?  search:
summary | log | graphiclog1 | graphiclog2 | commit | commitdiff | tree | refs | edit | fork
blame | history | raw | HEAD
tdf#143148 Use #pragma once instead of include guards
[LibreOffice.git] / i18nlangtag / source / isolang / isolang.cxx
blob88521f1587c58fb7b88570d6f0edae13e9b8942a
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 <o3tl/string_view.hxx>
22 #include <rtl/ustring.hxx>
23 #include <rtl/string.hxx>
24
25 #include <i18nlangtag/mslangid.hxx>
26 #include <i18nlangtag/languagetag.hxx>
27
28 using namespace com::sun::star;
29
30
31 constexpr LanguageType k0(0);
32 constexpr LanguageType kSAME(0xffff);
33
34 namespace {
35 LanguageType getOverrideLang( LanguageType nLang, LanguageType nOverride )
36 {
37 return nOverride ? ((nOverride == kSAME) ? nLang : nOverride) : nLang;
38 }
39 }
40
41 /* Usage of override mechanism:
42 * If a table entry's mnOverride is not 0, an override entry with an mnLang
43 * value of (mnOverride==kSAME ? mnLang : mnOverride) exists that should be
44 * used instead. There MUST exist one such entry that does not have an
45 * mnOverride value and within one table it MUST be located before any entry
46 * with that mnLang and an mnOverride value of not 0. Usually kSAME is used as
47 * override value, with rare exceptions, see tables below.
48 *
49 * The override serves these purposes:
50 * - With getOverride() it indicates that there is a different language tag
51 * (locale) that the requested language tag should be "canonicalized" to.
52 * - With lookupFallbackLocale() a locale may be returned where the language
53 * tag differs.
54 * - With convertLanguageToLocaleImpl() and bIgnoreOverride=false the override
55 * is followed and the override locale returned.
56 * - With convertLocaleToLanguageImpl() a different LangID may be returned in
57 * rare cases where the actual mapped ID differs.
58 */
59
60 struct IsoLanguageCountryEntry
61 {
62 LanguageType mnLang;
63 char maLanguage[4];
64 char maCountry[3];
65 LanguageType mnOverride;
66
67 /** Obtain a language tag string with '-' separator. */
68 OUString getTagString() const;
69
70 /** Obtain a locale. */
71 css::lang::Locale getLocale() const;
72 };
73
74 struct IsoLanguageScriptCountryEntry
75 {
76 LanguageType mnLang;
77 char maLanguageScript[9]; ///< "ll-Ssss" or "lll-Ssss"
78 char maCountry[3];
79 LanguageType mnOverride;
80
81 /** Obtain a language tag string with '-' separator. */
82 OUString getTagString() const;
83
84 /** Obtain a locale. */
85 css::lang::Locale getLocale() const;
86
87 /** If rStr starts with maLanguageScript ignoring case.
88
89 We don't have OUString::startsWithIgnoreAsciiCaseAscii()
90 */
91 bool startsInIgnoreAsciiCase( std::u16string_view aStr ) const;
92 };
93
94 struct Bcp47CountryEntry
95 {
96 LanguageType mnLang;
97 const char* mpBcp47;
98 char maCountry[3];
99 const char* mpFallback;
100 LanguageType mnOverride;
101
102 /** Obtain a language tag string with '-' separator. */
103 OUString getTagString() const;
104
105 /** Obtain a locale. */
106 css::lang::Locale getLocale() const;
107 };
108
109 namespace {
110
111 struct IsoLangEngEntry
112 {
113 LanguageType mnLang;
114 char maCountry[3];
115 };
116
117 struct IsoLangNoneStdEntry
118 {
119 LanguageType mnLang;
120 char maLanguage[4];
121 char maCountry[9];
122 };
123
124 struct IsoLangOtherEntry
125 {
126 LanguageType mnLang;
127 const char* mpLanguage;
128 };
129
130 }
131
132 // Entries for languages are lower case, for countries upper case, as
133 // recommended by rfc5646 (obsoletes rfc4646 (obsoletes rfc3066 (obsoletes
134 // rfc1766))). convertIsoNamesToLanguage(), convertLocaleToLanguageImpl()
135 // and lookupFallbackLocale() are case insensitive.
136 //
137 // Sort order: Most used first and within one language the default fallback
138 // locale of that language first.
139 //
140 // The default entry for a LangID <-> ISO mapping has to be first. For
141 // conversion of legacy mappings one LangID can map to multiple ISO codes
142 // except if the LangID is primary-only, and one ISO code combination can map
143 // to multiple LangIDs.
144
145 /* Currently (2013-08-29 and 2021-10-24) only these primary LangID are still
146 * used literally in code:
147 * LANGUAGE_ENGLISH LANGUAGE_ARABIC_PRIMARY_ONLY
148 */
149
150 IsoLanguageCountryEntry const aImplIsoLangEntries[] =
151 {
152 // MS-LANGID codes, ISO639-1/2/3, ISO3166, override
153 { LANGUAGE_ENGLISH_US, "en", "US", k0 },
154 { LANGUAGE_ENGLISH_UK, "en", "GB", k0 },
155 { LANGUAGE_ENGLISH, "en", "" , k0 },
156 { LANGUAGE_ENGLISH_AUS, "en", "AU", k0 },
157 { LANGUAGE_ENGLISH_CAN, "en", "CA", k0 },
158 { LANGUAGE_FRENCH, "fr", "FR", k0 },
159 { LANGUAGE_GERMAN, "de", "DE", k0 },
160 { LANGUAGE_ITALIAN, "it", "IT", k0 },
161 { LANGUAGE_DUTCH, "nl", "NL", k0 },
162 { LANGUAGE_SPANISH_MODERN, "es", "ES", k0 },
163 { LANGUAGE_PORTUGUESE, "pt", "PT", k0 },
164 { LANGUAGE_PORTUGUESE_BRAZILIAN, "pt", "BR", k0 },
165 { LANGUAGE_DANISH, "da", "DK", k0 },
166 { LANGUAGE_GREEK, "el", "GR", k0 },
167 { LANGUAGE_CHINESE_SIMPLIFIED, "zh", "CN", k0 },
168 { LANGUAGE_CHINESE_SIMPLIFIED_LEGACY, "zh", "CN", k0 },
169 { LANGUAGE_CHINESE_SIMPLIFIED, "cmn", "CN", kSAME },
170 { LANGUAGE_CHINESE_TRADITIONAL, "zh", "TW", k0 },
171 { LANGUAGE_CHINESE_TRADITIONAL, "cmn", "TW", kSAME },
172 { LANGUAGE_CHINESE_HONGKONG, "zh", "HK", k0 },
173 { LANGUAGE_CHINESE_SINGAPORE, "zh", "SG", k0 },
174 { LANGUAGE_CHINESE_MACAU, "zh", "MO", k0 },
175 { LANGUAGE_CHINESE_LSO, "zh", "" , k0 },
176 { LANGUAGE_YUE_CHINESE_HONGKONG, "yue", "HK", k0 },
177 { LANGUAGE_ENGLISH_HONG_KONG_SAR, "en", "HK", k0 },
178 { LANGUAGE_JAPANESE, "ja", "JP", k0 },
179 { LANGUAGE_KOREAN, "ko", "KR", k0 },
180 { LANGUAGE_KOREAN_JOHAB, "ko", "KR", k0 },
181 { LANGUAGE_USER_KOREAN_NORTH, "ko", "KP", k0 },
182 { LANGUAGE_SWEDISH, "sv", "SE", k0 },
183 { LANGUAGE_SWEDISH_FINLAND, "sv", "FI", k0 },
184 { LANGUAGE_FINNISH, "fi", "FI", k0 },
185 { LANGUAGE_RUSSIAN, "ru", "RU", k0 },
186 { LANGUAGE_TATAR, "tt", "RU", k0 },
187 { LANGUAGE_ENGLISH_NZ, "en", "NZ", k0 },
188 { LANGUAGE_ENGLISH_EIRE, "en", "IE", k0 },
189 { LANGUAGE_DUTCH_BELGIAN, "nl", "BE", k0 },
190 { LANGUAGE_FRENCH_BELGIAN, "fr", "BE", k0 },
191 { LANGUAGE_FRENCH_CANADIAN, "fr", "CA", k0 },
192 { LANGUAGE_FRENCH_SWISS, "fr", "CH", k0 },
193 { LANGUAGE_GERMAN_SWISS, "de", "CH", k0 },
194 { LANGUAGE_GERMAN_AUSTRIAN, "de", "AT", k0 },
195 { LANGUAGE_ITALIAN_SWISS, "it", "CH", k0 },
196 { LANGUAGE_ALBANIAN, "sq", "AL", k0 },
197 { LANGUAGE_ARABIC_SAUDI_ARABIA, "ar", "SA", k0 },
198 { LANGUAGE_ARABIC_EGYPT, "ar", "EG", k0 },
199 { LANGUAGE_ARABIC_UAE, "ar", "AE", k0 },
200 { LANGUAGE_ARABIC_IRAQ, "ar", "IQ", k0 },
201 { LANGUAGE_ARABIC_LIBYA, "ar", "LY", k0 },
202 { LANGUAGE_ARABIC_ALGERIA, "ar", "DZ", k0 },
203 { LANGUAGE_ARABIC_MOROCCO, "ar", "MA", k0 },
204 { LANGUAGE_ARABIC_TUNISIA, "ar", "TN", k0 },
205 { LANGUAGE_ARABIC_OMAN, "ar", "OM", k0 },
206 { LANGUAGE_ARABIC_YEMEN, "ar", "YE", k0 },
207 { LANGUAGE_ARABIC_SYRIA, "ar", "SY", k0 },
208 { LANGUAGE_ARABIC_JORDAN, "ar", "JO", k0 },
209 { LANGUAGE_ARABIC_LEBANON, "ar", "LB", k0 },
210 { LANGUAGE_ARABIC_KUWAIT, "ar", "KW", k0 },
211 { LANGUAGE_ARABIC_BAHRAIN, "ar", "BH", k0 },
212 { LANGUAGE_ARABIC_QATAR, "ar", "QA", k0 },
213 { LANGUAGE_USER_ARABIC_CHAD, "ar", "TD", k0 },
214 { LANGUAGE_USER_ARABIC_COMOROS, "ar", "KM", k0 },
215 { LANGUAGE_USER_ARABIC_DJIBOUTI, "ar", "DJ", k0 },
216 { LANGUAGE_USER_ARABIC_ERITREA, "ar", "ER", k0 },
217 { LANGUAGE_USER_ARABIC_ISRAEL, "ar", "IL", k0 },
218 { LANGUAGE_USER_ARABIC_MAURITANIA, "ar", "MR", k0 },
219 { LANGUAGE_USER_ARABIC_PALESTINE, "ar", "PS", k0 },
220 { LANGUAGE_USER_ARABIC_SOMALIA, "ar", "SO", k0 },
221 { LANGUAGE_USER_ARABIC_SUDAN, "ar", "SD", k0 },
222 { LANGUAGE_ARABIC_PRIMARY_ONLY, "ar", "" , k0 },
223 { LANGUAGE_BASQUE, "eu", "ES", k0 },
224 { LANGUAGE_BASQUE, "eu", "" , kSAME }, // our earlier definition
225 { LANGUAGE_BULGARIAN, "bg", "BG", k0 },
226 { LANGUAGE_CZECH, "cs", "CZ", k0 },
227 { LANGUAGE_CZECH, "cz", "" , kSAME },
228 { LANGUAGE_ENGLISH_JAMAICA, "en", "JM", k0 },
229 { LANGUAGE_ENGLISH_CARIBBEAN, "en", "BS", k0 }, // not 100%, because AG is Bahamas
230 { LANGUAGE_ENGLISH_BELIZE, "en", "BZ", k0 },
231 { LANGUAGE_ENGLISH_TRINIDAD, "en", "TT", k0 },
232 { LANGUAGE_ENGLISH_ZIMBABWE, "en", "ZW", k0 },
233 { LANGUAGE_ENGLISH_INDONESIA, "en", "ID", k0 }, // MS reserved
234 { LANGUAGE_ESTONIAN, "et", "EE", k0 },
235 { LANGUAGE_FAEROESE, "fo", "FO", k0 },
236 { LANGUAGE_FARSI, "fa", "IR", k0 },
237 { LANGUAGE_FRENCH_LUXEMBOURG, "fr", "LU", k0 },
