1449ab281SAndrew Rist /**************************************************************
2cdf0e10cSrcweir *
3449ab281SAndrew Rist * Licensed to the Apache Software Foundation (ASF) under one
4449ab281SAndrew Rist * or more contributor license agreements. See the NOTICE file
5449ab281SAndrew Rist * distributed with this work for additional information
6449ab281SAndrew Rist * regarding copyright ownership. The ASF licenses this file
7449ab281SAndrew Rist * to you under the Apache License, Version 2.0 (the
8449ab281SAndrew Rist * "License"); you may not use this file except in compliance
9449ab281SAndrew Rist * with the License. You may obtain a copy of the License at
10449ab281SAndrew Rist *
11449ab281SAndrew Rist * http://www.apache.org/licenses/LICENSE-2.0
12449ab281SAndrew Rist *
13449ab281SAndrew Rist * Unless required by applicable law or agreed to in writing,
14449ab281SAndrew Rist * software distributed under the License is distributed on an
15449ab281SAndrew Rist * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
16449ab281SAndrew Rist * KIND, either express or implied. See the License for the
17449ab281SAndrew Rist * specific language governing permissions and limitations
18449ab281SAndrew Rist * under the License.
19449ab281SAndrew Rist *
20449ab281SAndrew Rist *************************************************************/
21449ab281SAndrew Rist
22449ab281SAndrew Rist
23cdf0e10cSrcweir
24cdf0e10cSrcweir // MARKER(update_precomp.py): autogen include statement, do not remove
25cdf0e10cSrcweir #include "precompiled_i18npool.hxx"
26cdf0e10cSrcweir #include <rtl/ustring.hxx>
27cdf0e10cSrcweir #include <rtl/string.hxx>
28cdf0e10cSrcweir #include <rtl/ustrbuf.hxx>
29cdf0e10cSrcweir #include <rtl/strbuf.hxx>
30cdf0e10cSrcweir
31cdf0e10cSrcweir #include "i18npool/mslangid.hxx"
32cdf0e10cSrcweir
33cdf0e10cSrcweir // =======================================================================
34cdf0e10cSrcweir
35cdf0e10cSrcweir struct IsoLangEngEntry
36cdf0e10cSrcweir {
37cdf0e10cSrcweir LanguageType mnLang;
38cdf0e10cSrcweir sal_Char maCountry[3];
39cdf0e10cSrcweir };
40cdf0e10cSrcweir
41cdf0e10cSrcweir struct IsoLangNoneStdEntry
42cdf0e10cSrcweir {
43cdf0e10cSrcweir LanguageType mnLang;
44cdf0e10cSrcweir sal_Char maLangStr[4];
45cdf0e10cSrcweir sal_Char maCountry[9];
46cdf0e10cSrcweir };
47cdf0e10cSrcweir
48cdf0e10cSrcweir struct IsoLangOtherEntry
49cdf0e10cSrcweir {
50cdf0e10cSrcweir LanguageType mnLang;
51cdf0e10cSrcweir const sal_Char* mpLangStr;
52cdf0e10cSrcweir };
53cdf0e10cSrcweir
54cdf0e10cSrcweir // -----------------------------------------------------------------------
55cdf0e10cSrcweir
56cdf0e10cSrcweir // Entries for languages are lower case, for countries upper case, as
57cdf0e10cSrcweir // recommended by rfc4646 (obsoletes rfc3066 (obsoletes rfc1766)).
58cdf0e10cSrcweir // convertIsoNamesToLanguage() is case insensitive
59cdf0e10cSrcweir //
60cdf0e10cSrcweir // Sort order: Most used first.
61cdf0e10cSrcweir //
62cdf0e10cSrcweir // The default entry for a LangID <-> ISO mapping has to be first. For
63cdf0e10cSrcweir // conversion of legacy mappings one LangID can map to multiple ISO codes, and
64cdf0e10cSrcweir // one ISO code combination can map to multiple LangIDs. For compatibility with
65cdf0e10cSrcweir // already existing calls it can also be a sequence as follows:
66cdf0e10cSrcweir
67cdf0e10cSrcweir // LANGUAGE_ENGLISH, "en", ""
68cdf0e10cSrcweir // LANGUAGE_ENGLISH_US, "en", "US"
69cdf0e10cSrcweir
70cdf0e10cSrcweir // Here, in a convertIsoNamesToLanguage() call "en-US" is converted to
71cdf0e10cSrcweir // LANGUAGE_ENGLISH_US and "en" is converted to LANGUAGE_ENGLISH. A call with
72cdf0e10cSrcweir // "en-ZZ" (not in table) would result in LANGUAGE_ENGLISH because the first
73cdf0e10cSrcweir // entry matching the language and not having a country is returned, regardless
74cdf0e10cSrcweir // of whether being sorted before or after other entries of the same language
75cdf0e10cSrcweir // with some country. To obtain a _locale_ (not language only) in the order
76cdf0e10cSrcweir // given, convertLocaleToLanguageWithFallback() must be called.
77cdf0e10cSrcweir
78cdf0e10cSrcweir // If the sequence instead was
79cdf0e10cSrcweir
80cdf0e10cSrcweir // LANGUAGE_ENGLISH_US, "en", "US"
81cdf0e10cSrcweir // LANGUAGE_ENGLISH, "en", ""
82cdf0e10cSrcweir
83cdf0e10cSrcweir // in a convertIsoNamesToLanguage() call "en-US" is still converted to
84cdf0e10cSrcweir // LANGUAGE_ENGLISH_US, but "en" is _also_ converted to LANGUAGE_ENGLISH_US
85cdf0e10cSrcweir // because no country was passed and it is the first entry to match the
86cdf0e10cSrcweir // language, see code. A call with "en-ZZ" (not in table) would still result in
87cdf0e10cSrcweir // LANGUAGE_ENGLISH.
88cdf0e10cSrcweir
89cdf0e10cSrcweir /* erAck: 2007-07-05T20:01+0200 TODO: The entire suite's "primary language
90cdf0e10cSrcweir * only" usage and locale fall back should be cleaned up and made consistent. I
91cdf0e10cSrcweir * strongly doubt that most callers exactly expect the behavior described.
92cdf0e10cSrcweir * Currently these primary LangIDs are used literally in OOo code:
93cdf0e10cSrcweir * LANGUAGE_ENGLISH LANGUAGE_CHINESE LANGUAGE_MALAY
94cdf0e10cSrcweir * LANGUAGE_AZERI LANGUAGE_URDU LANGUAGE_KASHMIRI
95cdf0e10cSrcweir */
96cdf0e10cSrcweir
97cdf0e10cSrcweir static MsLangId::IsoLangEntry const aImplIsoLangEntries[] =
98cdf0e10cSrcweir {
99cdf0e10cSrcweir // MS-LANGID codes ISO639-1/2/3 ISO3166
100cdf0e10cSrcweir { LANGUAGE_ENGLISH, "en", "" },
101cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "en", "US" },
102cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "en", "GB" },
103cdf0e10cSrcweir { LANGUAGE_ENGLISH_AUS, "en", "AU" },
104cdf0e10cSrcweir { LANGUAGE_ENGLISH_CAN, "en", "CA" },
105cdf0e10cSrcweir { LANGUAGE_FRENCH, "fr", "FR" },
106cdf0e10cSrcweir { LANGUAGE_FRENCH, "fr", "" },
107cdf0e10cSrcweir { LANGUAGE_GERMAN, "de", "DE" },
108cdf0e10cSrcweir { LANGUAGE_ITALIAN, "it", "IT" },
109cdf0e10cSrcweir { LANGUAGE_DUTCH, "nl", "NL" },
110cdf0e10cSrcweir { LANGUAGE_SPANISH_MODERN, "es", "ES" },
111cdf0e10cSrcweir { LANGUAGE_SPANISH_DATED, "es", "ES" },
112cdf0e10cSrcweir { LANGUAGE_PORTUGUESE, "pt", "PT" },
113cdf0e10cSrcweir { LANGUAGE_PORTUGUESE_BRAZILIAN, "pt", "BR" },
114cdf0e10cSrcweir { LANGUAGE_DANISH, "da", "DK" },
115cdf0e10cSrcweir { LANGUAGE_GREEK, "el", "GR" },
116cdf0e10cSrcweir { LANGUAGE_CHINESE, "zh", "" },
117cdf0e10cSrcweir { LANGUAGE_CHINESE_SIMPLIFIED, "zh", "CN" },
118cdf0e10cSrcweir { LANGUAGE_CHINESE_TRADITIONAL, "zh", "TW" },
119cdf0e10cSrcweir { LANGUAGE_CHINESE_HONGKONG, "zh", "HK" },
120cdf0e10cSrcweir { LANGUAGE_CHINESE_SINGAPORE, "zh", "SG" },
121cdf0e10cSrcweir { LANGUAGE_CHINESE_MACAU, "zh", "MO" },
