1 /**************************************************************
2  *
3  * Licensed to the Apache Software Foundation (ASF) under one
4  * or more contributor license agreements.  See the NOTICE file
5  * distributed with this work for additional information
6  * regarding copyright ownership.  The ASF licenses this file
7  * to you under the Apache License, Version 2.0 (the
8  * "License"); you may not use this file except in compliance
9  * with the License.  You may obtain a copy of the License at
10  *
11  *   http://www.apache.org/licenses/LICENSE-2.0
12  *
13  * Unless required by applicable law or agreed to in writing,
14  * software distributed under the License is distributed on an
15  * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
16  * KIND, either express or implied.  See the License for the
17  * specific language governing permissions and limitations
18  * under the License.
19  *
20  *************************************************************/
21 
22 
23 
24 // MARKER(update_precomp.py): autogen include statement, do not remove
25 #include "precompiled_i18npool.hxx"
26 #include <rtl/ustring.hxx>
27 #include <rtl/string.hxx>
28 #include <rtl/ustrbuf.hxx>
29 #include <rtl/strbuf.hxx>
30 
31 #include "i18npool/mslangid.hxx"
32 
33 // =======================================================================
34 
35 struct IsoLangEngEntry
36 {
37     LanguageType        mnLang;
38     sal_Char            maCountry[3];
39 };
40 
41 struct IsoLangNoneStdEntry
42 {
43     LanguageType        mnLang;
44     sal_Char            maLangStr[4];
45     sal_Char            maCountry[9];
46 };
47 
48 struct IsoLangOtherEntry
49 {
50     LanguageType        mnLang;
51     const sal_Char*     mpLangStr;
52 };
53 
54 // -----------------------------------------------------------------------
55 
56 // Entries for languages are lower case, for countries upper case, as
57 // recommended by rfc4646 (obsoletes rfc3066 (obsoletes rfc1766)).
58 // convertIsoNamesToLanguage() is case insensitive
59 //
60 // Sort order: Most used first.
61 //
62 // The default entry for a LangID <-> ISO mapping has to be first. For
63 // conversion of legacy mappings one LangID can map to multiple ISO codes, and
64 // one ISO code combination can map to multiple LangIDs. For compatibility with
65 // already existing calls it can also be a sequence as follows:
66 
67 // LANGUAGE_ENGLISH,    "en", ""
68 // LANGUAGE_ENGLISH_US, "en", "US"
69 
70 // Here, in a convertIsoNamesToLanguage() call "en-US" is converted to
71 // LANGUAGE_ENGLISH_US and "en" is converted to LANGUAGE_ENGLISH. A call with
72 // "en-ZZ" (not in table) would result in LANGUAGE_ENGLISH because the first
73 // entry matching the language and not having a country is returned, regardless
74 // of whether being sorted before or after other entries of the same language
75 // with some country. To obtain a _locale_ (not language only) in the order
76 // given, convertLocaleToLanguageWithFallback() must be called.
77 
78 // If the sequence instead was
79 
80 // LANGUAGE_ENGLISH_US, "en", "US"
81 // LANGUAGE_ENGLISH,    "en", ""
82 
83 // in a convertIsoNamesToLanguage() call "en-US" is still converted to
84 // LANGUAGE_ENGLISH_US, but "en" is _also_ converted to LANGUAGE_ENGLISH_US
85 // because no country was passed and it is the first entry to match the
86 // language, see code. A call with "en-ZZ" (not in table) would still result in
87 // LANGUAGE_ENGLISH.
88 
89 /* erAck: 2007-07-05T20:01+0200  TODO: The entire suite's "primary language
90  * only" usage and locale fall back should be cleaned up and made consistent. I
91  * strongly doubt that most callers exactly expect the behavior described.
92  * Currently these primary LangIDs are used literally in OOo code:
93  * LANGUAGE_ENGLISH LANGUAGE_CHINESE LANGUAGE_MALAY
94  * LANGUAGE_AZERI LANGUAGE_URDU LANGUAGE_KASHMIRI
95  */
96 
97 static MsLangId::IsoLangEntry const aImplIsoLangEntries[] =
98 {
99     // MS-LANGID codes               ISO639-1/2/3 ISO3166
100     { LANGUAGE_ENGLISH,                     "en", ""   },
101     { LANGUAGE_ENGLISH_US,                  "en", "US" },
102     { LANGUAGE_ENGLISH_UK,                  "en", "GB" },
103     { LANGUAGE_ENGLISH_AUS,                 "en", "AU" },
104     { LANGUAGE_ENGLISH_CAN,                 "en", "CA" },
105     { LANGUAGE_FRENCH,                      "fr", "FR" },
106     { LANGUAGE_FRENCH,                      "fr", ""   },
107     { LANGUAGE_GERMAN,                      "de", "DE" },
108     { LANGUAGE_ITALIAN,                     "it", "IT" },
109     { LANGUAGE_DUTCH,                       "nl", "NL" },
110     { LANGUAGE_SPANISH_MODERN,              "es", "ES" },
111     { LANGUAGE_SPANISH_DATED,               "es", "ES" },
112     { LANGUAGE_PORTUGUESE,                  "pt", "PT" },
113     { LANGUAGE_PORTUGUESE_BRAZILIAN,        "pt", "BR" },
114     { LANGUAGE_DANISH,                      "da", "DK" },
115     { LANGUAGE_GREEK,                       "el", "GR" },
116     { LANGUAGE_CHINESE,                     "zh", ""   },
117     { LANGUAGE_CHINESE_SIMPLIFIED,          "zh", "CN" },
118     { LANGUAGE_CHINESE_TRADITIONAL,         "zh", "TW" },
119     { LANGUAGE_CHINESE_HONGKONG,            "zh", "HK" },
120     { LANGUAGE_CHINESE_SINGAPORE,           "zh", "SG" },
121     { LANGUAGE_CHINESE_MACAU,               "zh", "MO" },
122     { LANGUAGE_ENGLISH_HONG_KONG_SAR,       "en", "HK" },
123     { LANGUAGE_JAPANESE,                    "ja", "JP" },
124     { LANGUAGE_KOREAN,                      "ko", "KR" },
125     { LANGUAGE_KOREAN_JOHAB,                "ko", "KR" },
126     { LANGUAGE_USER_KOREAN_NORTH,           "ko", "KP" },
127     { LANGUAGE_SWEDISH,                     "sv", "SE" },
