four different locales.*/
1.383 +ILCID_POSIX_SUBTABLE(hr) {
1.384 + {0x1a, "hr"},
1.385 + {0x141a, "bs_Latn_BA"}, /* Bosnian, Bosnia and Herzegovina */
1.386 + {0x681a, "bs_Latn"}, /* Bosnian, Bosnia and Herzegovina */
1.387 + {0x141a, "bs_BA"}, /* Bosnian, Bosnia and Herzegovina */
1.388 + {0x781a, "bs"}, /* Bosnian */
1.389 + {0x201a, "bs_Cyrl_BA"}, /* Bosnian, Bosnia and Herzegovina */
1.390 + {0x641a, "bs_Cyrl"}, /* Bosnian, Bosnia and Herzegovina */
1.391 + {0x101a, "hr_BA"}, /* Croatian in Bosnia */
1.392 + {0x041a, "hr_HR"}, /* Croatian*/
1.393 + {0x2c1a, "sr_Latn_ME"},
1.394 + {0x241a, "sr_Latn_RS"},
1.395 + {0x181a, "sr_Latn_BA"}, /* Serbo-Croatian in Bosnia */
1.396 + {0x081a, "sr_Latn_CS"}, /* Serbo-Croatian*/
1.397 + {0x701a, "sr_Latn"}, /* It's 0x1a or 0x081a, pick one to make the test program happy. */
1.398 + {0x1c1a, "sr_Cyrl_BA"}, /* Serbo-Croatian in Bosnia */
1.399 + {0x0c1a, "sr_Cyrl_CS"}, /* Serbian*/
1.400 + {0x301a, "sr_Cyrl_ME"},
1.401 + {0x281a, "sr_Cyrl_RS"},
1.402 + {0x6c1a, "sr_Cyrl"}, /* It's 0x1a or 0x0c1a, pick one to make the test program happy. */
1.403 + {0x7c1a, "sr"} /* In CLDR sr is sr_Cyrl. */
1.404 +};
1.405 +
1.406 +ILCID_POSIX_ELEMENT_ARRAY(0x040e, hu, hu_HU)
1.407 +ILCID_POSIX_ELEMENT_ARRAY(0x042b, hy, hy_AM)
1.408 +ILCID_POSIX_ELEMENT_ARRAY(0x0469, ibb, ibb_NG)
1.409 +ILCID_POSIX_ELEMENT_ARRAY(0x0421, id, id_ID)
1.410 +ILCID_POSIX_ELEMENT_ARRAY(0x0470, ig, ig_NG)
1.411 +ILCID_POSIX_ELEMENT_ARRAY(0x0478, ii, ii_CN)
1.412 +ILCID_POSIX_ELEMENT_ARRAY(0x040f, is, is_IS)
1.413 +
1.414 +ILCID_POSIX_SUBTABLE(it) {
1.415 + {0x10, "it"},
1.416 + {0x0810, "it_CH"},
1.417 + {0x0410, "it_IT"}
1.418 +};
1.419 +
1.420 +ILCID_POSIX_SUBTABLE(iu) {
1.421 + {0x5d, "iu"},
1.422 + {0x045d, "iu_Cans_CA"},
1.423 + {0x785d, "iu_Cans"},
1.424 + {0x085d, "iu_Latn_CA"},
1.425 + {0x7c5d, "iu_Latn"}
1.426 +};
1.427 +
1.428 +ILCID_POSIX_ELEMENT_ARRAY(0x040d, iw, iw_IL) /*Left in for compatibility*/
1.429 +ILCID_POSIX_ELEMENT_ARRAY(0x0411, ja, ja_JP)
1.430 +ILCID_POSIX_ELEMENT_ARRAY(0x0437, ka, ka_GE)
1.431 +ILCID_POSIX_ELEMENT_ARRAY(0x043f, kk, kk_KZ)
1.432 +ILCID_POSIX_ELEMENT_ARRAY(0x046f, kl, kl_GL)
1.433 +ILCID_POSIX_ELEMENT_ARRAY(0x0453, km, km_KH)
1.434 +ILCID_POSIX_ELEMENT_ARRAY(0x044b, kn, kn_IN)
1.435 +
1.436 +ILCID_POSIX_SUBTABLE(ko) {
1.437 + {0x12, "ko"},
1.438 + {0x0812, "ko_KP"},
1.439 + {0x0412, "ko_KR"}
1.440 +};
1.441 +
1.442 +ILCID_POSIX_ELEMENT_ARRAY(0x0457, kok, kok_IN)
1.443 +ILCID_POSIX_ELEMENT_ARRAY(0x0471, kr, kr_NG)
1.444 +
1.445 +ILCID_POSIX_SUBTABLE(ks) { /* We could add PK and CN too */
1.446 + {0x60, "ks"},
1.447 + {0x0860, "ks_IN"}, /* Documentation doesn't mention script */
1.448 + {0x0460, "ks_Arab_IN"},
1.449 + {0x0860, "ks_Deva_IN"}
1.450 +};
1.451 +
1.452 +ILCID_POSIX_ELEMENT_ARRAY(0x0440, ky, ky_KG) /* Kyrgyz is spoken in Kyrgyzstan */
1.453 +ILCID_POSIX_ELEMENT_ARRAY(0x0476, la, la_IT) /* TODO: Verify the country */
1.454 +ILCID_POSIX_ELEMENT_ARRAY(0x046e, lb, lb_LU)
1.455 +ILCID_POSIX_ELEMENT_ARRAY(0x0454, lo, lo_LA)
1.456 +ILCID_POSIX_ELEMENT_ARRAY(0x0427, lt, lt_LT)
1.457 +ILCID_POSIX_ELEMENT_ARRAY(0x0426, lv, lv_LV)
1.458 +ILCID_POSIX_ELEMENT_ARRAY(0x0481, mi, mi_NZ)
