1 /* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */ 2 /* 3 * This file is part of the LibreOffice project. 4 * 5 * This Source Code Form is subject to the terms of the Mozilla Public 6 * License, v. 2.0. If a copy of the MPL was not distributed with this 7 * file, You can obtain one at http://mozilla.org/MPL/2.0/. 8 * 9 * This file incorporates work covered by the following license notice: 10 * 11 * Licensed to the Apache Software Foundation (ASF) under one or more 12 * contributor license agreements. See the NOTICE file distributed 13 * with this work for additional information regarding copyright 14 * ownership. The ASF licenses this file to you under the Apache 15 * License, Version 2.0 (the "License"); you may not use this file 16 * except in compliance with the License. You may obtain a copy of 17 * the License at http://www.apache.org/licenses/LICENSE-2.0 . 18 */ 19 20 #include <sal/log.hxx> 21 #include <rtl/ustring.hxx> 22 #include <rtl/string.hxx> 23 24 #include <i18nlangtag/mslangid.hxx> 25 #include <i18nlangtag/languagetag.hxx> 26 27 using namespace com::sun::star; 28 29 30 constexpr LanguageType k0(0); 31 constexpr LanguageType kSAME(0xffff); 32 33 namespace { 34 LanguageType getOverrideLang( LanguageType nLang, LanguageType nOverride ) 35 { 36 return nOverride ? ((nOverride == kSAME) ? nLang : nOverride) : nLang; 37 } 38 } 39 40 /* Usage of override mechanism: 41 * If a table entry's mnOverride is not 0, an override entry with an mnLang 42 * value of (mnOverride==kSAME ? mnLang : mnOverride) exists that should be 43 * used instead. There MUST exist one such entry that does not have an 44 * mnOverride value and within one table it MUST be located before any entry 45 * with that mnLang and an mnOverride value of not 0. Usually kSAME is used as 46 * override value, with rare exceptions, see tables below. 47 * 48 * The override serves these purposes: 49 * - With getOverride() it indicates that there is a different language tag 50 * (locale) that the requested language tag should be "canonicalized" to. 51 * - With lookupFallbackLocale() a locale may be returned where the language 52 * tag differs. 53 * - With convertLanguageToLocaleImpl() and bIgnoreOverride=false the override 54 * is followed and the override locale returned. 55 * - With convertLocaleToLanguageImpl() a different LangID may be returned in 56 * rare cases where the actual mapped ID differs. 57 */ 58 59 struct IsoLanguageCountryEntry 60 { 61 LanguageType mnLang; 62 char maLanguage[4]; 63 char maCountry[3]; 64 LanguageType mnOverride; 65 66 /** Obtain a language tag string with '-' separator. */ 67 OUString getTagString() const; 68 69 /** Obtain a locale. */ 70 css::lang::Locale getLocale() const; 71 }; 72 73 struct IsoLanguageScriptCountryEntry 74 { 75 LanguageType mnLang; 76 char maLanguageScript[9]; ///< "ll-Ssss" or "lll-Ssss" 77 char maCountry[3]; 78 LanguageType mnOverride; 79 80 /** Obtain a language tag string with '-' separator. */ 81 OUString getTagString() const; 82 83 /** Obtain a locale. */ 84 css::lang::Locale getLocale() const; 85 86 /** If rStr starts with maLanguageScript ignoring case. 87 88 We don't have OUString::startsWithIgnoreAsciiCaseAscii() 89 */ 90 bool startsInIgnoreAsciiCase( const OUString & rStr ) const; 91 }; 92 93 struct Bcp47CountryEntry 94 { 95 LanguageType mnLang; 96 const char* mpBcp47; 97 char maCountry[3]; 98 const char* mpFallback; 99 LanguageType mnOverride; 100 101 /** Obtain a language tag string with '-' separator. */ 102 OUString getTagString() const; 103 104 /** Obtain a locale. */ 105 css::lang::Locale getLocale() const; 106 }; 107 108 namespace { 109 110 struct IsoLangEngEntry 111 { 112 LanguageType mnLang; 113 char maCountry[3]; 114 }; 115 116 struct IsoLangNoneStdEntry 117 { 118 LanguageType mnLang; 119 char maLanguage[4]; 120 char maCountry[9]; 121 }; 122 123 struct IsoLangOtherEntry 124 { 125 LanguageType mnLang; 126 const char* mpLanguage; 127 }; 128 129 } 130 131 // Entries for languages are lower case, for countries upper case, as 132 // recommended by rfc5646 (obsoletes rfc4646 (obsoletes rfc3066 (obsoletes 133 // rfc1766))). convertIsoNamesToLanguage(), convertLocaleToLanguageImpl() 134 // and lookupFallbackLocale() are case insensitive. 135 // 136 // Sort order: Most used first and within one language the default fallback 137 // locale of that language first. 138 // 139 // The default entry for a LangID <-> ISO mapping has to be first. For 140 // conversion of legacy mappings one LangID can map to multiple ISO codes 141 // except if the LangID is primary-only, and one ISO code combination can map 142 // to multiple LangIDs. 143 144 /* Currently (2013-08-29 and 2021-10-24) only these primary LangID are still 145 * used literally in code: 146 * LANGUAGE_ENGLISH LANGUAGE_ARABIC_PRIMARY_ONLY 147 */ 148 149 IsoLanguageCountryEntry const aImplIsoLangEntries[] = 150 { 151 // MS-LANGID codes, ISO639-1/2/3, ISO3166, override 152 { LANGUAGE_ENGLISH_US, "en", "US", k0 }, 153 { LANGUAGE_ENGLISH_UK, "en", "GB", k0 }, 154 { LANGUAGE_ENGLISH, "en", "" , k0 }, 155 { LANGUAGE_ENGLISH_AUS, "en", "AU", k0 }, 156 { LANGUAGE_ENGLISH_CAN, "en", "CA", k0 }, 157 { LANGUAGE_FRENCH, "fr", "FR", k0 }, 158 { LANGUAGE_GERMAN, "de", "DE", k0 }, 159 { LANGUAGE_ITALIAN, "it", "IT", k0 }, 160 { LANGUAGE_DUTCH, "nl", "NL", k0 }, 161 { LANGUAGE_SPANISH_MODERN, "es", "ES", k0 }, 162 { LANGUAGE_PORTUGUESE, "pt", "PT", k0 }, 163 { LANGUAGE_PORTUGUESE_BRAZILIAN, "pt", "BR", k0 }, 164 { LANGUAGE_DANISH, "da", "DK", k0 }, 165 { LANGUAGE_GREEK, "el", "GR", k0 }, 166 { LANGUAGE_CHINESE_SIMPLIFIED, "zh", "CN", k0 }, 167 { LANGUAGE_CHINESE_SIMPLIFIED_LEGACY, "zh", "CN", k0 }, 168 { LANGUAGE_CHINESE_SIMPLIFIED, "cmn", "CN", kSAME }, 169 { LANGUAGE_CHINESE_TRADITIONAL, "zh", "TW", k0 }, 170 { LANGUAGE_CHINESE_TRADITIONAL, "cmn", "TW", kSAME }, 171 { LANGUAGE_CHINESE_HONGKONG, "zh", "HK", k0 }, 172 { LANGUAGE_CHINESE_SINGAPORE, "zh", "SG", k0 }, 173 { LANGUAGE_CHINESE_MACAU, "zh", "MO", k0 }, 174 { LANGUAGE_CHINESE_LSO, "zh", "" , k0 }, 175 { LANGUAGE_YUE_CHINESE_HONGKONG, "yue", "HK", k0 }, 176 { LANGUAGE_ENGLISH_HONG_KONG_SAR, "en", "HK", k0 }, 177 { LANGUAGE_JAPANESE, "ja", "JP", k0 }, 178 { LANGUAGE_KOREAN, "ko", "KR", k0 }, 179 { LANGUAGE_KOREAN_JOHAB, "ko", "KR", k0 }, 180 { LANGUAGE_USER_KOREAN_NORTH, "ko", "KP", k0 }, 181 { LANGUAGE_SWEDISH, "sv", "SE", k0 }, 182 { LANGUAGE_SWEDISH_FINLAND, "sv", "FI", k0 }, 183 { LANGUAGE_FINNISH, "fi", "FI", k0 }, 184 { LANGUAGE_RUSSIAN, "ru", "RU", k0 }, 185 { LANGUAGE_TATAR, "tt", "RU", k0 }, 186 { LANGUAGE_ENGLISH_NZ, "en", "NZ", k0 }, 187 { LANGUAGE_ENGLISH_EIRE, "en", "IE", k0 }, 188 { LANGUAGE_DUTCH_BELGIAN, "nl", "BE", k0 }, 189 { LANGUAGE_FRENCH_BELGIAN, "fr", "BE", k0 }, 190 { LANGUAGE_FRENCH_CANADIAN, "fr", "CA", k0 }, 191 { LANGUAGE_FRENCH_SWISS, "fr", "CH", k0 }, 192 { LANGUAGE_GERMAN_SWISS, "de", "CH", k0 }, 193 { LANGUAGE_GERMAN_AUSTRIAN, "de", "AT", k0 }, 194 { LANGUAGE_ITALIAN_SWISS, "it", "CH", k0 }, 195 { LANGUAGE_ALBANIAN, "sq", "AL", k0 }, 196 { LANGUAGE_ARABIC_SAUDI_ARABIA, "ar", "SA", k0 }, 197 { LANGUAGE_ARABIC_EGYPT, "ar", "EG", k0 }, 198 { LANGUAGE_ARABIC_UAE, "ar", "AE", k0 }, 199 { LANGUAGE_ARABIC_IRAQ, "ar", "IQ", k0 }, 200 { LANGUAGE_ARABIC_LIBYA, "ar", "LY", k0 }, 201 { LANGUAGE_ARABIC_ALGERIA, "ar", "DZ", k0 }, 202 { LANGUAGE_ARABIC_MOROCCO, "ar", "MA", k0 }, 203 { LANGUAGE_ARABIC_TUNISIA, "ar", "TN", k0 }, 204 { LANGUAGE_ARABIC_OMAN, "ar", "OM", k0 }, 205 { LANGUAGE_ARABIC_YEMEN, "ar", "YE", k0 }, 206 { LANGUAGE_ARABIC_SYRIA, "ar", "SY", k0 }, 207 { LANGUAGE_ARABIC_JORDAN, "ar", "JO", k0 }, 208 { LANGUAGE_ARABIC_LEBANON, "ar", "LB", k0 }, 209 { LANGUAGE_ARABIC_KUWAIT, "ar", "KW", k0 }, 210 { LANGUAGE_ARABIC_BAHRAIN, "ar", "BH", k0 }, 211 { LANGUAGE_ARABIC_QATAR, "ar", "QA", k0 }, 212 { LANGUAGE_USER_ARABIC_CHAD, "ar", "TD", k0 }, 213 { LANGUAGE_USER_ARABIC_COMOROS, "ar", "KM", k0 }, 214 { LANGUAGE_USER_ARABIC_DJIBOUTI, "ar", "DJ", k0 }, 215 { LANGUAGE_USER_ARABIC_ERITREA, "ar", "ER", k0 }, 216 { LANGUAGE_USER_ARABIC_ISRAEL, "ar", "IL", k0 }, 217 { LANGUAGE_USER_ARABIC_MAURITANIA, "ar", "MR", k0 }, 218 { LANGUAGE_USER_ARABIC_PALESTINE, "ar", "PS", k0 }, 219 { LANGUAGE_USER_ARABIC_SOMALIA, "ar", "SO", k0 }, 220 { LANGUAGE_USER_ARABIC_SUDAN, "ar", "SD", k0 }, 221 { LANGUAGE_ARABIC_PRIMARY_ONLY, "ar", "" , k0 }, 222 { LANGUAGE_BASQUE, "eu", "ES", k0 }, 223 { LANGUAGE_BASQUE, "eu", "" , kSAME }, // our earlier definition 224 { LANGUAGE_BULGARIAN, "bg", "BG", k0 }, 225 { LANGUAGE_CZECH, "cs", "CZ", k0 }, 226 { LANGUAGE_CZECH, "cz", "" , kSAME }, 227 { LANGUAGE_ENGLISH_JAMAICA, "en", "JM", k0 }, 228 { LANGUAGE_ENGLISH_CARIBBEAN, "en", "BS", k0 }, // not 100%, because AG is Bahamas 229 { LANGUAGE_ENGLISH_BELIZE, "en", "BZ", k0 }, 230 { LANGUAGE_ENGLISH_TRINIDAD, "en", "TT", k0 }, 231 { LANGUAGE_ENGLISH_ZIMBABWE, "en", "ZW", k0 }, 232 { LANGUAGE_ENGLISH_INDONESIA, "en", "ID", k0 }, // MS reserved 233 { LANGUAGE_ESTONIAN, "et", "EE", k0 }, 234 { LANGUAGE_FAEROESE, "fo", "FO", k0 }, 235 { LANGUAGE_FARSI, "fa", "IR", k0 }, 236 { LANGUAGE_FRENCH_LUXEMBOURG, "fr", "LU", k0 }, 237 { LANGUAGE_FRENCH_MONACO, "fr", "MC", k0 }, 238 { LANGUAGE_GERMAN_LUXEMBOURG, "de", "LU", k0 }, 239 { LANGUAGE_GERMAN_LIECHTENSTEIN, "de", "LI", k0 }, 240 { LANGUAGE_HEBREW, "he", "IL", k0 }, // new: old was "iw" 241 { LANGUAGE_HEBREW, "iw", "IL", kSAME }, // old: new is "he" 242 { LANGUAGE_HUNGARIAN, "hu", "HU", k0 }, 243 { LANGUAGE_ICELANDIC, "is", "IS", k0 }, 244 { LANGUAGE_INDONESIAN, "id", "ID", k0 }, // new: old was "in" 245 { LANGUAGE_INDONESIAN, "in", "ID", kSAME }, // old: new is "id" 246 { LANGUAGE_NORWEGIAN, "no", "NO", k0 }, 247 { LANGUAGE_NORWEGIAN_BOKMAL, "nb", "NO", k0 }, 248 { LANGUAGE_NORWEGIAN_BOKMAL_LSO, "nb", "" , k0 }, 249 { LANGUAGE_NORWEGIAN_NYNORSK, "nn", "NO", k0 }, 250 { LANGUAGE_NORWEGIAN_NYNORSK_LSO, "nn", "" , k0 }, 251 { LANGUAGE_POLISH, "pl", "PL", k0 }, 252 { LANGUAGE_RHAETO_ROMAN, "rm", "CH", k0 }, 253 { LANGUAGE_ROMANIAN, "ro", "RO", k0 }, 254 { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", k0 }, 255 { LANGUAGE_SLOVAK, "sk", "SK", k0 }, 256 { LANGUAGE_SLOVENIAN, "sl", "SI", k0 }, 257 { LANGUAGE_SPANISH_MEXICAN, "es", "MX", k0 }, 258 { LANGUAGE_SPANISH_GUATEMALA, "es", "GT", k0 }, 259 { LANGUAGE_SPANISH_COSTARICA, "es", "CR", k0 }, 260 { LANGUAGE_SPANISH_PANAMA, "es", "PA", k0 }, 261 { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC, "es", "DO", k0 }, 262 { LANGUAGE_SPANISH_VENEZUELA, "es", "VE", k0 }, 263 { LANGUAGE_SPANISH_COLOMBIA, "es", "CO", k0 }, 264 { LANGUAGE_SPANISH_PERU, "es", "PE", k0 }, 265 { LANGUAGE_SPANISH_ARGENTINA, "es", "AR", k0 }, 266 { LANGUAGE_SPANISH_ECUADOR, "es", "EC", k0 }, 267 { LANGUAGE_SPANISH_CHILE, "es", "CL", k0 }, 268 { LANGUAGE_SPANISH_URUGUAY, "es", "UY", k0 }, 269 { LANGUAGE_SPANISH_PARAGUAY, "es", "PY", k0 }, 270 { LANGUAGE_SPANISH_BOLIVIA, "es", "BO", k0 }, 271 { LANGUAGE_SPANISH_EL_SALVADOR, "es", "SV", k0 }, 272 { LANGUAGE_SPANISH_HONDURAS, "es", "HN", k0 }, 273 { LANGUAGE_SPANISH_NICARAGUA, "es", "NI", k0 }, 274 { LANGUAGE_SPANISH_PUERTO_RICO, "es", "PR", k0 }, 275 { LANGUAGE_SPANISH_UNITED_STATES, "es", "US", k0 }, 276 { LANGUAGE_SPANISH_LATIN_AMERICA, "es", "" , k0 }, 277 { LANGUAGE_TURKISH, "tr", "TR", k0 }, 278 { LANGUAGE_UKRAINIAN, "uk", "UA", k0 }, 279 { LANGUAGE_VIETNAMESE, "vi", "VN", k0 }, 280 { LANGUAGE_LATVIAN, "lv", "LV", k0 }, 281 { LANGUAGE_MACEDONIAN, "mk", "MK", k0 }, 282 { LANGUAGE_MALAY_MALAYSIA, "ms", "MY", k0 }, 283 { LANGUAGE_MALAY_BRUNEI_DARUSSALAM, "ms", "BN", k0 }, 284 { LANGUAGE_ENGLISH_MALAYSIA, "en", "MY", k0 }, 285 { LANGUAGE_THAI, "th", "TH", k0 }, 286 { LANGUAGE_LITHUANIAN, "lt", "LT", k0 }, 287 { LANGUAGE_LITHUANIAN_CLASSIC, "lt", "LT", k0 }, 288 { LANGUAGE_CROATIAN, "hr", "HR", k0 }, // Croatian in Croatia 289 { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA", k0 }, 290 { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs", "BA", k0 }, 291 { LANGUAGE_BOSNIAN_LSO, "bs", "" , k0 }, // so what is 'bs' vs 'bs-Latn'? 292 { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", k0 }, // Serbian Cyrillic in Serbia 293 { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_SERBIA, "sr", "RS", k0 }, 294 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "CS", k0 }, // Serbian Cyrillic in Serbia and Montenegro 295 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "YU", kSAME }, // legacy Serbian Cyrillic in Serbia and Montenegro (former Yugoslavia); kludge, sr_CS not supported by ICU 2.6 (3.4 does) 296 { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", k0 }, 297 { LANGUAGE_OBSOLETE_USER_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME", k0 }, 298 { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA", k0 }, 299 { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr", "" , k0 }, 300 { LANGUAGE_SERBIAN_LATIN_SERBIA, "sh", "RS", kSAME }, // legacy kludge, is sr-Latn-RS now 301 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sh", "RS", kSAME }, // legacy kludge, is sr-Latn-RS now 302 { LANGUAGE_SERBIAN_LATIN_SAM, "sh", "CS", kSAME }, // legacy kludge, is sr-Latn-CS now 303 { LANGUAGE_SERBIAN_LATIN_SAM, "sh", "YU", kSAME }, // legacy kludge, is sr-Latn-YU now 304 { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sh", "ME", kSAME }, // legacy kludge, is sr-Latn-ME now 305 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO, "sh", "ME", kSAME }, // legacy kludge, is sr-Latn-ME now 306 { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sh", "BA", kSAME }, // legacy kludge, is sr-Latn-BA now 307 { LANGUAGE_SERBIAN_LATIN_LSO, "sh", "" , kSAME }, // legacy kludge, is sr-Latn now 308 { LANGUAGE_ARMENIAN, "hy", "AM", k0 }, 309 { LANGUAGE_USER_ARMENIAN_RUSSIA, "hy", "RU", k0 }, 310 { LANGUAGE_USER_ARMENIAN_IRAN, "hy", "IR", k0 }, 311 { LANGUAGE_AZERI_LATIN, "az", "AZ", k0 }, // macrolanguage code 312 { LANGUAGE_UZBEK_LATIN, "uz", "UZ", k0 }, // macrolanguage code 313 { LANGUAGE_UZBEK_LATIN_LSO, "uz", "" , k0 }, // macrolanguage code 314 { LANGUAGE_BENGALI_BANGLADESH, "bn", "BD", k0 }, 315 { LANGUAGE_BENGALI, "bn", "IN", k0 }, 316 { LANGUAGE_BURMESE, "my", "MM", k0 }, 317 { LANGUAGE_KAZAKH, "kk", "KZ", k0 }, 318 { LANGUAGE_ENGLISH_INDIA, "en", "IN", k0 }, 319 { LANGUAGE_URDU_INDIA, "ur", "IN", k0 }, 320 { LANGUAGE_URDU_PAKISTAN, "ur", "PK", k0 }, 321 { LANGUAGE_HINDI, "hi", "IN", k0 }, 322 { LANGUAGE_GUJARATI, "gu", "IN", k0 }, 323 { LANGUAGE_KANNADA, "kn", "IN", k0 }, 324 { LANGUAGE_ASSAMESE, "as", "IN", k0 }, 325 { LANGUAGE_KASHMIRI_INDIA, "ks", "IN", kSAME }, 326 { LANGUAGE_KASHMIRI, "ks", "" , kSAME }, // Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that 327 { LANGUAGE_MALAYALAM, "ml", "IN", k0 }, 328 { LANGUAGE_MANIPURI, "mni", "IN", k0 }, // MS reserved 329 { LANGUAGE_MARATHI, "mr", "IN", k0 }, 330 { LANGUAGE_KONKANI, "kok", "IN", k0 }, 331 { LANGUAGE_NEPALI, "ne", "NP", k0 }, 332 { LANGUAGE_NEPALI_INDIA, "ne", "IN", k0 }, 333 { LANGUAGE_ODIA, "or", "IN", k0 }, 334 { LANGUAGE_PUNJABI, "pa", "IN", k0 }, 335 { LANGUAGE_SANSKRIT, "sa", "IN", k0 }, 336 { LANGUAGE_TAMIL, "ta", "IN", k0 }, 337 { LANGUAGE_TAMIL_SRI_LANKA, "ta", "LK", k0 }, 338 { LANGUAGE_TELUGU, "te", "IN", k0 }, 339 { LANGUAGE_PUNJABI_PAKISTAN, "pnb", "PK", k0 }, 340 { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb", "" , k0 }, 341 { LANGUAGE_PUNJABI_PAKISTAN, "lah", "PK", kSAME }, // macrolanguage code, earlier preferred 'lah' over 'pa' for Western Panjabi, now there is 'pnb' 342 { LANGUAGE_PUNJABI_PAKISTAN, "pa", "PK", kSAME }, // MS maps this to 'pa-Arab-PK', but 'pa'='pan' Eastern Panjabi is not used in PK, only in 343 { LANGUAGE_SINDHI_PAKISTAN, "sd", "PK", kSAME }, // Arabic script 344 { LANGUAGE_SINDHI, "sd", "IN", kSAME }, // Devanagari script 345 { LANGUAGE_BELARUSIAN, "be", "BY", k0 }, 346 { LANGUAGE_CATALAN, "ca", "ES", k0 }, // Spain (default) 347 { LANGUAGE_CATALAN, "ca", "AD", k0 }, // Andorra 348 //LANGUAGE_CATALAN_VALENCIAN ca-ES-valencia Bcp47CountryEntry takes precedence 349 { LANGUAGE_CATALAN_VALENCIAN, "ca", "XV", kSAME }, // XV: ISO 3166 user-assigned; old workaround for UI localization only, in case it escaped to document content 350 { LANGUAGE_CATALAN_VALENCIAN, "qcv", "ES", kSAME }, // qcv: ISO 639-3 reserved-for-local-use; old UI localization quirk only, in case it escaped to document content 351 { LANGUAGE_FRENCH_CAMEROON, "fr", "CM", k0 }, 352 { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI", k0 }, 353 { LANGUAGE_FRENCH_MALI, "fr", "ML", k0 }, 354 { LANGUAGE_FRENCH_SENEGAL, "fr", "SN", k0 }, 355 { LANGUAGE_FRENCH_ZAIRE, "fr", "CD", k0 }, // Democratic Republic Of Congo 356 { LANGUAGE_FRENCH_MOROCCO, "fr", "MA", k0 }, 357 { LANGUAGE_FRENCH_REUNION, "fr", "RE", k0 }, 358 { LANGUAGE_FRISIAN_NETHERLANDS, "fy", "NL", k0 }, 359 { LANGUAGE_GAELIC_IRELAND, "ga", "IE", k0 }, 360 { LANGUAGE_GAELIC_SCOTLAND, "gd", "GB", k0 }, 361 { LANGUAGE_GAELIC_SCOTLAND_LEGACY, "gd", "GB", k0 }, 362 { LANGUAGE_GALICIAN, "gl", "ES", k0 }, 363 { LANGUAGE_GEORGIAN, "ka", "GE", k0 }, 364 { LANGUAGE_KHMER, "km", "KH", k0 }, 365 { LANGUAGE_KIRGHIZ, "ky", "KG", k0 }, 366 { LANGUAGE_LAO, "lo", "LA", k0 }, 367 { LANGUAGE_MALTESE, "mt", "MT", k0 }, 368 { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn", "MN", k0 }, // macrolanguage code; should be khk-MN; Cyrillic script 369 { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn", "" , k0 }, // macrolanguage code; should be khk; Cyrillic script 370 { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", k0 }, 371 { LANGUAGE_ROMANIAN_MOLDOVA, "mo", "MD", k0 }, // mo-MD was associated with Russian Moldova LCID, apparently an error; 'mo' is retired, merged with 'ro', see http://www-01.sil.org/iso639-3/documentation.asp?id=mol 372 { LANGUAGE_RUSSIAN_MOLDOVA, "ru", "MD", k0 }, // as per [MS-LCID] rev. 7.0 2015-06-30 373 { LANGUAGE_SWAHILI, "sw", "KE", k0 }, 374 { LANGUAGE_USER_SWAHILI_TANZANIA, "sw", "TZ", k0 }, 375 { LANGUAGE_TAJIK, "tg", "TJ", k0 }, 376 { LANGUAGE_TAJIK_LSO, "tg", "" , k0 }, 377 { LANGUAGE_TIBETAN, "bo", "CN", k0 }, // CN politically correct? 