128     { LANGUAGE_SWEDISH_FINLAND,             "sv", "FI" },
129     { LANGUAGE_FINNISH,                     "fi", "FI" },
130     { LANGUAGE_RUSSIAN,                     "ru", "RU" },
131     { LANGUAGE_TATAR,                       "tt", "RU" },
132     { LANGUAGE_ENGLISH_NZ,                  "en", "NZ" },
133     { LANGUAGE_ENGLISH_EIRE,                "en", "IE" },
134     { LANGUAGE_DUTCH_BELGIAN,               "nl", "BE" },
135     { LANGUAGE_FRENCH_BELGIAN,              "fr", "BE" },
136     { LANGUAGE_FRENCH_CANADIAN,             "fr", "CA" },
137     { LANGUAGE_FRENCH_SWISS,                "fr", "CH" },
138     { LANGUAGE_GERMAN_SWISS,                "de", "CH" },
139     { LANGUAGE_GERMAN_AUSTRIAN,             "de", "AT" },
140     { LANGUAGE_ITALIAN_SWISS,               "it", "CH" },
141     { LANGUAGE_ALBANIAN,                    "sq", "AL" },
142     { LANGUAGE_ARABIC_SAUDI_ARABIA,         "ar", "SA" },
143     { LANGUAGE_ARABIC_EGYPT,                "ar", "EG" },
144     { LANGUAGE_ARABIC_UAE,                  "ar", "AE" },
145     { LANGUAGE_ARABIC_IRAQ,                 "ar", "IQ" },
146     { LANGUAGE_ARABIC_LIBYA,                "ar", "LY" },
147     { LANGUAGE_ARABIC_ALGERIA,              "ar", "DZ" },
148     { LANGUAGE_ARABIC_MOROCCO,              "ar", "MA" },
149     { LANGUAGE_ARABIC_TUNISIA,              "ar", "TN" },
150     { LANGUAGE_ARABIC_OMAN,                 "ar", "OM" },
151     { LANGUAGE_ARABIC_YEMEN,                "ar", "YE" },
152     { LANGUAGE_ARABIC_SYRIA,                "ar", "SY" },
153     { LANGUAGE_ARABIC_JORDAN,               "ar", "JO" },
154     { LANGUAGE_ARABIC_LEBANON,              "ar", "LB" },
155     { LANGUAGE_ARABIC_KUWAIT,               "ar", "KW" },
156     { LANGUAGE_ARABIC_BAHRAIN,              "ar", "BH" },
157     { LANGUAGE_ARABIC_QATAR,                "ar", "QA" },
158     { LANGUAGE_USER_ARABIC_CHAD,            "ar", "TD" },
159     { LANGUAGE_USER_ARABIC_COMOROS,         "ar", "KM" },
160     { LANGUAGE_USER_ARABIC_DJIBOUTI,        "ar", "DJ" },
161     { LANGUAGE_USER_ARABIC_ERITREA,         "ar", "ER" },
162     { LANGUAGE_USER_ARABIC_ISRAEL,          "ar", "IL" },
163     { LANGUAGE_USER_ARABIC_MAURITANIA,      "ar", "MR" },
164     { LANGUAGE_USER_ARABIC_PALESTINE,       "ar", "PS" },
165     { LANGUAGE_USER_ARABIC_SOMALIA,         "ar", "SO" },
166     { LANGUAGE_USER_ARABIC_SUDAN,           "ar", "SD" },
167     { LANGUAGE_ARABIC_PRIMARY_ONLY,         "ar", ""   },
168     { LANGUAGE_BASQUE,                      "eu", ""   },
169     { LANGUAGE_BULGARIAN,                   "bg", "BG" },
170     { LANGUAGE_CZECH,                       "cs", "CZ" },
171     { LANGUAGE_CZECH,                       "cz", ""   },
172     { LANGUAGE_ENGLISH_JAMAICA,             "en", "JM" },
173     { LANGUAGE_ENGLISH_CARRIBEAN,           "en", "BS" },   // not 100%, because AG is Bahamas
174     { LANGUAGE_ENGLISH_BELIZE,              "en", "BZ" },
175     { LANGUAGE_ENGLISH_TRINIDAD,            "en", "TT" },
176     { LANGUAGE_ENGLISH_ZIMBABWE,            "en", "ZW" },
177     { LANGUAGE_ENGLISH_INDONESIA,           "en", "ID" },
178     { LANGUAGE_ESTONIAN,                    "et", "EE" },
179     { LANGUAGE_FAEROESE,                    "fo", "FO" },
180     { LANGUAGE_FARSI,                       "fa", "IR" },
181     { LANGUAGE_FRENCH_LUXEMBOURG,           "fr", "LU" },
182     { LANGUAGE_FRENCH_MONACO,               "fr", "MC" },
183     { LANGUAGE_GERMAN_LUXEMBOURG,           "de", "LU" },
184     { LANGUAGE_GERMAN_LIECHTENSTEIN,        "de", "LI" },
185     { LANGUAGE_HEBREW,                      "he", "IL" },   // new: old was "iw"
186     { LANGUAGE_HEBREW,                      "iw", "IL" },   // old: new is "he"
187     { LANGUAGE_HUNGARIAN,                   "hu", "HU" },
188     { LANGUAGE_ICELANDIC,                   "is", "IS" },
189     { LANGUAGE_INDONESIAN,                  "id", "ID" },   // new: old was "in"
190     { LANGUAGE_INDONESIAN,                  "in", "ID" },   // old: new is "id"
191     { LANGUAGE_NORWEGIAN,                   "no", "NO" },
192     { LANGUAGE_NORWEGIAN_BOKMAL,            "nb", "NO" },
193     { LANGUAGE_NORWEGIAN_NYNORSK,           "nn", "NO" },
194     { LANGUAGE_POLISH,                      "pl", "PL" },
195     { LANGUAGE_RHAETO_ROMAN,                "rm", "CH" },
196     { LANGUAGE_ROMANIAN,                    "ro", "RO" },
197     { LANGUAGE_ROMANIAN_MOLDOVA,            "ro", "MD" },
198     { LANGUAGE_SLOVAK,                      "sk", "SK" },
199     { LANGUAGE_SLOVENIAN,                   "sl", "SI" },
200     { LANGUAGE_SPANISH_MEXICAN,             "es", "MX" },
201     { LANGUAGE_SPANISH_GUATEMALA,           "es", "GT" },
202     { LANGUAGE_SPANISH_COSTARICA,           "es", "CR" },
203     { LANGUAGE_SPANISH_PANAMA,              "es", "PA" },
204     { LANGUAGE_SPANISH_DOMINICAN_REPUBLIC,  "es", "DO" },
205     { LANGUAGE_SPANISH_VENEZUELA,           "es", "VE" },
206     { LANGUAGE_SPANISH_COLOMBIA,            "es", "CO" },
207     { LANGUAGE_SPANISH_PERU,                "es", "PE" },
208     { LANGUAGE_SPANISH_ARGENTINA,           "es", "AR" },
209     { LANGUAGE_SPANISH_ECUADOR,             "es", "EC" },
210     { LANGUAGE_SPANISH_CHILE,               "es", "CL" },
211     { LANGUAGE_SPANISH_URUGUAY,             "es", "UY" },
212     { LANGUAGE_SPANISH_PARAGUAY,            "es", "PY" },
213     { LANGUAGE_SPANISH_BOLIVIA,             "es", "BO" },
214     { LANGUAGE_SPANISH_EL_SALVADOR,         "es", "SV" },
215     { LANGUAGE_SPANISH_HONDURAS,            "es", "HN" },
216     { LANGUAGE_SPANISH_NICARAGUA,           "es", "NI" },
217     { LANGUAGE_SPANISH_PUERTO_RICO,         "es", "PR" },
218     { LANGUAGE_SPANISH_UNITED_STATES,       "es", "US" },