238 { LANGUAGE_FRENCH_MONACO, "fr", "MC", k0 },
239 { LANGUAGE_GERMAN_LUXEMBOURG, "de", "LU", k0 },
240 { LANGUAGE_GERMAN_LIECHTENSTEIN, "de", "LI", k0 },
241 { LANGUAGE_HEBREW, "he", "IL", k0 }, // new: old was "iw"
242 { LANGUAGE_HEBREW, "iw", "IL", kSAME }, // old: new is "he"
243 { LANGUAGE_HUNGARIAN, "hu", "HU", k0 },
244 { LANGUAGE_ICELANDIC, "is", "IS", k0 },
245 { LANGUAGE_INDONESIAN, "id", "ID", k0 }, // new: old was "in"
246 { LANGUAGE_INDONESIAN, "in", "ID", kSAME }, // old: new is "id"
247 { LANGUAGE_NORWEGIAN, "no", "NO", k0 },
248 { LANGUAGE_NORWEGIAN_BOKMAL, "nb", "NO", k0 },
249 { LANGUAGE_NORWEGIAN_BOKMAL_LSO, "nb", "" , k0 },
250 { LANGUAGE_NORWEGIAN_NYNORSK, "nn", "NO", k0 },
251 { LANGUAGE_NORWEGIAN_NYNORSK_LSO, "nn", "" , k0 },
252 { LANGUAGE_POLISH, "pl", "PL", k0 },
253 { LANGUAGE_RHAETO_ROMAN, "rm", "CH", k0 },
254 { LANGUAGE_ROMANIAN, "ro", "RO", k0 },
255 { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", k0 },
256 { LANGUAGE_SLOVAK, "sk", "SK", k0 },
257 { LANGUAGE_SLOVENIAN, "sl", "SI", k0 },
258 { LANGUAGE_SPANISH_MEXICAN, "es", "MX", k0 },
259 { LANGUAGE_SPANISH_GUATEMALA, "es", "GT", k0 },
260 { LANGUAGE_SPANISH_COSTARICA, "es", "CR", k0 },
261 { LANGUAGE_SPANISH_PANAMA, "es", "PA", k0 },
262 { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC, "es", "DO", k0 },
263 { LANGUAGE_SPANISH_VENEZUELA, "es", "VE", k0 },
264 { LANGUAGE_SPANISH_COLOMBIA, "es", "CO", k0 },
265 { LANGUAGE_SPANISH_PERU, "es", "PE", k0 },
266 { LANGUAGE_SPANISH_ARGENTINA, "es", "AR", k0 },
267 { LANGUAGE_SPANISH_ECUADOR, "es", "EC", k0 },
268 { LANGUAGE_SPANISH_CHILE, "es", "CL", k0 },
269 { LANGUAGE_SPANISH_URUGUAY, "es", "UY", k0 },
270 { LANGUAGE_SPANISH_PARAGUAY, "es", "PY", k0 },
271 { LANGUAGE_SPANISH_BOLIVIA, "es", "BO", k0 },
272 { LANGUAGE_SPANISH_EL_SALVADOR, "es", "SV", k0 },
273 { LANGUAGE_SPANISH_HONDURAS, "es", "HN", k0 },
274 { LANGUAGE_SPANISH_NICARAGUA, "es", "NI", k0 },
275 { LANGUAGE_SPANISH_PUERTO_RICO, "es", "PR", k0 },
276 { LANGUAGE_SPANISH_UNITED_STATES, "es", "US", 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_USER_CATALAN_ANDORRA, "ca", "AD", k0 },
348 { LANGUAGE_USER_CATALAN_FRANCE, "ca", "FR", k0 },
349 { LANGUAGE_USER_CATALAN_ITALY, "ca", "IT", k0 },
350 //LANGUAGE_CATALAN_VALENCIAN ca-ES-valencia Bcp47CountryEntry takes precedence
351 { LANGUAGE_CATALAN_VALENCIAN, "ca", "XV", kSAME }, // XV: ISO 3166 user-assigned; old workaround for UI localization only, in case it escaped to document content
352 { 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
353 { LANGUAGE_FRENCH_CAMEROON, "fr", "CM", k0 },
354 { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI", k0 },
355 { LANGUAGE_FRENCH_MALI, "fr", "ML", k0 },
356 { LANGUAGE_FRENCH_SENEGAL, "fr", "SN", k0 },
357 { LANGUAGE_FRENCH_ZAIRE, "fr", "CD", k0 }, // Democratic Republic Of Congo
358 { LANGUAGE_FRENCH_MOROCCO, "fr", "MA", k0 },
359 { LANGUAGE_FRENCH_REUNION, "fr", "RE", k0 },
360 { LANGUAGE_FRISIAN_NETHERLANDS, "fy", "NL", k0 },
361 { LANGUAGE_GAELIC_IRELAND, "ga", "IE", k0 },
362 { LANGUAGE_GAELIC_SCOTLAND, "gd", "GB", k0 },
363 { LANGUAGE_GAELIC_SCOTLAND_LEGACY, "gd", "GB", k0 },
364 { LANGUAGE_GALICIAN, "gl", "ES", k0 },
365 { LANGUAGE_GEORGIAN, "ka", "GE", k0 },
366 { LANGUAGE_KHMER, "km", "KH", k0 },
367 { LANGUAGE_KIRGHIZ, "ky", "KG", k0 },
368 { LANGUAGE_LAO, "lo", "LA", k0 },
369 { LANGUAGE_MALTESE, "mt", "MT", k0 },
370 { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn", "MN", k0 }, // macrolanguage code; should be khk-MN; Cyrillic script
371 { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn", "" , k0 }, // macrolanguage code; should be khk; Cyrillic script
372 { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD", k0 },
373 { 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
374 { LANGUAGE_RUSSIAN_MOLDOVA, "ru", "MD", k0 }, // as per [MS-LCID] rev. 7.0 2015-06-30
375 { LANGUAGE_SWAHILI, "sw", "KE", k0 },
376 { LANGUAGE_USER_SWAHILI_TANZANIA, "sw", "TZ", k0 },
377 { LANGUAGE_TAJIK, "tg", "TJ", k0 },
378 { LANGUAGE_TAJIK_LSO, "tg", "" , k0 },
379 { LANGUAGE_TIBETAN, "bo", "CN", k0 }, // CN politically correct?
380 { LANGUAGE_USER_TIBETAN_INDIA, "bo", "IN", k0 },
381 { LANGUAGE_USER_TIBETAN_BHUTAN, "bo", "BT", k0 },
382 { LANGUAGE_DZONGKHA_BHUTAN, "dz", "BT", k0 },
383 { LANGUAGE_TIBETAN_BHUTAN, "dz", "BT", k0 }, // MS reserved for bo-BT, but LCID was used as Dzongkha, see #i53497#
384 { LANGUAGE_USER_DZONGKHA_MAP_LONLY, "dz", "" , k0 }, // because of the MS error, see lang.h
385 { LANGUAGE_TURKMEN, "tk", "TM", k0 },
386 { LANGUAGE_WELSH, "cy", "GB", k0 },
387 { LANGUAGE_SESOTHO, "st", "ZA", k0 },
388 { LANGUAGE_SEPEDI, "nso", "ZA", k0 },
389 { LANGUAGE_SEPEDI, "ns", "ZA", kSAME }, // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents
390 { LANGUAGE_TSONGA, "ts", "ZA", k0 },
391 { LANGUAGE_TSWANA, "tn", "ZA", k0 },
392 { LANGUAGE_ENGLISH_SAFRICA, "en", "ZA", k0 },
393 { LANGUAGE_AFRIKAANS, "af", "ZA", k0 },
394 { LANGUAGE_VENDA, "ve", "ZA", k0 }, // default 639-1
395 { LANGUAGE_VENDA, "ven", "ZA", kSAME }, // 639-2 may have been used temporarily since 2004-07-23
396 { LANGUAGE_XHOSA, "xh", "ZA", k0 },
397 { LANGUAGE_ZULU, "zu", "ZA", k0 },
398 // { LANGUAGE_QUECHUA_COLOMBIA, "quc", "CO", k0 }, // MS reserved, and looks wrong, quc would be in Guatemala, not Colombia
399 { LANGUAGE_QUECHUA_ECUADOR, "quz", "EC", k0 }, // MS
400 { LANGUAGE_QUECHUA_ECUADOR, "qu", "EC", kSAME }, // macrolanguage code
401 { LANGUAGE_QUECHUA_PERU, "quz", "PE", k0 }, // MS
402 { LANGUAGE_QUECHUA_PERU, "qu", "PE", kSAME }, // macrolanguage code
403 { LANGUAGE_QUECHUA_BOLIVIA, "qu", "BO", k0 }, // macrolanguage code, TODO instead: quh-BO or qul-BO; MS says quz-BO which is wrong
404 { LANGUAGE_PASHTO, "ps", "AF", k0 },
405 { LANGUAGE_OROMO, "om", "ET", k0 },
406 { LANGUAGE_DHIVEHI, "dv", "MV", k0 },
407 { LANGUAGE_UIGHUR_CHINA, "ug", "CN", k0 },
408 { LANGUAGE_TIGRIGNA_ETHIOPIA, "ti", "ET", k0 },
409 { LANGUAGE_TIGRIGNA_ERITREA, "ti", "ER", k0 },
410 { LANGUAGE_AMHARIC_ETHIOPIA, "am", "ET", k0 },
411 { LANGUAGE_GUARANI_PARAGUAY, "gug", "PY", k0 },
412 { LANGUAGE_HAWAIIAN_UNITED_STATES, "haw", "US", k0 },
413 { LANGUAGE_EDO, "bin", "NG", k0 }, // MS reserved
414 { LANGUAGE_FULFULDE_NIGERIA, "ff", "NG", k0 }, // macrolanguage code; MS since rev.15
415 { LANGUAGE_FULFULDE_NIGERIA, "fuv", "NG", kSAME }, // MS reserved until rev.15, since rev.15 "ff-NG" and "ff-Latn-NG"
416 { LANGUAGE_FULFULDE_SENEGAL, "ff", "SN", k0 }, // macrolanguage code
417 { LANGUAGE_HAUSA_NIGERIA, "ha", "NG", kSAME },
418 { LANGUAGE_USER_HAUSA_GHANA, "ha", "GH", kSAME },
419 { LANGUAGE_IGBO_NIGERIA, "ig", "NG", k0 },
420 { LANGUAGE_KANURI_NIGERIA, "kr", "NG", k0 }, // macrolanguage code; MS reserved until rev.15
421 { LANGUAGE_YORUBA, "yo", "NG", k0 },
422 { LANGUAGE_SOMALI, "so", "SO", k0 },
423 { LANGUAGE_PAPIAMENTU, "pap", "AN", k0 },
424 { LANGUAGE_USER_PAPIAMENTU_ARUBA, "pap", "AW", k0 },
425 { LANGUAGE_USER_PAPIAMENTU_CURACAO, "pap", "CW", k0 },
426 { LANGUAGE_USER_PAPIAMENTU_BONAIRE, "pap", "BQ", k0 },
427 { LANGUAGE_ENGLISH_SINGAPORE, "en", "SG", k0 },
428 { LANGUAGE_USER_YIDDISH_US, "yi", "US", k0 },
429 { LANGUAGE_USER_YIDDISH_ISRAEL, "yi", "IL", k0 }, // new: old was "ji"
430 { LANGUAGE_USER_YIDDISH_ISRAEL, "ji", "IL", kSAME }, // old: new is "yi"
431 { LANGUAGE_SYRIAC, "syr", "TR", k0 }, // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
432 { LANGUAGE_SINHALESE_SRI_LANKA, "si", "LK", k0 },
433 { LANGUAGE_CHEROKEE_UNITED_STATES, "chr", "US", kSAME },
434 { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu", "CA", kSAME }, // macrolanguage code
435 { LANGUAGE_INUKTITUT_LATIN_LSO, "iu", "" , kSAME }, // macrolanguage code
436 { LANGUAGE_SAMI_NORTHERN_NORWAY, "se", "NO", k0 },
437 { LANGUAGE_SAMI_INARI, "smn", "FI", k0 },
438 { LANGUAGE_SAMI_INARI_LSO, "smn", "" , k0 },
439 { LANGUAGE_SAMI_LULE_NORWAY, "smj", "NO", k0 },
440 { LANGUAGE_SAMI_LULE_SWEDEN, "smj", "SE", k0 },
441 { LANGUAGE_SAMI_LULE_LSO, "smj", "" , k0 },
442 { LANGUAGE_SAMI_NORTHERN_FINLAND, "se", "FI", k0 },
443 { LANGUAGE_SAMI_NORTHERN_SWEDEN, "se", "SE", k0 },
444 { LANGUAGE_SAMI_SKOLT, "sms", "FI", k0 },
445 { LANGUAGE_SAMI_SKOLT_LSO, "sms", "" , k0 },
446 { LANGUAGE_SAMI_SOUTHERN_NORWAY, "sma", "NO", k0 },
447 { LANGUAGE_SAMI_SOUTHERN_SWEDEN, "sma", "SE", k0 },
448 { LANGUAGE_SAMI_SOUTHERN_LSO, "sma", "" , k0 },
449 { LANGUAGE_USER_SAMI_KILDIN_RUSSIA, "sjd", "RU", k0 },
450 { LANGUAGE_MAPUDUNGUN_CHILE, "arn", "CL", k0 },
451 { LANGUAGE_CORSICAN_FRANCE, "co", "FR", k0 },
452 { 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.