122cdf0e10cSrcweir { LANGUAGE_ENGLISH_HONG_KONG_SAR, "en", "HK" },
123cdf0e10cSrcweir { LANGUAGE_JAPANESE, "ja", "JP" },
124cdf0e10cSrcweir { LANGUAGE_KOREAN, "ko", "KR" },
125cdf0e10cSrcweir { LANGUAGE_KOREAN_JOHAB, "ko", "KR" },
126cdf0e10cSrcweir { LANGUAGE_USER_KOREAN_NORTH, "ko", "KP" },
127cdf0e10cSrcweir { LANGUAGE_SWEDISH, "sv", "SE" },
128cdf0e10cSrcweir { LANGUAGE_SWEDISH_FINLAND, "sv", "FI" },
129cdf0e10cSrcweir { LANGUAGE_FINNISH, "fi", "FI" },
130cdf0e10cSrcweir { LANGUAGE_RUSSIAN, "ru", "RU" },
131cdf0e10cSrcweir { LANGUAGE_TATAR, "tt", "RU" },
132cdf0e10cSrcweir { LANGUAGE_ENGLISH_NZ, "en", "NZ" },
133cdf0e10cSrcweir { LANGUAGE_ENGLISH_EIRE, "en", "IE" },
134cdf0e10cSrcweir { LANGUAGE_DUTCH_BELGIAN, "nl", "BE" },
135cdf0e10cSrcweir { LANGUAGE_FRENCH_BELGIAN, "fr", "BE" },
136cdf0e10cSrcweir { LANGUAGE_FRENCH_CANADIAN, "fr", "CA" },
137cdf0e10cSrcweir { LANGUAGE_FRENCH_SWISS, "fr", "CH" },
138cdf0e10cSrcweir { LANGUAGE_GERMAN_SWISS, "de", "CH" },
139cdf0e10cSrcweir { LANGUAGE_GERMAN_AUSTRIAN, "de", "AT" },
140cdf0e10cSrcweir { LANGUAGE_ITALIAN_SWISS, "it", "CH" },
141cdf0e10cSrcweir { LANGUAGE_ALBANIAN, "sq", "AL" },
142cdf0e10cSrcweir { LANGUAGE_ARABIC_SAUDI_ARABIA, "ar", "SA" },
143cdf0e10cSrcweir { LANGUAGE_ARABIC_EGYPT, "ar", "EG" },
144cdf0e10cSrcweir { LANGUAGE_ARABIC_UAE, "ar", "AE" },
145cdf0e10cSrcweir { LANGUAGE_ARABIC_IRAQ, "ar", "IQ" },
146cdf0e10cSrcweir { LANGUAGE_ARABIC_LIBYA, "ar", "LY" },
147cdf0e10cSrcweir { LANGUAGE_ARABIC_ALGERIA, "ar", "DZ" },
148cdf0e10cSrcweir { LANGUAGE_ARABIC_MOROCCO, "ar", "MA" },
149cdf0e10cSrcweir { LANGUAGE_ARABIC_TUNISIA, "ar", "TN" },
150cdf0e10cSrcweir { LANGUAGE_ARABIC_OMAN, "ar", "OM" },
151cdf0e10cSrcweir { LANGUAGE_ARABIC_YEMEN, "ar", "YE" },
152cdf0e10cSrcweir { LANGUAGE_ARABIC_SYRIA, "ar", "SY" },
153cdf0e10cSrcweir { LANGUAGE_ARABIC_JORDAN, "ar", "JO" },
154cdf0e10cSrcweir { LANGUAGE_ARABIC_LEBANON, "ar", "LB" },
155cdf0e10cSrcweir { LANGUAGE_ARABIC_KUWAIT, "ar", "KW" },
156cdf0e10cSrcweir { LANGUAGE_ARABIC_BAHRAIN, "ar", "BH" },
157cdf0e10cSrcweir { LANGUAGE_ARABIC_QATAR, "ar", "QA" },
158cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_CHAD, "ar", "TD" },
159cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_COMOROS, "ar", "KM" },
160cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_DJIBOUTI, "ar", "DJ" },
161cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_ERITREA, "ar", "ER" },
162cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_ISRAEL, "ar", "IL" },
163cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_MAURITANIA, "ar", "MR" },
164cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_PALESTINE, "ar", "PS" },
165cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_SOMALIA, "ar", "SO" },
166cdf0e10cSrcweir { LANGUAGE_USER_ARABIC_SUDAN, "ar", "SD" },
167cdf0e10cSrcweir { LANGUAGE_ARABIC_PRIMARY_ONLY, "ar", "" },
168cdf0e10cSrcweir { LANGUAGE_BASQUE, "eu", "" },
169cdf0e10cSrcweir { LANGUAGE_BULGARIAN, "bg", "BG" },
170cdf0e10cSrcweir { LANGUAGE_CZECH, "cs", "CZ" },
171cdf0e10cSrcweir { LANGUAGE_CZECH, "cz", "" },
172cdf0e10cSrcweir { LANGUAGE_ENGLISH_JAMAICA, "en", "JM" },
173cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "en", "BS" }, // not 100%, because AG is Bahamas
174cdf0e10cSrcweir { LANGUAGE_ENGLISH_BELIZE, "en", "BZ" },
175cdf0e10cSrcweir { LANGUAGE_ENGLISH_TRINIDAD, "en", "TT" },
176cdf0e10cSrcweir { LANGUAGE_ENGLISH_ZIMBABWE, "en", "ZW" },
177cdf0e10cSrcweir { LANGUAGE_ENGLISH_INDONESIA, "en", "ID" },
178cdf0e10cSrcweir { LANGUAGE_ESTONIAN, "et", "EE" },
179cdf0e10cSrcweir { LANGUAGE_FAEROESE, "fo", "FO" },
180cdf0e10cSrcweir { LANGUAGE_FARSI, "fa", "IR" },
181cdf0e10cSrcweir { LANGUAGE_FRENCH_LUXEMBOURG, "fr", "LU" },
182cdf0e10cSrcweir { LANGUAGE_FRENCH_MONACO, "fr", "MC" },
183cdf0e10cSrcweir { LANGUAGE_GERMAN_LUXEMBOURG, "de", "LU" },
184cdf0e10cSrcweir { LANGUAGE_GERMAN_LIECHTENSTEIN, "de", "LI" },
185cdf0e10cSrcweir { LANGUAGE_HEBREW, "he", "IL" }, // new: old was "iw"
186cdf0e10cSrcweir { LANGUAGE_HEBREW, "iw", "IL" }, // old: new is "he"
187cdf0e10cSrcweir { LANGUAGE_HUNGARIAN, "hu", "HU" },
188cdf0e10cSrcweir { LANGUAGE_ICELANDIC, "is", "IS" },
189cdf0e10cSrcweir { LANGUAGE_INDONESIAN, "id", "ID" }, // new: old was "in"
190cdf0e10cSrcweir { LANGUAGE_INDONESIAN, "in", "ID" }, // old: new is "id"
191cdf0e10cSrcweir { LANGUAGE_NORWEGIAN, "no", "NO" },
192cdf0e10cSrcweir { LANGUAGE_NORWEGIAN_BOKMAL, "nb", "NO" },
193cdf0e10cSrcweir { LANGUAGE_NORWEGIAN_NYNORSK, "nn", "NO" },
194cdf0e10cSrcweir { LANGUAGE_POLISH, "pl", "PL" },
195cdf0e10cSrcweir { LANGUAGE_RHAETO_ROMAN, "rm", "CH" },
196cdf0e10cSrcweir { LANGUAGE_ROMANIAN, "ro", "RO" },
197cdf0e10cSrcweir { LANGUAGE_ROMANIAN_MOLDOVA, "ro", "MD" },
198cdf0e10cSrcweir { LANGUAGE_SLOVAK, "sk", "SK" },
199cdf0e10cSrcweir { LANGUAGE_SLOVENIAN, "sl", "SI" },
200cdf0e10cSrcweir { LANGUAGE_SPANISH_MEXICAN, "es", "MX" },
201cdf0e10cSrcweir { LANGUAGE_SPANISH_GUATEMALA, "es", "GT" },
202cdf0e10cSrcweir { LANGUAGE_SPANISH_COSTARICA, "es", "CR" },
203cdf0e10cSrcweir { LANGUAGE_SPANISH_PANAMA, "es", "PA" },
204cdf0e10cSrcweir { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC, "es", "DO" },
205cdf0e10cSrcweir { LANGUAGE_SPANISH_VENEZUELA, "es", "VE" },
206cdf0e10cSrcweir { LANGUAGE_SPANISH_COLOMBIA, "es", "CO" },
207cdf0e10cSrcweir { LANGUAGE_SPANISH_PERU, "es", "PE" },
208cdf0e10cSrcweir { LANGUAGE_SPANISH_ARGENTINA, "es", "AR" },
209cdf0e10cSrcweir { LANGUAGE_SPANISH_ECUADOR, "es", "EC" },
210cdf0e10cSrcweir { LANGUAGE_SPANISH_CHILE, "es", "CL" },
211cdf0e10cSrcweir { LANGUAGE_SPANISH_URUGUAY, "es", "UY" },
212cdf0e10cSrcweir { LANGUAGE_SPANISH_PARAGUAY, "es", "PY" },
213cdf0e10cSrcweir { LANGUAGE_SPANISH_BOLIVIA, "es", "BO" },
214cdf0e10cSrcweir { LANGUAGE_SPANISH_EL_SALVADOR, "es", "SV" },
215cdf0e10cSrcweir { LANGUAGE_SPANISH_HONDURAS, "es", "HN" },
216cdf0e10cSrcweir { LANGUAGE_SPANISH_NICARAGUA, "es", "NI" },
217cdf0e10cSrcweir { LANGUAGE_SPANISH_PUERTO_RICO, "es", "PR" },
218cdf0e10cSrcweir { LANGUAGE_SPANISH_UNITED_STATES, "es", "US" },
219cdf0e10cSrcweir { LANGUAGE_SPANISH_LATIN_AMERICA, "es", "" },
220cdf0e10cSrcweir { LANGUAGE_TURKISH, "tr", "TR" },
221cdf0e10cSrcweir { LANGUAGE_UKRAINIAN, "uk", "UA" },
222cdf0e10cSrcweir { LANGUAGE_VIETNAMESE, "vi", "VN" },
223cdf0e10cSrcweir { LANGUAGE_LATVIAN, "lv", "LV" },
224cdf0e10cSrcweir { LANGUAGE_MACEDONIAN, "mk", "MK" },
225cdf0e10cSrcweir { LANGUAGE_MALAY, "ms", "" },
226cdf0e10cSrcweir { LANGUAGE_MALAY_MALAYSIA, "ms", "MY" },
227cdf0e10cSrcweir { LANGUAGE_MALAY_BRUNEI_DARUSSALAM, "ms", "BN" },
228cdf0e10cSrcweir { LANGUAGE_ENGLISH_MALAYSIA, "en", "MY" },
229cdf0e10cSrcweir { LANGUAGE_THAI, "th", "TH" },
230cdf0e10cSrcweir { LANGUAGE_LITHUANIAN, "lt", "LT" },