1.459 +ILCID_POSIX_ELEMENT_ARRAY(0x042f, mk, mk_MK)
1.460 +ILCID_POSIX_ELEMENT_ARRAY(0x044c, ml, ml_IN)
1.461 +
1.462 +ILCID_POSIX_SUBTABLE(mn) {
1.463 + {0x50, "mn"},
1.464 + {0x0450, "mn_MN"},
1.465 + {0x7c50, "mn_Mong"},
1.466 + {0x0850, "mn_Mong_CN"},
1.467 + {0x0850, "mn_CN"},
1.468 + {0x7850, "mn_Cyrl"}
1.469 +};
1.470 +
1.471 +ILCID_POSIX_ELEMENT_ARRAY(0x0458, mni,mni_IN)
1.472 +ILCID_POSIX_ELEMENT_ARRAY(0x047c, moh,moh_CA)
1.473 +ILCID_POSIX_ELEMENT_ARRAY(0x044e, mr, mr_IN)
1.474 +
1.475 +ILCID_POSIX_SUBTABLE(ms) {
1.476 + {0x3e, "ms"},
1.477 + {0x083e, "ms_BN"}, /* Brunei Darussalam*/
1.478 + {0x043e, "ms_MY"} /* Malaysia*/
1.479 +};
1.480 +
1.481 +ILCID_POSIX_ELEMENT_ARRAY(0x043a, mt, mt_MT)
1.482 +ILCID_POSIX_ELEMENT_ARRAY(0x0455, my, my_MM)
1.483 +
1.484 +ILCID_POSIX_SUBTABLE(ne) {
1.485 + {0x61, "ne"},
1.486 + {0x0861, "ne_IN"}, /* India*/
1.487 + {0x0461, "ne_NP"} /* Nepal*/
1.488 +};
1.489 +
1.490 +ILCID_POSIX_SUBTABLE(nl) {
1.491 + {0x13, "nl"},
1.492 + {0x0813, "nl_BE"},
1.493 + {0x0413, "nl_NL"}
1.494 +};
1.495 +
1.496 +/* The "no" locale split into nb and nn. By default in ICU, "no" is nb.*/
1.497 +ILCID_POSIX_SUBTABLE(no) {
1.498 + {0x14, "no"}, /* really nb_NO */
1.499 + {0x7c14, "nb"}, /* really nb */
1.500 + {0x0414, "nb_NO"}, /* really nb_NO. Keep first in the 414 list. */
1.501 + {0x0414, "no_NO"}, /* really nb_NO */
1.502 + {0x0814, "nn_NO"}, /* really nn_NO. Keep first in the 814 list. */
1.503 + {0x7814, "nn"}, /* It's 0x14 or 0x814, pick one to make the test program happy. */
1.504 + {0x0814, "no_NO_NY"}/* really nn_NO */
1.505 +};
1.506 +
1.507 +ILCID_POSIX_ELEMENT_ARRAY(0x046c, nso,nso_ZA) /* TODO: Verify the ISO-639 code */
1.508 +ILCID_POSIX_ELEMENT_ARRAY(0x0482, oc, oc_FR)
1.509 +
1.510 +ILCID_POSIX_SUBTABLE(om) { /* TODO: Verify the country */
1.511 + {0x72, "om"},
1.512 + {0x0472, "om_ET"},
1.513 + {0x0472, "gaz_ET"}
1.514 +};
1.515 +
1.516 +/* Declared as or_IN to get around compiler errors*/
1.517 +ILCID_POSIX_SUBTABLE(or_IN) {
1.518 + {0x48, "or"},
1.519 + {0x0448, "or_IN"},
1.520 +};
1.521 +
1.522 +
1.523 +ILCID_POSIX_SUBTABLE(pa) {
1.524 + {0x46, "pa"},
1.525 + {0x0446, "pa_IN"},
1.526 + {0x0846, "pa_PK"},
1.527 + {0x0846, "pa_Arab_PK"}
1.528 +};
1.529 +
1.530 +ILCID_POSIX_ELEMENT_ARRAY(0x0479, pap, pap_AN)
1.531 +ILCID_POSIX_ELEMENT_ARRAY(0x0415, pl, pl_PL)
1.532 +ILCID_POSIX_ELEMENT_ARRAY(0x0463, ps, ps_AF)
1.533 +
1.534 +ILCID_POSIX_SUBTABLE(pt) {
1.535 + {0x16, "pt"},
1.536 + {0x0416, "pt_BR"},
1.537 + {0x0816, "pt_PT"}
1.538 +};
1.539 +
1.540 +ILCID_POSIX_SUBTABLE(qu) {
1.541 + {0x6b, "qu"},
1.542 + {0x046b, "qu_BO"},
1.543 + {0x086b, "qu_EC"},
1.544 + {0x0C6b, "qu_PE"},
1.545 + {0x046b, "quz_BO"},
1.546 + {0x086b, "quz_EC"},
1.547 + {0x0C6b, "quz_PE"}
1.548 +};
1.549 +
1.550 +ILCID_POSIX_ELEMENT_ARRAY(0x0486, qut, qut_GT) /* qut is an ISO-639-3 code */
1.551 +ILCID_POSIX_ELEMENT_ARRAY(0x0417, rm, rm_CH)
1.552 +
1.553 +ILCID_POSIX_SUBTABLE(ro) {
1.554 + {0x18, "ro"},
1.555 + {0x0418, "ro_RO"},
1.556 + {0x0818, "ro_MD"}
1.557 +};
1.558 +
1.559 +ILCID_POSIX_SUBTABLE(root) {
1.560 + {0x00, "root"}
1.561 +};
1.562 +
1.563 +ILCID_POSIX_SUBTABLE(ru) {
1.564 + {0x19, "ru"},