453 { LANGUAGE_YAKUT_RUSSIA, "sah", "RU", k0 },
454 { LANGUAGE_MOHAWK_CANADA, "moh", "CA", k0 },
455 { LANGUAGE_BASHKIR_RUSSIA, "ba", "RU", k0 },
456 { LANGUAGE_KICHE_GUATEMALA, "qut", "GT", k0 }, // MS reserved since rev.15
457 { LANGUAGE_DARI_AFGHANISTAN, "prs", "AF", k0 },
458 { LANGUAGE_DARI_AFGHANISTAN, "gbz", "AF", kSAME }, // was an error
459 { LANGUAGE_WOLOF_SENEGAL, "wo", "SN", k0 },
460 { LANGUAGE_FILIPINO, "fil", "PH", k0 },
461 { LANGUAGE_USER_TAGALOG, "tl", "PH", k0 },
462 { LANGUAGE_ENGLISH_PHILIPPINES, "en", "PH", k0 },
463 { LANGUAGE_IBIBIO_NIGERIA, "ibb", "NG", k0 }, // MS reserved
464 { LANGUAGE_YI, "ii", "CN", k0 },
465 { LANGUAGE_ENGLISH_ARAB_EMIRATES, "en", "AE", k0 },
466 { LANGUAGE_ENGLISH_BAHRAIN, "en", "BH", k0 }, // MS reserved
467 { LANGUAGE_ENGLISH_EGYPT, "en", "EG", k0 }, // MS reserved
468 { LANGUAGE_ENGLISH_JORDAN, "en", "JO", k0 }, // MS reserved
469 { LANGUAGE_ENGLISH_KUWAIT, "en", "KW", k0 }, // MS reserved
470 { LANGUAGE_ENGLISH_TURKEY, "en", "TR", k0 }, // MS reserved
471 { LANGUAGE_ENGLISH_YEMEN, "en", "YE", k0 }, // MS reserved
472 { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "kab", "DZ", k0 }, // In practice Kabyle is the language used for this
473 { LANGUAGE_OBSOLETE_USER_KABYLE, "kab", "DZ", k0 },
474 { 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.
475 { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tmz", "MA", kSAME },
476 { LANGUAGE_TAMAZIGHT_MOROCCO, "tmz", "MA", k0 }, // MS reserved
477 { 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
478 { LANGUAGE_LATIN, "la", "VA", k0 },
479 { LANGUAGE_OBSOLETE_USER_LATIN_VATICAN, "la", "VA", LANGUAGE_LATIN },
480 { LANGUAGE_OBSOLETE_USER_LATIN, "la", "VA", LANGUAGE_LATIN },
481 { LANGUAGE_LATIN, "la", "" , kSAME },
482 { LANGUAGE_USER_ESPERANTO, "eo", "" , k0 },
483 { LANGUAGE_USER_INTERLINGUA, "ia", "" , k0 },
484 { LANGUAGE_USER_INTERLINGUE, "ie", "" , k0 },
485 { LANGUAGE_MAORI_NEW_ZEALAND, "mi", "NZ", k0 },
486 { LANGUAGE_OBSOLETE_USER_MAORI, "mi", "NZ", k0 },
487 { LANGUAGE_KINYARWANDA_RWANDA, "rw", "RW", k0 },
488 { LANGUAGE_OBSOLETE_USER_KINYARWANDA, "rw", "RW", k0 },
489 { 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
490 { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE", k0 },
491 { 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
492 { LANGUAGE_LOWER_SORBIAN_LSO, "dsb", "" , k0 },
493 { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE", k0 },
494 { LANGUAGE_OCCITAN_FRANCE, "oc", "FR", kSAME },
495 { LANGUAGE_OBSOLETE_USER_OCCITAN, "oc", "FR", LANGUAGE_OCCITAN_FRANCE },
496 { LANGUAGE_USER_KURDISH_TURKEY, "kmr", "TR", kSAME },
497 { LANGUAGE_USER_KURDISH_TURKEY, "ku", "TR", kSAME },
498 { LANGUAGE_USER_KURDISH_SYRIA, "kmr", "SY", kSAME },
499 { LANGUAGE_USER_KURDISH_SYRIA, "ku", "SY", kSAME },
500 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ckb", "IQ", k0 },
501 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku", "IQ", kSAME },
502 { LANGUAGE_OBSOLETE_USER_KURDISH_IRAQ, "ku", "IQ", LANGUAGE_KURDISH_ARABIC_IRAQ },
503 { LANGUAGE_USER_KURDISH_SOUTHERN_IRAN, "sdh", "IR", k0 },
504 { LANGUAGE_USER_KURDISH_SOUTHERN_IRAQ, "sdh", "IQ", k0 },
505 { LANGUAGE_USER_KURDISH_IRAN, "ckb", "IR", k0 },
506 { LANGUAGE_USER_KURDISH_IRAN, "ku", "IR", kSAME },
507 { LANGUAGE_KURDISH_ARABIC_LSO, "ckb", "" , k0 },
508 { LANGUAGE_USER_SARDINIAN, "sc", "IT", k0 }, // macrolanguage code
509 { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT", k0 },
510 { LANGUAGE_USER_SARDINIAN_GALLURESE, "sdn", "IT", k0 },
511 { LANGUAGE_USER_SARDINIAN_LOGUDORESE, "src", "IT", k0 },
512 { LANGUAGE_USER_SARDINIAN_SASSARESE, "sdc", "IT", k0 },
513 { LANGUAGE_BRETON_FRANCE, "br", "FR", k0 },
514 { LANGUAGE_OBSOLETE_USER_BRETON, "br", "FR", k0 },
515 { LANGUAGE_KALAALLISUT_GREENLAND, "kl", "GL", k0 },
516 { LANGUAGE_OBSOLETE_USER_KALAALLISUT, "kl", "GL", k0 },
517 { LANGUAGE_USER_SWAZI, "ss", "ZA", k0 },
518 { LANGUAGE_USER_NDEBELE_SOUTH, "nr", "ZA", k0 },
519 { LANGUAGE_TSWANA_BOTSWANA, "tn", "BW", k0 },
520 { LANGUAGE_OBSOLETE_USER_TSWANA_BOTSWANA, "tn", "BW", k0 },
521 { LANGUAGE_USER_ENGLISH_BOTSWANA, "en", "BW", k0 },
522 { LANGUAGE_USER_MOORE, "mos", "BF", k0 },
523 { LANGUAGE_USER_BAMBARA, "bm", "ML", k0 },
524 { LANGUAGE_USER_AKAN, "ak", "GH", k0 },
525 { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG, "lb", "LU", k0 },
526 { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU", k0 },
527 { LANGUAGE_USER_FRIULIAN, "fur", "IT", k0 },
528 { LANGUAGE_USER_FIJIAN, "fj", "FJ", k0 },
529 { LANGUAGE_USER_AFRIKAANS_NAMIBIA, "af", "NA", k0 },
530 { LANGUAGE_USER_ENGLISH_NAMIBIA, "en", "NA", k0 },
531 { LANGUAGE_USER_WALLOON, "wa", "BE", k0 },
532 { LANGUAGE_USER_COPTIC, "cop", "EG", k0 },
533 { LANGUAGE_USER_GASCON, "gsc", "FR", k0 },
534 { LANGUAGE_USER_GERMAN_BELGIUM, "de", "BE", k0 },
535 { LANGUAGE_USER_CHUVASH, "cv", "RU", k0 },
536 { LANGUAGE_USER_EWE_GHANA, "ee", "GH", k0 },
537 { LANGUAGE_USER_ENGLISH_GHANA, "en", "GH", k0 },
538 { LANGUAGE_USER_SANGO, "sg", "CF", k0 },
539 { LANGUAGE_USER_GANDA, "lg", "UG", k0 },
540 { LANGUAGE_USER_LINGALA_DRCONGO, "ln", "CD", k0 },
541 { LANGUAGE_USER_LOW_GERMAN, "nds", "DE", k0 },
542 { LANGUAGE_USER_HILIGAYNON, "hil", "PH", k0 },
543 { LANGUAGE_USER_ENGLISH_MALAWI, "en", "MW", k0 }, /* en default for MW */
544 { LANGUAGE_USER_NYANJA, "ny", "MW", k0 },
545 { LANGUAGE_USER_KASHUBIAN, "csb", "PL", k0 },
546 { LANGUAGE_SPANISH_CUBA, "es", "CU", k0 },
547 { LANGUAGE_OBSOLETE_USER_SPANISH_CUBA, "es", "CU", k0 },
548 { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO", k0 },
549 { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO", k0 },
550 { LANGUAGE_USER_BODO_INDIA, "brx", "IN", k0 },
551 { LANGUAGE_USER_DOGRI_INDIA, "dgo", "IN", k0 },
552 { LANGUAGE_USER_MAITHILI_INDIA, "mai", "IN", k0 },
553 { LANGUAGE_USER_SANTALI_INDIA, "sat", "IN", k0 },
554 { LANGUAGE_USER_TETUN, "tet", "ID", k0 },
555 { LANGUAGE_USER_TETUN_TIMOR_LESTE, "tet", "TL", k0 },
556 { LANGUAGE_USER_TOK_PISIN, "tpi", "PG", k0 },
557 { LANGUAGE_USER_SHUSWAP, "shs", "CA", k0 },
558 { LANGUAGE_USER_ANCIENT_GREEK, "grc", "GR", k0 },
559 { LANGUAGE_USER_ASTURIAN, "ast", "ES", k0 },
560 { LANGUAGE_USER_LATGALIAN, "ltg", "LV", k0 },
561 { LANGUAGE_USER_MAORE, "swb", "YT", k0 },
562 { LANGUAGE_USER_BUSHI, "buc", "YT", k0 },
563 { LANGUAGE_USER_TAHITIAN, "ty", "PF", k0 },
564 { LANGUAGE_MALAGASY_PLATEAU, "plt", "MG", k0 }, // MS reserved
565 { LANGUAGE_MALAGASY_PLATEAU, "mg", "MG", kSAME },
566 { LANGUAGE_OBSOLETE_USER_MALAGASY_PLATEAU, "plt", "MG", k0 },
567 { LANGUAGE_USER_BAFIA, "ksf", "CM", k0 },
568 { LANGUAGE_USER_GIKUYU, "ki", "KE", k0 },
569 { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA", k0 },
570 { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK", k0 },
571 { LANGUAGE_USER_LIMBU, "lif", "NP", k0 },
572 { LANGUAGE_USER_LOJBAN, "jbo", "" , k0 },
573 { LANGUAGE_USER_HAITIAN, "ht", "HT", k0 },
574 { LANGUAGE_FRENCH_HAITI, "fr", "HT", k0 },
575 { LANGUAGE_USER_BEEMBE, "beq", "CG", k0 },
576 { LANGUAGE_USER_BEKWEL, "bkw", "CG", k0 },
577 { LANGUAGE_USER_KITUBA, "mkw", "CG", k0 },
578 { LANGUAGE_USER_LARI, "ldi", "CG", k0 },
579 { LANGUAGE_USER_MBOCHI, "mdw", "CG", k0 },
580 { LANGUAGE_USER_TEKE_EBOO, "ebo", "CG", k0 },
581 { LANGUAGE_USER_TEKE_IBALI, "tek", "CG", k0 },
582 { LANGUAGE_USER_TEKE_TYEE, "tyx", "CG", k0 },
583 { LANGUAGE_USER_VILI, "vif", "CG", k0 },
584 { LANGUAGE_USER_PORTUGUESE_ANGOLA, "pt", "AO", k0 },
585 { LANGUAGE_USER_MANX, "gv", "GB", k0 },
586 { LANGUAGE_USER_ARAGONESE, "an", "ES", k0 },
587 { LANGUAGE_USER_KEYID, "qtz", "" , k0 }, // key id pseudolanguage used for UI testing
588 { LANGUAGE_USER_PALI_LATIN, "pli", "" , kSAME }, // Pali with Latin script, ISO 639-3 (sigh..) back-compat, Latin is not a default script though...