231cdf0e10cSrcweir { LANGUAGE_LITHUANIAN_CLASSIC, "lt", "LT" },
232cdf0e10cSrcweir { LANGUAGE_CROATIAN, "hr", "HR" }, // Croatian in Croatia
233cdf0e10cSrcweir { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA" },
234cdf0e10cSrcweir { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA, "bs", "BA" },
235cdf0e10cSrcweir // { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_AND_HERZEGOVINA, "bs", "BA" }, // script codes not supported yet
236cdf0e10cSrcweir { LANGUAGE_USER_SERBIAN_CYRILLIC_SERBIA, "sr", "RS" }, // Serbian Cyrillic in Serbia
237cdf0e10cSrcweir { LANGUAGE_SERBIAN_CYRILLIC, "sr", "YU" }, // legacy Serbian Cyrillic in Serbia and Montenegro (former Yugoslavia); kludge, needed to be sr_CS instead, sr_CS not supported by ICU 2.6 (3.4 does)
238cdf0e10cSrcweir { LANGUAGE_SERBIAN_CYRILLIC, "sr", "CS" }, // alias to be able to integrate localizations, rsc needs it
239cdf0e10cSrcweir { LANGUAGE_USER_SERBIAN_CYRILLIC_MONTENEGRO, "sr", "ME" },
240cdf0e10cSrcweir { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA" },
241cdf0e10cSrcweir { LANGUAGE_SERBIAN, "sr", "" }, // SERBIAN is only LID, MS-LCID not defined (was dupe of CROATIAN)
242cdf0e10cSrcweir { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sh", "RS" }, // Serbian Latin in Serbia; kludge, needed to be sr_Latn_RS instead, script codes not supported yet
243cdf0e10cSrcweir { LANGUAGE_SERBIAN_LATIN, "sh", "YU" }, // legacy Serbian Latin in Serbia and Montenegro (former Yugoslavia); kludge, needed to be sr_Latn_CS instead, script codes not supported yet
244cdf0e10cSrcweir { LANGUAGE_SERBIAN_LATIN, "sh", "CS" }, // Serbian Latin in Serbia and Montenegro; kludge, needed to be sr_Latn_CS instead, script codes not supported yet
245cdf0e10cSrcweir { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sh", "ME" }, // Serbian Latin in Montenegro; kludge, needed to be sr_Latn_ME instead, script codes not supported yet
246cdf0e10cSrcweir { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA, "sh", "BA" },
247cdf0e10cSrcweir { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sh", "" }, // kludge, needed to be sr_Latn instead, script codes not supported yet
248cdf0e10cSrcweir { LANGUAGE_ARMENIAN, "hy", "AM" },
249cdf0e10cSrcweir { LANGUAGE_AZERI, "az", "" },
250cdf0e10cSrcweir { LANGUAGE_AZERI_LATIN, "az", "AZ" },
251cdf0e10cSrcweir // { LANGUAGE_AZERI_CYRILLIC, "az", "AZ" }, // script codes not supported yet
252cdf0e10cSrcweir { LANGUAGE_UZBEK_LATIN, "uz", "UZ" },
253cdf0e10cSrcweir // { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ" }, // script codes not supported yet
254cdf0e10cSrcweir { LANGUAGE_BENGALI_BANGLADESH, "bn", "BD" },
255cdf0e10cSrcweir { LANGUAGE_BENGALI, "bn", "IN" },
256cdf0e10cSrcweir { LANGUAGE_BURMESE, "my", "MM" },
257cdf0e10cSrcweir { LANGUAGE_KAZAK, "kk", "KZ" },
258cdf0e10cSrcweir { LANGUAGE_ENGLISH_INDIA, "en", "IN" },
259cdf0e10cSrcweir { LANGUAGE_URDU, "ur", "" },
260cdf0e10cSrcweir { LANGUAGE_URDU_INDIA, "ur", "IN" },
261cdf0e10cSrcweir { LANGUAGE_URDU_PAKISTAN, "ur", "PK" },
262cdf0e10cSrcweir { LANGUAGE_HINDI, "hi", "IN" },
263cdf0e10cSrcweir { LANGUAGE_GUJARATI, "gu", "IN" },
264cdf0e10cSrcweir { LANGUAGE_KANNADA, "kn", "IN" },
265cdf0e10cSrcweir { LANGUAGE_ASSAMESE, "as", "IN" },
266cdf0e10cSrcweir { LANGUAGE_KASHMIRI, "ks", "" },
267cdf0e10cSrcweir { LANGUAGE_KASHMIRI_INDIA, "ks", "IN" },
268cdf0e10cSrcweir { LANGUAGE_MALAYALAM, "ml", "IN" },
269cdf0e10cSrcweir { LANGUAGE_MANIPURI, "mni", "IN" },
270cdf0e10cSrcweir { LANGUAGE_MARATHI, "mr", "IN" },
271cdf0e10cSrcweir { LANGUAGE_KONKANI, "kok", "IN" },
272cdf0e10cSrcweir { LANGUAGE_NEPALI, "ne", "NP" },
273cdf0e10cSrcweir { LANGUAGE_NEPALI_INDIA, "ne", "IN" },
274cdf0e10cSrcweir { LANGUAGE_ORIYA, "or", "IN" },
275cdf0e10cSrcweir { LANGUAGE_PUNJABI, "pa", "IN" },
276cdf0e10cSrcweir { LANGUAGE_SANSKRIT, "sa", "IN" },
277cdf0e10cSrcweir { LANGUAGE_SINDHI, "sd", "IN" },
278cdf0e10cSrcweir { LANGUAGE_TAMIL, "ta", "IN" },
279cdf0e10cSrcweir { LANGUAGE_TELUGU, "te", "IN" },
280cdf0e10cSrcweir { LANGUAGE_PUNJABI_PAKISTAN, "lah", "PK" }, // preferring "lah" over "pa" for Western Punjabi, see http://www.ethnologue.com/show_language.asp?code=PNB
281cdf0e10cSrcweir { LANGUAGE_PUNJABI_PAKISTAN, "pa", "PK" },
282cdf0e10cSrcweir { LANGUAGE_SINDHI_PAKISTAN, "sd", "PK" },
283cdf0e10cSrcweir { LANGUAGE_BELARUSIAN, "be", "BY" },
284cdf0e10cSrcweir { LANGUAGE_CATALAN, "ca", "ES" }, // Spain (default)
285cdf0e10cSrcweir { LANGUAGE_CATALAN, "ca", "AD" }, // Andorra
286*df5bc930SJuergen Schmidt { LANGUAGE_USER_CATALAN_VALENCIAN_RACV, "ca", "XR" }, // XR: ISO ???? user-assigned; workaround for UI localization only, do not use in document content!
287*df5bc930SJuergen Schmidt { LANGUAGE_USER_CATALAN_VALENCIAN, "ca", "XV" }, // XV: ISO 3166 user-assigned; workaround for UI localization only, do not use in document content!
288cdf0e10cSrcweir { LANGUAGE_CATALAN, "qcv", "ES" }, // qcv: ISO 639-3 reserved-for-local-use; UI localization quirk only, do not use in document content!
289cdf0e10cSrcweir // { LANGUAGE_USER_CATALAN_VALENCIAN, "ca", "ES" }, // In case MS format files escaped into the wild, map them back.
290cdf0e10cSrcweir { LANGUAGE_FRENCH_CAMEROON, "fr", "CM" },
291cdf0e10cSrcweir { LANGUAGE_FRENCH_COTE_D_IVOIRE, "fr", "CI" },
292cdf0e10cSrcweir { LANGUAGE_FRENCH_MALI, "fr", "ML" },
293cdf0e10cSrcweir { LANGUAGE_FRENCH_SENEGAL, "fr", "SN" },
294cdf0e10cSrcweir { LANGUAGE_FRENCH_ZAIRE, "fr", "CD" }, // Democratic Republic Of Congo
295cdf0e10cSrcweir { LANGUAGE_FRENCH_MOROCCO, "fr", "MA" },
296cdf0e10cSrcweir { LANGUAGE_FRENCH_REUNION, "fr", "RE" },
297cdf0e10cSrcweir { LANGUAGE_FRENCH_NORTH_AFRICA, "fr", "" },
298cdf0e10cSrcweir { LANGUAGE_FRENCH_WEST_INDIES, "fr", "" }, // unknown ISO country code
299cdf0e10cSrcweir { LANGUAGE_FRISIAN_NETHERLANDS, "fy", "NL" },
300cdf0e10cSrcweir { LANGUAGE_GAELIC_IRELAND, "ga", "IE" },
301cdf0e10cSrcweir { LANGUAGE_GAELIC_SCOTLAND, "gd", "GB" },
302cdf0e10cSrcweir { LANGUAGE_GALICIAN, "gl", "ES" },
303cdf0e10cSrcweir { LANGUAGE_GEORGIAN, "ka", "GE" },
304cdf0e10cSrcweir { LANGUAGE_KHMER, "km", "KH" },
305cdf0e10cSrcweir { LANGUAGE_KIRGHIZ, "ky", "KG" },
306cdf0e10cSrcweir { LANGUAGE_LAO, "lo", "LA" },
307cdf0e10cSrcweir { LANGUAGE_MALTESE, "mt", "MT" },
308cdf0e10cSrcweir { LANGUAGE_MONGOLIAN, "mn", "MN" }, // Cyrillic script
309cdf0e10cSrcweir { LANGUAGE_MONGOLIAN_MONGOLIAN, "mn", "MN" },
310cdf0e10cSrcweir { LANGUAGE_RUSSIAN_MOLDOVA, "mo", "MD" },
311cdf0e10cSrcweir { LANGUAGE_SWAHILI, "sw", "KE" },
312cdf0e10cSrcweir { LANGUAGE_USER_SWAHILI_TANZANIA, "sw", "TZ" },
313cdf0e10cSrcweir { LANGUAGE_TAJIK, "tg", "TJ" },
314cdf0e10cSrcweir { LANGUAGE_TIBETAN, "bo", "CN" }, // CN politically correct?