219     { LANGUAGE_SPANISH_LATIN_AMERICA,       "es", ""   },
220     { LANGUAGE_TURKISH,                     "tr", "TR" },
221     { LANGUAGE_UKRAINIAN,                   "uk", "UA" },
222     { LANGUAGE_VIETNAMESE,                  "vi", "VN" },
223     { LANGUAGE_LATVIAN,                     "lv", "LV" },
224     { LANGUAGE_MACEDONIAN,                  "mk", "MK" },
225     { LANGUAGE_MALAY,                       "ms", ""   },
226     { LANGUAGE_MALAY_MALAYSIA,              "ms", "MY" },
227     { LANGUAGE_MALAY_BRUNEI_DARUSSALAM,     "ms", "BN" },
228     { LANGUAGE_ENGLISH_MALAYSIA,            "en", "MY" },
229     { LANGUAGE_THAI,                        "th", "TH" },
230     { LANGUAGE_LITHUANIAN,                  "lt", "LT" },
231     { LANGUAGE_LITHUANIAN_CLASSIC,          "lt", "LT" },
232     { LANGUAGE_CROATIAN,                    "hr", "HR" },   // Croatian in Croatia
233     { LANGUAGE_CROATIAN_BOSNIA_HERZEGOVINA, "hr", "BA" },
234     { LANGUAGE_BOSNIAN_LATIN_BOSNIA_HERZEGOVINA,        "bs", "BA" },
235 //  { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_AND_HERZEGOVINA, "bs", "BA" },   // script codes not supported yet
236     { LANGUAGE_USER_SERBIAN_CYRILLIC_SERBIA,        "sr", "RS" },   // Serbian Cyrillic in Serbia
237     { 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)
238     { LANGUAGE_SERBIAN_CYRILLIC,                    "sr", "CS" },   // alias to be able to integrate localizations, rsc needs it
239     { LANGUAGE_USER_SERBIAN_CYRILLIC_MONTENEGRO,    "sr", "ME" },
240     { LANGUAGE_SERBIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "sr", "BA" },
241     { LANGUAGE_SERBIAN,                             "sr", ""   },   // SERBIAN is only LID, MS-LCID not defined (was dupe of CROATIAN)
242     { LANGUAGE_USER_SERBIAN_LATIN_SERBIA,           "sh", "RS" },   // Serbian Latin in Serbia; kludge, needed to be sr_Latn_RS instead, script codes not supported yet
243     { 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
244     { LANGUAGE_SERBIAN_LATIN,                       "sh", "CS" },   // Serbian Latin in Serbia and Montenegro; kludge, needed to be sr_Latn_CS instead, script codes not supported yet
245     { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO,       "sh", "ME" },   // Serbian Latin in Montenegro; kludge, needed to be sr_Latn_ME instead, script codes not supported yet
246     { LANGUAGE_SERBIAN_LATIN_BOSNIA_HERZEGOVINA,    "sh", "BA" },
247     { LANGUAGE_SERBIAN_LATIN_NEUTRAL,               "sh", ""   },   // kludge, needed to be sr_Latn instead, script codes not supported yet
248     { LANGUAGE_ARMENIAN,                    "hy", "AM" },
249     { LANGUAGE_AZERI,                       "az", ""   },
250     { LANGUAGE_AZERI_LATIN,                 "az", "AZ" },
251 //  { LANGUAGE_AZERI_CYRILLIC,              "az", "AZ" },   // script codes not supported yet
252     { LANGUAGE_UZBEK_LATIN,                 "uz", "UZ" },
253 //  { LANGUAGE_UZBEK_CYRILLIC,              "uz", "UZ" },   // script codes not supported yet
254     { LANGUAGE_BENGALI_BANGLADESH,          "bn", "BD" },
255     { LANGUAGE_BENGALI,                     "bn", "IN" },
256     { LANGUAGE_BURMESE,                     "my", "MM" },
257     { LANGUAGE_KAZAK,                       "kk", "KZ" },
258     { LANGUAGE_ENGLISH_INDIA,               "en", "IN" },
259     { LANGUAGE_URDU,                        "ur", ""   },
260     { LANGUAGE_URDU_INDIA,                  "ur", "IN" },
261     { LANGUAGE_URDU_PAKISTAN,               "ur", "PK" },
262     { LANGUAGE_HINDI,                       "hi", "IN" },
263     { LANGUAGE_GUJARATI,                    "gu", "IN" },
264     { LANGUAGE_KANNADA,                     "kn", "IN" },
265     { LANGUAGE_ASSAMESE,                    "as", "IN" },
266     { LANGUAGE_KASHMIRI,                    "ks", ""   },
267     { LANGUAGE_KASHMIRI_INDIA,              "ks", "IN" },
268     { LANGUAGE_MALAYALAM,                   "ml", "IN" },
269     { LANGUAGE_MANIPURI,                   "mni", "IN" },
270     { LANGUAGE_MARATHI,                     "mr", "IN" },
271     { LANGUAGE_KONKANI,                    "kok", "IN" },
272     { LANGUAGE_NEPALI,                      "ne", "NP" },
273     { LANGUAGE_NEPALI_INDIA,                "ne", "IN" },
274     { LANGUAGE_ORIYA,                       "or", "IN" },
275     { LANGUAGE_PUNJABI,                     "pa", "IN" },
276     { LANGUAGE_SANSKRIT,                    "sa", "IN" },
277     { LANGUAGE_SINDHI,                      "sd", "IN" },
278     { LANGUAGE_TAMIL,                       "ta", "IN" },
279     { LANGUAGE_TELUGU,                      "te", "IN" },
280     { LANGUAGE_PUNJABI_PAKISTAN,           "lah", "PK" },   // preferring "lah" over "pa" for Western Punjabi, see http://www.ethnologue.com/show_language.asp?code=PNB
281     { LANGUAGE_PUNJABI_PAKISTAN,            "pa", "PK" },
282     { LANGUAGE_SINDHI_PAKISTAN,             "sd", "PK" },
283     { LANGUAGE_BELARUSIAN,                  "be", "BY" },
284     { LANGUAGE_CATALAN,                     "ca", "ES" },   // Spain (default)
285     { LANGUAGE_CATALAN,                     "ca", "AD" },   // Andorra
286     { LANGUAGE_USER_CATALAN_VALENCIAN_RACV, "ca", "XR" },   // XR: ISO ???? user-assigned; workaround for UI localization only, do not use in document content!
287     { LANGUAGE_USER_CATALAN_VALENCIAN,      "ca", "XV" },   // XV: ISO 3166 user-assigned; workaround for UI localization only, do not use in document content!
288     { LANGUAGE_CATALAN,                    "qcv", "ES" },   // qcv: ISO 639-3 reserved-for-local-use; UI localization quirk only, do not use in document content!
289 //    { LANGUAGE_USER_CATALAN_VALENCIAN,      "ca", "ES" },   // In case MS format files escaped into the wild, map them back.