589 { LANGUAGE_USER_KYRGYZ_CHINA, "ky", "CN", k0 },
590 { LANGUAGE_USER_KOMI_ZYRIAN, "kpv", "RU", k0 },
591 { LANGUAGE_USER_KOMI_PERMYAK, "koi", "RU", k0 },
592 { LANGUAGE_USER_PITJANTJATJARA, "pjt", "AU", k0 },
593 { LANGUAGE_USER_ERZYA, "myv", "RU", k0 },
594 { LANGUAGE_USER_MARI_MEADOW, "mhr", "RU", k0 },
595 { LANGUAGE_USER_KHANTY, "kca", "RU", k0 },
596 { LANGUAGE_USER_LIVONIAN, "liv", "RU", k0 },
597 { LANGUAGE_USER_MOKSHA, "mdf", "RU", k0 },
598 { LANGUAGE_USER_MARI_HILL, "mrj", "RU", k0 },
599 { LANGUAGE_USER_NGANASAN, "nio", "RU", k0 },
600 { LANGUAGE_USER_OLONETS, "olo", "RU", k0 },
601 { LANGUAGE_USER_VEPS, "vep", "RU", k0 },
602 { LANGUAGE_USER_VORO, "vro", "EE", k0 },
603 { LANGUAGE_USER_NENETS, "yrk", "RU", k0 },
604 { LANGUAGE_USER_AKA, "axk", "CF", k0 },
605 { LANGUAGE_USER_AKA_CONGO, "axk", "CG", k0 },
606 { LANGUAGE_USER_DIBOLE, "bvx", "CG", k0 },
607 { LANGUAGE_USER_DOONDO, "dde", "CG", k0 },
608 { LANGUAGE_USER_KAAMBA, "xku", "CG", k0 },
609 { LANGUAGE_USER_KOONGO, "kng", "CD", k0 },
610 { LANGUAGE_USER_KOONGO_CONGO, "kng", "CG", k0 },
611 { LANGUAGE_USER_KUNYI, "njx", "CG", k0 },
612 { LANGUAGE_USER_NGUNGWEL, "ngz", "CG", k0 },
613 { LANGUAGE_USER_NJYEM, "njy", "CM", k0 },
614 { LANGUAGE_USER_NJYEM_CONGO, "njy", "CG", k0 },
615 { LANGUAGE_USER_PUNU, "puu", "GA", k0 },
616 { LANGUAGE_USER_PUNU_CONGO, "puu", "CG", k0 },
617 { LANGUAGE_USER_SUUNDI, "sdj", "CG", k0 },
618 { LANGUAGE_USER_TEKE_KUKUYA, "kkw", "CG", k0 },
619 { LANGUAGE_USER_TSAANGI, "tsa", "CG", k0 },
620 { LANGUAGE_USER_YAKA, "iyx", "CG", k0 },
621 { LANGUAGE_USER_YOMBE, "yom", "CD", k0 },
622 { LANGUAGE_USER_YOMBE_CONGO, "yom", "CG", k0 },
623 { LANGUAGE_USER_SIDAMA, "sid", "ET", k0 },
624 { LANGUAGE_USER_NKO, "nqo", "GN", k0 },
625 { LANGUAGE_USER_UDMURT, "udm", "RU", k0 },
626 { LANGUAGE_USER_CORNISH, "kw", "GB", k0 },
627 { LANGUAGE_USER_CORNISH, "kw", "UK", kSAME }, // old erroneous tag
628 { LANGUAGE_USER_SAMI_PITE_SWEDEN, "sje", "SE", k0 },
629 { LANGUAGE_USER_NGAEBERE, "gym", "PA", k0 },
630 { LANGUAGE_USER_KUMYK, "kum", "RU", k0 },
631 { LANGUAGE_USER_NOGAI, "nog", "RU", k0 },
632 { LANGUAGE_USER_LADIN, "lld", "IT", k0 },
633 { LANGUAGE_USER_FRENCH_BURKINA_FASO, "fr", "BF", k0 },
634 { LANGUAGE_USER_PUINAVE, "pui", "CO", k0 },
635 { LANGUAGE_USER_AVAR, "av", "RU", k0 },
636 { LANGUAGE_USER_LENGO, "lgr", "SB", k0 },
637 { LANGUAGE_USER_FRENCH_BENIN, "fr", "BJ", k0 },
638 { LANGUAGE_USER_FRENCH_NIGER, "fr", "NE", k0 },
639 { LANGUAGE_USER_FRENCH_TOGO, "fr", "TG", k0 },
640 { LANGUAGE_USER_KVEN_FINNISH, "fkv", "NO", k0 },
641 { LANGUAGE_USER_CHURCH_SLAVIC, "cu", "RU", k0 },
642 { LANGUAGE_USER_VENETIAN, "vec", "IT", k0 },
643 { LANGUAGE_USER_ENGLISH_GAMBIA, "en", "GM", k0 },
644 { LANGUAGE_USER_OCCITAN_ARANESE, "oc", "ES", kSAME },
645 { LANGUAGE_USER_ARPITAN_FRANCE, "frp", "FR", k0 },
646 { LANGUAGE_USER_ARPITAN_ITALY, "frp", "IT", k0 },
647 { LANGUAGE_USER_ARPITAN_SWITZERLAND, "frp", "CH", k0 },
648 { LANGUAGE_USER_APATANI, "apt", "IN", k0 },
649 { LANGUAGE_USER_ENGLISH_MAURITIUS, "en", "MU", k0 },
650 { LANGUAGE_USER_FRENCH_MAURITIUS, "fr", "MU", k0 },
651 { LANGUAGE_USER_SILESIAN, "szl", "PL", k0 },
652 { LANGUAGE_USER_MANCHU, "mnc", "CN", k0 },
653 { LANGUAGE_USER_XIBE, "sjo", "CN", k0 },
654 { LANGUAGE_USER_KITUBA_DRCONGO, "ktu", "CD", k0 },
655 { LANGUAGE_USER_FON, "fon", "BJ", k0 },
656 { LANGUAGE_USER_PLAUTDIETSCH, "pdt", "CA", k0 },
657 { LANGUAGE_USER_ARMENIAN_WESTERN, "hyw", "AM", k0 },
658 { LANGUAGE_USER_ARMENIAN_CLASSICAL, "xcl", "AM", k0 },
659 { LANGUAGE_USER_JUHOAN, "ktz", "NA", k0 },
660 { LANGUAGE_USER_NARO, "nhr", "BW", k0 },
661 { LANGUAGE_USER_ILOKO, "ilo", "PH", k0 },
662 { LANGUAGE_USER_ENGLISH_ZAMBIA, "en", "ZM", k0 },
663 { LANGUAGE_USER_ENGLISH_SRI_LANKA, "en", "LK", k0 },
664 { LANGUAGE_USER_ENGLISH_NIGERIA, "en", "NG", k0 },
665 { LANGUAGE_USER_KABARDIAN, "kbd", "RU", k0 }, // Cyrillic script
666 { LANGUAGE_USER_GUADELOUPEAN_CREOLE_FRENCH, "gcf", "GP", k0 },
667 { LANGUAGE_USER_LIGURIAN, "lij", "IT", k0 },
668 { LANGUAGE_USER_MINANGKABAU, "min", "ID", k0 },
669 { LANGUAGE_USER_SUNDANESE, "sun", "ID", k0 },
670 { LANGUAGE_USER_YAKA_DRCONGO, "yaf", "CD", k0 },
671 { LANGUAGE_USER_ENGLISH_KENYA, "en", "KE", k0 },
672 { LANGUAGE_USER_CABECAR, "cjp", "CR", k0 },
673 { LANGUAGE_USER_BRIBRI, "bzd", "CR", k0 },
674 { LANGUAGE_USER_ENGLISH_DENMARK, "en", "DK", k0 },
675 { LANGUAGE_USER_SESOTHO_LESOTHO, "st", "LS", k0 },
676 { LANGUAGE_USER_KLINGON, "tlh", "" , k0 },
677 { LANGUAGE_USER_ENGLISH_ISRAEL, "en", "IL", k0 },
678 { LANGUAGE_USER_PENNSYLVANIA_DUTCH, "pdc", "US", k0 },
679 { LANGUAGE_USER_PORTUGUESE_MOZAMBIQUE, "pt", "MZ", k0 },
680 { LANGUAGE_USER_SPANISH_EQUATORIAL_GUINEA, "es", "GQ", k0 },
681 { LANGUAGE_USER_SPANISH_PHILIPPINES, "es", "PH", k0 },
682 { LANGUAGE_USER_ENGLISH_ANTIGUA_BARBUDA,"en", "AG", k0 },
683 { LANGUAGE_USER_SARAIKI, "skr", "PK", k0 },
684 { LANGUAGE_USER_MORISYEN, "mfe", "MU", k0 },
685 { LANGUAGE_USER_FRENCH_GUINEA, "fr", "GN", k0 },
686 // Add new languages ^^^ there.