378 { LANGUAGE_USER_TIBETAN_INDIA, "bo", "IN", k0 }, 379 { LANGUAGE_USER_TIBETAN_BHUTAN, "bo", "BT", k0 }, 380 { LANGUAGE_DZONGKHA_BHUTAN, "dz", "BT", k0 }, 381 { LANGUAGE_TIBETAN_BHUTAN, "dz", "BT", k0 }, // MS reserved for bo-BT, but LCID was used as Dzongkha, see #i53497# 382 { LANGUAGE_USER_DZONGKHA_MAP_LONLY, "dz", "" , k0 }, // because of the MS error, see lang.h 383 { LANGUAGE_TURKMEN, "tk", "TM", k0 }, 384 { LANGUAGE_WELSH, "cy", "GB", k0 }, 385 { LANGUAGE_SESOTHO, "st", "ZA", k0 }, 386 { LANGUAGE_SEPEDI, "nso", "ZA", k0 }, 387 { LANGUAGE_SEPEDI, "ns", "ZA", kSAME }, // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents 388 { LANGUAGE_TSONGA, "ts", "ZA", k0 }, 389 { LANGUAGE_TSWANA, "tn", "ZA", k0 }, 390 { LANGUAGE_ENGLISH_SAFRICA, "en", "ZA", k0 }, 391 { LANGUAGE_AFRIKAANS, "af", "ZA", k0 }, 392 { LANGUAGE_VENDA, "ve", "ZA", k0 }, // default 639-1 393 { LANGUAGE_VENDA, "ven", "ZA", kSAME }, // 639-2 may have been used temporarily since 2004-07-23 394 { LANGUAGE_XHOSA, "xh", "ZA", k0 }, 395 { LANGUAGE_ZULU, "zu", "ZA", k0 }, 396 // { LANGUAGE_QUECHUA_COLOMBIA, "quc", "CO", k0 }, // MS reserved, and looks wrong, quc would be in Guatemala, not Colombia 397 { LANGUAGE_QUECHUA_ECUADOR, "quz", "EC", k0 }, // MS 398 { LANGUAGE_QUECHUA_ECUADOR, "qu", "EC", kSAME }, // macrolanguage code 399 { LANGUAGE_QUECHUA_PERU, "quz", "PE", k0 }, // MS 400 { LANGUAGE_QUECHUA_PERU, "qu", "PE", kSAME }, // macrolanguage code 401 { LANGUAGE_QUECHUA_BOLIVIA, "qu", "BO", k0 }, // macrolanguage code, TODO instead: quh-BO or qul-BO; MS says quz-BO which is wrong 402 { LANGUAGE_PASHTO, "ps", "AF", k0 }, 403 { LANGUAGE_OROMO, "om", "ET", k0 }, 404 { LANGUAGE_DHIVEHI, "dv", "MV", k0 }, 405 { LANGUAGE_UIGHUR_CHINA, "ug", "CN", k0 }, 406 { LANGUAGE_TIGRIGNA_ETHIOPIA, "ti", "ET", k0 }, 407 { LANGUAGE_TIGRIGNA_ERITREA, "ti", "ER", k0 }, 408 { LANGUAGE_AMHARIC_ETHIOPIA, "am", "ET", k0 }, 409 { LANGUAGE_GUARANI_PARAGUAY, "gug", "PY", k0 }, 410 { LANGUAGE_HAWAIIAN_UNITED_STATES, "haw", "US", k0 }, 411 { LANGUAGE_EDO, "bin", "NG", k0 }, // MS reserved 412 { LANGUAGE_FULFULDE_NIGERIA, "ff", "NG", k0 }, // macrolanguage code; MS since rev.15 413 { LANGUAGE_FULFULDE_NIGERIA, "fuv", "NG", kSAME }, // MS reserved until rev.15, since rev.15 "ff-NG" and "ff-Latn-NG" 414 { LANGUAGE_FULFULDE_SENEGAL, "ff", "SN", k0 }, // macrolanguage code 415 { LANGUAGE_HAUSA_NIGERIA, "ha", "NG", kSAME }, 416 { LANGUAGE_USER_HAUSA_GHANA, "ha", "GH", kSAME }, 417 { LANGUAGE_IGBO_NIGERIA, "ig", "NG", k0 }, 418 { LANGUAGE_KANURI_NIGERIA, "kr", "NG", k0 }, // macrolanguage code; MS reserved until rev.15 419 { LANGUAGE_YORUBA, "yo", "NG", k0 }, 420 { LANGUAGE_SOMALI, "so", "SO", k0 }, 421 { LANGUAGE_PAPIAMENTU, "pap", "AN", k0 }, 422 { LANGUAGE_USER_PAPIAMENTU_ARUBA, "pap", "AW", k0 }, 423 { LANGUAGE_USER_PAPIAMENTU_CURACAO, "pap", "CW", k0 }, 424 { LANGUAGE_USER_PAPIAMENTU_BONAIRE, "pap", "BQ", k0 }, 425 { LANGUAGE_ENGLISH_SINGAPORE, "en", "SG", k0 }, 426 { LANGUAGE_USER_YIDDISH_US, "yi", "US", k0 }, 427 { LANGUAGE_USER_YIDDISH_ISRAEL, "yi", "IL", k0 }, // new: old was "ji" 428 { LANGUAGE_USER_YIDDISH_ISRAEL, "ji", "IL", kSAME }, // old: new is "yi" 429 { LANGUAGE_SYRIAC, "syr", "TR", k0 }, // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC 430 { LANGUAGE_SINHALESE_SRI_LANKA, "si", "LK", k0 }, 431 { LANGUAGE_CHEROKEE_UNITED_STATES, "chr", "US", kSAME }, 432 { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu", "CA", kSAME }, // macrolanguage code 433 { LANGUAGE_INUKTITUT_LATIN_LSO, "iu", "" , kSAME }, // macrolanguage code 434 { LANGUAGE_SAMI_NORTHERN_NORWAY, "se", "NO", k0 }, 435 { LANGUAGE_SAMI_INARI, "smn", "FI", k0 }, 436 { LANGUAGE_SAMI_INARI_LSO, "smn", "" , k0 }, 437 { LANGUAGE_SAMI_LULE_NORWAY, "smj", "NO", k0 }, 438 { LANGUAGE_SAMI_LULE_SWEDEN, "smj", "SE", k0 }, 439 { LANGUAGE_SAMI_LULE_LSO, "smj", "" , k0 }, 440 { LANGUAGE_SAMI_NORTHERN_FINLAND, "se", "FI", k0 }, 441 { LANGUAGE_SAMI_NORTHERN_SWEDEN, "se", "SE", k0 }, 442 { LANGUAGE_SAMI_SKOLT, "sms", "FI", k0 }, 443 { LANGUAGE_SAMI_SKOLT_LSO, "sms", "" , k0 }, 444 { LANGUAGE_SAMI_SOUTHERN_NORWAY, "sma", "NO", k0 }, 445 { LANGUAGE_SAMI_SOUTHERN_SWEDEN, "sma", "SE", k0 }, 446 { LANGUAGE_SAMI_SOUTHERN_LSO, "sma", "" , k0 }, 447 { LANGUAGE_USER_SAMI_KILDIN_RUSSIA, "sjd", "RU", k0 }, 448 { LANGUAGE_MAPUDUNGUN_CHILE, "arn", "CL", k0 }, 449 { LANGUAGE_CORSICAN_FRANCE, "co", "FR", k0 }, 450 { LANGUAGE_ALSATIAN_FRANCE, "gsw", "FR", k0 }, // in fact 'gsw' is Schwyzerduetsch (Swiss German), which is a dialect of Alemannic German, as is Alsatian. They aren't distinct languages and share this code. 451 { LANGUAGE_YAKUT_RUSSIA, "sah", "RU", k0 }, 452 { LANGUAGE_MOHAWK_CANADA, "moh", "CA", k0 }, 453 { LANGUAGE_BASHKIR_RUSSIA, "ba", "RU", k0 }, 454 { LANGUAGE_KICHE_GUATEMALA, "qut", "GT", k0 }, // MS reserved since rev.15 455 { LANGUAGE_DARI_AFGHANISTAN, "prs", "AF", k0 }, 456 { LANGUAGE_DARI_AFGHANISTAN, "gbz", "AF", kSAME }, // was an error 457 { LANGUAGE_WOLOF_SENEGAL, "wo", "SN", k0 }, 458 { LANGUAGE_FILIPINO, "fil", "PH", k0 }, 459 { LANGUAGE_USER_TAGALOG, "tl", "PH", k0 }, 460 { LANGUAGE_ENGLISH_PHILIPPINES, "en", "PH", k0 }, 461 { LANGUAGE_IBIBIO_NIGERIA, "ibb", "NG", k0 }, // MS reserved 462 { LANGUAGE_YI, "ii", "CN", k0 }, 463 { LANGUAGE_ENGLISH_ARAB_EMIRATES, "en", "AE", k0 }, 464 { LANGUAGE_ENGLISH_BAHRAIN, "en", "BH", k0 }, // MS reserved 465 { LANGUAGE_ENGLISH_EGYPT, "en", "EG", k0 }, // MS reserved 466 { LANGUAGE_ENGLISH_JORDAN, "en", "JO", k0 }, // MS reserved 467 { LANGUAGE_ENGLISH_KUWAIT, "en", "KW", k0 }, // MS reserved 468 { LANGUAGE_ENGLISH_TURKEY, "en", "TR", k0 }, // MS reserved 469 { LANGUAGE_ENGLISH_YEMEN, "en", "YE", k0 }, // MS reserved 470 { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "kab", "DZ", k0 }, // In practice Kabyle is the language used for this 471 { LANGUAGE_OBSOLETE_USER_KABYLE, "kab", "DZ", k0 }, 472 { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "ber", "DZ", kSAME }, // In practice Algeria has standardized on Kabyle as the member of the "ber" collective which gets used there. 473 { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tmz", "MA", kSAME }, 474 { LANGUAGE_TAMAZIGHT_MOROCCO, "tmz", "MA", k0 }, // MS reserved 475 { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "ber", "MA", kSAME }, // Morocco is officially using Tifinagh for its Berber languages, old kludge to distinguish from LANGUAGE_TAMAZIGHT_LATIN_ALGERIA 476 { LANGUAGE_LATIN, "la", "VA", k0 }, 477 { LANGUAGE_OBSOLETE_USER_LATIN_VATICAN, "la", "VA", LANGUAGE_LATIN }, 478 { LANGUAGE_OBSOLETE_USER_LATIN, "la", "VA", LANGUAGE_LATIN }, 479 { LANGUAGE_LATIN, "la", "" , kSAME }, 480 { LANGUAGE_USER_ESPERANTO, "eo", "" , k0 }, 481 { LANGUAGE_USER_INTERLINGUA, "ia", "" , k0 }, 482 { LANGUAGE_USER_INTERLINGUE, "ie", "" , k0 }, 483 { LANGUAGE_MAORI_NEW_ZEALAND, "mi", "NZ", k0 }, 484 { LANGUAGE_OBSOLETE_USER_MAORI, "mi", "NZ", k0 }, 485 { LANGUAGE_KINYARWANDA_RWANDA, "rw", "RW", k0 }, 486 { LANGUAGE_OBSOLETE_USER_KINYARWANDA, "rw", "RW", k0 }, 487 { LANGUAGE_UPPER_SORBIAN_GERMANY, "hsb", "DE", k0 }, // MS maps this to 'wen-DE', which is nonsense. 'wen' is a collective language code, 'WEN' is a SIL code, see http://www.ethnologue.com/14/show_iso639.asp?code=wen and http://www.ethnologue.com/14/show_language.asp?code=WEN 488 { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE", k0 }, 489 { LANGUAGE_LOWER_SORBIAN_GERMANY, "dsb", "DE", k0 }, // MS maps this to 'wee-DE', which is nonsense. 'WEE' is a SIL code, see http://www.ethnologue.com/14/show_language.asp?code=WEE 490 { LANGUAGE_LOWER_SORBIAN_LSO, "dsb", "" , k0 }, 491 { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE", k0 }, 492 { LANGUAGE_OCCITAN_FRANCE, "oc", "FR", k0 }, 493 { LANGUAGE_OBSOLETE_USER_OCCITAN, "oc", "FR", k0 }, 494 { LANGUAGE_USER_KURDISH_TURKEY, "kmr", "TR", kSAME }, 495 { LANGUAGE_USER_KURDISH_TURKEY, "ku", "TR", kSAME }, 496 { LANGUAGE_USER_KURDISH_SYRIA, "kmr", "SY", kSAME }, 497 { LANGUAGE_USER_KURDISH_SYRIA, "ku", "SY", kSAME }, 498 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ckb", "IQ", k0 }, 499 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku", "IQ", kSAME }, 500 { LANGUAGE_OBSOLETE_USER_KURDISH_IRAQ, "ku", "IQ", LANGUAGE_KURDISH_ARABIC_IRAQ }, 501 { LANGUAGE_USER_KURDISH_SOUTHERN_IRAN, "sdh", "IR", k0 }, 502 { LANGUAGE_USER_KURDISH_SOUTHERN_IRAQ, "sdh", "IQ", k0 }, 503 { LANGUAGE_USER_KURDISH_IRAN, "ckb", "IR", k0 }, 504 { LANGUAGE_USER_KURDISH_IRAN, "ku", "IR", kSAME }, 505 { LANGUAGE_KURDISH_ARABIC_LSO, "ckb", "" , k0 }, 506 { LANGUAGE_USER_SARDINIAN, "sc", "IT", k0 }, // macrolanguage code 507 { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT", k0 }, 508 { LANGUAGE_USER_SARDINIAN_GALLURESE, "sdn", "IT", k0 }, 509 { LANGUAGE_USER_SARDINIAN_LOGUDORESE, "src", "IT", k0 }, 510 { LANGUAGE_USER_SARDINIAN_SASSARESE, "sdc", "IT", k0 }, 511 { LANGUAGE_BRETON_FRANCE, "br", "FR", k0 }, 512 { LANGUAGE_OBSOLETE_USER_BRETON, "br", "FR", k0 }, 513 { LANGUAGE_KALAALLISUT_GREENLAND, "kl", "GL", k0 }, 514 { LANGUAGE_OBSOLETE_USER_KALAALLISUT, "kl", "GL", k0 }, 515 { LANGUAGE_USER_SWAZI, "ss", "ZA", k0 }, 516 { LANGUAGE_USER_NDEBELE_SOUTH, "nr", "ZA", k0 }, 517 { LANGUAGE_TSWANA_BOTSWANA, "tn", "BW", k0 }, 518 { LANGUAGE_OBSOLETE_USER_TSWANA_BOTSWANA, "tn", "BW", k0 }, 519 { LANGUAGE_USER_ENGLISH_BOTSWANA, "en", "BW", k0 }, 520 { LANGUAGE_USER_MOORE, "mos", "BF", k0 }, 521 { LANGUAGE_USER_BAMBARA, "bm", "ML", k0 }, 522 { LANGUAGE_USER_AKAN, "ak", "GH", k0 }, 523 { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG, "lb", "LU", k0 }, 524 { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU", k0 }, 525 { LANGUAGE_USER_FRIULIAN, "fur", "IT", k0 }, 526 { LANGUAGE_USER_FIJIAN, "fj", "FJ", k0 }, 527 { LANGUAGE_USER_AFRIKAANS_NAMIBIA, "af", "NA", k0 }, 528 { LANGUAGE_USER_ENGLISH_NAMIBIA, "en", "NA", k0 }, 529 { LANGUAGE_USER_WALLOON, "wa", "BE", k0 }, 530 { LANGUAGE_USER_COPTIC, "cop", "EG", k0 }, 531 { LANGUAGE_USER_GASCON, "gsc", "FR", k0 }, 532 { LANGUAGE_USER_GERMAN_BELGIUM, "de", "BE", k0 }, 533 { LANGUAGE_USER_CHUVASH, "cv", "RU", k0 }, 534 { LANGUAGE_USER_EWE_GHANA, "ee", "GH", k0 }, 535 { LANGUAGE_USER_ENGLISH_GHANA, "en", "GH", k0 }, 536 { LANGUAGE_USER_SANGO, "sg", "CF", k0 }, 537 { LANGUAGE_USER_GANDA, "lg", "UG", k0 }, 538 { LANGUAGE_USER_LINGALA_DRCONGO, "ln", "CD", k0 }, 539 { LANGUAGE_USER_LOW_GERMAN, "nds", "DE", k0 }, 540 { LANGUAGE_USER_HILIGAYNON, "hil", "PH", k0 }, 541 { LANGUAGE_USER_ENGLISH_MALAWI, "en", "MW", k0 }, /* en default for MW */ 542 { LANGUAGE_USER_NYANJA, "ny", "MW", k0 }, 543 { LANGUAGE_USER_KASHUBIAN, "csb", "PL", k0 }, 544 { LANGUAGE_SPANISH_CUBA, "es", "CU", k0 }, 545 { LANGUAGE_OBSOLETE_USER_SPANISH_CUBA, "es", "CU", k0 }, 546 { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO", k0 }, 547 { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO", k0 }, 548 { LANGUAGE_USER_BODO_INDIA, "brx", "IN", k0 }, 549 { LANGUAGE_USER_DOGRI_INDIA, "dgo", "IN", k0 }, 550 { LANGUAGE_USER_MAITHILI_INDIA, "mai", "IN", k0 }, 551 { LANGUAGE_USER_SANTALI_INDIA, "sat", "IN", k0 }, 552 { LANGUAGE_USER_TETUN, "tet", "ID", k0 }, 553 { LANGUAGE_USER_TETUN_TIMOR_LESTE, "tet", "TL", k0 }, 554 { LANGUAGE_USER_TOK_PISIN, "tpi", "PG", k0 }, 555 { LANGUAGE_USER_SHUSWAP, "shs", "CA", k0 }, 556 { LANGUAGE_USER_ANCIENT_GREEK, "grc", "GR", k0 }, 557 { LANGUAGE_USER_ASTURIAN, "ast", "ES", k0 }, 558 { LANGUAGE_USER_LATGALIAN, "ltg", "LV", k0 }, 559 { LANGUAGE_USER_MAORE, "swb", "YT", k0 }, 560 { LANGUAGE_USER_BUSHI, "buc", "YT", k0 }, 561 { LANGUAGE_USER_TAHITIAN, "ty", "PF", k0 }, 562 { LANGUAGE_MALAGASY_PLATEAU, "plt", "MG", k0 }, // MS reserved 563 { LANGUAGE_MALAGASY_PLATEAU, "mg", "MG", kSAME }, 564 { LANGUAGE_OBSOLETE_USER_MALAGASY_PLATEAU, "plt", "MG", k0 }, 565 { LANGUAGE_USER_BAFIA, "ksf", "CM", k0 }, 566 { LANGUAGE_USER_GIKUYU, "ki", "KE", k0 }, 567 { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA", k0 }, 568 { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK", k0 }, 569 { LANGUAGE_USER_LIMBU, "lif", "NP", k0 }, 570 { LANGUAGE_USER_LOJBAN, "jbo", "" , k0 }, 571 { LANGUAGE_USER_HAITIAN, "ht", "HT", k0 }, 572 { LANGUAGE_FRENCH_HAITI, "fr", "HT", k0 }, 573 { LANGUAGE_USER_BEEMBE, "beq", "CG", k0 }, 574 { LANGUAGE_USER_BEKWEL, "bkw", "CG", k0 }, 575 { LANGUAGE_USER_KITUBA, "mkw", "CG", k0 }, 576 { LANGUAGE_USER_LARI, "ldi", "CG", k0 }, 577 { LANGUAGE_USER_MBOCHI, "mdw", "CG", k0 }, 578 { LANGUAGE_USER_TEKE_EBOO, "ebo", "CG", k0 }, 579 { LANGUAGE_USER_TEKE_IBALI, "tek", "CG", k0 }, 580 { LANGUAGE_USER_TEKE_TYEE, "tyx", "CG", k0 }, 581 { LANGUAGE_USER_VILI, "vif", "CG", k0 }, 582 { LANGUAGE_USER_PORTUGUESE_ANGOLA, "pt", "AO", k0 }, 583 { LANGUAGE_USER_MANX, "gv", "GB", k0 }, 584 { LANGUAGE_USER_ARAGONESE, "an", "ES", k0 }, 585 { LANGUAGE_USER_KEYID, "qtz", "" , k0 }, // key id pseudolanguage used for UI testing 586 { LANGUAGE_USER_PALI_LATIN, "pli", "" , kSAME }, // Pali with Latin script, ISO 639-3 (sigh..) back-compat, Latin is not a default script though... 587 { LANGUAGE_USER_KYRGYZ_CHINA, "ky", "CN", k0 }, 588 { LANGUAGE_USER_KOMI_ZYRIAN, "kpv", "RU", k0 }, 589 { LANGUAGE_USER_KOMI_PERMYAK, "koi", "RU", k0 }, 590 { LANGUAGE_USER_PITJANTJATJARA, "pjt", "AU", k0 }, 591 { LANGUAGE_USER_ERZYA, "myv", "RU", k0 }, 592 { LANGUAGE_USER_MARI_MEADOW, "mhr", "RU", k0 }, 593 { LANGUAGE_USER_KHANTY, "kca", "RU", k0 }, 594 { LANGUAGE_USER_LIVONIAN, "liv", "RU", k0 }, 595 { LANGUAGE_USER_MOKSHA, "mdf", "RU", k0 }, 596 { LANGUAGE_USER_MARI_HILL, "mrj", "RU", k0 }, 597 { LANGUAGE_USER_NGANASAN, "nio", "RU", k0 }, 598 { LANGUAGE_USER_OLONETS, "olo", "RU", k0 }, 599 { LANGUAGE_USER_VEPS, "vep", "RU", k0 }, 600 { LANGUAGE_USER_VORO, "vro", "EE", k0 }, 601 { LANGUAGE_USER_NENETS, "yrk", "RU", k0 }, 602 { LANGUAGE_USER_AKA, "axk", "CF", k0 }, 603 { LANGUAGE_USER_AKA_CONGO, "axk", "CG", k0 }, 604 { LANGUAGE_USER_DIBOLE, "bvx", "CG", k0 }, 605 { LANGUAGE_USER_DOONDO, "dde", "CG", k0 }, 606 { LANGUAGE_USER_KAAMBA, "xku", "CG", k0 }, 607 { LANGUAGE_USER_KOONGO, "kng", "CD", k0 }, 608 { LANGUAGE_USER_KOONGO_CONGO, "kng", "CG", k0 }, 609 { LANGUAGE_USER_KUNYI, "njx", "CG", k0 }, 610 { LANGUAGE_USER_NGUNGWEL, "ngz", "CG", k0 }, 611 { LANGUAGE_USER_NJYEM, "njy", "CM", k0 }, 612 { LANGUAGE_USER_NJYEM_CONGO, "njy", "CG", k0 }, 613 { LANGUAGE_USER_PUNU, "puu", "GA", k0 }, 614 { LANGUAGE_USER_PUNU_CONGO, "puu", "CG", k0 }, 615 { LANGUAGE_USER_SUUNDI, "sdj", "CG", k0 }, 616 { LANGUAGE_USER_TEKE_KUKUYA, "kkw", "CG", k0 }, 617 { LANGUAGE_USER_TSAANGI, "tsa", "CG", k0 }, 618 { LANGUAGE_USER_YAKA, "iyx", "CG", k0 }, 619 { LANGUAGE_USER_YOMBE, "yom", "CD", k0 }, 620 { LANGUAGE_USER_YOMBE_CONGO, "yom", "CG", k0 }, 621 { LANGUAGE_USER_SIDAMA, "sid", "ET", k0 }, 622 { LANGUAGE_USER_NKO, "nqo", "GN", k0 }, 623 { LANGUAGE_USER_UDMURT, "udm", "RU", k0 }, 624 { LANGUAGE_USER_CORNISH, "kw", "GB", k0 }, 625 { LANGUAGE_USER_CORNISH, "kw", "UK", kSAME }, // old erroneous tag 626 { LANGUAGE_USER_SAMI_PITE_SWEDEN, "sje", "SE", k0 }, 627 { LANGUAGE_USER_NGAEBERE, "gym", "PA", k0 }, 628 { LANGUAGE_USER_KUMYK, "kum", "RU", k0 }, 629 { LANGUAGE_USER_NOGAI, "nog", "RU", k0 }, 630 { LANGUAGE_USER_LADIN, "lld", "IT", k0 }, 631 { LANGUAGE_USER_FRENCH_BURKINA_FASO, "fr", "BF", k0 }, 632 { LANGUAGE_USER_PUINAVE, "pui", "CO", k0 }, 633 { LANGUAGE_USER_AVAR, "av", "RU", k0 }, 634 { LANGUAGE_USER_LENGO, "lgr", "SB", k0 }, 635 { LANGUAGE_USER_FRENCH_BENIN, "fr", "BJ", k0 }, 636 { LANGUAGE_USER_FRENCH_NIGER, "fr", "NE", k0 }, 637 { LANGUAGE_USER_FRENCH_TOGO, "fr", "TG", k0 }, 638 { LANGUAGE_USER_KVEN_FINNISH, "fkv", "NO", k0 }, 639 { LANGUAGE_USER_CHURCH_SLAVIC, "cu", "RU", k0 }, 640 { LANGUAGE_USER_VENETIAN, "vec", "IT", k0 }, 641 { LANGUAGE_USER_ENGLISH_GAMBIA, "en", "GM", k0 }, 642 { LANGUAGE_USER_OCCITAN_ARANESE, "oc", "ES", k0 }, 643 { LANGUAGE_USER_ARPITAN_FRANCE, "frp", "FR", k0 }, 644 { LANGUAGE_USER_ARPITAN_ITALY, "frp", "IT", k0 }, 645 { LANGUAGE_USER_ARPITAN_SWITZERLAND, "frp", "CH", k0 }, 646 { LANGUAGE_USER_APATANI, "apt", "IN", k0 }, 647 { LANGUAGE_USER_ENGLISH_MAURITIUS, "en", "MU", k0 }, 648 { LANGUAGE_USER_FRENCH_MAURITIUS, "fr", "MU", k0 }, 649 { LANGUAGE_USER_SILESIAN, "szl", "PL", k0 }, 650 { LANGUAGE_USER_MANCHU, "mnc", "CN", k0 }, 651 { LANGUAGE_USER_XIBE, "sjo", "CN", k0 }, 652 { LANGUAGE_USER_KITUBA_DRCONGO, "ktu", "CD", k0 }, 653 { LANGUAGE_USER_FON, "fon", "BJ", k0 }, 654 { LANGUAGE_USER_PLAUTDIETSCH, "pdt", "CA", k0 }, 655 { LANGUAGE_USER_ARMENIAN_WESTERN, "hyw", "AM", k0 }, 656 { LANGUAGE_USER_ARMENIAN_CLASSICAL, "xcl", "AM", k0 }, 657 { LANGUAGE_USER_JUHOAN, "ktz", "NA", k0 }, 658 { LANGUAGE_USER_NARO, "nhr", "BW", k0 }, 659 { LANGUAGE_USER_ILOKO, "ilo", "PH", k0 }, 660 { LANGUAGE_USER_ENGLISH_ZAMBIA, "en", "ZM", k0 }, 661 { LANGUAGE_USER_ENGLISH_SRI_LANKA, "en", "LK", k0 }, 662 { LANGUAGE_USER_ENGLISH_NIGERIA, "en", "NG", k0 }, 663 { LANGUAGE_USER_KABARDIAN, "kbd", "RU", k0 }, // Cyrillic script 664 { LANGUAGE_USER_GUADELOUPEAN_CREOLE_FRENCH, "gcf", "GP", k0 }, 665 { LANGUAGE_USER_LIGURIAN, "lij", "IT", k0 }, 666 { LANGUAGE_USER_MINANGKABAU, "min", "ID", k0 }, 667 { LANGUAGE_USER_SUNDANESE, "sun", "ID", k0 }, 668 { LANGUAGE_USER_YAKA_DRCONGO, "yaf", "CD", k0 }, 669 { LANGUAGE_USER_ENGLISH_KENYA, "en", "KE", k0 }, 670 { LANGUAGE_USER_CABECAR, "cjp", "CR", k0 }, 671 { LANGUAGE_USER_BRIBRI, "bzd", "CR", k0 }, 672 { LANGUAGE_USER_ENGLISH_DENMARK, "en", "DK", k0 }, 673 { LANGUAGE_USER_SESOTHO_LESOTHO, "st", "LS", k0 }, 674 { LANGUAGE_USER_KLINGON, "tlh", "" , k0 }, 675 { LANGUAGE_USER_ENGLISH_ISRAEL, "en", "IL", k0 }, 676 { LANGUAGE_USER_PENNSYLVANIA_DUTCH, "pdc", "US", k0 }, 677 { LANGUAGE_MULTIPLE, "mul", "" , k0 }, // multiple languages, many languages are used 678 { LANGUAGE_UNDETERMINED, "und", "" , k0 }, // undetermined language, language cannot be identified 679 { LANGUAGE_NONE, "zxx", "" , k0 }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information 680 { LANGUAGE_DONTKNOW, "", "" , k0 } // marks end of table 681 }; 682 683 IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] = 684 { 685 // MS-LangID, ISO639-ISO15924, ISO3166, override 686 { LANGUAGE_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", k0 }, 687 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", k0 }, 688 { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sr-Latn", "ME", k0 }, 689 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO,"sr-Latn", "ME", k0 }, 690 { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sr-Latn", "BA", k0 }, 691 { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "CS", k0 }, // Serbian Latin in Serbia and Montenegro; note that not all applications may know about the 'CS' reusage mess, see https://en.wikipedia.org/wiki/ISO_3166-2:CS 692 { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "YU", k0 }, // legacy Serbian Latin in Yugoslavia 693 { LANGUAGE_SERBIAN_LATIN_LSO, "sr-Latn", "" , k0 }, 694 { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sr-Latn", "" , LANGUAGE_SERBIAN_LATIN_LSO }, // MS lists this as 'sr' only, what a mess 695 { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr-Cyrl", "RS", kSAME }, // MS 696 { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr-Cyrl", "ME", kSAME }, // MS 697 { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr-Cyrl", "BA", kSAME }, // MS 698 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr-Cyrl", "CS", kSAME }, // MS 699 { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr-Cyrl", "" , kSAME }, // MS 700 { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs-Cyrl", "BA", k0 }, 701 { LANGUAGE_BOSNIAN_CYRILLIC_LSO, "bs-Cyrl", "" , k0 }, 702 { LANGUAGE_AZERI_CYRILLIC, "az-Cyrl", "AZ", k0 }, // macrolanguage code; MS reserved since rev.15 703 { LANGUAGE_AZERI_CYRILLIC_LSO, "az-Cyrl", "" , k0 }, // macrolanguage code 704 { LANGUAGE_UZBEK_CYRILLIC, "uz-Cyrl", "UZ", k0 }, // macrolanguage code; MS reserved since rev.15 705 { LANGUAGE_UZBEK_CYRILLIC_LSO, "uz-Cyrl", "" , k0 }, // macrolanguage code 706 { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn-Cyrl", "MN", k0 }, // macrolanguage code; should be khk-MN or khk-Cyrl-MN 707 { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn-Cyrl", "" , k0 }, // macrolanguage code; MS, should be khk or khk-Cyrl 708 { LANGUAGE_MONGOLIAN_MONGOLIAN_MONGOLIA, "mn-Mong", "MN", k0 }, // macrolanguage code; MS, should be khk-Mong-MN 709 { LANGUAGE_MONGOLIAN_MONGOLIAN_CHINA, "mn-Mong", "CN", k0 }, // macrolanguage code; MS reserved since rev.15; should actually be mvf-CN 710 { LANGUAGE_MONGOLIAN_MONGOLIAN_LSO, "mn-Mong", "" , k0 }, // macrolanguage code 711 { LANGUAGE_USER_PALI_LATIN, "pi-Latn", "" , k0 }, 712 { LANGUAGE_USER_PALI_THAI, "pi-Thai", "" , k0 }, 713 { LANGUAGE_USER_KARAKALPAK_LATIN, "kaa-Latn", "UZ", k0 }, 714 { LANGUAGE_TAJIK, "tg-Cyrl", "TJ", k0 }, // MS 715 { LANGUAGE_TAJIK_LSO, "tg-Cyrl", "" , k0 }, // MS 716 { LANGUAGE_AZERI_LATIN, "az-Latn", "AZ", k0 }, // macrolanguage code; MS 717 { LANGUAGE_AZERI_LATIN_LSO, "az-Latn", "" , k0 }, // macrolanguage code; MS 718 { LANGUAGE_USER_YIDDISH_US, "yi-Hebr", "US", kSAME }, // macrolanguage code; MS, Hebr is suppress-script 719 { LANGUAGE_USER_YIDDISH_ISRAEL, "yi-Hebr", "IL", kSAME }, // macrolanguage code; MS, Hebr is suppress-script 720 { LANGUAGE_UZBEK_LATIN, "uz-Latn", "UZ", k0 }, // macrolanguage code 721 { LANGUAGE_UZBEK_LATIN_LSO, "uz-Latn", "" , k0 }, 722 { LANGUAGE_SINDHI, "sd-Deva", "IN", k0 }, // MS reserved 723 { LANGUAGE_SINDHI_PAKISTAN, "sd-Arab", "PK", k0 }, // MS 724 { LANGUAGE_SINDHI_ARABIC_LSO, "sd-Arab", "" , k0 }, 725 { LANGUAGE_CHEROKEE_UNITED_STATES, "chr-Cher", "US", k0 }, // MS 726 { LANGUAGE_CHEROKEE_CHEROKEE_LSO, "chr-Cher", "" , k0 }, 727 { LANGUAGE_INUKTITUT_SYLLABICS_CANADA, "iu-Cans", "CA", k0 }, // macrolanguage code, MS 728 { LANGUAGE_INUKTITUT_SYLLABICS_LSO, "iu-Cans", "" , k0 }, // macrolanguage code, MS 729 { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu-Latn", "CA", k0 }, // macrolanguage code, MS 730 { LANGUAGE_INUKTITUT_LATIN_LSO, "iu-Latn", "" , k0 }, // macrolanguage code, MS 731 { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tzm-Tfng", "MA", k0 }, 732 { LANGUAGE_TAMAZIGHT_TIFINAGH_LSO, "tzm-Tfng", "" , k0 }, 733 { LANGUAGE_KASHMIRI_INDIA, "ks-Deva", "IN", k0 }, // MS since rev.15, earlier was "ks-Deva" reserved 734 { LANGUAGE_KASHMIRI, "ks-Arab", "" , k0 }, // MS, Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that 735 { LANGUAGE_HAUSA_NIGERIA, "ha-Latn", "NG", k0 }, // MS 736 { LANGUAGE_USER_HAUSA_GHANA, "ha-Latn", "GH", k0 }, 737 { LANGUAGE_HAUSA_LATIN_LSO, "ha-Latn", "" , k0 }, 738 { LANGUAGE_LATIN, "la-Latn", "" , kSAME }, // MS reserved until rev.15, though Latn is suppress-script, "la-VA" since rev.15 739 { LANGUAGE_TAI_NUA_CHINA, "tdd-Tale", "CN", k0 }, // MS reserved 740 { LANGUAGE_LU_CHINA, "khb-Talu", "CN", k0 }, // MS reserved 741 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku-Arab", "IQ", kSAME }, // macrolanguage code, MS 742 { LANGUAGE_KURDISH_ARABIC_LSO, "ku-Arab", "" , kSAME }, // macrolanguage code, MS 743 { LANGUAGE_USER_KURDISH_TURKEY, "kmr-Latn", "TR", k0 }, 744 { LANGUAGE_USER_KURDISH_SYRIA, "kmr-Latn", "SY", k0 }, 745 { LANGUAGE_PUNJABI_PAKISTAN, "pnb-Arab", "PK", k0 }, 746 { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb-Arab", "" , k0 }, 747 { LANGUAGE_PUNJABI_PAKISTAN, "pa-Arab", "PK", k0 }, // MS, incorrect 748 { LANGUAGE_PUNJABI_ARABIC_LSO, "pa-Arab", "" , k0 }, // MS, incorrect 749 { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "tzm-Latn", "DZ", kSAME }, // MS 750 { LANGUAGE_TAMAZIGHT_LATIN_LSO, "tzm-Latn", "" , k0 }, // MS 751 { LANGUAGE_FULFULDE_NIGERIA, "ff-Latn", "NG", kSAME }, // macrolanguage code; MS since rev.15 752 { LANGUAGE_FULFULDE_SENEGAL, "ff-Latn", "SN", k0 }, // macrolanguage code, MS 753 { LANGUAGE_FULFULDE_LATIN_LSO, "ff-Latn", "" , k0 }, // macrolanguage code 754 { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs-Latn", "BA", kSAME }, // MS, though Latn is suppress-script 755 { LANGUAGE_BOSNIAN_LATIN_LSO, "bs-Latn", "" , LANGUAGE_BOSNIAN_LSO }, // MS, though Latn is suppress-script 756 { LANGUAGE_CHINESE_TRADITIONAL_LSO, "zh-Hant", "" , k0 }, 757 { LANGUAGE_USER_MANINKAKAN_EASTERN_LATIN, "emk-Latn", "GN", k0 }, 758 { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CA", k0 }, 759 { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CA", k0 }, 760 { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CN", kSAME }, // erroneous tdf#73973 761 { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CN", kSAME }, // erroneous tdf#73973 762 { LANGUAGE_USER_HUNGARIAN_ROVAS, "hu-Hung", "HU", k0 }, 763 { LANGUAGE_USER_MALAY_ARABIC_MALAYSIA, "ms-Arab", "MY", k0 }, 764 { LANGUAGE_USER_MALAY_ARABIC_BRUNEI, "ms-Arab", "BN", k0 }, 765 { LANGUAGE_KAZAKH_LATIN, "kk-Latn", "KZ", k0 }, 766 { LANGUAGE_KAZAKH_LATIN_LSO, "kk-Latn", "" , k0 }, // MS reserved 767 { LANGUAGE_KAZAKH_CYRILLIC_LSO, "kk-Cyrl", "" , k0 }, // MS reserved 768 { LANGUAGE_KANURI_NIGERIA, "kr-Latn", "NG", k0 }, // macrolanguage code; MS since rev.15 769 { LANGUAGE_TAMAZIGHT_ARABIC_MOROCCO, "tzm-Arab", "MA", k0 }, // MS since rev.15, was reserved 770 { LANGUAGE_DONTKNOW, "", "" , k0 } // marks end of table 771 }; 772 773 Bcp47CountryEntry const aImplBcp47CountryEntries[] = 774 { 775 // MS-LangID full BCP47, ISO3166, ISO639-Variant or other fallback 776 { LANGUAGE_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "ca-valencia", k0 }, 777 { LANGUAGE_OBSOLETE_USER_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "", k0 }, // In case MS format files using the old value escaped into the wild, map them back. 778 { LANGUAGE_USER_ENGLISH_UK_OXENDICT, "en-GB-oxendict", "GB", "", k0 }, 779 { LANGUAGE_USER_ENGLISH_UK_OED, "en-GB-oed", "GB", "", LANGUAGE_USER_ENGLISH_UK_OXENDICT }, // grandfathered, deprecated, prefer en-GB-oxendict 780 { LANGUAGE_SPANISH_DATED, "es-ES-u-co-trad", "ES", "es-u-co-trad", k0 }, // RFC6067/CLDR 781 { LANGUAGE_SPANISH_DATED, "es-ES_tradnl", "ES", "", kSAME }, // MS malformed 782 // { LANGUAGE_YUE_CHINESE_HONGKONG, "zh-yue-HK", "HK", "", 0 }, // MS reserved, prefer yue-HK; do not add unless LanguageTag::simpleExtract() can handle it to not call liblangtag for rsc! 783 { LANGUAGE_YIDDISH, "yi-001", "", "", k0 }, // MS since rev.15, was "yi-Hebr" reserved, "001"="World" 784 { LANGUAGE_FRENCH_WEST_INDIES, "fr-029", "", "", k0 }, // MS since rev.15, was "Neither defined nor reserved", "029"="Caribbean" 785 { LANGUAGE_USER_INTERSLAVIC_LATIN, "art-Latn-x-interslv", "", "", k0 }, // see discussion in tdf#145853 786 { LANGUAGE_USER_INTERSLAVIC_CYRILLIC, "art-Cyrl-x-interslv", "", "", k0 }, 787 { LANGUAGE_DONTKNOW, "", "", "", k0 } // marks end of table 788 }; 789 790 const IsoLanguageCountryEntry aLastResortFallbackEntry = 791 { LANGUAGE_ENGLISH_US, "en", "US", k0 }; 792 793 OUString IsoLanguageCountryEntry::getTagString() const 