315cdf0e10cSrcweir { LANGUAGE_DZONGKHA, "dz", "BT" },
316cdf0e10cSrcweir { LANGUAGE_TURKMEN, "tk", "TM" },
317cdf0e10cSrcweir { LANGUAGE_WELSH, "cy", "GB" },
318cdf0e10cSrcweir { LANGUAGE_SESOTHO, "st", "ZA" },
319cdf0e10cSrcweir { LANGUAGE_SEPEDI, "nso", "ZA" },
320cdf0e10cSrcweir { LANGUAGE_SEPEDI, "ns", "ZA" }, // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents
321cdf0e10cSrcweir { LANGUAGE_TSONGA, "ts", "ZA" },
322cdf0e10cSrcweir { LANGUAGE_TSWANA, "tn", "ZA" },
323cdf0e10cSrcweir { LANGUAGE_ENGLISH_SAFRICA, "en", "ZA" },
324cdf0e10cSrcweir { LANGUAGE_AFRIKAANS, "af", "ZA" },
325cdf0e10cSrcweir { LANGUAGE_VENDA, "ve", "ZA" }, // default 639-1
326cdf0e10cSrcweir { LANGUAGE_VENDA, "ven", "ZA" }, // 639-2 may have been used temporarily since 2004-07-23
327cdf0e10cSrcweir { LANGUAGE_XHOSA, "xh", "ZA" },
328cdf0e10cSrcweir { LANGUAGE_ZULU, "zu", "ZA" },
329cdf0e10cSrcweir { LANGUAGE_QUECHUA_ECUADOR, "qu", "EC" },
330cdf0e10cSrcweir { LANGUAGE_QUECHUA_PERU, "qu", "PE" },
331cdf0e10cSrcweir { LANGUAGE_QUECHUA_BOLIVIA, "qu", "BO" }, // macro: quh-BO, qul-BO
332cdf0e10cSrcweir { LANGUAGE_PASHTO, "ps", "AF" },
333cdf0e10cSrcweir { LANGUAGE_OROMO, "om", "ET" },
334cdf0e10cSrcweir { LANGUAGE_DHIVEHI, "dv", "MV" },
335cdf0e10cSrcweir { LANGUAGE_UIGHUR_CHINA, "ug", "CN" },
336cdf0e10cSrcweir { LANGUAGE_TIGRIGNA_ETHIOPIA, "ti", "ET" },
337cdf0e10cSrcweir { LANGUAGE_TIGRIGNA_ERITREA, "ti", "ER" },
338cdf0e10cSrcweir { LANGUAGE_AMHARIC_ETHIOPIA, "am", "ET" },
339cdf0e10cSrcweir { LANGUAGE_GUARANI_PARAGUAY, "gug", "PY" },
340cdf0e10cSrcweir { LANGUAGE_HAWAIIAN_UNITED_STATES, "haw", "US" },
341cdf0e10cSrcweir { LANGUAGE_EDO, "bin", "NG" },
342cdf0e10cSrcweir { LANGUAGE_FULFULDE_NIGERIA, "ff", "NG" },
343cdf0e10cSrcweir { LANGUAGE_HAUSA_NIGERIA, "ha", "NG" },
344cdf0e10cSrcweir { LANGUAGE_USER_HAUSA_GHANA, "ha", "GH" },
345cdf0e10cSrcweir { LANGUAGE_IGBO_NIGERIA, "ig", "NG" },
346cdf0e10cSrcweir { LANGUAGE_KANURI_NIGERIA, "kr", "NG" },
347cdf0e10cSrcweir { LANGUAGE_YORUBA, "yo", "NG" },
348cdf0e10cSrcweir { LANGUAGE_SOMALI, "so", "SO" },
349cdf0e10cSrcweir { LANGUAGE_PAPIAMENTU, "pap", "AN" },
350cdf0e10cSrcweir { LANGUAGE_USER_PAPIAMENTU_ARUBA, "pap", "AW" },
351cdf0e10cSrcweir { LANGUAGE_ENGLISH_SINGAPORE, "en", "SG" },
352cdf0e10cSrcweir { LANGUAGE_USER_YIDDISH_US, "yi", "US" },
353cdf0e10cSrcweir { LANGUAGE_YIDDISH, "yi", "IL" }, // new: old was "ji"
354cdf0e10cSrcweir { LANGUAGE_YIDDISH, "ji", "IL" }, // old: new is "yi"
355cdf0e10cSrcweir { LANGUAGE_SYRIAC, "syr", "TR" }, // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
356cdf0e10cSrcweir { LANGUAGE_SINHALESE_SRI_LANKA, "si", "LK" },
357cdf0e10cSrcweir { LANGUAGE_CHEROKEE_UNITED_STATES, "chr", "US" },
358cdf0e10cSrcweir { LANGUAGE_INUKTITUT_LATIN_CANADA, "iu", "CA" },
359cdf0e10cSrcweir // { LANGUAGE_INUKTITUT_SYLLABICS_CANADA, "iu", "CA" }, // script codes not supported yet
360cdf0e10cSrcweir { LANGUAGE_SAMI_NORTHERN_NORWAY, "se", "NO" },
361cdf0e10cSrcweir { LANGUAGE_SAMI_INARI, "smn", "FI" },
362cdf0e10cSrcweir { LANGUAGE_SAMI_LULE_NORWAY, "smj", "NO" },
363cdf0e10cSrcweir { LANGUAGE_SAMI_LULE_SWEDEN, "smj", "SE" },
364cdf0e10cSrcweir { LANGUAGE_SAMI_NORTHERN_FINLAND, "se", "FI" },
365cdf0e10cSrcweir { LANGUAGE_SAMI_NORTHERN_SWEDEN, "se", "SE" },
366cdf0e10cSrcweir { LANGUAGE_SAMI_SKOLT, "sms", "FI" },
367cdf0e10cSrcweir { LANGUAGE_SAMI_SOUTHERN_NORWAY, "sma", "NO" },
368cdf0e10cSrcweir { LANGUAGE_SAMI_SOUTHERN_SWEDEN, "sma", "SE" },
369cdf0e10cSrcweir { LANGUAGE_USER_SAMI_KILDIN_RUSSIA, "sjd", "RU" },
370cdf0e10cSrcweir { LANGUAGE_MAPUDUNGUN_CHILE, "arn", "CL" },
371cdf0e10cSrcweir { LANGUAGE_CORSICAN_FRANCE, "co", "FR" },
372cdf0e10cSrcweir { LANGUAGE_ALSATIAN_FRANCE, "gsw", "FR" }, // 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.
373cdf0e10cSrcweir { LANGUAGE_YAKUT_RUSSIA, "sah", "RU" },
374cdf0e10cSrcweir { LANGUAGE_MOHAWK_CANADA, "moh", "CA" },
375cdf0e10cSrcweir { LANGUAGE_BASHKIR_RUSSIA, "ba", "RU" },
376cdf0e10cSrcweir { LANGUAGE_KICHE_GUATEMALA, "qut", "GT" },
377cdf0e10cSrcweir { LANGUAGE_DARI_AFGHANISTAN, "gbz", "AF" },
378cdf0e10cSrcweir { LANGUAGE_WOLOF_SENEGAL, "wo", "SN" },
379cdf0e10cSrcweir { LANGUAGE_FILIPINO, "fil", "PH" },
380cdf0e10cSrcweir { LANGUAGE_USER_TAGALOG, "tl", "PH" },
381cdf0e10cSrcweir { LANGUAGE_ENGLISH_PHILIPPINES, "en", "PH" },
382cdf0e10cSrcweir // { LANGUAGE_IBIBIO_NIGERIA, "nic", "NG" }, // ISO "nic" is only a collective language code
383cdf0e10cSrcweir { LANGUAGE_YI, "ii", "CN" },
384cdf0e10cSrcweir // { LANGUAGE_TAMAZIGHT_LATIN, "ber", "" }, // ISO "ber" only collective!
385cdf0e10cSrcweir // { LANGUAGE_TAMAZIGHT_ARABIC, "ber", "" }, // ISO "ber" only collective!
386cdf0e10cSrcweir { LANGUAGE_LATIN, "la", "VA" },
387cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_LATIN, "la", "VA" },
388cdf0e10cSrcweir { LANGUAGE_USER_ESPERANTO, "eo", "" },
389cdf0e10cSrcweir { LANGUAGE_USER_INTERLINGUA, "ia", "" },
390cdf0e10cSrcweir { LANGUAGE_MAORI_NEW_ZEALAND, "mi", "NZ" },
391cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_MAORI, "mi", "NZ" },
392cdf0e10cSrcweir { LANGUAGE_KINYARWANDA_RWANDA, "rw", "RW" },
393cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_KINYARWANDA, "rw", "RW" },
394cdf0e10cSrcweir { LANGUAGE_UPPER_SORBIAN_GERMANY, "hsb", "DE" }, // 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
395cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE" },
396cdf0e10cSrcweir { LANGUAGE_LOWER_SORBIAN_GERMANY, "dsb", "DE" }, // 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
397cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE" },
398cdf0e10cSrcweir { LANGUAGE_OCCITAN_FRANCE, "oc", "FR" },
399cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_OCCITAN, "oc", "FR" },
400cdf0e10cSrcweir { LANGUAGE_USER_KURDISH_TURKEY, "ku", "TR" },
401cdf0e10cSrcweir { LANGUAGE_USER_KURDISH_SYRIA, "ku", "SY" },
402cdf0e10cSrcweir { LANGUAGE_USER_KURDISH_IRAQ, "ku", "IQ" },
403cdf0e10cSrcweir { LANGUAGE_USER_KURDISH_IRAN, "ku", "IR" },
404cdf0e10cSrcweir { LANGUAGE_USER_SARDINIAN, "sc", "IT" }, // macrolanguage code
405cdf0e10cSrcweir { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT" },
406cdf0e10cSrcweir { LANGUAGE_USER_SARDINIAN_GALLURESE, "sdn", "IT" },
407cdf0e10cSrcweir { LANGUAGE_USER_SARDINIAN_LOGUDORESE, "src", "IT" },
408cdf0e10cSrcweir { LANGUAGE_USER_SARDINIAN_SASSARESE, "sdc", "IT" },
409cdf0e10cSrcweir { LANGUAGE_BRETON_FRANCE, "br", "FR" },
410cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_BRETON, "br", "FR" },
411cdf0e10cSrcweir { LANGUAGE_KALAALLISUT_GREENLAND, "kl", "GL" },
412cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_KALAALLISUT, "kl", "GL" },
413cdf0e10cSrcweir { LANGUAGE_USER_SWAZI, "ss", "ZA" },
414cdf0e10cSrcweir { LANGUAGE_USER_NDEBELE_SOUTH, "nr", "ZA" },
415cdf0e10cSrcweir { LANGUAGE_USER_TSWANA_BOTSWANA, "tn", "BW" },
416cdf0e10cSrcweir { LANGUAGE_USER_MOORE, "mos", "BF" },
417cdf0e10cSrcweir { LANGUAGE_USER_BAMBARA, "bm", "ML" },
418cdf0e10cSrcweir { LANGUAGE_USER_AKAN, "ak", "GH" },
419cdf0e10cSrcweir { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG, "lb", "LU" },
420cdf0e10cSrcweir { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU" },
421cdf0e10cSrcweir { LANGUAGE_USER_FRIULIAN, "fur", "IT" },
422cdf0e10cSrcweir { LANGUAGE_USER_FIJIAN, "fj", "FJ" },
423cdf0e10cSrcweir { LANGUAGE_USER_AFRIKAANS_NAMIBIA, "af", "NA" },
424cdf0e10cSrcweir { LANGUAGE_USER_ENGLISH_NAMIBIA, "en", "NA" },
425cdf0e10cSrcweir { LANGUAGE_USER_WALLOON, "wa", "BE" },
426cdf0e10cSrcweir { LANGUAGE_USER_COPTIC, "cop", "EG" },
427cdf0e10cSrcweir { LANGUAGE_USER_GASCON, "gsc", "FR" },
428cdf0e10cSrcweir { LANGUAGE_USER_GERMAN_BELGIUM, "de", "BE" },
429cdf0e10cSrcweir { LANGUAGE_USER_CHUVASH, "cv", "RU" },
430cdf0e10cSrcweir { LANGUAGE_USER_EWE_GHANA, "ee", "GH" },
431cdf0e10cSrcweir { LANGUAGE_USER_ENGLISH_GHANA, "en", "GH" },
432cdf0e10cSrcweir { LANGUAGE_USER_SANGO, "sg", "CF" },
433cdf0e10cSrcweir { LANGUAGE_USER_GANDA, "lg", "UG" },
434cdf0e10cSrcweir { LANGUAGE_USER_LINGALA_DRCONGO, "ln", "CD" },
435cdf0e10cSrcweir { LANGUAGE_USER_LOW_GERMAN, "nds", "DE" },
436cdf0e10cSrcweir { LANGUAGE_USER_HILIGAYNON, "hil", "PH" },
437cdf0e10cSrcweir { LANGUAGE_USER_NYANJA, "ny", "MW" },
438cdf0e10cSrcweir { LANGUAGE_USER_KASHUBIAN, "csb", "PL" },
439cdf0e10cSrcweir { LANGUAGE_USER_SPANISH_CUBA, "es", "CU" },
440cdf0e10cSrcweir { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO" },
441cdf0e10cSrcweir { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO" },
442cdf0e10cSrcweir { LANGUAGE_USER_BODO_INDIA, "brx", "IN" },
443cdf0e10cSrcweir { LANGUAGE_USER_DOGRI_INDIA, "dgo", "IN" },
444cdf0e10cSrcweir { LANGUAGE_USER_MAITHILI_INDIA, "mai", "IN" },
445cdf0e10cSrcweir { LANGUAGE_USER_SANTALI_INDIA, "sat", "IN" },
446cdf0e10cSrcweir { LANGUAGE_USER_TETUN, "tet", "ID" },
447cdf0e10cSrcweir { LANGUAGE_USER_TETUN_TIMOR_LESTE, "tet", "TL" },
448cdf0e10cSrcweir { LANGUAGE_USER_TOK_PISIN, "tpi", "PG" },
449cdf0e10cSrcweir { LANGUAGE_USER_SHUSWAP, "shs", "CA" },
450cdf0e10cSrcweir { LANGUAGE_USER_ANCIENT_GREEK, "grc", "GR" },
451cdf0e10cSrcweir { LANGUAGE_USER_ASTURIAN, "ast", "ES" },
452cdf0e10cSrcweir { LANGUAGE_USER_LATGALIAN, "ltg", "LV" },
453cdf0e10cSrcweir { LANGUAGE_USER_MAORE, "swb", "YT" },
454cdf0e10cSrcweir { LANGUAGE_USER_BUSHI, "buc", "YT" },
455cdf0e10cSrcweir { LANGUAGE_USER_TAHITIAN, "ty", "PF" },
456cdf0e10cSrcweir { LANGUAGE_USER_MALAGASY_PLATEAU, "plt", "MG" },
457cdf0e10cSrcweir { LANGUAGE_USER_BAFIA, "ksf", "CM" },