687 { LANGUAGE_MULTIPLE, "mul", "" , k0 }, // multiple languages, many languages are used
688 { LANGUAGE_UNDETERMINED, "und", "" , k0 }, // undetermined language, language cannot be identified
689 { LANGUAGE_NONE, "zxx", "" , k0 }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information
690 };
691
692 IsoLanguageScriptCountryEntry const aImplIsoLangScriptEntries[] =
693 {
694 // MS-LangID, ISO639-ISO15924, ISO3166, override
695 { LANGUAGE_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", k0 },
696 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_SERBIA, "sr-Latn", "RS", k0 },
697 { LANGUAGE_SERBIAN_LATIN_MONTENEGRO, "sr-Latn", "ME", k0 },
698 { LANGUAGE_OBSOLETE_USER_SERBIAN_LATIN_MONTENEGRO,"sr-Latn", "ME", k0 },
699 { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sr-Latn", "BA", k0 },
700 { 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
701 { LANGUAGE_SERBIAN_LATIN_SAM, "sr-Latn", "YU", k0 }, // legacy Serbian Latin in Yugoslavia
702 { LANGUAGE_SERBIAN_LATIN_LSO, "sr-Latn", "" , k0 },
703 { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sr-Latn", "" , LANGUAGE_SERBIAN_LATIN_LSO }, // MS lists this as 'sr' only, what a mess
704 { LANGUAGE_SERBIAN_CYRILLIC_SERBIA, "sr-Cyrl", "RS", kSAME }, // MS
705 { LANGUAGE_SERBIAN_CYRILLIC_MONTENEGRO, "sr-Cyrl", "ME", kSAME }, // MS
706 { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr-Cyrl", "BA", kSAME }, // MS
707 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr-Cyrl", "CS", kSAME }, // MS
708 { LANGUAGE_SERBIAN_CYRILLIC_LSO, "sr-Cyrl", "" , kSAME }, // MS
709 { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs-Cyrl", "BA", k0 },
710 { LANGUAGE_BOSNIAN_CYRILLIC_LSO, "bs-Cyrl", "" , k0 },
711 { LANGUAGE_AZERI_CYRILLIC, "az-Cyrl", "AZ", k0 }, // macrolanguage code; MS reserved since rev.15
712 { LANGUAGE_AZERI_CYRILLIC_LSO, "az-Cyrl", "" , k0 }, // macrolanguage code
713 { LANGUAGE_UZBEK_CYRILLIC, "uz-Cyrl", "UZ", k0 }, // macrolanguage code; MS reserved since rev.15
714 { LANGUAGE_UZBEK_CYRILLIC_LSO, "uz-Cyrl", "" , k0 }, // macrolanguage code
715 { LANGUAGE_MONGOLIAN_CYRILLIC_MONGOLIA, "mn-Cyrl", "MN", k0 }, // macrolanguage code; should be khk-MN or khk-Cyrl-MN
716 { LANGUAGE_MONGOLIAN_CYRILLIC_LSO, "mn-Cyrl", "" , k0 }, // macrolanguage code; MS, should be khk or khk-Cyrl
717 { LANGUAGE_MONGOLIAN_MONGOLIAN_MONGOLIA, "mn-Mong", "MN", k0 }, // macrolanguage code; MS, should be khk-Mong-MN
718 { LANGUAGE_MONGOLIAN_MONGOLIAN_CHINA, "mn-Mong", "CN", k0 }, // macrolanguage code; MS reserved since rev.15; should actually be mvf-CN
719 { LANGUAGE_MONGOLIAN_MONGOLIAN_LSO, "mn-Mong", "" , k0 }, // macrolanguage code
720 { LANGUAGE_USER_PALI_LATIN, "pi-Latn", "" , k0 },
721 { LANGUAGE_USER_PALI_THAI, "pi-Thai", "" , k0 },
722 { LANGUAGE_USER_KARAKALPAK_LATIN, "kaa-Latn", "UZ", k0 },
723 { LANGUAGE_TAJIK, "tg-Cyrl", "TJ", k0 }, // MS
724 { LANGUAGE_TAJIK_LSO, "tg-Cyrl", "" , k0 }, // MS
725 { LANGUAGE_AZERI_LATIN, "az-Latn", "AZ", k0 }, // macrolanguage code; MS
726 { LANGUAGE_AZERI_LATIN_LSO, "az-Latn", "" , k0 }, // macrolanguage code; MS
727 { LANGUAGE_USER_YIDDISH_US, "yi-Hebr", "US", kSAME }, // macrolanguage code; MS, Hebr is suppress-script
728 { LANGUAGE_USER_YIDDISH_ISRAEL, "yi-Hebr", "IL", kSAME }, // macrolanguage code; MS, Hebr is suppress-script
729 { LANGUAGE_UZBEK_LATIN, "uz-Latn", "UZ", k0 }, // macrolanguage code
730 { LANGUAGE_UZBEK_LATIN_LSO, "uz-Latn", "" , k0 },
731 { LANGUAGE_SINDHI, "sd-Deva", "IN", k0 }, // MS reserved
732 { LANGUAGE_SINDHI_PAKISTAN, "sd-Arab", "PK", k0 }, // MS
733 { LANGUAGE_SINDHI_ARABIC_LSO, "sd-Arab", "" , k0 },
734 { LANGUAGE_CHEROKEE_UNITED_STATES, "chr-Cher", "US", k0 }, // MS
735 { LANGUAGE_CHEROKEE_CHEROKEE_LSO, "chr-Cher", "" , k0 },
736 { LANGUAGE_INUKTITUT_SYLLABICS_CANADA, "iu-Cans", "CA", k0 }, // macrolanguage code, MS
737 { LANGUAGE_INUKTITUT_SYLLABICS_LSO, "iu-Cans", "" , k0 }, // macrolanguage code, MS
738 { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu-Latn", "CA", k0 }, // macrolanguage code, MS
739 { LANGUAGE_INUKTITUT_LATIN_LSO, "iu-Latn", "" , k0 }, // macrolanguage code, MS
740 { LANGUAGE_TAMAZIGHT_TIFINAGH_MOROCCO, "tzm-Tfng", "MA", k0 },
741 { LANGUAGE_TAMAZIGHT_TIFINAGH_LSO, "tzm-Tfng", "" , k0 },
742 { LANGUAGE_KASHMIRI_INDIA, "ks-Deva", "IN", k0 }, // MS since rev.15, earlier was "ks-Deva" reserved
743 { LANGUAGE_KASHMIRI, "ks-Arab", "" , k0 }, // MS, Kashmiri in "Jammu and Kashmir" ... no ISO3166 code for that
744 { LANGUAGE_HAUSA_NIGERIA, "ha-Latn", "NG", k0 }, // MS
745 { LANGUAGE_USER_HAUSA_GHANA, "ha-Latn", "GH", k0 },
746 { LANGUAGE_HAUSA_LATIN_LSO, "ha-Latn", "" , k0 },
747 { LANGUAGE_LATIN, "la-Latn", "" , kSAME }, // MS reserved until rev.15, though Latn is suppress-script, "la-VA" since rev.15
748 { LANGUAGE_TAI_NUA_CHINA, "tdd-Tale", "CN", k0 }, // MS reserved
749 { LANGUAGE_LU_CHINA, "khb-Talu", "CN", k0 }, // MS reserved
750 { LANGUAGE_KURDISH_ARABIC_IRAQ, "ku-Arab", "IQ", kSAME }, // macrolanguage code, MS
751 { LANGUAGE_KURDISH_ARABIC_LSO, "ku-Arab", "" , kSAME }, // macrolanguage code, MS
752 { LANGUAGE_USER_KURDISH_TURKEY, "kmr-Latn", "TR", k0 },
753 { LANGUAGE_USER_KURDISH_SYRIA, "kmr-Latn", "SY", k0 },
754 { LANGUAGE_PUNJABI_PAKISTAN, "pnb-Arab", "PK", k0 },
755 { LANGUAGE_PUNJABI_ARABIC_LSO, "pnb-Arab", "" , k0 },
756 { LANGUAGE_PUNJABI_PAKISTAN, "pa-Arab", "PK", k0 }, // MS, incorrect
757 { LANGUAGE_PUNJABI_ARABIC_LSO, "pa-Arab", "" , k0 }, // MS, incorrect
758 { LANGUAGE_TAMAZIGHT_LATIN_ALGERIA, "tzm-Latn", "DZ", kSAME }, // MS
759 { LANGUAGE_TAMAZIGHT_LATIN_LSO, "tzm-Latn", "" , k0 }, // MS
760 { LANGUAGE_FULFULDE_NIGERIA, "ff-Latn", "NG", kSAME }, // macrolanguage code; MS since rev.15
761 { LANGUAGE_FULFULDE_SENEGAL, "ff-Latn", "SN", k0 }, // macrolanguage code, MS
762 { LANGUAGE_FULFULDE_LATIN_LSO, "ff-Latn", "" , k0 }, // macrolanguage code
763 { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs-Latn", "BA", kSAME }, // MS, though Latn is suppress-script
764 { LANGUAGE_BOSNIAN_LATIN_LSO, "bs-Latn", "" , LANGUAGE_BOSNIAN_LSO }, // MS, though Latn is suppress-script
765 { LANGUAGE_CHINESE_TRADITIONAL_LSO, "zh-Hant", "" , k0 },
766 { LANGUAGE_CHINESE_SIMPLIFIED, "zh-Hans", "CN", kSAME }, // canonical, but prefer legacy zh-CN
767 { LANGUAGE_CHINESE_TRADITIONAL, "zh-Hant", "TW", kSAME }, // canonical, but prefer legacy zh-TW
768 { LANGUAGE_CHINESE_SINGAPORE, "zh-Hans", "SG", kSAME }, // canonical, but prefer legacy zh-SG
769 { LANGUAGE_CHINESE_HONGKONG, "zh-Hant", "HK", kSAME }, // canonical, but prefer legacy zh-HK
770 { LANGUAGE_CHINESE_MACAU, "zh-Hant", "MO", kSAME }, // canonical, but prefer legacy zh-MO
771 { LANGUAGE_USER_MANINKAKAN_EASTERN_LATIN, "emk-Latn", "GN", k0 },
772 { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CA", k0 },
773 { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CA", k0 },
774 { LANGUAGE_USER_CREE_PLAINS_LATIN, "crk-Latn", "CN", kSAME }, // erroneous tdf#73973
775 { LANGUAGE_USER_CREE_PLAINS_SYLLABICS, "crk-Cans", "CN", kSAME }, // erroneous tdf#73973
776 { LANGUAGE_USER_HUNGARIAN_ROVAS, "hu-Hung", "HU", k0 },
777 { LANGUAGE_USER_MALAY_ARABIC_MALAYSIA, "ms-Arab", "MY", k0 },
778 { LANGUAGE_USER_MALAY_ARABIC_BRUNEI, "ms-Arab", "BN", k0 },
779 { LANGUAGE_KAZAKH_LATIN, "kk-Latn", "KZ", k0 },
780 { LANGUAGE_KAZAKH_LATIN_LSO, "kk-Latn", "" , k0 }, // MS reserved
781 { LANGUAGE_KAZAKH_CYRILLIC_LSO, "kk-Cyrl", "" , k0 }, // MS reserved
782 { LANGUAGE_KANURI_NIGERIA, "kr-Latn", "NG", k0 }, // macrolanguage code; MS since rev.15
783 { LANGUAGE_TAMAZIGHT_ARABIC_MOROCCO, "tzm-Arab", "MA", k0 }, // MS since rev.15, was reserved
784 { LANGUAGE_USER_ROHINGYA_HANIFI, "rhg-Rhog", "MM", k0 },
785 { LANGUAGE_USER_SANTALI_OLCHIKI_INDIA, "sat-Olck", "IN", k0 },
786 };
787
788 Bcp47CountryEntry const aImplBcp47CountryEntries[] =
789 {
790 // MS-LangID full BCP47, ISO3166, ISO639-Variant or other fallback
791 { LANGUAGE_CATALAN_VALENCIAN, "ca-ES-valencia", "ES", "ca-valencia", k0 },
792 { 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.