290     { LANGUAGE_FRENCH_CAMEROON,             "fr", "CM" },
291     { LANGUAGE_FRENCH_COTE_D_IVOIRE,        "fr", "CI" },
292     { LANGUAGE_FRENCH_MALI,                 "fr", "ML" },
293     { LANGUAGE_FRENCH_SENEGAL,              "fr", "SN" },
294     { LANGUAGE_FRENCH_ZAIRE,                "fr", "CD" },   // Democratic Republic Of Congo
295     { LANGUAGE_FRENCH_MOROCCO,              "fr", "MA" },
296     { LANGUAGE_FRENCH_REUNION,              "fr", "RE" },
297     { LANGUAGE_FRENCH_NORTH_AFRICA,         "fr", ""   },
298     { LANGUAGE_FRENCH_WEST_INDIES,          "fr", ""   },   // unknown ISO country code
299     { LANGUAGE_FRISIAN_NETHERLANDS,         "fy", "NL" },
300     { LANGUAGE_GAELIC_IRELAND,              "ga", "IE" },
301     { LANGUAGE_GAELIC_SCOTLAND,             "gd", "GB" },
302     { LANGUAGE_GALICIAN,                    "gl", "ES" },
303     { LANGUAGE_GEORGIAN,                    "ka", "GE" },
304     { LANGUAGE_KHMER,                       "km", "KH" },
305     { LANGUAGE_KIRGHIZ,                     "ky", "KG" },
306     { LANGUAGE_LAO,                         "lo", "LA" },
307     { LANGUAGE_MALTESE,                     "mt", "MT" },
308     { LANGUAGE_MONGOLIAN,                   "mn", "MN" },   // Cyrillic script
309     { LANGUAGE_MONGOLIAN_MONGOLIAN,         "mn", "MN" },
310     { LANGUAGE_RUSSIAN_MOLDOVA,             "mo", "MD" },
311     { LANGUAGE_SWAHILI,                     "sw", "KE" },
312     { LANGUAGE_USER_SWAHILI_TANZANIA,       "sw", "TZ" },
313     { LANGUAGE_TAJIK,                       "tg", "TJ" },
314     { LANGUAGE_TIBETAN,                     "bo", "CN" },   // CN politically correct?
315     { LANGUAGE_DZONGKHA,                    "dz", "BT" },
316     { LANGUAGE_TURKMEN,                     "tk", "TM" },
317     { LANGUAGE_WELSH,                       "cy", "GB" },
318     { LANGUAGE_SESOTHO,                     "st", "ZA" },
319     { LANGUAGE_SEPEDI,                     "nso", "ZA" },
320     { LANGUAGE_SEPEDI,                      "ns", "ZA" },   // fake "ns" for compatibility with existing OOo1.1.x localization to be able to read those documents
321     { LANGUAGE_TSONGA,                      "ts", "ZA" },
322     { LANGUAGE_TSWANA,                      "tn", "ZA" },
323     { LANGUAGE_ENGLISH_SAFRICA,             "en", "ZA" },
324     { LANGUAGE_AFRIKAANS,                   "af", "ZA" },
325     { LANGUAGE_VENDA,                       "ve", "ZA" },   // default 639-1
326     { LANGUAGE_VENDA,                      "ven", "ZA" },   // 639-2 may have been used temporarily since 2004-07-23
327     { LANGUAGE_XHOSA,                       "xh", "ZA" },
328     { LANGUAGE_ZULU,                        "zu", "ZA" },
329     { LANGUAGE_QUECHUA_ECUADOR,             "qu", "EC" },
330     { LANGUAGE_QUECHUA_PERU,                "qu", "PE" },
331     { LANGUAGE_QUECHUA_BOLIVIA,             "qu", "BO" },   // macro: quh-BO, qul-BO
332     { LANGUAGE_PASHTO,                      "ps", "AF" },
333     { LANGUAGE_OROMO,                       "om", "ET" },
334     { LANGUAGE_DHIVEHI,                     "dv", "MV" },
335     { LANGUAGE_UIGHUR_CHINA,                "ug", "CN" },
336     { LANGUAGE_TIGRIGNA_ETHIOPIA,           "ti", "ET" },
337     { LANGUAGE_TIGRIGNA_ERITREA,            "ti", "ER" },
338     { LANGUAGE_AMHARIC_ETHIOPIA,            "am", "ET" },
339     { LANGUAGE_GUARANI_PARAGUAY,           "gug", "PY" },
340     { LANGUAGE_HAWAIIAN_UNITED_STATES,     "haw", "US" },
341     { LANGUAGE_EDO,                        "bin", "NG" },
342     { LANGUAGE_FULFULDE_NIGERIA,            "ff", "NG" },
343     { LANGUAGE_HAUSA_NIGERIA,               "ha", "NG" },
344     { LANGUAGE_USER_HAUSA_GHANA,            "ha", "GH" },
345     { LANGUAGE_IGBO_NIGERIA,                "ig", "NG" },
346     { LANGUAGE_KANURI_NIGERIA,              "kr", "NG" },
347     { LANGUAGE_YORUBA,                      "yo", "NG" },
348     { LANGUAGE_SOMALI,                      "so", "SO" },
349     { LANGUAGE_PAPIAMENTU,                 "pap", "AN" },
350     { LANGUAGE_USER_PAPIAMENTU_ARUBA,      "pap", "AW" },
351     { LANGUAGE_ENGLISH_SINGAPORE,           "en", "SG" },
352     { LANGUAGE_USER_YIDDISH_US,             "yi", "US" },
353     { LANGUAGE_YIDDISH,                     "yi", "IL" },   // new: old was "ji"
354     { LANGUAGE_YIDDISH,                     "ji", "IL" },   // old: new is "yi"
355     { LANGUAGE_SYRIAC,                     "syr", "TR" },   // "TR" according to http://www.ethnologue.com/show_language.asp?code=SYC
356     { LANGUAGE_SINHALESE_SRI_LANKA,         "si", "LK" },
357     { LANGUAGE_CHEROKEE_UNITED_STATES,     "chr", "US" },
358     { LANGUAGE_INUKTITUT_LATIN_CANADA,      "iu", "CA" },
359 //  { LANGUAGE_INUKTITUT_SYLLABICS_CANADA,  "iu", "CA" },   // script codes not supported yet
360     { LANGUAGE_SAMI_NORTHERN_NORWAY,        "se", "NO" },
361     { LANGUAGE_SAMI_INARI,                 "smn", "FI" },
362     { LANGUAGE_SAMI_LULE_NORWAY,           "smj", "NO" },
363     { LANGUAGE_SAMI_LULE_SWEDEN,           "smj", "SE" },
364     { LANGUAGE_SAMI_NORTHERN_FINLAND,       "se", "FI" },
365     { LANGUAGE_SAMI_NORTHERN_SWEDEN,        "se", "SE" },
366     { LANGUAGE_SAMI_SKOLT,                 "sms", "FI" },
367     { LANGUAGE_SAMI_SOUTHERN_NORWAY,       "sma", "NO" },
368     { LANGUAGE_SAMI_SOUTHERN_SWEDEN,       "sma", "SE" },
369     { LANGUAGE_USER_SAMI_KILDIN_RUSSIA,    "sjd", "RU" },
370     { LANGUAGE_MAPUDUNGUN_CHILE,           "arn", "CL" },
371     { LANGUAGE_CORSICAN_FRANCE,             "co", "FR" },
372     { 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.