1.565 + {0x0419, "ru_RU"},
1.566 + {0x0819, "ru_MD"}
1.567 +};
1.568 +
1.569 +ILCID_POSIX_ELEMENT_ARRAY(0x0487, rw, rw_RW)
1.570 +ILCID_POSIX_ELEMENT_ARRAY(0x044f, sa, sa_IN)
1.571 +ILCID_POSIX_ELEMENT_ARRAY(0x0485, sah,sah_RU)
1.572 +
1.573 +ILCID_POSIX_SUBTABLE(sd) {
1.574 + {0x59, "sd"},
1.575 + {0x0459, "sd_IN"},
1.576 + {0x0859, "sd_PK"}
1.577 +};
1.578 +
1.579 +ILCID_POSIX_SUBTABLE(se) {
1.580 + {0x3b, "se"},
1.581 + {0x0c3b, "se_FI"},
1.582 + {0x043b, "se_NO"},
1.583 + {0x083b, "se_SE"},
1.584 + {0x783b, "sma"},
1.585 + {0x183b, "sma_NO"},
1.586 + {0x1c3b, "sma_SE"},
1.587 + {0x7c3b, "smj"},
1.588 + {0x703b, "smn"},
1.589 + {0x743b, "sms"},
1.590 + {0x103b, "smj_NO"},
1.591 + {0x143b, "smj_SE"},
1.592 + {0x243b, "smn_FI"},
1.593 + {0x203b, "sms_FI"},
1.594 +};
1.595 +
1.596 +ILCID_POSIX_ELEMENT_ARRAY(0x045b, si, si_LK)
1.597 +ILCID_POSIX_ELEMENT_ARRAY(0x041b, sk, sk_SK)
1.598 +ILCID_POSIX_ELEMENT_ARRAY(0x0424, sl, sl_SI)
1.599 +
1.600 +ILCID_POSIX_SUBTABLE(so) { /* TODO: Verify the country */
1.601 + {0x77, "so"},
1.602 + {0x0477, "so_ET"},
1.603 + {0x0477, "so_SO"}
1.604 +};
1.605 +
1.606 +ILCID_POSIX_ELEMENT_ARRAY(0x041c, sq, sq_AL)
1.607 +ILCID_POSIX_ELEMENT_ARRAY(0x0430, st, st_ZA)
1.608 +
1.609 +ILCID_POSIX_SUBTABLE(sv) {
1.610 + {0x1d, "sv"},
1.611 + {0x081d, "sv_FI"},
1.612 + {0x041d, "sv_SE"}
1.613 +};
1.614 +
1.615 +ILCID_POSIX_ELEMENT_ARRAY(0x0441, sw, sw_KE)
1.616 +ILCID_POSIX_ELEMENT_ARRAY(0x045A, syr, syr_SY)
1.617 +
1.618 +ILCID_POSIX_SUBTABLE(ta) {
1.619 + {0x49, "ta"},
1.620 + {0x0449, "ta_IN"},
1.621 + {0x0849, "ta_LK"}
1.622 +};
1.623 +
1.624 +ILCID_POSIX_ELEMENT_ARRAY(0x044a, te, te_IN)
1.625 +
1.626 +/* Cyrillic based by default */
1.627 +ILCID_POSIX_SUBTABLE(tg) {
1.628 + {0x28, "tg"},
1.629 + {0x7c28, "tg_Cyrl"},
1.630 + {0x0428, "tg_Cyrl_TJ"}
1.631 +};
1.632 +
1.633 +ILCID_POSIX_ELEMENT_ARRAY(0x041e, th, th_TH)
1.634 +
1.635 +ILCID_POSIX_SUBTABLE(ti) {
1.636 + {0x73, "ti"},
1.637 + {0x0873, "ti_ER"},
1.638 + {0x0473, "ti_ET"}
1.639 +};
1.640 +
1.641 +ILCID_POSIX_ELEMENT_ARRAY(0x0442, tk, tk_TM)
1.642 +
1.643 +ILCID_POSIX_SUBTABLE(tn) {
1.644 + {0x32, "tn"},
1.645 + {0x0832, "tn_BW"},
1.646 + {0x0432, "tn_ZA"}
1.647 +};
1.648 +
1.649 +ILCID_POSIX_ELEMENT_ARRAY(0x041f, tr, tr_TR)
1.650 +ILCID_POSIX_ELEMENT_ARRAY(0x0431, ts, ts_ZA)
1.651 +ILCID_POSIX_ELEMENT_ARRAY(0x0444, tt, tt_RU)
1.652 +
1.653 +ILCID_POSIX_SUBTABLE(tzm) {
1.654 + {0x5f, "tzm"},
1.655 + {0x7c5f, "tzm_Latn"},
1.656 + {0x085f, "tzm_Latn_DZ"},
1.657 + {0x105f, "tzm_Tfng_MA"},
1.658 + {0x045f, "tmz"}
1.659 +};
1.660 +
1.661 +ILCID_POSIX_SUBTABLE(ug) {
1.662 + {0x80, "ug"},
1.663 + {0x0480, "ug_CN"},
1.664 + {0x0480, "ug_Arab_CN"}
1.665 +};
1.666 +
1.667 +ILCID_POSIX_ELEMENT_ARRAY(0x0422, uk, uk_UA)
1.668 +
1.669 +ILCID_POSIX_SUBTABLE(ur) {
1.670 + {0x20, "ur"},
1.671 + {0x0820, "ur_IN"},
1.672 + {0x0420, "ur_PK"}
1.673 +};
1.674 +
1.675 +ILCID_POSIX_SUBTABLE(uz) {
1.676 + {0x43, "uz"},
1.677 + {0x0843, "uz_Cyrl_UZ"}, /* Cyrillic based */
1.678 + {0x7843, "uz_Cyrl"}, /* Cyrillic based */
1.679 + {0x0843, "uz_UZ"}, /* Cyrillic based */
1.680 + {0x0443, "uz_Latn_UZ"}, /* Latin based */
1.681 + {0x7c43, "uz_Latn"} /* Latin based */