794 { 795 if (maCountry[0]) 796 return OUString( OUString::createFromAscii( maLanguage) + "-" + OUString::createFromAscii( maCountry)); 797 else 798 return OUString::createFromAscii( maLanguage); 799 } 800 801 css::lang::Locale IsoLanguageCountryEntry::getLocale() const 802 { 803 return lang::Locale( OUString::createFromAscii( maLanguage), OUString::createFromAscii( maCountry), OUString()); 804 } 805 806 OUString IsoLanguageScriptCountryEntry::getTagString() const 807 { 808 if (maCountry[0]) 809 return OUString( OUString::createFromAscii( maLanguageScript) + "-" + OUString::createFromAscii( maCountry)); 810 else 811 return OUString::createFromAscii( maLanguageScript); 812 } 813 814 css::lang::Locale IsoLanguageScriptCountryEntry::getLocale() const 815 { 816 return lang::Locale( I18NLANGTAG_QLT, OUString::createFromAscii( maCountry), getTagString()); 817 } 818 819 bool IsoLanguageScriptCountryEntry::startsInIgnoreAsciiCase( const OUString & rStr ) const 820 { 821 return rStr.matchIgnoreAsciiCaseAsciiL( maLanguageScript, strlen( maLanguageScript) ); 822 } 823 824 OUString Bcp47CountryEntry::getTagString() const 825 { 826 return OUString::createFromAscii( mpBcp47); 827 } 828 829 css::lang::Locale Bcp47CountryEntry::getLocale() const 830 { 831 return lang::Locale( I18NLANGTAG_QLT, OUString::createFromAscii( maCountry), getTagString()); 832 } 833 834 835 // In this table are the countries which should mapped to a specific 836 // english language 837 IsoLangEngEntry const aImplIsoLangEngEntries[] = 838 { 839 { LANGUAGE_ENGLISH_UK, "AO" }, // Angola 840 { LANGUAGE_ENGLISH_UK, "BJ" }, // Benin 841 { LANGUAGE_ENGLISH_UK, "BW" }, // Botswana 842 { LANGUAGE_ENGLISH_UK, "BI" }, // Burundi 843 { LANGUAGE_ENGLISH_UK, "CM" }, // Cameroon 844 { LANGUAGE_ENGLISH_UK, "GA" }, // Gabon 845 { LANGUAGE_ENGLISH_UK, "GM" }, // Gambia 846 { LANGUAGE_ENGLISH_UK, "GH" }, // Ghana 847 { LANGUAGE_ENGLISH_UK, "GN" }, // Guinea 848 { LANGUAGE_ENGLISH_UK, "LS" }, // Lesotho 849 { LANGUAGE_ENGLISH_UK, "MW" }, // Malawi 850 { LANGUAGE_ENGLISH_UK, "MT" }, // Malta 851 { LANGUAGE_ENGLISH_UK, "NA" }, // Namibia 852 { LANGUAGE_ENGLISH_UK, "NG" }, // Nigeria 853 { LANGUAGE_ENGLISH_UK, "UG" }, // Uganda 854 { LANGUAGE_ENGLISH_UK, "ZM" }, // Zambia 855 { LANGUAGE_ENGLISH_UK, "ZW" }, // Zimbabwe 856 { LANGUAGE_ENGLISH_UK, "SZ" }, // Swaziland 857 { LANGUAGE_ENGLISH_UK, "NG" }, // Sierra Leone 858 { LANGUAGE_ENGLISH_UK, "KN" }, // Saint Kitts and Nevis 859 { LANGUAGE_ENGLISH_UK, "SH" }, // St. Helena 860 { LANGUAGE_ENGLISH_UK, "IO" }, // British Indian Oceanic Territory 861 { LANGUAGE_ENGLISH_UK, "FK" }, // Falkland Islands 862 { LANGUAGE_ENGLISH_UK, "GI" }, // Gibraltar 863 { LANGUAGE_ENGLISH_UK, "KI" }, // Kiribati 864 { LANGUAGE_ENGLISH_UK, "VG" }, // Virgin Islands 865 { LANGUAGE_ENGLISH_UK, "MU" }, // Mauritius 866 { LANGUAGE_ENGLISH_UK, "FJ" }, // Fiji 867 { LANGUAGE_ENGLISH_US, "KI" }, // Kiribati 868 { LANGUAGE_ENGLISH_US, "LR" }, // Liberia 869 { LANGUAGE_ENGLISH_US, "GU" }, // Guam 870 { LANGUAGE_ENGLISH_US, "MH" }, // Marshall Islands 871 { LANGUAGE_ENGLISH_US, "PW" }, // Palau 872 { LANGUAGE_ENGLISH_CARIBBEAN, "AI" }, // Anguilla 873 { LANGUAGE_ENGLISH_CARIBBEAN, "AG" }, // Antigua and Barbuda 874 { LANGUAGE_ENGLISH_CARIBBEAN, "BS" }, // Bahamas 875 { LANGUAGE_ENGLISH_CARIBBEAN, "BB" }, // Barbados 876 { LANGUAGE_ENGLISH_CARIBBEAN, "BM" }, // Bermuda 877 { LANGUAGE_ENGLISH_CARIBBEAN, "KY" }, // Cayman Islands 878 { LANGUAGE_ENGLISH_CARIBBEAN, "GD" }, // Grenada 879 { LANGUAGE_ENGLISH_CARIBBEAN, "DM" }, // Dominica 880 { LANGUAGE_ENGLISH_CARIBBEAN, "HT" }, // Haiti 881 { LANGUAGE_ENGLISH_CARIBBEAN, "MS" }, // Montserrat 882 { LANGUAGE_ENGLISH_CARIBBEAN, "FM" }, // Micronesia 883 { LANGUAGE_ENGLISH_CARIBBEAN, "VC" }, // St. Vincent / Grenadines 884 { LANGUAGE_ENGLISH_CARIBBEAN, "LC" }, // Saint Lucia 885 { LANGUAGE_ENGLISH_CARIBBEAN, "TC" }, // Turks & Caicos Islands 886 { LANGUAGE_ENGLISH_CARIBBEAN, "GY" }, // Guyana 887 { LANGUAGE_ENGLISH_CARIBBEAN, "TT" }, // Trinidad and Tobago 888 { LANGUAGE_ENGLISH_AUS, "CX" }, // Christmas Islands 889 { LANGUAGE_ENGLISH_AUS, "CC" }, // Cocos (Keeling) Islands 890 { LANGUAGE_ENGLISH_AUS, "NF" }, // Norfolk Island 891 { LANGUAGE_ENGLISH_AUS, "PG" }, // Papua New Guinea 892 { LANGUAGE_ENGLISH_AUS, "SB" }, // Solomon Islands 893 { LANGUAGE_ENGLISH_AUS, "TV" }, // Tuvalu 894 { LANGUAGE_ENGLISH_AUS, "NR" }, // Nauru 895 { LANGUAGE_ENGLISH_NZ, "CK" }, // Cook Islands 896 { LANGUAGE_ENGLISH_NZ, "NU" }, // Niue 897 { LANGUAGE_ENGLISH_NZ, "TK" }, // Tokelau 898 { LANGUAGE_ENGLISH_NZ, "TO" }, // Tonga 899 { LANGUAGE_DONTKNOW, "" } // marks end of table 900 }; 901 902 903 IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries[] = 904 { 905 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "BOK" }, // registered subtags for "no" in rfc1766 906 { LANGUAGE_NORWEGIAN_NYNORSK, "no", "NYN" }, // registered subtags for "no" in rfc1766 907 { LANGUAGE_SERBIAN_LATIN_SAM, "sr", "latin" }, 908 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "cyrillic" }, 909 { LANGUAGE_AZERI_LATIN, "az", "latin" }, 910 { LANGUAGE_AZERI_CYRILLIC, "az", "cyrillic" }, 911 { LANGUAGE_DONTKNOW, "", "" } // marks end of table 912 }; 913 914 915 // in this table are only names to find the best language 916 IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries2[] = 917 { 918 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmaal" }, 919 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmal" }, 920 { LANGUAGE_NORWEGIAN_NYNORSK, "no", "nynorsk" }, 921 { LANGUAGE_DONTKNOW, "", "" } // marks end of table 922 }; 923 924 925 // in this table are only names to find the best language 926 IsoLangOtherEntry const aImplOtherEntries[] = 927 { 928 { LANGUAGE_ENGLISH_US, "c" }, 929 { LANGUAGE_CHINESE, "chinese" }, 930 { LANGUAGE_GERMAN, "german" }, 931 { LANGUAGE_JAPANESE, "japanese" }, 932 { LANGUAGE_KOREAN, "korean" }, 933 { LANGUAGE_ENGLISH_US, "posix" }, 934 { LANGUAGE_CHINESE_TRADITIONAL, "tchinese" }, 935 { LANGUAGE_DONTKNOW, nullptr } // marks end of table 936 }; 937 938 939 // in this table are only privateuse names 940 IsoLangOtherEntry const aImplPrivateUseEntries[] = 941 { 942 { LANGUAGE_USER_PRIV_NOTRANSLATE, "x-no-translate" }, //! not BCP47 but legacy in .xcu configmgr 943 { LANGUAGE_USER_PRIV_DEFAULT, "x-default" }, 944 { LANGUAGE_USER_PRIV_COMMENT, "x-comment" }, 945 { LANGUAGE_USER_PRIV_NONE, "x-none" }, 946 { LANGUAGE_USER_PRIV_JOKER, "*" }, //! not BCP47 but transferable in configmgr 947 { LANGUAGE_DONTKNOW, nullptr } // marks end of table 948 }; 949 950 951 // static 952 void MsLangId::Conversion::convertLanguageToLocaleImpl( LanguageType nLang, 953 css::lang::Locale & rLocale, bool bIgnoreOverride ) 954 { 955 const Bcp47CountryEntry* pBcp47EntryOverride = nullptr; 956 const IsoLanguageScriptCountryEntry* pScriptEntryOverride = nullptr; 957 const IsoLanguageCountryEntry* pEntryOverride = nullptr; 958 959 Label_Override_Lang_Locale: 960 961 // Search for LangID in BCP47 962 for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries; 963 pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry) 964 { 965 if (pBcp47Entry->mnLang == nLang) 966 { 967 if (bIgnoreOverride || !pBcp47Entry->mnOverride) 968 { 969 rLocale.Language = I18NLANGTAG_QLT; 970 rLocale.Country = OUString::createFromAscii( pBcp47Entry->maCountry); 971 rLocale.Variant = pBcp47Entry->getTagString(); 972 return; 973 } 974 else if (pBcp47Entry->mnOverride && pBcp47EntryOverride != pBcp47Entry) 975 { 976 pBcp47EntryOverride = pBcp47Entry; 977 nLang = getOverrideLang( pBcp47Entry->mnLang, pBcp47Entry->mnOverride); 978 goto Label_Override_Lang_Locale; 979 } 980 } 981 } 982 983 // Search for LangID in ISO lll-Ssss-CC 984 for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries; 985 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry) 986 { 987 if (pScriptEntry->mnLang == nLang) 988 { 989 if (bIgnoreOverride || !pScriptEntry->mnOverride) 990 { 991 rLocale.Language = I18NLANGTAG_QLT; 992 rLocale.Country = OUString::createFromAscii( pScriptEntry->maCountry); 993 rLocale.Variant = pScriptEntry->getTagString(); 994 return; 995 } 996 else if (pScriptEntry->mnOverride && pScriptEntryOverride != pScriptEntry) 997 { 998 pScriptEntryOverride = pScriptEntry; 999 nLang = getOverrideLang( pScriptEntry->mnLang, pScriptEntry->mnOverride); 1000 goto Label_Override_Lang_Locale; 1001 } 1002 } 1003 } 1004 1005 // Search for LangID in ISO lll-CC 1006 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries; 1007 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1008 { 1009 if (pEntry->mnLang == nLang) 1010 { 1011 if (bIgnoreOverride || !pEntry->mnOverride) 1012 { 1013 rLocale.Language = OUString::createFromAscii( pEntry->maLanguage ); 1014 rLocale.Country = OUString::createFromAscii( pEntry->maCountry ); 1015 rLocale.Variant.clear(); 1016 return; 1017 } 1018 else if (pEntry->mnOverride && pEntryOverride != pEntry) 1019 { 1020 pEntryOverride = pEntry; 1021 nLang = getOverrideLang( pEntry->mnLang, pEntry->mnOverride); 1022 goto Label_Override_Lang_Locale; 1023 } 1024 } 1025 } 1026 1027 // Look for privateuse definitions. 