373     { LANGUAGE_YAKUT_RUSSIA,               "sah", "RU" },
374     { LANGUAGE_MOHAWK_CANADA,              "moh", "CA" },
375     { LANGUAGE_BASHKIR_RUSSIA,              "ba", "RU" },
376     { LANGUAGE_KICHE_GUATEMALA,            "qut", "GT" },
377     { LANGUAGE_DARI_AFGHANISTAN,           "gbz", "AF" },
378     { LANGUAGE_WOLOF_SENEGAL,               "wo", "SN" },
379     { LANGUAGE_FILIPINO,                   "fil", "PH" },
380     { LANGUAGE_USER_TAGALOG,                "tl", "PH" },
381     { LANGUAGE_ENGLISH_PHILIPPINES,         "en", "PH" },
382 //  { LANGUAGE_IBIBIO_NIGERIA,             "nic", "NG" },   // ISO "nic" is only a collective language code
383     { LANGUAGE_YI,                          "ii", "CN" },
384 //  { LANGUAGE_TAMAZIGHT_LATIN,            "ber", ""   },   // ISO "ber" only collective!
385 //  { LANGUAGE_TAMAZIGHT_ARABIC,           "ber", ""   },   // ISO "ber" only collective!
386     { LANGUAGE_LATIN,                       "la", "VA" },
387     { LANGUAGE_OBSOLETE_USER_LATIN,         "la", "VA" },
388     { LANGUAGE_USER_ESPERANTO,              "eo", ""   },
389     { LANGUAGE_USER_INTERLINGUA,            "ia", ""   },
390     { LANGUAGE_MAORI_NEW_ZEALAND,           "mi", "NZ" },
391     { LANGUAGE_OBSOLETE_USER_MAORI,         "mi", "NZ" },
392     { LANGUAGE_KINYARWANDA_RWANDA,          "rw", "RW" },
393     { LANGUAGE_OBSOLETE_USER_KINYARWANDA,   "rw", "RW" },
394     { 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
395     { LANGUAGE_OBSOLETE_USER_UPPER_SORBIAN,"hsb", "DE" },
396     { 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
397     { LANGUAGE_OBSOLETE_USER_LOWER_SORBIAN,"dsb", "DE" },
398     { LANGUAGE_OCCITAN_FRANCE,              "oc", "FR" },
399     { LANGUAGE_OBSOLETE_USER_OCCITAN,       "oc", "FR" },
400     { LANGUAGE_USER_KURDISH_TURKEY,         "ku", "TR" },
401     { LANGUAGE_USER_KURDISH_SYRIA,          "ku", "SY" },
402     { LANGUAGE_USER_KURDISH_IRAQ,           "ku", "IQ" },
403     { LANGUAGE_USER_KURDISH_IRAN,           "ku", "IR" },
404     { LANGUAGE_USER_SARDINIAN,              "sc", "IT" },   // macrolanguage code
405     { LANGUAGE_USER_SARDINIAN_CAMPIDANESE, "sro", "IT" },
406     { LANGUAGE_USER_SARDINIAN_GALLURESE,   "sdn", "IT" },
407     { LANGUAGE_USER_SARDINIAN_LOGUDORESE,  "src", "IT" },
408     { LANGUAGE_USER_SARDINIAN_SASSARESE,   "sdc", "IT" },
409     { LANGUAGE_BRETON_FRANCE,               "br", "FR" },
410     { LANGUAGE_OBSOLETE_USER_BRETON,        "br", "FR" },
411     { LANGUAGE_KALAALLISUT_GREENLAND,       "kl", "GL" },
412     { LANGUAGE_OBSOLETE_USER_KALAALLISUT,   "kl", "GL" },
413     { LANGUAGE_USER_SWAZI,                  "ss", "ZA" },
414     { LANGUAGE_USER_NDEBELE_SOUTH,          "nr", "ZA" },
415     { LANGUAGE_USER_TSWANA_BOTSWANA,        "tn", "BW" },
416     { LANGUAGE_USER_MOORE,                 "mos", "BF" },
417     { LANGUAGE_USER_BAMBARA,                "bm", "ML" },
418     { LANGUAGE_USER_AKAN,                   "ak", "GH" },
419     { LANGUAGE_LUXEMBOURGISH_LUXEMBOURG,    "lb", "LU" },
420     { LANGUAGE_OBSOLETE_USER_LUXEMBOURGISH, "lb", "LU" },
421     { LANGUAGE_USER_FRIULIAN,              "fur", "IT" },
422     { LANGUAGE_USER_FIJIAN,                 "fj", "FJ" },
423     { LANGUAGE_USER_AFRIKAANS_NAMIBIA,      "af", "NA" },
424     { LANGUAGE_USER_ENGLISH_NAMIBIA,        "en", "NA" },
425     { LANGUAGE_USER_WALLOON,                "wa", "BE" },
426     { LANGUAGE_USER_COPTIC,                "cop", "EG" },
427     { LANGUAGE_USER_GASCON,                "gsc", "FR" },
428     { LANGUAGE_USER_GERMAN_BELGIUM,         "de", "BE" },
429     { LANGUAGE_USER_CHUVASH,                "cv", "RU" },
430     { LANGUAGE_USER_EWE_GHANA,              "ee", "GH" },
431     { LANGUAGE_USER_ENGLISH_GHANA,          "en", "GH" },
432     { LANGUAGE_USER_SANGO,                  "sg", "CF" },
433     { LANGUAGE_USER_GANDA,                  "lg", "UG" },
434     { LANGUAGE_USER_LINGALA_DRCONGO,        "ln", "CD" },
435     { LANGUAGE_USER_LOW_GERMAN,            "nds", "DE" },
436     { LANGUAGE_USER_HILIGAYNON,            "hil", "PH" },
437     { LANGUAGE_USER_NYANJA,                 "ny", "MW" },
438     { LANGUAGE_USER_KASHUBIAN,             "csb", "PL" },
439     { LANGUAGE_USER_SPANISH_CUBA,           "es", "CU" },
440     { LANGUAGE_USER_QUECHUA_NORTH_BOLIVIA, "qul", "BO" },
441     { LANGUAGE_USER_QUECHUA_SOUTH_BOLIVIA, "quh", "BO" },
442     { LANGUAGE_USER_BODO_INDIA,            "brx", "IN" },
443     { LANGUAGE_USER_DOGRI_INDIA,           "dgo", "IN" },
444     { LANGUAGE_USER_MAITHILI_INDIA,        "mai", "IN" },
445     { LANGUAGE_USER_SANTALI_INDIA,         "sat", "IN" },
446     { LANGUAGE_USER_TETUN,                 "tet", "ID" },
447     { LANGUAGE_USER_TETUN_TIMOR_LESTE,     "tet", "TL" },
448     { LANGUAGE_USER_TOK_PISIN,             "tpi", "PG" },
449     { LANGUAGE_USER_SHUSWAP,               "shs", "CA" },
450     { LANGUAGE_USER_ANCIENT_GREEK,         "grc", "GR" },
451     { LANGUAGE_USER_ASTURIAN,              "ast", "ES" },
452     { LANGUAGE_USER_LATGALIAN,             "ltg", "LV" },
453     { LANGUAGE_USER_MAORE,                 "swb", "YT" },
454     { LANGUAGE_USER_BUSHI,                 "buc", "YT" },
455     { LANGUAGE_USER_TAHITIAN,               "ty", "PF" },
456     { LANGUAGE_USER_MALAGASY_PLATEAU,      "plt", "MG" },
457     { LANGUAGE_USER_BAFIA,                 "ksf", "CM" },
458     { LANGUAGE_USER_GIKUYU,                 "ki", "KE" },
459     { LANGUAGE_USER_RUSYN_UKRAINE,         "rue", "UA" },
460     { LANGUAGE_USER_RUSYN_SLOVAKIA,        "rue", "SK" },
461     { LANGUAGE_USER_LIMBU,                 "lif", "NP" },
462     { LANGUAGE_USER_LOJBAN,                "jbo", ""   },
463     { LANGUAGE_USER_KABYLE,                "kab", "DZ" },
464     { LANGUAGE_USER_HAITIAN,                "ht", "HT" },