1.682 +};
1.683 +
1.684 +ILCID_POSIX_SUBTABLE(ve) { /* TODO: Verify the country */
1.685 + {0x33, "ve"},
1.686 + {0x0433, "ve_ZA"},
1.687 + {0x0433, "ven_ZA"}
1.688 +};
1.689 +
1.690 +ILCID_POSIX_ELEMENT_ARRAY(0x042a, vi, vi_VN)
1.691 +
1.692 +ILCID_POSIX_SUBTABLE(wen) {
1.693 + {0x2E, "wen"},
1.694 + {0x042E, "wen_DE"},
1.695 + {0x042E, "hsb_DE"},
1.696 + {0x082E, "dsb_DE"},
1.697 + {0x7C2E, "dsb"},
1.698 + {0x2E, "hsb"}
1.699 +};
1.700 +
1.701 +ILCID_POSIX_ELEMENT_ARRAY(0x0488, wo, wo_SN)
1.702 +ILCID_POSIX_ELEMENT_ARRAY(0x0434, xh, xh_ZA)
1.703 +ILCID_POSIX_ELEMENT_ARRAY(0x043d, yi, yi)
1.704 +ILCID_POSIX_ELEMENT_ARRAY(0x046a, yo, yo_NG)
1.705 +
1.706 +ILCID_POSIX_SUBTABLE(zh) {
1.707 + {0x0004, "zh_Hans"},
1.708 + {0x7804, "zh"},
1.709 + {0x0804, "zh_CN"},
1.710 + {0x0804, "zh_Hans_CN"},
1.711 + {0x0c04, "zh_Hant_HK"},
1.712 + {0x0c04, "zh_HK"},
1.713 + {0x1404, "zh_Hant_MO"},
1.714 + {0x1404, "zh_MO"},
1.715 + {0x1004, "zh_Hans_SG"},
1.716 + {0x1004, "zh_SG"},
1.717 + {0x0404, "zh_Hant_TW"},
1.718 + {0x7c04, "zh_Hant"},
1.719 + {0x0404, "zh_TW"},
1.720 + {0x30404,"zh_Hant_TW"}, /* Bopomofo order */
1.721 + {0x30404,"zh_TW"}, /* Bopomofo order */
1.722 + {0x20004,"zh@collation=stroke"},
1.723 + {0x20404,"zh_Hant@collation=stroke"},
1.724 + {0x20404,"zh_Hant_TW@collation=stroke"},
1.725 + {0x20404,"zh_TW@collation=stroke"},
1.726 + {0x20804,"zh_Hans@collation=stroke"},
1.727 + {0x20804,"zh_Hans_CN@collation=stroke"},
1.728 + {0x20804,"zh_CN@collation=stroke"}
1.729 +};
1.730 +
1.731 +ILCID_POSIX_ELEMENT_ARRAY(0x0435, zu, zu_ZA)
1.732 +
1.733 +/* This must be static and grouped by LCID. */
1.734 +static const ILcidPosixMap gPosixIDmap[] = {
1.735 + ILCID_POSIX_MAP(af), /* af Afrikaans 0x36 */
1.736 + ILCID_POSIX_MAP(am), /* am Amharic 0x5e */
1.737 + ILCID_POSIX_MAP(ar), /* ar Arabic 0x01 */
1.738 + ILCID_POSIX_MAP(arn), /* arn Araucanian/Mapudungun 0x7a */
1.739 + ILCID_POSIX_MAP(as), /* as Assamese 0x4d */
1.740 + ILCID_POSIX_MAP(az), /* az Azerbaijani 0x2c */
1.741 + ILCID_POSIX_MAP(ba), /* ba Bashkir 0x6d */
1.742 + ILCID_POSIX_MAP(be), /* be Belarusian 0x23 */
1.743 +/* ILCID_POSIX_MAP(ber), ber Berber/Tamazight 0x5f */
1.744 + ILCID_POSIX_MAP(bg), /* bg Bulgarian 0x02 */
1.745 + ILCID_POSIX_MAP(bin), /* bin Edo 0x66 */
1.746 + ILCID_POSIX_MAP(bn), /* bn Bengali; Bangla 0x45 */
1.747 + ILCID_POSIX_MAP(bo), /* bo Tibetan 0x51 */
1.748 + ILCID_POSIX_MAP(br), /* br Breton 0x7e */
1.749 + ILCID_POSIX_MAP(ca), /* ca Catalan 0x03 */
1.750 + ILCID_POSIX_MAP(chr), /* chr Cherokee 0x5c */
1.751 + ILCID_POSIX_MAP(ckb), /* ckb Sorani (Central Kurdish) 0x92 */
1.752 + ILCID_POSIX_MAP(co), /* co Corsican 0x83 */
1.753 + ILCID_POSIX_MAP(cs), /* cs Czech 0x05 */
1.754 + ILCID_POSIX_MAP(cy), /* cy Welsh 0x52 */
1.755 + ILCID_POSIX_MAP(da), /* da Danish 0x06 */
1.756 + ILCID_POSIX_MAP(de), /* de German 0x07 */
1.757 + ILCID_POSIX_MAP(dv), /* dv Divehi 0x65 */
1.758 + ILCID_POSIX_MAP(el), /* el Greek 0x08 */
1.759 + ILCID_POSIX_MAP(en), /* en English 0x09 */
1.760 + ILCID_POSIX_MAP(en_US_POSIX), /* invariant 0x7f */
1.761 + ILCID_POSIX_MAP(es), /* es Spanish 0x0a */
1.762 + ILCID_POSIX_MAP(et), /* et Estonian 0x25 */