458cdf0e10cSrcweir { LANGUAGE_USER_GIKUYU, "ki", "KE" },
459cdf0e10cSrcweir { LANGUAGE_USER_RUSYN_UKRAINE, "rue", "UA" },
460cdf0e10cSrcweir { LANGUAGE_USER_RUSYN_SLOVAKIA, "rue", "SK" },
461cdf0e10cSrcweir { LANGUAGE_USER_LIMBU, "lif", "NP" },
462cdf0e10cSrcweir { LANGUAGE_USER_LOJBAN, "jbo", "" },
463cdf0e10cSrcweir { LANGUAGE_USER_KABYLE, "kab", "DZ" },
464cdf0e10cSrcweir { LANGUAGE_USER_HAITIAN, "ht", "HT" },
465cdf0e10cSrcweir { LANGUAGE_FRENCH_HAITI, "fr", "HT" },
466cdf0e10cSrcweir { LANGUAGE_NONE, "zxx", "" }, // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information
467cdf0e10cSrcweir { LANGUAGE_DONTKNOW, "", "" } // marks end of table
468cdf0e10cSrcweir };
469cdf0e10cSrcweir
470cdf0e10cSrcweir static MsLangId::IsoLangEntry aLastResortFallbackEntry =
471cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "en", "US" };
472cdf0e10cSrcweir
473cdf0e10cSrcweir // -----------------------------------------------------------------------
474cdf0e10cSrcweir
475cdf0e10cSrcweir // In this table are the countries which should mapped to a specific
476cdf0e10cSrcweir // english language
477cdf0e10cSrcweir static IsoLangEngEntry const aImplIsoLangEngEntries[] =
478cdf0e10cSrcweir {
479cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "AO" }, // Angola
480cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "BJ" }, // Benin
481cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "BW" }, // Botswana
482cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "BI" }, // Burundi
483cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "CM" }, // Cameroon
484cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "GA" }, // Gabon
485cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "GM" }, // Gambia
486cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "GH" }, // Ghana
487cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "GN" }, // Guinea
488cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "LS" }, // Lesotho
489cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "MW" }, // Malawi
490cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "MT" }, // Malta
491cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "NA" }, // Namibia
492cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "NG" }, // Nigeria
493cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "UG" }, // Uganda
494cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "ZM" }, // Zambia
495cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "ZW" }, // Zimbabwe
496cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "SZ" }, // Swaziland
497cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "NG" }, // Sierra Leone
498cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "KN" }, // Saint Kitts and Nevis
499cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "SH" }, // St. Helena
500cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "IO" }, // British Indian Oceanic Territory
501cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "FK" }, // Falkland Islands
502cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "GI" }, // Gibraltar
503cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "KI" }, // Kiribati
504cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "VG" }, // Virgin Islands
505cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "MU" }, // Mauritius
506cdf0e10cSrcweir { LANGUAGE_ENGLISH_UK, "FJ" }, // Fiji
507cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "KI" }, // Kiribati
508cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "LR" }, // Liberia
509cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "GU" }, // Guam
510cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "MH" }, // Marshall Islands
511cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "PW" }, // Palau
512cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "AI" }, // Anguilla
513cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "AG" }, // Antigua and Barbuda
514cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "BS" }, // Bahamas
515cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "BB" }, // Barbedos
516cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "BM" }, // Bermuda
517cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "KY" }, // Cayman Islands
518cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "GD" }, // Grenada
519cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "DM" }, // Dominica
520cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "HT" }, // Haiti
521cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "MS" }, // Montserrat
522cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "FM" }, // Micronesia
523cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "VC" }, // St. Vincent / Grenadines
524cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "LC" }, // Saint Lucia
525cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "TC" }, // Turks & Caicos Islands
526cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "GY" }, // Guyana
527cdf0e10cSrcweir { LANGUAGE_ENGLISH_CARRIBEAN, "TT" }, // Trinidad and Tobago
528cdf0e10cSrcweir { LANGUAGE_ENGLISH_AUS, "CX" }, // Christmas Islands
529cdf0e10cSrcweir { LANGUAGE_ENGLISH_AUS, "CC" }, // Cocos (Keeling) Islands
530cdf0e10cSrcweir { LANGUAGE_ENGLISH_AUS, "NF" }, // Norfolk Island
531cdf0e10cSrcweir { LANGUAGE_ENGLISH_AUS, "PG" }, // Papua New Guinea
532cdf0e10cSrcweir { LANGUAGE_ENGLISH_AUS, "SB" }, // Solomon Islands
533cdf0e10cSrcweir { LANGUAGE_ENGLISH_AUS, "TV" }, // Tuvalu
534cdf0e10cSrcweir { LANGUAGE_ENGLISH_AUS, "NR" }, // Nauru
535cdf0e10cSrcweir { LANGUAGE_ENGLISH_NZ, "CK" }, // Cook Islands
536cdf0e10cSrcweir { LANGUAGE_ENGLISH_NZ, "NU" }, // Niue
537cdf0e10cSrcweir { LANGUAGE_ENGLISH_NZ, "TK" }, // Tokelau
538cdf0e10cSrcweir { LANGUAGE_ENGLISH_NZ, "TO" }, // Tonga
539cdf0e10cSrcweir { LANGUAGE_DONTKNOW, "" } // marks end of table
540cdf0e10cSrcweir };
541cdf0e10cSrcweir
542cdf0e10cSrcweir // -----------------------------------------------------------------------
543cdf0e10cSrcweir
544cdf0e10cSrcweir static IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries[] =
545cdf0e10cSrcweir {
546cdf0e10cSrcweir { LANGUAGE_NORWEGIAN_BOKMAL, "no", "BOK" }, // registered subtags for "no" in rfc1766
547cdf0e10cSrcweir { LANGUAGE_NORWEGIAN_NYNORSK, "no", "NYN" }, // registered subtags for "no" in rfc1766
548cdf0e10cSrcweir { LANGUAGE_SERBIAN_LATIN, "sr", "latin" },
549cdf0e10cSrcweir { LANGUAGE_SERBIAN_CYRILLIC, "sr", "cyrillic" },
550cdf0e10cSrcweir { LANGUAGE_AZERI_LATIN, "az", "latin" },
551cdf0e10cSrcweir { LANGUAGE_AZERI_CYRILLIC, "az", "cyrillic" },
552cdf0e10cSrcweir { LANGUAGE_DONTKNOW, "", "" } // marks end of table
553cdf0e10cSrcweir };
554cdf0e10cSrcweir
555cdf0e10cSrcweir // -----------------------------------------------------------------------
556cdf0e10cSrcweir
557cdf0e10cSrcweir // in this table are only names to find the best language
558cdf0e10cSrcweir static IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries2[] =
559cdf0e10cSrcweir {
560cdf0e10cSrcweir { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmaal" },
561cdf0e10cSrcweir { LANGUAGE_NORWEGIAN_BOKMAL, "no", "bokmal" },
562cdf0e10cSrcweir { LANGUAGE_NORWEGIAN_NYNORSK, "no", "nynorsk" },
563cdf0e10cSrcweir { LANGUAGE_DONTKNOW, "", "" } // marks end of table
564cdf0e10cSrcweir };
565cdf0e10cSrcweir
566cdf0e10cSrcweir // -----------------------------------------------------------------------
567cdf0e10cSrcweir
568cdf0e10cSrcweir // in this table are only names to find the best language
569cdf0e10cSrcweir static IsoLangOtherEntry const aImplOtherEntries[] =
570cdf0e10cSrcweir {
571cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "c" },
572cdf0e10cSrcweir { LANGUAGE_CHINESE, "chinese" },
573cdf0e10cSrcweir { LANGUAGE_GERMAN, "german" },
574cdf0e10cSrcweir { LANGUAGE_JAPANESE, "japanese" },
575cdf0e10cSrcweir { LANGUAGE_KOREAN, "korean" },
576cdf0e10cSrcweir { LANGUAGE_ENGLISH_US, "posix" },
577cdf0e10cSrcweir { LANGUAGE_CHINESE_TRADITIONAL, "tchinese" },
578cdf0e10cSrcweir { LANGUAGE_DONTKNOW, NULL } // marks end of table
579cdf0e10cSrcweir };
580cdf0e10cSrcweir
581cdf0e10cSrcweir // =======================================================================
582cdf0e10cSrcweir
583cdf0e10cSrcweir // static
convertLanguageToIsoNames(LanguageType nLang,rtl::OUString & rLangStr,rtl::OUString & rCountry)584cdf0e10cSrcweir void MsLangId::convertLanguageToIsoNames( LanguageType nLang,
585cdf0e10cSrcweir rtl::OUString& rLangStr, rtl::OUString& rCountry )
586cdf0e10cSrcweir {
587cdf0e10cSrcweir if ( nLang == LANGUAGE_SYSTEM )
588cdf0e10cSrcweir nLang = MsLangId::getSystemLanguage();
589cdf0e10cSrcweir
590cdf0e10cSrcweir // Search for LangID (in this table we find only defined ISO combinations)
591cdf0e10cSrcweir const IsoLangEntry* pEntry = aImplIsoLangEntries;
592cdf0e10cSrcweir do
593cdf0e10cSrcweir {
594cdf0e10cSrcweir if ( pEntry->mnLang == nLang )
595cdf0e10cSrcweir {
596cdf0e10cSrcweir rLangStr = rtl::OUString::createFromAscii( pEntry->maLangStr );
597cdf0e10cSrcweir rCountry = rtl::OUString::createFromAscii( pEntry->maCountry );
598cdf0e10cSrcweir return;
599cdf0e10cSrcweir }
600cdf0e10cSrcweir ++pEntry;
601cdf0e10cSrcweir }
602cdf0e10cSrcweir while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
603cdf0e10cSrcweir
604cdf0e10cSrcweir // Search for LangID if we didn't find a specific ISO combination.
605cdf0e10cSrcweir // All entries in this table are allowed for mime specifications,
606cdf0e10cSrcweir // but not defined ISO combinations.