465     { LANGUAGE_FRENCH_HAITI,                "fr", "HT" },
466     { LANGUAGE_NONE,                       "zxx", ""   },   // added to ISO 639-2 on 2006-01-11: Used to declare the absence of linguistic information
467     { LANGUAGE_DONTKNOW,                    "",   ""   }    // marks end of table
468 };
469 
470 static MsLangId::IsoLangEntry aLastResortFallbackEntry =
471 { LANGUAGE_ENGLISH_US, "en", "US" };
472 
473 // -----------------------------------------------------------------------
474 
475 // In this table are the countries which should mapped to a specific
476 // english language
477 static IsoLangEngEntry const aImplIsoLangEngEntries[] =
478 {
479     { LANGUAGE_ENGLISH_UK,                  "AO" },         // Angola
480     { LANGUAGE_ENGLISH_UK,                  "BJ" },         // Benin
481     { LANGUAGE_ENGLISH_UK,                  "BW" },         // Botswana
482     { LANGUAGE_ENGLISH_UK,                  "BI" },         // Burundi
483     { LANGUAGE_ENGLISH_UK,                  "CM" },         // Cameroon
484     { LANGUAGE_ENGLISH_UK,                  "GA" },         // Gabon
485     { LANGUAGE_ENGLISH_UK,                  "GM" },         // Gambia
486     { LANGUAGE_ENGLISH_UK,                  "GH" },         // Ghana
487     { LANGUAGE_ENGLISH_UK,                  "GN" },         // Guinea
488     { LANGUAGE_ENGLISH_UK,                  "LS" },         // Lesotho
489     { LANGUAGE_ENGLISH_UK,                  "MW" },         // Malawi
490     { LANGUAGE_ENGLISH_UK,                  "MT" },         // Malta
491     { LANGUAGE_ENGLISH_UK,                  "NA" },         // Namibia
492     { LANGUAGE_ENGLISH_UK,                  "NG" },         // Nigeria
493     { LANGUAGE_ENGLISH_UK,                  "UG" },         // Uganda
494     { LANGUAGE_ENGLISH_UK,                  "ZM" },         // Zambia
495     { LANGUAGE_ENGLISH_UK,                  "ZW" },         // Zimbabwe
496     { LANGUAGE_ENGLISH_UK,                  "SZ" },         // Swaziland
497     { LANGUAGE_ENGLISH_UK,                  "NG" },         // Sierra Leone
498     { LANGUAGE_ENGLISH_UK,                  "KN" },         // Saint Kitts and Nevis
499     { LANGUAGE_ENGLISH_UK,                  "SH" },         // St. Helena
500     { LANGUAGE_ENGLISH_UK,                  "IO" },         // British Indian Oceanic Territory
501     { LANGUAGE_ENGLISH_UK,                  "FK" },         // Falkland Islands
502     { LANGUAGE_ENGLISH_UK,                  "GI" },         // Gibraltar
503     { LANGUAGE_ENGLISH_UK,                  "KI" },         // Kiribati
504     { LANGUAGE_ENGLISH_UK,                  "VG" },         // Virgin Islands
505     { LANGUAGE_ENGLISH_UK,                  "MU" },         // Mauritius
506     { LANGUAGE_ENGLISH_UK,                  "FJ" },         // Fiji
507     { LANGUAGE_ENGLISH_US,                  "KI" },         // Kiribati
508     { LANGUAGE_ENGLISH_US,                  "LR" },         // Liberia
509     { LANGUAGE_ENGLISH_US,                  "GU" },         // Guam
510     { LANGUAGE_ENGLISH_US,                  "MH" },         // Marshall Islands
511     { LANGUAGE_ENGLISH_US,                  "PW" },         // Palau
512     { LANGUAGE_ENGLISH_CARRIBEAN,           "AI" },         // Anguilla
513     { LANGUAGE_ENGLISH_CARRIBEAN,           "AG" },         // Antigua and Barbuda
514     { LANGUAGE_ENGLISH_CARRIBEAN,           "BS" },         // Bahamas
515     { LANGUAGE_ENGLISH_CARRIBEAN,           "BB" },         // Barbedos
516     { LANGUAGE_ENGLISH_CARRIBEAN,           "BM" },         // Bermuda
517     { LANGUAGE_ENGLISH_CARRIBEAN,           "KY" },         // Cayman Islands
518     { LANGUAGE_ENGLISH_CARRIBEAN,           "GD" },         // Grenada
519     { LANGUAGE_ENGLISH_CARRIBEAN,           "DM" },         // Dominica
520     { LANGUAGE_ENGLISH_CARRIBEAN,           "HT" },         // Haiti
521     { LANGUAGE_ENGLISH_CARRIBEAN,           "MS" },         // Montserrat
522     { LANGUAGE_ENGLISH_CARRIBEAN,           "FM" },         // Micronesia
523     { LANGUAGE_ENGLISH_CARRIBEAN,           "VC" },         // St. Vincent / Grenadines
524     { LANGUAGE_ENGLISH_CARRIBEAN,           "LC" },         // Saint Lucia
525     { LANGUAGE_ENGLISH_CARRIBEAN,           "TC" },         // Turks & Caicos Islands
526     { LANGUAGE_ENGLISH_CARRIBEAN,           "GY" },         // Guyana
527     { LANGUAGE_ENGLISH_CARRIBEAN,           "TT" },         // Trinidad and Tobago
528     { LANGUAGE_ENGLISH_AUS,                 "CX" },         // Christmas Islands
529     { LANGUAGE_ENGLISH_AUS,                 "CC" },         // Cocos (Keeling) Islands
530     { LANGUAGE_ENGLISH_AUS,                 "NF" },         // Norfolk Island
531     { LANGUAGE_ENGLISH_AUS,                 "PG" },         // Papua New Guinea
532     { LANGUAGE_ENGLISH_AUS,                 "SB" },         // Solomon Islands
533     { LANGUAGE_ENGLISH_AUS,                 "TV" },         // Tuvalu
534     { LANGUAGE_ENGLISH_AUS,                 "NR" },         // Nauru
535     { LANGUAGE_ENGLISH_NZ,                  "CK" },         // Cook Islands
536     { LANGUAGE_ENGLISH_NZ,                  "NU" },         // Niue
537     { LANGUAGE_ENGLISH_NZ,                  "TK" },         // Tokelau
538     { LANGUAGE_ENGLISH_NZ,                  "TO" },         // Tonga
539     { LANGUAGE_DONTKNOW,                    ""   }          // marks end of table
540 };
541 
542 // -----------------------------------------------------------------------
543 
544 static IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries[] =
545 {
546     { LANGUAGE_NORWEGIAN_BOKMAL,            "no", "BOK"      }, // registered subtags for "no" in rfc1766
547     { LANGUAGE_NORWEGIAN_NYNORSK,           "no", "NYN"      }, // registered subtags for "no" in rfc1766