1028 for (const IsoLangOtherEntry* pPrivateEntry = aImplPrivateUseEntries; 1029 pPrivateEntry->mnLang != LANGUAGE_DONTKNOW; ++pPrivateEntry) 1030 { 1031 if (pPrivateEntry->mnLang == nLang) 1032 { 1033 rLocale.Language = I18NLANGTAG_QLT; 1034 rLocale.Country.clear(); 1035 rLocale.Variant = OUString::createFromAscii( pPrivateEntry->mpLanguage ); 1036 return; 1037 } 1038 } 1039 1040 // Not found. Passed rLocale argument remains unchanged. 1041 } 1042 1043 1044 // static 1045 css::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageCountryEntry * pEntry ) 1046 { 1047 if (pEntry->mnOverride) 1048 { 1049 lang::Locale aLocale; 1050 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false); 1051 return aLocale; 1052 } 1053 else 1054 return pEntry->getLocale(); 1055 } 1056 1057 // static 1058 css::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageScriptCountryEntry * pEntry ) 1059 { 1060 if (pEntry->mnOverride) 1061 { 1062 lang::Locale aLocale; 1063 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false); 1064 return aLocale; 1065 } 1066 else 1067 return pEntry->getLocale(); 1068 } 1069 1070 // static 1071 css::lang::Locale MsLangId::Conversion::getLocale( const Bcp47CountryEntry * pEntry ) 1072 { 1073 if (pEntry->mnOverride) 1074 { 1075 lang::Locale aLocale; 1076 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false); 1077 return aLocale; 1078 } 1079 else 1080 return pEntry->getLocale(); 1081 } 1082 1083 // static 1084 css::lang::Locale MsLangId::Conversion::lookupFallbackLocale( 1085 const css::lang::Locale & rLocale ) 1086 { 1087 // language is lower case in table 1088 OUString aLowerLang = rLocale.Language.toAsciiLowerCase(); 1089 // country is upper case in table 1090 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase(); 1091 sal_Int32 nCountryLen = aUpperCountry.getLength(); 1092 1093 if (rLocale.Language == I18NLANGTAG_QLT) 1094 { 1095 // Search in BCP47, only full match and one fallback, for other 1096 // fallbacks only LanguageTag can decide. 1097 for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries; 1098 pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry) 1099 { 1100 if ( rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString()) || 1101 rLocale.Variant.equalsIgnoreAsciiCaseAscii( pBcp47Entry->mpFallback)) 1102 return getLocale( pBcp47Entry); // may override 1103 } 1104 1105 // Search in ISO lll-Ssss-CC 1106 const IsoLanguageScriptCountryEntry* pFirstScript = nullptr; 1107 for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries; 1108 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry) 1109 { 1110 if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant)) 1111 { 1112 if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString())) 1113 return getLocale( pScriptEntry); // may override 1114 if (!pFirstScript) 1115 pFirstScript = pScriptEntry; 1116 } 1117 } 1118 // If at least a lll-Ssss matched, try that with country or use it as 1119 // fallback. 1120 if (pFirstScript) 1121 { 1122 // Check for country only if there is more than lll-Ssss-CC in tag 1123 // string, else we would had matched it already. 1124 if (!aUpperCountry.isEmpty() && rLocale.Variant.getLength() > 11) 1125 { 1126 for (const IsoLanguageScriptCountryEntry* pScriptEntry = pFirstScript; 1127 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry) 1128 { 1129 if (aUpperCountry.equalsAscii( pScriptEntry->maCountry) && 1130 pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant)) 1131 return getLocale( pScriptEntry); // may override 1132 } 1133 } 1134 return getLocale( pFirstScript); // may override 1135 } 1136 1137 // Extract language from tag string, country is used as present in 1138 // Locale because in the tables that follow we have only ISO 3166 1139 // countries and if that is in the tag string we also have it in the 1140 // Locale. 1141 aLowerLang = rLocale.Variant.getToken(0, '-').toAsciiLowerCase(); 1142 // Nothing with "x-..." or "i-..." or any 1 letter in lll-CC table that 1143 // follows. 1144 if (aLowerLang.getLength() == 1) 1145 return aLastResortFallbackEntry.getLocale(); 1146 } 1147 1148 // Search for locale and remember first lang-only. 1149 const IsoLanguageCountryEntry* pFirstLang = nullptr; 1150 const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries; 1151 for ( ; pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1152 { 1153 if (aLowerLang.equalsAscii( pEntry->maLanguage)) 1154 { 1155 if (*pEntry->maCountry) 1156 { 1157 if (nCountryLen && aUpperCountry.equalsAscii( pEntry->maCountry)) 1158 return getLocale( pEntry); // may override 1159 } 1160 else 1161 { 1162 if (pEntry->mnLang.anyOf( 1163 // These are known to have no country assigned. 1164 LANGUAGE_USER_ESPERANTO, 1165 LANGUAGE_USER_INTERLINGUA, 1166 LANGUAGE_USER_INTERLINGUE, 1167 LANGUAGE_USER_LOJBAN, 1168 LANGUAGE_KASHMIRI, 1169 LANGUAGE_USER_KLINGON, 1170 LANGUAGE_USER_KEYID, 1171 // And the special codes without country. 1172 LANGUAGE_MULTIPLE, 1173 LANGUAGE_UNDETERMINED, 1174 LANGUAGE_NONE)) 1175 { 1176 return getLocale( pEntry); // may override 1177 } 1178 } 1179 if (!pFirstLang) 1180 pFirstLang = pEntry; 1181 } 1182 } 1183 1184 // Language not found at all => use default. 1185 if (!pFirstLang) 1186 return aLastResortFallbackEntry.getLocale(); 1187 1188 // Search for first entry of language with any country. 1189 pEntry = pFirstLang; 1190 for ( ; pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1191 { 1192 if (aLowerLang.equalsAscii( pEntry->maLanguage)) 1193 { 1194 if (*pEntry->maCountry) 1195 return getLocale( pEntry); // may override 1196 } 1197 } 1198 1199 return aLastResortFallbackEntry.getLocale(); 1200 } 1201 1202 1203 // static 1204 LanguageType MsLangId::Conversion::convertPrivateUseToLanguage( const OUString& rPriv ) 1205 { 1206 for (const IsoLangOtherEntry* pPrivateEntry = aImplPrivateUseEntries; 1207 pPrivateEntry->mnLang != LANGUAGE_DONTKNOW; ++pPrivateEntry) 1208 { 1209 if ( rPriv.equalsIgnoreAsciiCaseAscii( pPrivateEntry->mpLanguage ) ) 1210 return pPrivateEntry->mnLang; 1211 } 1212 return LANGUAGE_DONTKNOW; 1213 } 1214 1215 1216 // static 1217 LanguageType MsLangId::Conversion::convertLocaleToLanguageImpl( 1218 const css::lang::Locale& rLocale ) 1219 { 1220 if (rLocale.Language == I18NLANGTAG_QLT) 1221 { 1222 // "x-..." private use and the nasty "*" joker 1223 if (rLocale.Variant.startsWithIgnoreAsciiCase( "x-") || (rLocale.Variant == "*")) 1224 return convertPrivateUseToLanguage( rLocale.Variant); 1225 1226 // Search in BCP47 1227 for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries; 1228 pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry) 1229 { 1230 if (rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString())) 1231 return getOverrideLang( pBcp47Entry->mnLang, pBcp47Entry->mnOverride); 1232 } 1233 1234 // Search in ISO lll-Ssss-CC 1235 for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries; 1236 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry) 1237 { 1238 if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant)) 1239 { 1240 if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString())) 1241 return getOverrideLang( pScriptEntry->mnLang, pScriptEntry->mnOverride); 1242 } 1243 } 1244 } 1245 else 1246 { 1247 // language is lower case in table 1248 OUString aLowerLang = rLocale.Language.toAsciiLowerCase(); 1249 // country is upper case in table 1250 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase(); 1251 1252 // Search in ISO lll-CC 1253 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries; 1254 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1255 { 1256 if (aLowerLang.equalsAscii( pEntry->maLanguage) && aUpperCountry.equalsAscii( pEntry->maCountry)) 1257 return getOverrideLang( pEntry->mnLang, pEntry->mnOverride); 1258 } 1259 } 1260 return LANGUAGE_DONTKNOW; 1261 } 1262 1263 1264 // static 1265 css::lang::Locale MsLangId::Conversion::getOverride( const css::lang::Locale& rLocale ) 1266 { 1267 if (rLocale.Language == I18NLANGTAG_QLT) 1268 { 1269 // "x-..." private use and the nasty "*" joker 1270 if (rLocale.Variant.startsWithIgnoreAsciiCase( "x-") || (rLocale.Variant == "*")) 1271 return rLocale; // no overrides 1272 1273 // Search in BCP47 1274 for (const Bcp47CountryEntry* pBcp47Entry = aImplBcp47CountryEntries; 1275 pBcp47Entry->mnLang != LANGUAGE_DONTKNOW; ++pBcp47Entry) 1276 { 1277 if (rLocale.Variant.equalsIgnoreAsciiCase( pBcp47Entry->getTagString())) 1278 return getLocale( pBcp47Entry); // may override 1279 } 1280 1281 // Search in ISO lll-Ssss-CC 1282 for (const IsoLanguageScriptCountryEntry* pScriptEntry = aImplIsoLangScriptEntries; 1283 pScriptEntry->mnLang != LANGUAGE_DONTKNOW; ++pScriptEntry) 1284 { 1285 if (pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant)) 