793 { LANGUAGE_USER_ENGLISH_UK_OXENDICT, "en-GB-oxendict", "GB", "", k0 },
794 { LANGUAGE_USER_ENGLISH_UK_OED, "en-GB-oed", "GB", "", LANGUAGE_USER_ENGLISH_UK_OXENDICT }, // grandfathered, deprecated, prefer en-GB-oxendict
795 { LANGUAGE_SPANISH_DATED, "es-ES-u-co-trad", "ES", "es-u-co-trad", k0 }, // RFC6067/CLDR
796 { LANGUAGE_SPANISH_DATED, "es-ES_tradnl", "ES", "", kSAME }, // MS malformed
797 { LANGUAGE_OCCITAN_FRANCE, "oc-FR-lengadoc", "FR", "oc-lengadoc", k0 },
798 { LANGUAGE_USER_OCCITAN_ARANESE, "oc-ES-aranes", "ES", "oc-aranes", k0 },
799 // { 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!
800 { LANGUAGE_YIDDISH, "yi-001", "", "", k0 }, // MS since rev.15, was "yi-Hebr" reserved, "001"="World"
801 { LANGUAGE_FRENCH_WEST_INDIES, "fr-029", "", "", k0 }, // MS since rev.15, was "Neither defined nor reserved", "029"="Caribbean"
802 { LANGUAGE_SPANISH_LATIN_AMERICA, "es-419", "", "", k0 }, // MS reserved since rev.15, "419"="Latin America and the Caribbean"
803 { LANGUAGE_OBSOLETE_USER_SPANISH_LATIN_AMERICA, "es-419", "", "", LANGUAGE_SPANISH_LATIN_AMERICA },
804 { LANGUAGE_USER_INTERSLAVIC_LATIN, "art-Latn-x-interslv", "", "", k0 }, // see discussion in tdf#145853
805 { LANGUAGE_USER_INTERSLAVIC_CYRILLIC, "art-Cyrl-x-interslv", "", "", k0 },
806 };
807
808 const IsoLanguageCountryEntry aLastResortFallbackEntry =
809 { LANGUAGE_ENGLISH_US, "en", "US", k0 };
810
811 OUString IsoLanguageCountryEntry::getTagString() const
812 {
813 if (maCountry[0])
814 return OUString( OUString::createFromAscii( maLanguage) + "-" + OUString::createFromAscii( maCountry));
815 else
816 return OUString::createFromAscii( maLanguage);
817 }
818
819 css::lang::Locale IsoLanguageCountryEntry::getLocale() const
820 {
821 return lang::Locale( OUString::createFromAscii( maLanguage), OUString::createFromAscii( maCountry), OUString());
822 }
823
824 OUString IsoLanguageScriptCountryEntry::getTagString() const
825 {
826 if (maCountry[0])
827 return OUString( OUString::createFromAscii( maLanguageScript) + "-" + OUString::createFromAscii( maCountry));
828 else
829 return OUString::createFromAscii( maLanguageScript);
830 }
831
832 css::lang::Locale IsoLanguageScriptCountryEntry::getLocale() const
833 {
834 return lang::Locale( I18NLANGTAG_QLT, OUString::createFromAscii( maCountry), getTagString());
835 }
836
837 bool IsoLanguageScriptCountryEntry::startsInIgnoreAsciiCase( std::u16string_view aStr ) const
838 {
839 return o3tl::matchIgnoreAsciiCase(aStr, std::string_view(maLanguageScript) );
840 }
841
842 OUString Bcp47CountryEntry::getTagString() const
843 {
844 return OUString::createFromAscii( mpBcp47);
845 }
846
847 css::lang::Locale Bcp47CountryEntry::getLocale() const
848 {
849 return lang::Locale( I18NLANGTAG_QLT, OUString::createFromAscii( maCountry), getTagString());
850 }
851
852
853 // In this table are the countries which should mapped to a specific
854 // english language
855 IsoLangEngEntry const aImplIsoLangEngEntries[] =
856 {
857 { LANGUAGE_ENGLISH_UK, "AO" }, // Angola
858 { LANGUAGE_ENGLISH_UK, "BJ" }, // Benin
859 { LANGUAGE_ENGLISH_UK, "BW" }, // Botswana
860 { LANGUAGE_ENGLISH_UK, "BI" }, // Burundi
861 { LANGUAGE_ENGLISH_UK, "CM" }, // Cameroon
862 { LANGUAGE_ENGLISH_UK, "GA" }, // Gabon
863 { LANGUAGE_ENGLISH_UK, "GM" }, // Gambia
864 { LANGUAGE_ENGLISH_UK, "GH" }, // Ghana
865 { LANGUAGE_ENGLISH_UK, "GN" }, // Guinea
866 { LANGUAGE_ENGLISH_UK, "LS" }, // Lesotho
867 { LANGUAGE_ENGLISH_UK, "MW" }, // Malawi
868 { LANGUAGE_ENGLISH_UK, "MT" }, // Malta
869 { LANGUAGE_ENGLISH_UK, "NA" }, // Namibia
870 { LANGUAGE_ENGLISH_UK, "NG" }, // Nigeria
871 { LANGUAGE_ENGLISH_UK, "UG" }, // Uganda
872 { LANGUAGE_ENGLISH_UK, "ZM" }, // Zambia
873 { LANGUAGE_ENGLISH_UK, "ZW" }, // Zimbabwe
874 { LANGUAGE_ENGLISH_UK, "SZ" }, // Swaziland
875 { LANGUAGE_ENGLISH_UK, "NG" }, // Sierra Leone
876 { LANGUAGE_ENGLISH_UK, "KN" }, // Saint Kitts and Nevis
877 { LANGUAGE_ENGLISH_UK, "SH" }, // St. Helena
878 { LANGUAGE_ENGLISH_UK, "IO" }, // British Indian Oceanic Territory
879 { LANGUAGE_ENGLISH_UK, "FK" }, // Falkland Islands
880 { LANGUAGE_ENGLISH_UK, "GI" }, // Gibraltar
881 { LANGUAGE_ENGLISH_UK, "KI" }, // Kiribati
882 { LANGUAGE_ENGLISH_UK, "VG" }, // Virgin Islands
883 { LANGUAGE_ENGLISH_UK, "MU" }, // Mauritius
884 { LANGUAGE_ENGLISH_UK, "FJ" }, // Fiji
885 { LANGUAGE_ENGLISH_US, "KI" }, // Kiribati
886 { LANGUAGE_ENGLISH_US, "LR" }, // Liberia
887 { LANGUAGE_ENGLISH_US, "GU" }, // Guam
888 { LANGUAGE_ENGLISH_US, "MH" }, // Marshall Islands
889 { LANGUAGE_ENGLISH_US, "PW" }, // Palau
890 { LANGUAGE_ENGLISH_CARIBBEAN, "AI" }, // Anguilla
891 { LANGUAGE_ENGLISH_CARIBBEAN, "AG" }, // Antigua and Barbuda
892 { LANGUAGE_ENGLISH_CARIBBEAN, "BS" }, // Bahamas
893 { LANGUAGE_ENGLISH_CARIBBEAN, "BB" }, // Barbados
894 { LANGUAGE_ENGLISH_CARIBBEAN, "BM" }, // Bermuda
895 { LANGUAGE_ENGLISH_CARIBBEAN, "KY" }, // Cayman Islands
896 { LANGUAGE_ENGLISH_CARIBBEAN, "GD" }, // Grenada
897 { LANGUAGE_ENGLISH_CARIBBEAN, "DM" }, // Dominica
898 { LANGUAGE_ENGLISH_CARIBBEAN, "HT" }, // Haiti
899 { LANGUAGE_ENGLISH_CARIBBEAN, "MS" }, // Montserrat
900 { LANGUAGE_ENGLISH_CARIBBEAN, "FM" }, // Micronesia
901 { LANGUAGE_ENGLISH_CARIBBEAN, "VC" }, // St. Vincent / Grenadines
902 { LANGUAGE_ENGLISH_CARIBBEAN, "LC" }, // Saint Lucia
903 { LANGUAGE_ENGLISH_CARIBBEAN, "TC" }, // Turks & Caicos Islands
904 { LANGUAGE_ENGLISH_CARIBBEAN, "GY" }, // Guyana
905 { LANGUAGE_ENGLISH_CARIBBEAN, "TT" }, // Trinidad and Tobago
906 { LANGUAGE_ENGLISH_AUS, "CX" }, // Christmas Islands
907 { LANGUAGE_ENGLISH_AUS, "CC" }, // Cocos (Keeling) Islands
908 { LANGUAGE_ENGLISH_AUS, "NF" }, // Norfolk Island
909 { LANGUAGE_ENGLISH_AUS, "PG" }, // Papua New Guinea
910 { LANGUAGE_ENGLISH_AUS, "SB" }, // Solomon Islands
911 { LANGUAGE_ENGLISH_AUS, "TV" }, // Tuvalu
912 { LANGUAGE_ENGLISH_AUS, "NR" }, // Nauru
913 { LANGUAGE_ENGLISH_NZ, "CK" }, // Cook Islands
914 { LANGUAGE_ENGLISH_NZ, "NU" }, // Niue
915 { LANGUAGE_ENGLISH_NZ, "TK" }, // Tokelau
916 { LANGUAGE_ENGLISH_NZ, "TO" }, // Tonga
917 { LANGUAGE_DONTKNOW, "" } // marks end of table
918 };
919
920
921 IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries[] =
922 {
923 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "BOK" }, // registered subtags for "no" in rfc1766
924 { LANGUAGE_NORWEGIAN_NYNORSK, "no", "NYN" }, // registered subtags for "no" in rfc1766
925 { LANGUAGE_SERBIAN_LATIN_SAM, "sr", "latin" },
926 { LANGUAGE_SERBIAN_CYRILLIC_SAM, "sr", "cyrillic" },
927 { LANGUAGE_AZERI_LATIN, "az", "latin" },
928 { LANGUAGE_AZERI_CYRILLIC, "az", "cyrillic" },
929 { LANGUAGE_DONTKNOW, "", "" } // marks end of table
930 };
931
932
933 // in this table are only names to find the best language
934 IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries2[] =
935 {
936 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmaal" },
937 { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmal" },
938 { LANGUAGE_NORWEGIAN_NYNORSK, "no", "nynorsk" },
939 { LANGUAGE_DONTKNOW, "", "" } // marks end of table
940 };
941
942
943 // in this table are only names to find the best language
944 IsoLangOtherEntry const aImplOtherEntries[] =
945 {
946 { LANGUAGE_ENGLISH_US, "c" },
947 { LANGUAGE_CHINESE, "chinese" },
948 { LANGUAGE_GERMAN, "german" },
949 { LANGUAGE_JAPANESE, "japanese" },
950 { LANGUAGE_KOREAN, "korean" },
951 { LANGUAGE_ENGLISH_US, "posix" },
952 { LANGUAGE_CHINESE_TRADITIONAL, "tchinese" },
953 { LANGUAGE_DONTKNOW, nullptr } // marks end of table
954 };
955
956
957 // in this table are only privateuse names
958 IsoLangOtherEntry const aImplPrivateUseEntries[] =
959 {
960 { LANGUAGE_USER_PRIV_NOTRANSLATE, "x-no-translate" }, //! not BCP47 but legacy in .xcu configmgr
961 { LANGUAGE_USER_PRIV_DEFAULT, "x-default" },
962 { LANGUAGE_USER_PRIV_COMMENT, "x-comment" },
963 { LANGUAGE_USER_PRIV_NONE, "x-none" },
964 { LANGUAGE_USER_PRIV_JOKER, "*" }, //! not BCP47 but transferable in configmgr
965 { LANGUAGE_DONTKNOW, nullptr } // marks end of table
966 };
967
968
969 // static
970 void MsLangId::Conversion::convertLanguageToLocaleImpl( LanguageType nLang,
971 css::lang::Locale & rLocale, bool bIgnoreOverride )
972 {
973 if (nLang == LANGUAGE_ENGLISH_US)
974 {
975 // Speed-up a gazillion fallback cases, not iterating through
976 // aImplBcp47CountryEntries nor aImplIsoLangScriptEntries.