548     { LANGUAGE_SERBIAN_LATIN,               "sr", "latin"    },
549     { LANGUAGE_SERBIAN_CYRILLIC,            "sr", "cyrillic" },
550     { LANGUAGE_AZERI_LATIN,                 "az", "latin"    },
551     { LANGUAGE_AZERI_CYRILLIC,              "az", "cyrillic" },
552     { LANGUAGE_DONTKNOW,                    "",   ""         }  // marks end of table
553 };
554 
555 // -----------------------------------------------------------------------
556 
557 // in this table are only names to find the best language
558 static IsoLangNoneStdEntry const aImplIsoNoneStdLangEntries2[] =
559 {
560     { LANGUAGE_NORWEGIAN_BOKMAL,            "no", "bokmaal"  },
561     { LANGUAGE_NORWEGIAN_BOKMAL,            "no", "bokmal"   },
562     { LANGUAGE_NORWEGIAN_NYNORSK,           "no", "nynorsk"  },
563     { LANGUAGE_DONTKNOW,                    "",   ""         }  // marks end of table
564 };
565 
566 // -----------------------------------------------------------------------
567 
568 // in this table are only names to find the best language
569 static IsoLangOtherEntry const aImplOtherEntries[] =
570 {
571     { LANGUAGE_ENGLISH_US,                  "c"              },
572     { LANGUAGE_CHINESE,                     "chinese"        },
573     { LANGUAGE_GERMAN,                      "german"         },
574     { LANGUAGE_JAPANESE,                    "japanese"       },
575     { LANGUAGE_KOREAN,                      "korean"         },
576     { LANGUAGE_ENGLISH_US,                  "posix"          },
577     { LANGUAGE_CHINESE_TRADITIONAL,         "tchinese"       },
578     { LANGUAGE_DONTKNOW,                    NULL             }  // marks end of table
579 };
580 
581 // =======================================================================
582 
583 // static
convertLanguageToIsoNames(LanguageType nLang,rtl::OUString & rLangStr,rtl::OUString & rCountry)584 void MsLangId::convertLanguageToIsoNames( LanguageType nLang,
585         rtl::OUString& rLangStr, rtl::OUString& rCountry )
586 {
587     if ( nLang == LANGUAGE_SYSTEM )
588         nLang = MsLangId::getSystemLanguage();
589 
590     // Search for LangID (in this table we find only defined ISO combinations)
591     const IsoLangEntry* pEntry = aImplIsoLangEntries;
592     do
593     {
594         if ( pEntry->mnLang == nLang )
595         {
596             rLangStr = rtl::OUString::createFromAscii( pEntry->maLangStr );
597             rCountry = rtl::OUString::createFromAscii( pEntry->maCountry );
598             return;
599         }
600         ++pEntry;
601     }
602     while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
603 
604     // Search for LangID if we didn't find a specific ISO combination.
605     // All entries in this table are allowed for mime specifications,
606     // but not defined ISO combinations.
607     const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
608     do
609     {
610         if ( pNoneStdEntry->mnLang == nLang )
611         {
612             rLangStr = rtl::OUString::createFromAscii( pNoneStdEntry->maLangStr );
613             rCountry = rtl::OUString::createFromAscii( pNoneStdEntry->maCountry );
614             return;
615         }
616         ++pNoneStdEntry;
617     }
618     while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
619 
620     // not found
621     rLangStr = rtl::OUString();
622     rCountry = rtl::OUString();
623 }
624 
625 // -----------------------------------------------------------------------
626 
627 // static
convertLanguageToIsoNames(LanguageType nLang,rtl::OString & rLangStr,rtl::OString & rCountry)628 void MsLangId::convertLanguageToIsoNames( LanguageType nLang,
629         rtl::OString& rLangStr, rtl::OString& rCountry )
630 {
631     if ( nLang == LANGUAGE_SYSTEM )
632         nLang = MsLangId::getSystemLanguage();
633 
634     // Search for LangID (in this table we find only defined ISO combinations)
635     const IsoLangEntry* pEntry = aImplIsoLangEntries;
636     do
637     {
638         if ( pEntry->mnLang == nLang )
639         {
640             rLangStr = rtl::OString( pEntry->maLangStr );
641             rCountry = rtl::OString( pEntry->maCountry );
642             return;
643         }
644         ++pEntry;
645     }
646     while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
647 
648     // Search for LangID if we didn't find a specific ISO combination.
649     // All entries in this table are allowed for mime specifications,
650     // but not defined ISO combinations.
651     const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
652     do
653     {
654         if ( pNoneStdEntry->mnLang == nLang )
655         {
656             rLangStr = rtl::OString( pNoneStdEntry->maLangStr );
657             rCountry = rtl::OString( pNoneStdEntry->maCountry );
658             return;
659         }
660         ++pNoneStdEntry;
661     }
662     while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
663 
664     // not found
665     rLangStr = rtl::OString();
666     rCountry = rtl::OString();
667 }
668 
669 // -----------------------------------------------------------------------
670 
lcl_lookupFallbackEntry(LanguageType nLang)671 static const MsLangId::IsoLangEntry & lcl_lookupFallbackEntry( LanguageType nLang )
672 {
673     LanguageType nPrimary = MsLangId::getPrimaryLanguage( nLang);
674 
675     // Search for LangID and remember first lang-only.
676     const MsLangId::IsoLangEntry* pFirstPrimary = NULL;
677     const MsLangId::IsoLangEntry* pEntry = aImplIsoLangEntries;
678     do
679     {
680         if (pEntry->mnLang == nLang)
681         {
682             if (*pEntry->maCountry)
683                 return *pEntry;
684             switch (nLang)
685             {
686                 // These are known to have no country assigned.