1286 { 1287 if (rLocale.Variant.equalsIgnoreAsciiCase( pScriptEntry->getTagString())) 1288 return getLocale( pScriptEntry); // may override 1289 } 1290 } 1291 } 1292 else 1293 { 1294 // language is lower case in table 1295 OUString aLowerLang = rLocale.Language.toAsciiLowerCase(); 1296 // country is upper case in table 1297 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase(); 1298 1299 // Search in ISO lll-CC 1300 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries; 1301 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1302 { 1303 if (aLowerLang.equalsAscii( pEntry->maLanguage) && aUpperCountry.equalsAscii( pEntry->maCountry)) 1304 return getLocale( pEntry); // may override 1305 } 1306 } 1307 return lang::Locale(); 1308 } 1309 1310 1311 // static 1312 LanguageType MsLangId::Conversion::convertIsoNamesToLanguage( const OUString& rLang, 1313 const OUString& rCountry, bool bSkipIsoTable ) 1314 { 1315 // language is lower case in table 1316 OUString aLowerLang = rLang.toAsciiLowerCase(); 1317 // country is upper case in table 1318 OUString aUpperCountry = rCountry.toAsciiUpperCase(); 1319 1320 if (!bSkipIsoTable) 1321 { 1322 // first look for exact match 1323 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries; 1324 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1325 { 1326 if ( aLowerLang.equalsAscii( pEntry->maLanguage ) ) 1327 { 1328 if ( aUpperCountry.isEmpty() || 1329 aUpperCountry.equalsAscii( pEntry->maCountry ) ) 1330 return pEntry->mnLang; 1331 } 1332 } 1333 1334 // some eng countries should be mapped to a specific english language 1335 if ( aLowerLang == "en" ) 1336 { 1337 for (const IsoLangEngEntry* pEngEntry = aImplIsoLangEngEntries; 1338 pEngEntry->mnLang != LANGUAGE_DONTKNOW; ++pEngEntry) 1339 { 1340 if ( aUpperCountry.equalsAscii( pEngEntry->maCountry ) ) 1341 return pEngEntry->mnLang; 1342 } 1343 } 1344 } 1345 1346 // test for specific languages which are not used standard ISO 3166 codes 1347 for (const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries; 1348 pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW; ++pNoneStdEntry) 1349 { 1350 if ( aLowerLang.equalsAscii( pNoneStdEntry->maLanguage ) ) 1351 { 1352 // The countries in this table are not all in upper case 1353 if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) ) 1354 return pNoneStdEntry->mnLang; 1355 } 1356 } 1357 for (const IsoLangNoneStdEntry* pNoneStdEntry2 = aImplIsoNoneStdLangEntries2; 1358 pNoneStdEntry2->mnLang != LANGUAGE_DONTKNOW; ++pNoneStdEntry2) 1359 { 1360 if ( aLowerLang.equalsAscii( pNoneStdEntry2->maLanguage ) ) 1361 { 1362 // The countries in this table are not all in upper case 1363 if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry2->maCountry ) ) 1364 return pNoneStdEntry2->mnLang; 1365 } 1366 } 1367 1368 if (!bSkipIsoTable) 1369 { 1370 // if only the country is set, look for any entry matching the country 1371 // (to allow reading country and language in separate steps, in any order) 1372 if ( !rCountry.isEmpty() && rLang.isEmpty() ) 1373 { 1374 for (const IsoLanguageCountryEntry* pEntry2 = aImplIsoLangEntries; 1375 pEntry2->mnLang != LANGUAGE_DONTKNOW; ++pEntry2) 1376 { 1377 if ( aUpperCountry.equalsAscii( pEntry2->maCountry ) ) 1378 return pEntry2->mnLang; 1379 } 1380 1381 aLowerLang = aUpperCountry.toAsciiLowerCase(); 1382 } 1383 } 1384 1385 // Look for privateuse definitions. 1386 LanguageType nLang = convertPrivateUseToLanguage( aLowerLang); 1387 if (nLang != LANGUAGE_DONTKNOW) 1388 return nLang; 1389 1390 // Now look for all other definitions, which are not standard 1391 for (const IsoLangOtherEntry* pOtherEntry = aImplOtherEntries; 1392 pOtherEntry->mnLang != LANGUAGE_DONTKNOW; ++pOtherEntry) 1393 { 1394 if ( aLowerLang.equalsAscii( pOtherEntry->mpLanguage ) ) 1395 return pOtherEntry->mnLang; 1396 } 1397 1398 return LANGUAGE_DONTKNOW; 1399 } 1400 1401 1402 // static 1403 LanguageType MsLangId::Conversion::convertIsoNamesToLanguage( std::string_view rLang, 1404 std::string_view rCountry ) 1405 { 1406 OUString aLang = OStringToOUString( rLang, RTL_TEXTENCODING_ASCII_US); 1407 OUString aCountry = OStringToOUString( rCountry, RTL_TEXTENCODING_ASCII_US); 1408 LanguageType nLang = convertIsoNamesToLanguage( aLang, aCountry, false); 1409 1410 // XXX: called *only* by static convertUnxByteStringToLanguage() so we can 1411 // actually call into LanguageTag to create an on-the-fly mapping. 1412 if (nLang == LANGUAGE_DONTKNOW) 1413 { 1414 OUString aTag( aCountry.isEmpty() ? aLang : aLang + "-" + aCountry ); 1415 nLang = LanguageTag( aTag).getLanguageType(false); 1416 SAL_WARN("i18nlangtag", "convertIsoNamesToLanguage(string_view): on-the-fly for {" 1417 << aTag << "} " << nLang); 1418 // Do not leave empty as SYSTEM unresolved. 1419 if (nLang == LANGUAGE_DONTKNOW || nLang == LANGUAGE_SYSTEM) 1420 { 1421 SAL_WARN("i18nlangtag", "convertIsoNamesToLanguage(string_view): on-the-fly bad, using {en-US}"); 1422 nLang = LANGUAGE_ENGLISH_US; 1423 } 1424 } 1425 return nLang; 1426 } 1427 1428 namespace { 1429 1430 struct IsoLangGLIBCModifiersEntry 1431 { 1432 LanguageType mnLang; 1433 char maLanguage[4]; 1434 char maCountry[3]; 1435 char maAtString[9]; 1436 }; 1437 1438 } 1439 1440 IsoLangGLIBCModifiersEntry const aImplIsoLangGLIBCModifiersEntries[] = 1441 { 1442 // MS-LANGID codes ISO639-1/2/3 ISO3166 glibc modifier 1443 { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs", "BA", "cyrillic" }, 1444 { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sr", "RS", "latin" }, // Serbian Latin in Serbia 1445 { LANGUAGE_SERBIAN_LATIN_SAM, "sr", "CS", "latin" }, // Serbian Latin in Serbia and Montenegro 1446 { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sr", "ME", "latin" }, // Serbian Latin in Montenegro 1447 { LANGUAGE_SERBIAN_LATIN_LSO, "sr", "", "latin" }, 1448 { LANGUAGE_AZERI_CYRILLIC, "az", "AZ", "cyrillic" }, 1449 { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ", "cyrillic" }, 1450 { LANGUAGE_CATALAN_VALENCIAN, "ca", "ES", "valencia" }, 1451 { LANGUAGE_DONTKNOW, "", "", "" } // marks end of table 1452 }; 1453 1454 // convert a unix locale string into LanguageType 1455 1456 // static 1457 LanguageType MsLangId::convertUnxByteStringToLanguage( 1458 const OString& rString ) 1459 { 1460 OString aLang; 1461 OString aCountry; 1462 OString aAtString; 1463 1464 sal_Int32 nLangSepPos = rString.indexOf( '_' ); 1465 sal_Int32 nCountrySepPos = rString.indexOf( '.' ); 1466 sal_Int32 nAtPos = rString.indexOf( '@' ); 1467 1468 if (nCountrySepPos < 0) 1469 nCountrySepPos = nAtPos; 1470 if (nCountrySepPos < 0) 1471 nCountrySepPos = rString.getLength(); 1472 1473 if (nAtPos >= 0) 1474 aAtString = rString.copy( nAtPos+1 ); 1475 1476 if (((nLangSepPos >= 0) && (nLangSepPos > nCountrySepPos)) || (nLangSepPos < 0)) 1477 { 1478 // eg. "el.sun_eu_greek", "tchinese", "es.ISO8859-15" 1479 aLang = rString.copy( 0, nCountrySepPos ); 1480 } 1481 else if ( nLangSepPos >= 0 ) 1482 { 1483 // well formed iso names like "en_US.UTF-8", "sh_BA.ISO8859-2@bosnia" 1484 aLang = rString.copy( 0, nLangSepPos ); 1485 aCountry = rString.copy( nLangSepPos+1, nCountrySepPos - nLangSepPos - 1); 1486 } 1487 1488 // if there is a glibc modifier, first look for exact match in modifier table 1489 if (!aAtString.isEmpty()) 1490 { 1491 // language is lower case in table 1492 OString aLowerLang = aLang.toAsciiLowerCase(); 1493 // country is upper case in table 1494 OString aUpperCountry = aCountry.toAsciiUpperCase(); 1495 for (const IsoLangGLIBCModifiersEntry* pGLIBCModifiersEntry = aImplIsoLangGLIBCModifiersEntries; 1496 pGLIBCModifiersEntry->mnLang != LANGUAGE_DONTKNOW; ++pGLIBCModifiersEntry) 1497 { // avoid embedded \0 warning 1498 if (aLowerLang == pGLIBCModifiersEntry->maLanguage && 1499 aAtString == pGLIBCModifiersEntry->maAtString ) 1500 { 1501 if (aUpperCountry.isEmpty() || 1502 aUpperCountry == pGLIBCModifiersEntry->maCountry ) 1503 { 1504 return pGLIBCModifiersEntry->mnLang; 1505 } 1506 } 1507 } 1508 } 1509 1510 return Conversion::convertIsoNamesToLanguage( aLang, aCountry ); 1511 } 1512 1513 1514 // static 1515 ::std::vector< MsLangId::LanguagetagMapping > MsLangId::getDefinedLanguagetags() 1516 { 1517 ::std::vector< LanguagetagMapping > aVec; 1518 for (const Bcp47CountryEntry* pEntry = aImplBcp47CountryEntries; 1519 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1520 { 1521 aVec.emplace_back( pEntry->getTagString(), pEntry->mnLang); 1522 } 1523 for (const IsoLanguageScriptCountryEntry* pEntry = aImplIsoLangScriptEntries; 1524 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1525 { 1526 aVec.emplace_back( pEntry->getTagString(), pEntry->mnLang); 1527 } 1528 for (const IsoLanguageCountryEntry* pEntry = aImplIsoLangEntries; 1529 pEntry->mnLang != LANGUAGE_DONTKNOW; ++pEntry) 1530 { 1531 aVec.emplace_back( pEntry->getTagString(), pEntry->mnLang); 1532 } 1533 return aVec; 1534 } 1535 1536 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */ 1537