977 rLocale.Language = "en";
978 rLocale.Country = "US";
979 rLocale.Variant.clear();
980 return;
981 }
982
983 const Bcp47CountryEntry* pBcp47EntryOverride = nullptr;
984 const IsoLanguageScriptCountryEntry* pScriptEntryOverride = nullptr;
985 const IsoLanguageCountryEntry* pEntryOverride = nullptr;
986
987 Label_Override_Lang_Locale:
988
989 // Search for LangID in BCP47
990 for (const auto& rBcp47Entry : aImplBcp47CountryEntries)
991 {
992 if (rBcp47Entry.mnLang == nLang)
993 {
994 if (bIgnoreOverride || !rBcp47Entry.mnOverride)
995 {
996 rLocale.Language = I18NLANGTAG_QLT;
997 rLocale.Country = OUString::createFromAscii(rBcp47Entry.maCountry);
998 rLocale.Variant = rBcp47Entry.getTagString();
999 return;
1000 }
1001 else if (rBcp47Entry.mnOverride && pBcp47EntryOverride != &rBcp47Entry)
1002 {
1003 pBcp47EntryOverride = &rBcp47Entry;
1004 nLang = getOverrideLang(rBcp47Entry.mnLang, rBcp47Entry.mnOverride);
1005 goto Label_Override_Lang_Locale;
1006 }
1007 }
1008 }
1009
1010 // Search for LangID in ISO lll-Ssss-CC
1011 for (const auto& rScriptEntry : aImplIsoLangScriptEntries)
1012 {
1013 if (rScriptEntry.mnLang == nLang)
1014 {
1015 if (bIgnoreOverride || !rScriptEntry.mnOverride)
1016 {
1017 rLocale.Language = I18NLANGTAG_QLT;
1018 rLocale.Country = OUString::createFromAscii(rScriptEntry.maCountry);
1019 rLocale.Variant = rScriptEntry.getTagString();
1020 return;
1021 }
1022 else if (rScriptEntry.mnOverride && pScriptEntryOverride != &rScriptEntry)
1023 {
1024 pScriptEntryOverride = &rScriptEntry;
1025 nLang = getOverrideLang(rScriptEntry.mnLang, rScriptEntry.mnOverride);
1026 goto Label_Override_Lang_Locale;
1027 }
1028 }
1029 }
1030
1031 // Search for LangID in ISO lll-CC
1032 for (const auto& rEntry : aImplIsoLangEntries)
1033 {
1034 if (rEntry.mnLang == nLang)
1035 {
1036 if (bIgnoreOverride || !rEntry.mnOverride)
1037 {
1038 rLocale.Language = OUString::createFromAscii(rEntry.maLanguage);
1039 rLocale.Country = OUString::createFromAscii(rEntry.maCountry);
1040 rLocale.Variant.clear();
1041 return;
1042 }
1043 else if (rEntry.mnOverride && pEntryOverride != &rEntry)
1044 {
1045 pEntryOverride = &rEntry;
1046 nLang = getOverrideLang(rEntry.mnLang, rEntry.mnOverride);
1047 goto Label_Override_Lang_Locale;
1048 }
1049 }
1050 }
1051
1052 // Look for privateuse definitions.
1053 for (const IsoLangOtherEntry* pPrivateEntry = aImplPrivateUseEntries;
1054 pPrivateEntry->mnLang != LANGUAGE_DONTKNOW; ++pPrivateEntry)
1055 {
1056 if (pPrivateEntry->mnLang == nLang)
1057 {
1058 rLocale.Language = I18NLANGTAG_QLT;
1059 rLocale.Country.clear();
1060 rLocale.Variant = OUString::createFromAscii( pPrivateEntry->mpLanguage );
1061 return;
1062 }
1063 }
1064
1065 // Not found. Passed rLocale argument remains unchanged.
1066 }
1067
1068
1069 // static
1070 css::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageCountryEntry * pEntry )
1071 {
1072 if (pEntry->mnOverride)
1073 {
1074 lang::Locale aLocale;
1075 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false);
1076 return aLocale;
1077 }
1078 else
1079 return pEntry->getLocale();
1080 }
1081
1082 // static
1083 css::lang::Locale MsLangId::Conversion::getLocale( const IsoLanguageScriptCountryEntry * pEntry )
1084 {
1085 if (pEntry->mnOverride)
1086 {
1087 lang::Locale aLocale;
1088 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false);
1089 return aLocale;
1090 }
1091 else
1092 return pEntry->getLocale();
1093 }
1094
1095 // static
1096 css::lang::Locale MsLangId::Conversion::getLocale( const Bcp47CountryEntry * pEntry )
1097 {
1098 if (pEntry->mnOverride)
1099 {
1100 lang::Locale aLocale;
1101 convertLanguageToLocaleImpl( getOverrideLang( pEntry->mnLang, pEntry->mnOverride), aLocale, false);
1102 return aLocale;
1103 }
1104 else
1105 return pEntry->getLocale();
1106 }
1107
1108 // static
1109 css::lang::Locale MsLangId::Conversion::lookupFallbackLocale(
1110 const css::lang::Locale & rLocale )
1111 {
1112 // language is lower case in table
1113 OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1114 // country is upper case in table
1115 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1116 sal_Int32 nCountryLen = aUpperCountry.getLength();
1117
1118 if (rLocale.Language == I18NLANGTAG_QLT)
1119 {
1120 // Search in BCP47, only full match and one fallback, for other
1121 // fallbacks only LanguageTag can decide.
1122 for (const auto& rBcp47Entry : aImplBcp47CountryEntries)
1123 {
1124 if ( rLocale.Variant.equalsIgnoreAsciiCase(rBcp47Entry.getTagString()) ||
1125 rLocale.Variant.equalsIgnoreAsciiCaseAscii(rBcp47Entry.mpFallback))
1126 return getLocale(&rBcp47Entry); // may override
1127 }
1128
1129 // Search in ISO lll-Ssss-CC
1130 const IsoLanguageScriptCountryEntry* pFirstScript = nullptr;
1131 for (const auto& rScriptEntry : aImplIsoLangScriptEntries)
1132 {
1133 if (rScriptEntry.startsInIgnoreAsciiCase(rLocale.Variant))
1134 {
1135 if (rLocale.Variant.equalsIgnoreAsciiCase(rScriptEntry.getTagString()))
1136 return getLocale(&rScriptEntry); // may override
1137 if (!pFirstScript)
1138 pFirstScript = &rScriptEntry;
1139 }
1140 }
1141 // If at least a lll-Ssss matched, try that with country or use it as
1142 // fallback.
1143 if (pFirstScript)
1144 {
1145 // Check for country only if there is more than lll-Ssss-CC in tag
1146 // string, else we would had matched it already.
1147 if (!aUpperCountry.isEmpty() && rLocale.Variant.getLength() > 11)
1148 {
1149 for (const IsoLanguageScriptCountryEntry* pScriptEntry = pFirstScript;
1150 pScriptEntry != std::end(aImplIsoLangScriptEntries); ++pScriptEntry)
1151 {
1152 if (aUpperCountry.equalsAscii( pScriptEntry->maCountry) &&
1153 pScriptEntry->startsInIgnoreAsciiCase( rLocale.Variant))
1154 return getLocale( pScriptEntry); // may override
1155 }
1156 }
1157 return getLocale( pFirstScript); // may override
1158 }
1159
1160 // Extract language from tag string, country is used as present in
1161 // Locale because in the tables that follow we have only ISO 3166
1162 // countries and if that is in the tag string we also have it in the
1163 // Locale.
1164 aLowerLang = rLocale.Variant.getToken(0, '-').toAsciiLowerCase();
1165 // Nothing with "x-..." or "i-..." or any 1 letter in lll-CC table that
1166 // follows.
1167 if (aLowerLang.getLength() == 1)
1168 return aLastResortFallbackEntry.getLocale();
1169 }
1170
1171 // Search for locale and remember first lang-only.
1172 const IsoLanguageCountryEntry* pFirstLang = nullptr;
1173 for (const auto& rEntry : aImplIsoLangEntries)
1174 {
1175 if (aLowerLang.equalsAscii(rEntry.maLanguage))
1176 {
1177 if (*rEntry.maCountry)
1178 {
1179 if (nCountryLen && aUpperCountry.equalsAscii(rEntry.maCountry))
1180 return getLocale(&rEntry); // may override
1181 }
1182 else
1183 {
1184 if (rEntry.mnLang.anyOf(
1185 // These are known to have no country assigned.
1186 LANGUAGE_USER_ESPERANTO,
1187 LANGUAGE_USER_INTERLINGUA,
1188 LANGUAGE_USER_INTERLINGUE,
1189 LANGUAGE_USER_LOJBAN,
1190 LANGUAGE_KASHMIRI,
1191 LANGUAGE_USER_KLINGON,
1192 LANGUAGE_USER_KEYID,
1193 // And the special codes without country.
1194 LANGUAGE_MULTIPLE,
1195 LANGUAGE_UNDETERMINED,
1196 LANGUAGE_NONE))
1197 {
1198 return getLocale(&rEntry); // may override
1199 }
1200 }
1201 // Search for first entry of language with any country.