1.763 + ILCID_POSIX_MAP(eu), /* eu Basque 0x2d */
1.764 + ILCID_POSIX_MAP(fa), /* fa Persian/Farsi 0x29 */
1.765 + ILCID_POSIX_MAP(fa_AF), /* fa Persian/Dari 0x8c */
1.766 + ILCID_POSIX_MAP(ff), /* ff Fula 0x67 */
1.767 + ILCID_POSIX_MAP(fi), /* fi Finnish 0x0b */
1.768 + ILCID_POSIX_MAP(fil), /* fil Filipino 0x64 */
1.769 + ILCID_POSIX_MAP(fo), /* fo Faroese 0x38 */
1.770 + ILCID_POSIX_MAP(fr), /* fr French 0x0c */
1.771 + ILCID_POSIX_MAP(fuv), /* fuv Fulfulde - Nigeria 0x67 */
1.772 + ILCID_POSIX_MAP(fy), /* fy Frisian 0x62 */
1.773 + ILCID_POSIX_MAP(ga), /* * Gaelic (Ireland,Scotland) 0x3c */
1.774 + ILCID_POSIX_MAP(gd), /* gd Gaelic (United Kingdom) 0x91 */
1.775 + ILCID_POSIX_MAP(gl), /* gl Galician 0x56 */
1.776 + ILCID_POSIX_MAP(gn), /* gn Guarani 0x74 */
1.777 + ILCID_POSIX_MAP(gsw), /* gsw Alemanic/Alsatian/Swiss German 0x84 */
1.778 + ILCID_POSIX_MAP(gu), /* gu Gujarati 0x47 */
1.779 + ILCID_POSIX_MAP(ha), /* ha Hausa 0x68 */
1.780 + ILCID_POSIX_MAP(haw), /* haw Hawaiian 0x75 */
1.781 + ILCID_POSIX_MAP(he), /* he Hebrew (formerly iw) 0x0d */
1.782 + ILCID_POSIX_MAP(hi), /* hi Hindi 0x39 */
1.783 + ILCID_POSIX_MAP(hr), /* * Croatian and others 0x1a */
1.784 + ILCID_POSIX_MAP(hu), /* hu Hungarian 0x0e */
1.785 + ILCID_POSIX_MAP(hy), /* hy Armenian 0x2b */
1.786 + ILCID_POSIX_MAP(ibb), /* ibb Ibibio - Nigeria 0x69 */
1.787 + ILCID_POSIX_MAP(id), /* id Indonesian (formerly in) 0x21 */
1.788 + ILCID_POSIX_MAP(ig), /* ig Igbo 0x70 */
1.789 + ILCID_POSIX_MAP(ii), /* ii Sichuan Yi 0x78 */
1.790 + ILCID_POSIX_MAP(is), /* is Icelandic 0x0f */
1.791 + ILCID_POSIX_MAP(it), /* it Italian 0x10 */
1.792 + ILCID_POSIX_MAP(iu), /* iu Inuktitut 0x5d */
1.793 + ILCID_POSIX_MAP(iw), /* iw Hebrew 0x0d */
1.794 + ILCID_POSIX_MAP(ja), /* ja Japanese 0x11 */
1.795 + ILCID_POSIX_MAP(ka), /* ka Georgian 0x37 */
1.796 + ILCID_POSIX_MAP(kk), /* kk Kazakh 0x3f */
1.797 + ILCID_POSIX_MAP(kl), /* kl Kalaallisut 0x6f */
1.798 + ILCID_POSIX_MAP(km), /* km Khmer 0x53 */
1.799 + ILCID_POSIX_MAP(kn), /* kn Kannada 0x4b */
1.800 + ILCID_POSIX_MAP(ko), /* ko Korean 0x12 */
1.801 + ILCID_POSIX_MAP(kok), /* kok Konkani 0x57 */
1.802 + ILCID_POSIX_MAP(kr), /* kr Kanuri 0x71 */
1.803 + ILCID_POSIX_MAP(ks), /* ks Kashmiri 0x60 */
1.804 + ILCID_POSIX_MAP(ky), /* ky Kyrgyz 0x40 */
1.805 + ILCID_POSIX_MAP(lb), /* lb Luxembourgish 0x6e */
1.806 + ILCID_POSIX_MAP(la), /* la Latin 0x76 */
1.807 + ILCID_POSIX_MAP(lo), /* lo Lao 0x54 */
1.808 + ILCID_POSIX_MAP(lt), /* lt Lithuanian 0x27 */
1.809 + ILCID_POSIX_MAP(lv), /* lv Latvian, Lettish 0x26 */
1.810 + ILCID_POSIX_MAP(mi), /* mi Maori 0x81 */
1.811 + ILCID_POSIX_MAP(mk), /* mk Macedonian 0x2f */
1.812 + ILCID_POSIX_MAP(ml), /* ml Malayalam 0x4c */
1.813 + ILCID_POSIX_MAP(mn), /* mn Mongolian 0x50 */
1.814 + ILCID_POSIX_MAP(mni), /* mni Manipuri 0x58 */
1.815 + ILCID_POSIX_MAP(moh), /* moh Mohawk 0x7c */
1.816 + ILCID_POSIX_MAP(mr), /* mr Marathi 0x4e */
1.817 + ILCID_POSIX_MAP(ms), /* ms Malay 0x3e */
1.818 + ILCID_POSIX_MAP(mt), /* mt Maltese 0x3a */
1.819 + ILCID_POSIX_MAP(my), /* my Burmese 0x55 */
1.820 +/* ILCID_POSIX_MAP(nb), // no Norwegian 0x14 */
1.821 + ILCID_POSIX_MAP(ne), /* ne Nepali 0x61 */