607cdf0e10cSrcweir const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
608cdf0e10cSrcweir do
609cdf0e10cSrcweir {
610cdf0e10cSrcweir if ( pNoneStdEntry->mnLang == nLang )
611cdf0e10cSrcweir {
612cdf0e10cSrcweir rLangStr = rtl::OUString::createFromAscii( pNoneStdEntry->maLangStr );
613cdf0e10cSrcweir rCountry = rtl::OUString::createFromAscii( pNoneStdEntry->maCountry );
614cdf0e10cSrcweir return;
615cdf0e10cSrcweir }
616cdf0e10cSrcweir ++pNoneStdEntry;
617cdf0e10cSrcweir }
618cdf0e10cSrcweir while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
619cdf0e10cSrcweir
620cdf0e10cSrcweir // not found
621cdf0e10cSrcweir rLangStr = rtl::OUString();
622cdf0e10cSrcweir rCountry = rtl::OUString();
623cdf0e10cSrcweir }
624cdf0e10cSrcweir
625cdf0e10cSrcweir // -----------------------------------------------------------------------
626cdf0e10cSrcweir
627cdf0e10cSrcweir // static
convertLanguageToIsoNames(LanguageType nLang,rtl::OString & rLangStr,rtl::OString & rCountry)628cdf0e10cSrcweir void MsLangId::convertLanguageToIsoNames( LanguageType nLang,
629cdf0e10cSrcweir rtl::OString& rLangStr, rtl::OString& rCountry )
630cdf0e10cSrcweir {
631cdf0e10cSrcweir if ( nLang == LANGUAGE_SYSTEM )
632cdf0e10cSrcweir nLang = MsLangId::getSystemLanguage();
633cdf0e10cSrcweir
634cdf0e10cSrcweir // Search for LangID (in this table we find only defined ISO combinations)
635cdf0e10cSrcweir const IsoLangEntry* pEntry = aImplIsoLangEntries;
636cdf0e10cSrcweir do
637cdf0e10cSrcweir {
638cdf0e10cSrcweir if ( pEntry->mnLang == nLang )
639cdf0e10cSrcweir {
640cdf0e10cSrcweir rLangStr = rtl::OString( pEntry->maLangStr );
641cdf0e10cSrcweir rCountry = rtl::OString( pEntry->maCountry );
642cdf0e10cSrcweir return;
643cdf0e10cSrcweir }
644cdf0e10cSrcweir ++pEntry;
645cdf0e10cSrcweir }
646cdf0e10cSrcweir while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
647cdf0e10cSrcweir
648cdf0e10cSrcweir // Search for LangID if we didn't find a specific ISO combination.
649cdf0e10cSrcweir // All entries in this table are allowed for mime specifications,
650cdf0e10cSrcweir // but not defined ISO combinations.
651cdf0e10cSrcweir const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
652cdf0e10cSrcweir do
653cdf0e10cSrcweir {
654cdf0e10cSrcweir if ( pNoneStdEntry->mnLang == nLang )
655cdf0e10cSrcweir {
656cdf0e10cSrcweir rLangStr = rtl::OString( pNoneStdEntry->maLangStr );
657cdf0e10cSrcweir rCountry = rtl::OString( pNoneStdEntry->maCountry );
658cdf0e10cSrcweir return;
659cdf0e10cSrcweir }
660cdf0e10cSrcweir ++pNoneStdEntry;
661cdf0e10cSrcweir }
662cdf0e10cSrcweir while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
663cdf0e10cSrcweir
664cdf0e10cSrcweir // not found
665cdf0e10cSrcweir rLangStr = rtl::OString();
666cdf0e10cSrcweir rCountry = rtl::OString();
667cdf0e10cSrcweir }
668cdf0e10cSrcweir
669cdf0e10cSrcweir // -----------------------------------------------------------------------
670cdf0e10cSrcweir
lcl_lookupFallbackEntry(LanguageType nLang)671cdf0e10cSrcweir static const MsLangId::IsoLangEntry & lcl_lookupFallbackEntry( LanguageType nLang )
672cdf0e10cSrcweir {
673cdf0e10cSrcweir LanguageType nPrimary = MsLangId::getPrimaryLanguage( nLang);
674cdf0e10cSrcweir
675cdf0e10cSrcweir // Search for LangID and remember first lang-only.
676cdf0e10cSrcweir const MsLangId::IsoLangEntry* pFirstPrimary = NULL;
677cdf0e10cSrcweir const MsLangId::IsoLangEntry* pEntry = aImplIsoLangEntries;
678cdf0e10cSrcweir do
679cdf0e10cSrcweir {
680cdf0e10cSrcweir if (pEntry->mnLang == nLang)
681cdf0e10cSrcweir {
682cdf0e10cSrcweir if (*pEntry->maCountry)
683cdf0e10cSrcweir return *pEntry;
684cdf0e10cSrcweir switch (nLang)
685cdf0e10cSrcweir {
686cdf0e10cSrcweir // These are known to have no country assigned.
687cdf0e10cSrcweir case LANGUAGE_BASQUE:
688cdf0e10cSrcweir case LANGUAGE_USER_ESPERANTO:
689cdf0e10cSrcweir case LANGUAGE_USER_INTERLINGUA:
690cdf0e10cSrcweir case LANGUAGE_USER_LOJBAN:
691cdf0e10cSrcweir return *pEntry;
692cdf0e10cSrcweir default:
693cdf0e10cSrcweir ; // nothing
694cdf0e10cSrcweir }
695cdf0e10cSrcweir }
696cdf0e10cSrcweir if (!pFirstPrimary &&
697cdf0e10cSrcweir MsLangId::getPrimaryLanguage( pEntry->mnLang) == nPrimary)
698cdf0e10cSrcweir pFirstPrimary = pEntry;
699cdf0e10cSrcweir ++pEntry;
700cdf0e10cSrcweir }
701cdf0e10cSrcweir while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
702cdf0e10cSrcweir
703cdf0e10cSrcweir // Language not found at all => use default.
704cdf0e10cSrcweir if (!pFirstPrimary)
705cdf0e10cSrcweir return aLastResortFallbackEntry;
706cdf0e10cSrcweir
707cdf0e10cSrcweir // Search for first entry of primary language with any country.
708cdf0e10cSrcweir pEntry = pFirstPrimary;
709cdf0e10cSrcweir do
710cdf0e10cSrcweir {
711cdf0e10cSrcweir if (MsLangId::getPrimaryLanguage( pEntry->mnLang) == nLang)
712cdf0e10cSrcweir {
713cdf0e10cSrcweir if (*pEntry->maCountry)
714cdf0e10cSrcweir return *pEntry;
715cdf0e10cSrcweir }
716cdf0e10cSrcweir ++pEntry;
717cdf0e10cSrcweir }
718cdf0e10cSrcweir while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
719cdf0e10cSrcweir
720cdf0e10cSrcweir return aLastResortFallbackEntry;
721cdf0e10cSrcweir }
722cdf0e10cSrcweir
723cdf0e10cSrcweir // static
lookupFallbackLanguage(LanguageType nLang)724cdf0e10cSrcweir LanguageType MsLangId::lookupFallbackLanguage( LanguageType nLang )
725cdf0e10cSrcweir {
726cdf0e10cSrcweir return lcl_lookupFallbackEntry( nLang).mnLang;
727cdf0e10cSrcweir }
728cdf0e10cSrcweir
729cdf0e10cSrcweir
730cdf0e10cSrcweir // static
lookupFallbackLocale(LanguageType nLang)731cdf0e10cSrcweir ::com::sun::star::lang::Locale MsLangId::lookupFallbackLocale( LanguageType nLang )
732cdf0e10cSrcweir {
733cdf0e10cSrcweir const MsLangId::IsoLangEntry& rEntry = lcl_lookupFallbackEntry( nLang);
734cdf0e10cSrcweir return ::com::sun::star::lang::Locale(
735cdf0e10cSrcweir rtl::OUString::createFromAscii( rEntry.maLangStr),
736cdf0e10cSrcweir rtl::OUString::createFromAscii( rEntry.maCountry),
737cdf0e10cSrcweir rtl::OUString());
738cdf0e10cSrcweir }
739cdf0e10cSrcweir
740cdf0e10cSrcweir // -----------------------------------------------------------------------
741cdf0e10cSrcweir
lcl_lookupFallbackEntry(const::com::sun::star::lang::Locale & rLocale)742cdf0e10cSrcweir static const MsLangId::IsoLangEntry & lcl_lookupFallbackEntry(
743cdf0e10cSrcweir const ::com::sun::star::lang::Locale & rLocale )
744cdf0e10cSrcweir {
745cdf0e10cSrcweir // language is lower case in table
746cdf0e10cSrcweir rtl::OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
747cdf0e10cSrcweir // country is upper case in table
748cdf0e10cSrcweir rtl::OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
749cdf0e10cSrcweir sal_Int32 nCountryLen = aUpperCountry.getLength();
750cdf0e10cSrcweir
751cdf0e10cSrcweir // Search for locale and remember first lang-only.
752cdf0e10cSrcweir const MsLangId::IsoLangEntry* pFirstLang = NULL;
753cdf0e10cSrcweir const MsLangId::IsoLangEntry* pEntry = aImplIsoLangEntries;
754cdf0e10cSrcweir do
755cdf0e10cSrcweir {
756cdf0e10cSrcweir if (aLowerLang.equalsAscii( pEntry->maLangStr))
757cdf0e10cSrcweir {
758cdf0e10cSrcweir if (*pEntry->maCountry)
759cdf0e10cSrcweir {
760cdf0e10cSrcweir if (nCountryLen && aUpperCountry.equalsAscii( pEntry->maCountry))
761cdf0e10cSrcweir return *pEntry;
762cdf0e10cSrcweir }
763cdf0e10cSrcweir else
764cdf0e10cSrcweir {
765cdf0e10cSrcweir switch (pEntry->mnLang)
766cdf0e10cSrcweir {
767cdf0e10cSrcweir // These are known to have no country assigned.
768cdf0e10cSrcweir case LANGUAGE_BASQUE:
769cdf0e10cSrcweir case LANGUAGE_USER_ESPERANTO:
770cdf0e10cSrcweir case LANGUAGE_USER_INTERLINGUA:
771cdf0e10cSrcweir case LANGUAGE_USER_LOJBAN:
772cdf0e10cSrcweir return *pEntry;
773cdf0e10cSrcweir default:
774cdf0e10cSrcweir ; // nothing
775cdf0e10cSrcweir }
776cdf0e10cSrcweir }
777cdf0e10cSrcweir if (!pFirstLang)
778cdf0e10cSrcweir pFirstLang = pEntry;
779cdf0e10cSrcweir }
780cdf0e10cSrcweir ++pEntry;
781cdf0e10cSrcweir }
782cdf0e10cSrcweir while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
783cdf0e10cSrcweir
784cdf0e10cSrcweir // Language not found at all => use default.