1202 if (!pFirstLang && *rEntry.maCountry)
1203 pFirstLang = &rEntry;
1204 }
1205 }
1206
1207 if (pFirstLang)
1208 return getLocale(pFirstLang); // may override
1209
1210 return aLastResortFallbackEntry.getLocale();
1211 }
1212
1213
1214 // static
1215 LanguageType MsLangId::Conversion::convertPrivateUseToLanguage( std::u16string_view rPriv )
1216 {
1217 for (const IsoLangOtherEntry* pPrivateEntry = aImplPrivateUseEntries;
1218 pPrivateEntry->mnLang != LANGUAGE_DONTKNOW; ++pPrivateEntry)
1219 {
1220 if ( o3tl::equalsIgnoreAsciiCase(rPriv, pPrivateEntry->mpLanguage ) )
1221 return pPrivateEntry->mnLang;
1222 }
1223 return LANGUAGE_DONTKNOW;
1224 }
1225
1226
1227 // static
1228 LanguageType MsLangId::Conversion::convertLocaleToLanguageImpl(
1229 const css::lang::Locale& rLocale )
1230 {
1231 if (rLocale.Language == I18NLANGTAG_QLT)
1232 {
1233 // "x-..." private use and the nasty "*" joker
1234 if (rLocale.Variant.startsWithIgnoreAsciiCase( "x-") || (rLocale.Variant == "*"))
1235 return convertPrivateUseToLanguage( rLocale.Variant);
1236
1237 // Search in BCP47
1238 for (const auto& rBcp47Entry : aImplBcp47CountryEntries)
1239 {
1240 if (rLocale.Variant.equalsIgnoreAsciiCase(rBcp47Entry.getTagString()))
1241 return getOverrideLang(rBcp47Entry.mnLang, rBcp47Entry.mnOverride);
1242 }
1243
1244 // Search in ISO lll-Ssss-CC
1245 for (const auto& rScriptEntry : aImplIsoLangScriptEntries)
1246 {
1247 if (rScriptEntry.startsInIgnoreAsciiCase(rLocale.Variant))
1248 {
1249 if (rLocale.Variant.equalsIgnoreAsciiCase(rScriptEntry.getTagString()))
1250 return getOverrideLang(rScriptEntry.mnLang, rScriptEntry.mnOverride);
1251 }
1252 }
1253 }
1254 else
1255 {
1256 // language is lower case in table
1257 OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1258 // country is upper case in table
1259 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1260
1261 // Search in ISO lll-CC
1262 for (const auto& rEntry : aImplIsoLangEntries)
1263 {
1264 if (aLowerLang.equalsAscii(rEntry.maLanguage) && aUpperCountry.equalsAscii(rEntry.maCountry))
1265 return getOverrideLang(rEntry.mnLang, rEntry.mnOverride);
1266 }
1267 }
1268 return LANGUAGE_DONTKNOW;
1269 }
1270
1271
1272 // static
1273 css::lang::Locale MsLangId::Conversion::getOverride( const css::lang::Locale& rLocale )
1274 {
1275 if (rLocale.Language == I18NLANGTAG_QLT)
1276 {
1277 // "x-..." private use and the nasty "*" joker
1278 if (rLocale.Variant.startsWithIgnoreAsciiCase( "x-") || (rLocale.Variant == "*"))
1279 return rLocale; // no overrides
1280
1281 // Search in BCP47
1282 for (const auto& rBcp47Entry : aImplBcp47CountryEntries)
1283 {
1284 if (rLocale.Variant.equalsIgnoreAsciiCase(rBcp47Entry.getTagString()))
1285 return getLocale(&rBcp47Entry); // may override
1286 }
1287
1288 // Search in ISO lll-Ssss-CC
1289 for (const auto& rScriptEntry : aImplIsoLangScriptEntries)
1290 {
1291 if (rScriptEntry.startsInIgnoreAsciiCase(rLocale.Variant))
1292 {
1293 if (rLocale.Variant.equalsIgnoreAsciiCase(rScriptEntry.getTagString()))
1294 return getLocale(&rScriptEntry); // may override
1295 }
1296 }
1297 }
1298 else
1299 {
1300 // language is lower case in table
1301 OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
1302 // country is upper case in table
1303 OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
1304
1305 // Search in ISO lll-CC
1306 for (const auto& rEntry : aImplIsoLangEntries)
1307 {
1308 if (aLowerLang.equalsAscii(rEntry.maLanguage) && aUpperCountry.equalsAscii(rEntry.maCountry))
1309 return getLocale(&rEntry); // may override
1310 }
1311 }
1312 return lang::Locale();
1313 }
1314
1315
1316 // static
1317 LanguageType MsLangId::Conversion::convertIsoNamesToLanguage( const OUString& rLang,
1318 const OUString& rCountry, bool bSkipIsoTable )
1319 {
1320 // language is lower case in table
1321 OUString aLowerLang = rLang.toAsciiLowerCase();
1322 // country is upper case in table
1323 OUString aUpperCountry = rCountry.toAsciiUpperCase();
1324
1325 if (!bSkipIsoTable)
1326 {
1327 // first look for exact match
1328 for (const auto& rEntry : aImplIsoLangEntries)
1329 {
1330 if ( aLowerLang.equalsAscii(rEntry.maLanguage) )
1331 {
1332 if ( aUpperCountry.isEmpty() ||
1333 aUpperCountry.equalsAscii(rEntry.maCountry) )
1334 return rEntry.mnLang;
1335 }
1336 }
1337
1338 // some eng countries should be mapped to a specific english language
1339 if ( aLowerLang == "en" )
1340 {
1341 for (const IsoLangEngEntry* pEngEntry = aImplIsoLangEngEntries;
1342 pEngEntry->mnLang != LANGUAGE_DONTKNOW; ++pEngEntry)
1343 {
1344 if ( aUpperCountry.equalsAscii( pEngEntry->maCountry ) )
1345 return pEngEntry->mnLang;
1346 }
1347 }
1348 }
1349
1350 // test for specific languages which are not used standard ISO 3166 codes
1351 for (const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
1352 pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW; ++pNoneStdEntry)
1353 {
1354 if ( aLowerLang.equalsAscii( pNoneStdEntry->maLanguage ) )
1355 {
1356 // The countries in this table are not all in upper case
1357 if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
1358 return pNoneStdEntry->mnLang;
1359 }
1360 }
1361 for (const IsoLangNoneStdEntry* pNoneStdEntry2 = aImplIsoNoneStdLangEntries2;
1362 pNoneStdEntry2->mnLang != LANGUAGE_DONTKNOW; ++pNoneStdEntry2)
1363 {
1364 if ( aLowerLang.equalsAscii( pNoneStdEntry2->maLanguage ) )
1365 {
1366 // The countries in this table are not all in upper case
1367 if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry2->maCountry ) )
1368 return pNoneStdEntry2->mnLang;
1369 }
1370 }
1371
1372 if (!bSkipIsoTable)
1373 {
1374 // if only the country is set, look for any entry matching the country
1375 // (to allow reading country and language in separate steps, in any order)
1376 if ( !rCountry.isEmpty() && rLang.isEmpty() )
1377 {
1378 for (const auto& rEntry2 : aImplIsoLangEntries)
1379 {
1380 if ( aUpperCountry.equalsAscii(rEntry2.maCountry) )
1381 return rEntry2.mnLang;
1382 }
1383
1384 aLowerLang = aUpperCountry.toAsciiLowerCase();
1385 }
1386 }
1387
1388 // Look for privateuse definitions.
1389 LanguageType nLang = convertPrivateUseToLanguage( aLowerLang);
1390 if (nLang != LANGUAGE_DONTKNOW)
1391 return nLang;
1392
1393 // Now look for all other definitions, which are not standard
1394 for (const IsoLangOtherEntry* pOtherEntry = aImplOtherEntries;
1395 pOtherEntry->mnLang != LANGUAGE_DONTKNOW; ++pOtherEntry)
1396 {
1397 if ( aLowerLang.equalsAscii( pOtherEntry->mpLanguage ) )
1398 return pOtherEntry->mnLang;
1399 }
1400
1401 return LANGUAGE_DONTKNOW;
1402 }
1403
1404
1405 // static
1406 LanguageType MsLangId::Conversion::convertIsoNamesToLanguage( std::string_view rLang,
1407 std::string_view rCountry )
1408 {
1409 OUString aLang = OStringToOUString( rLang, RTL_TEXTENCODING_ASCII_US);
1410 OUString aCountry = OStringToOUString( rCountry, RTL_TEXTENCODING_ASCII_US);
1411 LanguageType nLang = convertIsoNamesToLanguage( aLang, aCountry, false);
1412
1413 // XXX: called *only* by static convertUnxByteStringToLanguage() so we can
1414 // actually call into LanguageTag to create an on-the-fly mapping.
1415 if (nLang == LANGUAGE_DONTKNOW)
1416 {
1417 OUString aTag( aCountry.isEmpty() ? aLang : aLang + "-" + aCountry );
1418 nLang = LanguageTag( aTag).getLanguageType(false);
1419 SAL_WARN("i18nlangtag", "convertIsoNamesToLanguage(string_view): on-the-fly for {"
1420 << aTag << "} " << nLang);
1421 // Do not leave empty as SYSTEM unresolved.
1422 if (nLang == LANGUAGE_DONTKNOW || nLang == LANGUAGE_SYSTEM)
1423 {
1424 SAL_WARN("i18nlangtag", "convertIsoNamesToLanguage(string_view): on-the-fly bad, using {en-US}");
1425 nLang = LANGUAGE_ENGLISH_US;
1426 }
1427 }
1428 return nLang;
1429 }
1430
1431 namespace {
1432
1433 struct IsoLangGLIBCModifiersEntry
1434 {
1435 LanguageType mnLang;
1436 char maLanguage[4];
1437 char maCountry[3];
1438 char maAtString[9];
1439 };
1440
1441 }
1442
1443 IsoLangGLIBCModifiersEntry const aImplIsoLangGLIBCModifiersEntries[] =
1444 {
1445 // MS-LANGID codes ISO639-1/2/3 ISO3166 glibc modifier
1446 { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs", "BA", "cyrillic" },
1447 { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sr", "RS", "latin" }, // Serbian Latin in Serbia
1448 { LANGUAGE_SERBIAN_LATIN_SAM, "sr", "CS", "latin" }, // Serbian Latin in Serbia and Montenegro
1449 { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sr", "ME", "latin" }, // Serbian Latin in Montenegro
1450 { LANGUAGE_SERBIAN_LATIN_LSO, "sr", "", "latin" },
1451 { LANGUAGE_AZERI_CYRILLIC, "az", "AZ", "cyrillic" },
1452 { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ", "cyrillic" },
1453 { LANGUAGE_CATALAN_VALENCIAN, "ca", "ES", "valencia" },
1454 { LANGUAGE_DONTKNOW, "", "", "" } // marks end of table
1455 };
1456
1457 // convert a unix locale string into LanguageType
1458
1459 // static
1460 LanguageType MsLangId::convertUnxByteStringToLanguage(
1461 std::string_view rString )
1462 {
1463 OString aLang;
1464 OString aCountry;
1465 OString aAtString;
1466
1467 size_t nLangSepPos = rString.find( '_' );
1468 size_t nCountrySepPos = rString.find( '.' );
1469 size_t nAtPos = rString.find( '@' );
1470
1471 if (nCountrySepPos == std::string_view::npos)
1472 nCountrySepPos = nAtPos;
1473 if (nCountrySepPos == std::string_view::npos)
1474 nCountrySepPos = rString.size();
1475
1476 if (nAtPos != std::string_view::npos)
1477 aAtString = OString(rString.substr( nAtPos+1 ));
1478
1479 if (((nLangSepPos != std::string_view::npos) && (nLangSepPos > nCountrySepPos)) || (nLangSepPos == std::string_view::npos))
1480 {
1481 // eg. "el.sun_eu_greek", "tchinese", "es.ISO8859-15"
1482 aLang = OString(rString.substr( 0, nCountrySepPos ));
1483 }
1484 else if ( nLangSepPos != std::string_view::npos )
1485 {
1486 // well formed iso names like "en_US.UTF-8", "sh_BA.ISO8859-2@bosnia"
1487 aLang = OString(rString.substr( 0, nLangSepPos ));
1488 aCountry = OString(rString.substr( nLangSepPos+1, nCountrySepPos - nLangSepPos - 1));
1489 }
1490
1491 // if there is a glibc modifier, first look for exact match in modifier table
1492 if (!aAtString.isEmpty())
1493 {
1494 // language is lower case in table
1495 OString aLowerLang = aLang.toAsciiLowerCase();
1496 // country is upper case in table
1497 OString aUpperCountry = aCountry.toAsciiUpperCase();
1498 for (const IsoLangGLIBCModifiersEntry* pGLIBCModifiersEntry = aImplIsoLangGLIBCModifiersEntries;
1499 pGLIBCModifiersEntry->mnLang != LANGUAGE_DONTKNOW; ++pGLIBCModifiersEntry)
1500 { // avoid embedded \0 warning
1501 if (aLowerLang == pGLIBCModifiersEntry->maLanguage &&
1502 aAtString == pGLIBCModifiersEntry->maAtString )
1503 {
1504 if (aUpperCountry.isEmpty() ||
1505 aUpperCountry == pGLIBCModifiersEntry->maCountry )
1506 {
1507 return pGLIBCModifiersEntry->mnLang;
1508 }
1509 }
1510 }
1511 }
1512
1513 return Conversion::convertIsoNamesToLanguage( aLang, aCountry );
1514 }
1515
1516
1517 // static
1518 ::std::vector< MsLangId::LanguagetagMapping > MsLangId::getDefinedLanguagetags()
1519 {
1520 ::std::vector< LanguagetagMapping > aVec;
1521 aVec.reserve(std::size(aImplBcp47CountryEntries) + std::size(aImplIsoLangScriptEntries)
1522 + std::size(aImplIsoLangEntries));
1523
1524 for (const auto& rEntry : aImplBcp47CountryEntries)
1525 aVec.emplace_back(rEntry.getTagString(), rEntry.mnLang);
1526
1527 for (const auto& rEntry : aImplIsoLangScriptEntries)
1528 aVec.emplace_back(rEntry.getTagString(), rEntry.mnLang);
1529
1530 for (const auto& rEntry : aImplIsoLangEntries)
1531 aVec.emplace_back(rEntry.getTagString(), rEntry.mnLang);
1532
1533 return aVec;
1534 }
1535
1536 /* vim:set shiftwidth=4 softtabstop=4 expandtab: */
FREE OFFICE SUITE