1.822 + ILCID_POSIX_MAP(nl), /* nl Dutch 0x13 */
1.823 +/* ILCID_POSIX_MAP(nn), // no Norwegian 0x14 */
1.824 + ILCID_POSIX_MAP(no), /* * Norwegian 0x14 */
1.825 + ILCID_POSIX_MAP(nso), /* nso Sotho, Northern (Sepedi dialect) 0x6c */
1.826 + ILCID_POSIX_MAP(oc), /* oc Occitan 0x82 */
1.827 + ILCID_POSIX_MAP(om), /* om Oromo 0x72 */
1.828 + ILCID_POSIX_MAP(or_IN), /* or Oriya 0x48 */
1.829 + ILCID_POSIX_MAP(pa), /* pa Punjabi 0x46 */
1.830 + ILCID_POSIX_MAP(pap), /* pap Papiamentu 0x79 */
1.831 + ILCID_POSIX_MAP(pl), /* pl Polish 0x15 */
1.832 + ILCID_POSIX_MAP(ps), /* ps Pashto 0x63 */
1.833 + ILCID_POSIX_MAP(pt), /* pt Portuguese 0x16 */
1.834 + ILCID_POSIX_MAP(qu), /* qu Quechua 0x6B */
1.835 + ILCID_POSIX_MAP(qut), /* qut K'iche 0x86 */
1.836 + ILCID_POSIX_MAP(rm), /* rm Raeto-Romance/Romansh 0x17 */
1.837 + ILCID_POSIX_MAP(ro), /* ro Romanian 0x18 */
1.838 + ILCID_POSIX_MAP(root), /* root 0x00 */
1.839 + ILCID_POSIX_MAP(ru), /* ru Russian 0x19 */
1.840 + ILCID_POSIX_MAP(rw), /* rw Kinyarwanda 0x87 */
1.841 + ILCID_POSIX_MAP(sa), /* sa Sanskrit 0x4f */
1.842 + ILCID_POSIX_MAP(sah), /* sah Yakut 0x85 */
1.843 + ILCID_POSIX_MAP(sd), /* sd Sindhi 0x59 */
1.844 + ILCID_POSIX_MAP(se), /* se Sami 0x3b */
1.845 +/* ILCID_POSIX_MAP(sh), // sh Serbo-Croatian 0x1a */
1.846 + ILCID_POSIX_MAP(si), /* si Sinhalese 0x5b */
1.847 + ILCID_POSIX_MAP(sk), /* sk Slovak 0x1b */
1.848 + ILCID_POSIX_MAP(sl), /* sl Slovenian 0x24 */
1.849 + ILCID_POSIX_MAP(so), /* so Somali 0x77 */
1.850 + ILCID_POSIX_MAP(sq), /* sq Albanian 0x1c */
1.851 +/* ILCID_POSIX_MAP(sr), // sr Serbian 0x1a */
1.852 + ILCID_POSIX_MAP(st), /* st Sutu 0x30 */
1.853 + ILCID_POSIX_MAP(sv), /* sv Swedish 0x1d */
1.854 + ILCID_POSIX_MAP(sw), /* sw Swahili 0x41 */
1.855 + ILCID_POSIX_MAP(syr), /* syr Syriac 0x5A */
1.856 + ILCID_POSIX_MAP(ta), /* ta Tamil 0x49 */
1.857 + ILCID_POSIX_MAP(te), /* te Telugu 0x4a */
1.858 + ILCID_POSIX_MAP(tg), /* tg Tajik 0x28 */
1.859 + ILCID_POSIX_MAP(th), /* th Thai 0x1e */
1.860 + ILCID_POSIX_MAP(ti), /* ti Tigrigna 0x73 */
1.861 + ILCID_POSIX_MAP(tk), /* tk Turkmen 0x42 */
1.862 + ILCID_POSIX_MAP(tn), /* tn Tswana 0x32 */
1.863 + ILCID_POSIX_MAP(tr), /* tr Turkish 0x1f */
1.864 + ILCID_POSIX_MAP(ts), /* ts Tsonga 0x31 */
1.865 + ILCID_POSIX_MAP(tt), /* tt Tatar 0x44 */
1.866 + ILCID_POSIX_MAP(tzm), /* tzm Tamazight 0x5f */
1.867 + ILCID_POSIX_MAP(ug), /* ug Uighur 0x80 */
1.868 + ILCID_POSIX_MAP(uk), /* uk Ukrainian 0x22 */
1.869 + ILCID_POSIX_MAP(ur), /* ur Urdu 0x20 */
1.870 + ILCID_POSIX_MAP(uz), /* uz Uzbek 0x43 */
1.871 + ILCID_POSIX_MAP(ve), /* ve Venda 0x33 */
1.872 + ILCID_POSIX_MAP(vi), /* vi Vietnamese 0x2a */
1.873 + ILCID_POSIX_MAP(wen), /* wen Sorbian 0x2e */
1.874 + ILCID_POSIX_MAP(wo), /* wo Wolof 0x88 */
1.875 + ILCID_POSIX_MAP(xh), /* xh Xhosa 0x34 */
1.876 + ILCID_POSIX_MAP(yi), /* yi Yiddish 0x3d */
1.877 + ILCID_POSIX_MAP(yo), /* yo Yoruba 0x6a */
1.878 + ILCID_POSIX_MAP(zh), /* zh Chinese 0x04 */
1.879 + ILCID_POSIX_MAP(zu), /* zu Zulu 0x35 */
1.880 +};
1.881 +
1.882 +static const uint32_t gLocaleCount = sizeof(gPosixIDmap)/sizeof(ILcidPosixMap);
1.883 +
1.884 +/**
1.885 + * Do not call this function. It is called by hostID.