785cdf0e10cSrcweir if (!pFirstLang)
786cdf0e10cSrcweir return aLastResortFallbackEntry;
787cdf0e10cSrcweir
788cdf0e10cSrcweir // Search for first entry of language with any country.
789cdf0e10cSrcweir pEntry = pFirstLang;
790cdf0e10cSrcweir do
791cdf0e10cSrcweir {
792cdf0e10cSrcweir if (aLowerLang.equalsAscii( pEntry->maLangStr))
793cdf0e10cSrcweir {
794cdf0e10cSrcweir if (*pEntry->maCountry)
795cdf0e10cSrcweir return *pEntry;
796cdf0e10cSrcweir }
797cdf0e10cSrcweir ++pEntry;
798cdf0e10cSrcweir }
799cdf0e10cSrcweir while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
800cdf0e10cSrcweir
801cdf0e10cSrcweir return aLastResortFallbackEntry;
802cdf0e10cSrcweir }
803cdf0e10cSrcweir
804cdf0e10cSrcweir // static
lookupFallbackLanguage(const::com::sun::star::lang::Locale & rLocale)805cdf0e10cSrcweir LanguageType MsLangId::lookupFallbackLanguage(
806cdf0e10cSrcweir const ::com::sun::star::lang::Locale & rLocale )
807cdf0e10cSrcweir {
808cdf0e10cSrcweir return lcl_lookupFallbackEntry( rLocale).mnLang;
809cdf0e10cSrcweir }
810cdf0e10cSrcweir
811cdf0e10cSrcweir
812cdf0e10cSrcweir // static
lookupFallbackLocale(const::com::sun::star::lang::Locale & rLocale)813cdf0e10cSrcweir ::com::sun::star::lang::Locale MsLangId::lookupFallbackLocale(
814cdf0e10cSrcweir const ::com::sun::star::lang::Locale & rLocale )
815cdf0e10cSrcweir {
816cdf0e10cSrcweir const MsLangId::IsoLangEntry& rEntry = lcl_lookupFallbackEntry( rLocale);
817cdf0e10cSrcweir return ::com::sun::star::lang::Locale(
818cdf0e10cSrcweir rtl::OUString::createFromAscii( rEntry.maLangStr),
819cdf0e10cSrcweir rtl::OUString::createFromAscii( rEntry.maCountry),
820cdf0e10cSrcweir rtl::OUString());
821cdf0e10cSrcweir }
822cdf0e10cSrcweir
823cdf0e10cSrcweir // -----------------------------------------------------------------------
824cdf0e10cSrcweir
825cdf0e10cSrcweir // static
convertLanguageToIsoString(LanguageType nLang,sal_Unicode cSep)826cdf0e10cSrcweir rtl::OUString MsLangId::convertLanguageToIsoString( LanguageType nLang,
827cdf0e10cSrcweir sal_Unicode cSep )
828cdf0e10cSrcweir {
829cdf0e10cSrcweir rtl::OUString aLangStr;
830cdf0e10cSrcweir rtl::OUString aCountry;
831cdf0e10cSrcweir convertLanguageToIsoNames( nLang, aLangStr, aCountry );
832cdf0e10cSrcweir if ( aCountry.getLength() )
833cdf0e10cSrcweir {
834cdf0e10cSrcweir rtl::OUStringBuffer aBuf( aLangStr);
835cdf0e10cSrcweir aBuf.append( cSep );
836cdf0e10cSrcweir aBuf.append( aCountry );
837cdf0e10cSrcweir return aBuf.makeStringAndClear();
838cdf0e10cSrcweir }
839cdf0e10cSrcweir else
840cdf0e10cSrcweir return aLangStr;
841cdf0e10cSrcweir }
842cdf0e10cSrcweir
843cdf0e10cSrcweir // -----------------------------------------------------------------------
844cdf0e10cSrcweir
845cdf0e10cSrcweir // static
convertLanguageToIsoByteString(LanguageType nLang,sal_Char cSep)846cdf0e10cSrcweir rtl::OString MsLangId::convertLanguageToIsoByteString( LanguageType nLang,
847cdf0e10cSrcweir sal_Char cSep )
848cdf0e10cSrcweir {
849cdf0e10cSrcweir rtl::OString aLangStr;
850cdf0e10cSrcweir rtl::OString aCountry;
851cdf0e10cSrcweir convertLanguageToIsoNames( nLang, aLangStr, aCountry );
852cdf0e10cSrcweir if ( aCountry.getLength() )
853cdf0e10cSrcweir {
854cdf0e10cSrcweir rtl::OStringBuffer aBuf( aLangStr);
855cdf0e10cSrcweir aBuf.append( cSep );
856cdf0e10cSrcweir aBuf.append( aCountry );
857cdf0e10cSrcweir return aBuf.makeStringAndClear();
858cdf0e10cSrcweir }
859cdf0e10cSrcweir return aLangStr;
860cdf0e10cSrcweir }
861cdf0e10cSrcweir
862cdf0e10cSrcweir // =======================================================================
863cdf0e10cSrcweir
864cdf0e10cSrcweir // static
convertIsoNamesToLanguage(const rtl::OUString & rLang,const rtl::OUString & rCountry)865cdf0e10cSrcweir LanguageType MsLangId::convertIsoNamesToLanguage( const rtl::OUString& rLang,
866cdf0e10cSrcweir const rtl::OUString& rCountry )
867cdf0e10cSrcweir {
868cdf0e10cSrcweir // language is lower case in table
869cdf0e10cSrcweir rtl::OUString aLowerLang = rLang.toAsciiLowerCase();
870cdf0e10cSrcweir // country is upper case in table
871cdf0e10cSrcweir rtl::OUString aUpperCountry = rCountry.toAsciiUpperCase();
872cdf0e10cSrcweir
873cdf0e10cSrcweir // first look for exact match
874cdf0e10cSrcweir const IsoLangEntry* pFirstLang = NULL;
875cdf0e10cSrcweir const IsoLangEntry* pEntry = aImplIsoLangEntries;
876cdf0e10cSrcweir do
877cdf0e10cSrcweir {
878cdf0e10cSrcweir if ( aLowerLang.equalsAscii( pEntry->maLangStr ) )
879cdf0e10cSrcweir {
880cdf0e10cSrcweir if ( !aUpperCountry.getLength() ||
881cdf0e10cSrcweir aUpperCountry.equalsAscii( pEntry->maCountry ) )
882cdf0e10cSrcweir return pEntry->mnLang;
883cdf0e10cSrcweir if ( !pFirstLang )
884cdf0e10cSrcweir pFirstLang = pEntry;
885cdf0e10cSrcweir else if ( !*pEntry->maCountry )
886cdf0e10cSrcweir pFirstLang = pEntry;
887cdf0e10cSrcweir }
888cdf0e10cSrcweir ++pEntry;
889cdf0e10cSrcweir }
890cdf0e10cSrcweir while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
891cdf0e10cSrcweir
892cdf0e10cSrcweir // some eng countries should be mapped to a specific english language
893cdf0e10cSrcweir if ( aLowerLang.equalsAscii( "en" ) )
894cdf0e10cSrcweir {
895cdf0e10cSrcweir const IsoLangEngEntry* pEngEntry = aImplIsoLangEngEntries;
896cdf0e10cSrcweir do
897cdf0e10cSrcweir {
898cdf0e10cSrcweir if ( aUpperCountry.equalsAscii( pEngEntry->maCountry ) )
899cdf0e10cSrcweir return pEngEntry->mnLang;
900cdf0e10cSrcweir ++pEngEntry;
901cdf0e10cSrcweir }
902cdf0e10cSrcweir while ( pEngEntry->mnLang != LANGUAGE_DONTKNOW );
903cdf0e10cSrcweir }
904cdf0e10cSrcweir
905cdf0e10cSrcweir // test for specific languages which are not used standard ISO 3166 codes
906cdf0e10cSrcweir const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
907cdf0e10cSrcweir do
908cdf0e10cSrcweir {
909cdf0e10cSrcweir if ( aLowerLang.equalsAscii( pNoneStdEntry->maLangStr ) )
910cdf0e10cSrcweir {
911cdf0e10cSrcweir // The countries in this table are not all in upper case
912cdf0e10cSrcweir if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
913cdf0e10cSrcweir return pNoneStdEntry->mnLang;
914cdf0e10cSrcweir }
915cdf0e10cSrcweir ++pNoneStdEntry;
916cdf0e10cSrcweir }
917cdf0e10cSrcweir while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
918cdf0e10cSrcweir pNoneStdEntry = aImplIsoNoneStdLangEntries2;
919cdf0e10cSrcweir do
920cdf0e10cSrcweir {
921cdf0e10cSrcweir if ( aLowerLang.equalsAscii( pNoneStdEntry->maLangStr ) )
922cdf0e10cSrcweir {
923cdf0e10cSrcweir // The countries in this table are not all in upper case
924cdf0e10cSrcweir if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
925cdf0e10cSrcweir return pNoneStdEntry->mnLang;
926cdf0e10cSrcweir }
927cdf0e10cSrcweir ++pNoneStdEntry;
928cdf0e10cSrcweir }
929cdf0e10cSrcweir while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
930cdf0e10cSrcweir
931cdf0e10cSrcweir // If the language is correct, than we return the default language
932cdf0e10cSrcweir if ( pFirstLang )
933cdf0e10cSrcweir return pFirstLang->mnLang;
934cdf0e10cSrcweir
935cdf0e10cSrcweir // if only the country is set, look for any entry matching the country
936cdf0e10cSrcweir // (to allow reading country and language in separate steps, in any order)
937cdf0e10cSrcweir if ( rCountry.getLength() && !rLang.getLength() )
938cdf0e10cSrcweir {
939cdf0e10cSrcweir const IsoLangEntry* pEntry2 = aImplIsoLangEntries;
940cdf0e10cSrcweir do
941cdf0e10cSrcweir {
942cdf0e10cSrcweir if ( aUpperCountry.equalsAscii( pEntry2->maCountry ) )
943cdf0e10cSrcweir return pEntry2->mnLang;
944cdf0e10cSrcweir ++pEntry2;
945cdf0e10cSrcweir }
946cdf0e10cSrcweir while ( pEntry2->mnLang != LANGUAGE_DONTKNOW );
947cdf0e10cSrcweir
948cdf0e10cSrcweir aLowerLang = aUpperCountry.toAsciiLowerCase();
949cdf0e10cSrcweir }
950cdf0e10cSrcweir
951cdf0e10cSrcweir // Now look for all other definitions, which are not standard
952cdf0e10cSrcweir const IsoLangOtherEntry* pOtherEntry = aImplOtherEntries;
953cdf0e10cSrcweir do