1.886 + * The function is not private because this struct must stay as a C struct,
1.887 + * and this is an internal class.
1.888 + */
1.889 +static int32_t
1.890 +idCmp(const char* id1, const char* id2)
1.891 +{
1.892 + int32_t diffIdx = 0;
1.893 + while (*id1 == *id2 && *id1 != 0) {
1.894 + diffIdx++;
1.895 + id1++;
1.896 + id2++;
1.897 + }
1.898 + return diffIdx;
1.899 +}
1.900 +
1.901 +/**
1.902 + * Searches for a Windows LCID
1.903 + *
1.904 + * @param posixid the Posix style locale id.
1.905 + * @param status gets set to U_ILLEGAL_ARGUMENT_ERROR when the Posix ID has
1.906 + * no equivalent Windows LCID.
1.907 + * @return the LCID
1.908 + */
1.909 +static uint32_t
1.910 +getHostID(const ILcidPosixMap *this_0, const char* posixID, UErrorCode* status)
1.911 +{
1.912 + int32_t bestIdx = 0;
1.913 + int32_t bestIdxDiff = 0;
1.914 + int32_t posixIDlen = (int32_t)uprv_strlen(posixID);
1.915 + uint32_t idx;
1.916 +
1.917 + for (idx = 0; idx < this_0->numRegions; idx++ ) {
1.918 + int32_t sameChars = idCmp(posixID, this_0->regionMaps[idx].posixID);
1.919 + if (sameChars > bestIdxDiff && this_0->regionMaps[idx].posixID[sameChars] == 0) {
1.920 + if (posixIDlen == sameChars) {
1.921 + /* Exact match */
1.922 + return this_0->regionMaps[idx].hostID;
1.923 + }
1.924 + bestIdxDiff = sameChars;
1.925 + bestIdx = idx;
1.926 + }
1.927 + }
1.928 + /* We asked for something unusual, like en_ZZ, and we try to return the number for the same language. */
1.929 + /* We also have to make sure that sid and si and similar string subsets don't match. */
1.930 + if ((posixID[bestIdxDiff] == '_' || posixID[bestIdxDiff] == '@')
1.931 + && this_0->regionMaps[bestIdx].posixID[bestIdxDiff] == 0)
1.932 + {
1.933 + *status = U_USING_FALLBACK_WARNING;
1.934 + return this_0->regionMaps[bestIdx].hostID;
1.935 + }
1.936 +
1.937 + /*no match found */
1.938 + *status = U_ILLEGAL_ARGUMENT_ERROR;
1.939 + return this_0->regionMaps->hostID;
1.940 +}
1.941 +
1.942 +static const char*
1.943 +getPosixID(const ILcidPosixMap *this_0, uint32_t hostID)
1.944 +{
1.945 + uint32_t i;
1.946 + for (i = 0; i <= this_0->numRegions; i++)
1.947 + {
1.948 + if (this_0->regionMaps[i].hostID == hostID)
1.949 + {
1.950 + return this_0->regionMaps[i].posixID;
1.951 + }
1.952 + }
1.953 +
1.954 + /* If you get here, then no matching region was found,
1.955 + so return the language id with the wild card region. */
1.956 + return this_0->regionMaps[0].posixID;
1.957 +}
1.958 +
1.959 +/*
1.960 +//////////////////////////////////////
1.961 +//
1.962 +// LCID --> POSIX
1.963 +//
1.964 +/////////////////////////////////////
1.965 +*/
1.966 +#ifdef USE_WINDOWS_LOCALE_API
1.967 +/*
1.968 + * Various language tags needs to be changed:
1.969 + * quz -> qu
1.970 + * prs -> fa
1.971 + */
1.972 +#define FIX_LANGUAGE_ID_TAG(buffer, len) \
1.973 + if (len >= 3) { \
1.974 + if (buffer[0] == 'q' && buffer[1] == 'u' && buffer[2] == 'z') {\
1.975 + buffer[2] = 0; \
1.976 + uprv_strcat(buffer, buffer+3); \
1.977 + } else if (buffer[0] == 'p' && buffer[1] == 'r' && buffer[2] == 's') {\
1.978 + buffer[0] = 'f'; buffer[1] = 'a'; buffer[2] = 0; \
1.979 + uprv_strcat(buffer, buffer+3); \
1.980 + } \
1.981 + }
1.982 +
1.983 +#endif
1.984 +U_CAPI int32_t
1.985 +uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UErrorCode* status)
1.986 +{
1.987 + uint16_t langID;
1.988 + uint32_t localeIndex;
1.989 + UBool bLookup = TRUE;
1.990 + const char *pPosixID = NULL;
1.991 +
1.992 +#ifdef USE_WINDOWS_LOCALE_API
1.993 + int32_t tmpLen = 0;
1.994 + char locName[157]; /* ULOC_FULLNAME_CAPACITY */
1.995 +
1.996 + tmpLen = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)locName, sizeof(locName)/sizeof(locName[0]));
1.997 + if (tmpLen > 1) {
1.998 + /* Windows locale name may contain sorting variant, such as "es-ES_tradnl".