954cdf0e10cSrcweir {
955cdf0e10cSrcweir if ( aLowerLang.equalsAscii( pOtherEntry->mpLangStr ) )
956cdf0e10cSrcweir return pOtherEntry->mnLang;
957cdf0e10cSrcweir ++pOtherEntry;
958cdf0e10cSrcweir }
959cdf0e10cSrcweir while ( pOtherEntry->mnLang != LANGUAGE_DONTKNOW );
960cdf0e10cSrcweir
961cdf0e10cSrcweir return LANGUAGE_DONTKNOW;
962cdf0e10cSrcweir }
963cdf0e10cSrcweir
964cdf0e10cSrcweir // -----------------------------------------------------------------------
965cdf0e10cSrcweir
966cdf0e10cSrcweir // static
convertIsoNamesToLanguage(const rtl::OString & rLang,const rtl::OString & rCountry)967cdf0e10cSrcweir LanguageType MsLangId::convertIsoNamesToLanguage( const rtl::OString& rLang,
968cdf0e10cSrcweir const rtl::OString& rCountry )
969cdf0e10cSrcweir {
970cdf0e10cSrcweir rtl::OUString aLang = OStringToOUString( rLang, RTL_TEXTENCODING_ASCII_US);
971cdf0e10cSrcweir rtl::OUString aCountry = OStringToOUString( rCountry, RTL_TEXTENCODING_ASCII_US);
972cdf0e10cSrcweir return convertIsoNamesToLanguage( aLang, aCountry);
973cdf0e10cSrcweir }
974cdf0e10cSrcweir
975cdf0e10cSrcweir // -----------------------------------------------------------------------
976cdf0e10cSrcweir
977cdf0e10cSrcweir // static
convertIsoStringToLanguage(const rtl::OUString & rString,sal_Unicode cSep)978cdf0e10cSrcweir LanguageType MsLangId::convertIsoStringToLanguage(
979cdf0e10cSrcweir const rtl::OUString& rString, sal_Unicode cSep )
980cdf0e10cSrcweir {
981cdf0e10cSrcweir rtl::OUString aLang;
982cdf0e10cSrcweir rtl::OUString aCountry;
983cdf0e10cSrcweir sal_Int32 nSepPos = rString.indexOf( cSep );
984cdf0e10cSrcweir if ( nSepPos >= 0 )
985cdf0e10cSrcweir {
986cdf0e10cSrcweir aLang = rString.copy( 0, nSepPos );
987cdf0e10cSrcweir aCountry = rString.copy( nSepPos+1 );
988cdf0e10cSrcweir }
989cdf0e10cSrcweir else
990cdf0e10cSrcweir aLang = rString;
991cdf0e10cSrcweir
992cdf0e10cSrcweir return convertIsoNamesToLanguage( aLang, aCountry );
993cdf0e10cSrcweir }
994cdf0e10cSrcweir
995cdf0e10cSrcweir // -----------------------------------------------------------------------
996cdf0e10cSrcweir
997cdf0e10cSrcweir // static
convertIsoByteStringToLanguage(const rtl::OString & rString,sal_Char cSep)998cdf0e10cSrcweir LanguageType MsLangId::convertIsoByteStringToLanguage(
999cdf0e10cSrcweir const rtl::OString& rString, sal_Char cSep )
1000cdf0e10cSrcweir {
1001cdf0e10cSrcweir rtl::OString aLang;
1002cdf0e10cSrcweir rtl::OString aCountry;
1003cdf0e10cSrcweir sal_Int32 nSepPos = rString.indexOf( cSep );
1004cdf0e10cSrcweir if ( nSepPos >= 0 )
1005cdf0e10cSrcweir {
1006cdf0e10cSrcweir aLang = rString.copy( 0, nSepPos );
1007cdf0e10cSrcweir aCountry = rString.copy( nSepPos+1 );
1008cdf0e10cSrcweir }
1009cdf0e10cSrcweir else
1010cdf0e10cSrcweir aLang = rString;
1011cdf0e10cSrcweir
1012cdf0e10cSrcweir return convertIsoNamesToLanguage( aLang, aCountry );
1013cdf0e10cSrcweir }
1014cdf0e10cSrcweir
1015cdf0e10cSrcweir // -----------------------------------------------------------------------
1016cdf0e10cSrcweir
1017cdf0e10cSrcweir struct IsoLangGLIBCModifiersEntry
1018cdf0e10cSrcweir {
1019cdf0e10cSrcweir LanguageType mnLang;
1020cdf0e10cSrcweir sal_Char maLangStr[4];
1021cdf0e10cSrcweir sal_Char maCountry[3];
1022cdf0e10cSrcweir sal_Char maAtString[9];
1023cdf0e10cSrcweir };
1024cdf0e10cSrcweir
1025cdf0e10cSrcweir static IsoLangGLIBCModifiersEntry const aImplIsoLangGLIBCModifiersEntries[] =
1026cdf0e10cSrcweir {
1027cdf0e10cSrcweir // MS-LANGID codes ISO639-1/2/3 ISO3166 glibc modifier
1028cdf0e10cSrcweir { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs", "BA", "cyrillic" },
1029cdf0e10cSrcweir { LANGUAGE_USER_SERBIAN_LATIN_SERBIA, "sr", "RS", "latin" }, // Serbian Latin in Serbia
1030cdf0e10cSrcweir { LANGUAGE_SERBIAN_LATIN, "sr", "CS", "latin" }, // Serbian Latin in Serbia and Montenegro
1031cdf0e10cSrcweir { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO, "sr", "ME", "latin" }, // Serbian Latin in Montenegro
1032cdf0e10cSrcweir { LANGUAGE_SERBIAN_LATIN_NEUTRAL, "sr", "", "latin" },
1033cdf0e10cSrcweir { LANGUAGE_AZERI_CYRILLIC, "az", "AZ", "cyrillic" },
1034cdf0e10cSrcweir { LANGUAGE_UZBEK_CYRILLIC, "uz", "UZ", "cyrillic" },
1035cdf0e10cSrcweir { LANGUAGE_DONTKNOW, "", "", "" } // marks end of table
1036cdf0e10cSrcweir };
1037cdf0e10cSrcweir
1038cdf0e10cSrcweir // convert a unix locale string into LanguageType
1039cdf0e10cSrcweir
1040cdf0e10cSrcweir // static
convertUnxByteStringToLanguage(const rtl::OString & rString)1041cdf0e10cSrcweir LanguageType MsLangId::convertUnxByteStringToLanguage(
1042cdf0e10cSrcweir const rtl::OString& rString )
1043cdf0e10cSrcweir {
1044cdf0e10cSrcweir rtl::OString aLang;
1045cdf0e10cSrcweir rtl::OString aCountry;
1046cdf0e10cSrcweir rtl::OString aAtString;
1047cdf0e10cSrcweir
1048cdf0e10cSrcweir sal_Int32 nLangSepPos = rString.indexOf( (sal_Char)'_' );
1049cdf0e10cSrcweir sal_Int32 nCountrySepPos = rString.indexOf( (sal_Char)'.' );
1050cdf0e10cSrcweir sal_Int32 nAtPos = rString.indexOf( (sal_Char)'@' );
1051cdf0e10cSrcweir
1052cdf0e10cSrcweir if (nCountrySepPos < 0)
1053cdf0e10cSrcweir nCountrySepPos = nAtPos;
1054cdf0e10cSrcweir if (nCountrySepPos < 0)
1055cdf0e10cSrcweir nCountrySepPos = rString.getLength();
1056cdf0e10cSrcweir
1057cdf0e10cSrcweir if (nAtPos >= 0)
1058cdf0e10cSrcweir aAtString = rString.copy( nAtPos+1 );
1059cdf0e10cSrcweir
1060cdf0e10cSrcweir if ( ((nLangSepPos >= 0) && (nLangSepPos > nCountrySepPos))
1061cdf0e10cSrcweir || ((nLangSepPos < 0)) )
1062cdf0e10cSrcweir {
1063cdf0e10cSrcweir // eg. "el.sun_eu_greek", "tchinese", "es.ISO8859-15"
1064cdf0e10cSrcweir aLang = rString.copy( 0, nCountrySepPos );
1065cdf0e10cSrcweir }
1066cdf0e10cSrcweir else if ( nLangSepPos >= 0 )
1067cdf0e10cSrcweir {
1068cdf0e10cSrcweir // well formed iso names like "en_US.UTF-8", "sh_BA.ISO8859-2@bosnia"
1069cdf0e10cSrcweir aLang = rString.copy( 0, nLangSepPos );
1070cdf0e10cSrcweir aCountry = rString.copy( nLangSepPos+1, nCountrySepPos - nLangSepPos - 1);
1071cdf0e10cSrcweir }
1072cdf0e10cSrcweir
1073cdf0e10cSrcweir // if there is a glibc modifier, first look for exact match in modifier table
1074cdf0e10cSrcweir if (aAtString.getLength())
1075cdf0e10cSrcweir {
1076cdf0e10cSrcweir // language is lower case in table
1077cdf0e10cSrcweir rtl::OString aLowerLang = aLang.toAsciiLowerCase();
1078cdf0e10cSrcweir // country is upper case in table
1079cdf0e10cSrcweir rtl::OString aUpperCountry = aCountry.toAsciiUpperCase();
1080cdf0e10cSrcweir const IsoLangGLIBCModifiersEntry* pGLIBCModifiersEntry = aImplIsoLangGLIBCModifiersEntries;
1081cdf0e10cSrcweir do
1082cdf0e10cSrcweir {
1083cdf0e10cSrcweir if (( aLowerLang.equals( pGLIBCModifiersEntry->maLangStr ) ) &&
1084cdf0e10cSrcweir ( aAtString.equals( pGLIBCModifiersEntry->maAtString ) ))
1085cdf0e10cSrcweir {
1086cdf0e10cSrcweir if ( !aUpperCountry.getLength() ||
1087cdf0e10cSrcweir aUpperCountry.equals( pGLIBCModifiersEntry->maCountry ) )
1088cdf0e10cSrcweir {
1089cdf0e10cSrcweir return pGLIBCModifiersEntry->mnLang;
1090cdf0e10cSrcweir }
1091cdf0e10cSrcweir }
1092cdf0e10cSrcweir ++pGLIBCModifiersEntry;
1093cdf0e10cSrcweir }
1094cdf0e10cSrcweir while ( pGLIBCModifiersEntry->mnLang != LANGUAGE_DONTKNOW );
1095cdf0e10cSrcweir }
1096cdf0e10cSrcweir
1097cdf0e10cSrcweir return convertIsoNamesToLanguage( aLang, aCountry );
1098cdf0e10cSrcweir }
1099cdf0e10cSrcweir
1100cdf0e10cSrcweir // -----------------------------------------------------------------------
1101cdf0e10cSrcweir // pass one IsoLangEntry to the outer world of the resource compiler
1102cdf0e10cSrcweir
1103cdf0e10cSrcweir // static
getIsoLangEntry(size_t nIndex)1104cdf0e10cSrcweir const MsLangId::IsoLangEntry* MsLangId::getIsoLangEntry( size_t nIndex )
1105cdf0e10cSrcweir {
1106cdf0e10cSrcweir if (nIndex < sizeof( aImplIsoLangEntries) / sizeof( IsoLangEntry))
1107cdf0e10cSrcweir return &aImplIsoLangEntries[ nIndex];
1108cdf0e10cSrcweir return 0;
1109cdf0e10cSrcweir }
1110