1.999 + In such case, we need special mapping data found in the hardcoded table
1.1000 + in this source file. */
1.1001 + char *p = uprv_strchr(locName, '_');
1.1002 + if (p) {
1.1003 + /* Keep the base locale, without variant */
1.1004 + *p = 0;
1.1005 + tmpLen = uprv_strlen(locName);
1.1006 + } else {
1.1007 + /* No hardcoded table lookup necessary */
1.1008 + bLookup = FALSE;
1.1009 + }
1.1010 + /* Change the tag separator from '-' to '_' */
1.1011 + p = locName;
1.1012 + while (*p) {
1.1013 + if (*p == '-') {
1.1014 + *p = '_';
1.1015 + }
1.1016 + p++;
1.1017 + }
1.1018 + FIX_LANGUAGE_ID_TAG(locName, tmpLen);
1.1019 + pPosixID = locName;
1.1020 + }
1.1021 +#endif
1.1022 + if (bLookup) {
1.1023 + const char *pCandidate = NULL;
1.1024 + langID = LANGUAGE_LCID(hostid);
1.1025 +
1.1026 + for (localeIndex = 0; localeIndex < gLocaleCount; localeIndex++) {
1.1027 + if (langID == gPosixIDmap[localeIndex].regionMaps->hostID) {
1.1028 + pCandidate = getPosixID(&gPosixIDmap[localeIndex], hostid);
1.1029 + break;
1.1030 + }
1.1031 + }
1.1032 +
1.1033 + /* On Windows, when locale name has a variant, we still look up the hardcoded table.
1.1034 + If a match in the hardcoded table is longer than the Windows locale name without
1.1035 + variant, we use the one as the result */
1.1036 + if (pCandidate && (pPosixID == NULL || uprv_strlen(pCandidate) > uprv_strlen(pPosixID))) {
1.1037 + pPosixID = pCandidate;
1.1038 + }
1.1039 + }
1.1040 +
1.1041 + if (pPosixID) {
1.1042 + int32_t resLen = uprv_strlen(pPosixID);
1.1043 + int32_t copyLen = resLen <= posixIDCapacity ? resLen : posixIDCapacity;
1.1044 + uprv_memcpy(posixID, pPosixID, copyLen);
1.1045 + if (resLen < posixIDCapacity) {
1.1046 + posixID[resLen] = 0;
1.1047 + if (*status == U_STRING_NOT_TERMINATED_WARNING) {
1.1048 + *status = U_ZERO_ERROR;
1.1049 + }
1.1050 + } else if (resLen == posixIDCapacity) {
1.1051 + *status = U_STRING_NOT_TERMINATED_WARNING;
1.1052 + } else {
1.1053 + *status = U_BUFFER_OVERFLOW_ERROR;
1.1054 + }
1.1055 + return resLen;
1.1056 + }
1.1057 +
1.1058 + /* no match found */
1.1059 + *status = U_ILLEGAL_ARGUMENT_ERROR;
1.1060 + return -1;
1.1061 +}
1.1062 +
1.1063 +/*
1.1064 +//////////////////////////////////////
1.1065 +//
1.1066 +// POSIX --> LCID
1.1067 +// This should only be called from uloc_getLCID.
1.1068 +// The locale ID must be in canonical form.
1.1069 +// langID is separate so that this file doesn't depend on the uloc_* API.
1.1070 +//
1.1071 +/////////////////////////////////////
1.1072 +*/
1.1073 +
1.1074 +U_CAPI uint32_t
1.1075 +uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status)
1.1076 +{
1.1077 +
1.1078 + uint32_t low = 0;
1.1079 + uint32_t high = gLocaleCount;
1.1080 + uint32_t mid;
1.1081 + uint32_t oldmid = 0;
1.1082 + int32_t compVal;
1.1083 +
1.1084 + uint32_t value = 0;
1.1085 + uint32_t fallbackValue = (uint32_t)-1;
1.1086 + UErrorCode myStatus;
1.1087 + uint32_t idx;
1.1088 +
1.1089 + /* Check for incomplete id. */
1.1090 + if (!langID || !posixID || uprv_strlen(langID) < 2 || uprv_strlen(posixID) < 2) {
1.1091 + return 0;
1.1092 + }
1.1093 +
1.1094 + /*Binary search for the map entry for normal cases */
1.1095 +
1.1096 + while (high > low) /*binary search*/{
1.1097 +
1.1098 + mid = (high+low) >> 1; /*Finds median*/
1.1099 +
1.1100 + if (mid == oldmid)
1.1101 + break;
1.1102 +
1.1103 + compVal = uprv_strcmp(langID, gPosixIDmap[mid].regionMaps->posixID);
1.1104 + if (compVal < 0){
1.1105 + high = mid;
1.1106 + }
1.1107 + else if (compVal > 0){
1.1108 + low = mid;
1.1109 + }
1.1110 + else /*we found it*/{
1.1111 + return getHostID(&gPosixIDmap[mid], posixID, status);
1.1112 + }
1.1113 + oldmid = mid;
1.1114 + }
1.1115 +
1.1116 + /*
1.1117 + * Sometimes we can't do a binary search on posixID because some LCIDs
1.1118 + * go to different locales. We hit one of those special cases.
1.1119 + */
1.1120 + for (idx = 0; idx < gLocaleCount; idx++ ) {
1.1121 + myStatus = U_ZERO_ERROR;
1.1122 + value = getHostID(&gPosixIDmap[idx], posixID, &myStatus);
1.1123 + if (myStatus == U_ZERO_ERROR) {
1.1124 + return value;
1.1125 + }
1.1126 + else if (myStatus == U_USING_FALLBACK_WARNING) {
1.1127 + fallbackValue = value;
1.1128 + }
1.1129 + }
1.1130 +
1.1131 + if (fallbackValue != (uint32_t)-1) {
1.1132 + *status = U_USING_FALLBACK_WARNING;
1.1133 + return fallbackValue;
1.1134 + }
1.1135 +
1.1136 + /* no match found */
1.1137 + *status = U_ILLEGAL_ARGUMENT_ERROR;
1.1138 + return 0; /* return international (root) */
1.1139 +}
1.1140 +