687                 case LANGUAGE_BASQUE:
688                 case LANGUAGE_USER_ESPERANTO:
689                 case LANGUAGE_USER_INTERLINGUA:
690                 case LANGUAGE_USER_LOJBAN:
691                     return *pEntry;
692                 default:
693                     ;   // nothing
694             }
695         }
696         if (!pFirstPrimary &&
697                 MsLangId::getPrimaryLanguage( pEntry->mnLang) == nPrimary)
698             pFirstPrimary = pEntry;
699         ++pEntry;
700     }
701     while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
702 
703     // Language not found at all => use default.
704     if (!pFirstPrimary)
705         return aLastResortFallbackEntry;
706 
707     // Search for first entry of primary language with any country.
708     pEntry = pFirstPrimary;
709     do
710     {
711         if (MsLangId::getPrimaryLanguage( pEntry->mnLang) == nLang)
712         {
713             if (*pEntry->maCountry)
714                 return *pEntry;
715         }
716         ++pEntry;
717     }
718     while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
719 
720     return aLastResortFallbackEntry;
721 }
722 
723 // static
lookupFallbackLanguage(LanguageType nLang)724 LanguageType MsLangId::lookupFallbackLanguage( LanguageType nLang )
725 {
726     return lcl_lookupFallbackEntry( nLang).mnLang;
727 }
728 
729 
730 // static
lookupFallbackLocale(LanguageType nLang)731 ::com::sun::star::lang::Locale MsLangId::lookupFallbackLocale( LanguageType nLang )
732 {
733     const MsLangId::IsoLangEntry& rEntry = lcl_lookupFallbackEntry( nLang);
734     return ::com::sun::star::lang::Locale(
735             rtl::OUString::createFromAscii( rEntry.maLangStr),
736             rtl::OUString::createFromAscii( rEntry.maCountry),
737             rtl::OUString());
738 }
739 
740 // -----------------------------------------------------------------------
741 
lcl_lookupFallbackEntry(const::com::sun::star::lang::Locale & rLocale)742 static const MsLangId::IsoLangEntry & lcl_lookupFallbackEntry(
743         const ::com::sun::star::lang::Locale & rLocale )
744 {
745     // language is lower case in table
746     rtl::OUString aLowerLang = rLocale.Language.toAsciiLowerCase();
747     // country is upper case in table
748     rtl::OUString aUpperCountry = rLocale.Country.toAsciiUpperCase();
749     sal_Int32 nCountryLen = aUpperCountry.getLength();
750 
751     // Search for locale and remember first lang-only.
752     const MsLangId::IsoLangEntry* pFirstLang = NULL;
753     const MsLangId::IsoLangEntry* pEntry = aImplIsoLangEntries;
754     do
755     {
756         if (aLowerLang.equalsAscii( pEntry->maLangStr))
757         {
758             if (*pEntry->maCountry)
759             {
760                 if (nCountryLen && aUpperCountry.equalsAscii( pEntry->maCountry))
761                     return *pEntry;
762             }
763             else
764             {
765                 switch (pEntry->mnLang)
766                 {
767                     // These are known to have no country assigned.
768                     case LANGUAGE_BASQUE:
769                     case LANGUAGE_USER_ESPERANTO:
770                     case LANGUAGE_USER_INTERLINGUA:
771                     case LANGUAGE_USER_LOJBAN:
772                         return *pEntry;
773                     default:
774                         ;   // nothing
775                 }
776             }
777             if (!pFirstLang)
778                 pFirstLang = pEntry;
779         }
780         ++pEntry;
781     }
782     while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
783 
784     // Language not found at all => use default.
785     if (!pFirstLang)
786         return aLastResortFallbackEntry;
787 
788     // Search for first entry of language with any country.
789     pEntry = pFirstLang;
790     do
791     {
792         if (aLowerLang.equalsAscii( pEntry->maLangStr))
793         {
794             if (*pEntry->maCountry)
795                 return *pEntry;
796         }
797         ++pEntry;
798     }
799     while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
800 
801     return aLastResortFallbackEntry;
802 }
803 
804 // static
lookupFallbackLanguage(const::com::sun::star::lang::Locale & rLocale)805 LanguageType MsLangId::lookupFallbackLanguage(
806         const ::com::sun::star::lang::Locale & rLocale )
807 {
808     return lcl_lookupFallbackEntry( rLocale).mnLang;
809 }
810 
811 
812 // static
lookupFallbackLocale(const::com::sun::star::lang::Locale & rLocale)813 ::com::sun::star::lang::Locale MsLangId::lookupFallbackLocale(
814         const ::com::sun::star::lang::Locale & rLocale )
815 {
816     const MsLangId::IsoLangEntry& rEntry = lcl_lookupFallbackEntry( rLocale);
817     return ::com::sun::star::lang::Locale(
818             rtl::OUString::createFromAscii( rEntry.maLangStr),
819             rtl::OUString::createFromAscii( rEntry.maCountry),
820             rtl::OUString());
821 }
822 
823 // -----------------------------------------------------------------------
824 
825 // static
convertLanguageToIsoString(LanguageType nLang,sal_Unicode cSep)826 rtl::OUString MsLangId::convertLanguageToIsoString( LanguageType nLang,
827         sal_Unicode cSep )
828 {
829     rtl::OUString   aLangStr;
830     rtl::OUString   aCountry;
831     convertLanguageToIsoNames( nLang, aLangStr, aCountry );
832     if ( aCountry.getLength() )
833     {
834         rtl::OUStringBuffer aBuf( aLangStr);
835         aBuf.append( cSep );
836         aBuf.append( aCountry );
837         return aBuf.makeStringAndClear();
838     }
839     else
840         return aLangStr;
841 }
842 
843 // -----------------------------------------------------------------------
844 
845 // static
convertLanguageToIsoByteString(LanguageType nLang,sal_Char cSep)846 rtl::OString MsLangId::convertLanguageToIsoByteString( LanguageType nLang,
847         sal_Char cSep )
848 {
849     rtl::OString  aLangStr;
850     rtl::OString  aCountry;
851     convertLanguageToIsoNames( nLang, aLangStr, aCountry );
852     if ( aCountry.getLength() )
853     {
854         rtl::OStringBuffer aBuf( aLangStr);
855         aBuf.append( cSep );
856         aBuf.append( aCountry );
857         return aBuf.makeStringAndClear();
858     }
859     return aLangStr;
860 }
861 
862 // =======================================================================
863 
864 // static
convertIsoNamesToLanguage(const rtl::OUString & rLang,const rtl::OUString & rCountry)865 LanguageType MsLangId::convertIsoNamesToLanguage( const rtl::OUString& rLang,
866         const rtl::OUString& rCountry )
867 {
868     // language is lower case in table
869     rtl::OUString aLowerLang = rLang.toAsciiLowerCase();
870     // country is upper case in table
871     rtl::OUString aUpperCountry = rCountry.toAsciiUpperCase();
872 
873     //  first look for exact match
874     const IsoLangEntry* pFirstLang = NULL;
875     const IsoLangEntry* pEntry = aImplIsoLangEntries;
876     do
877     {
878         if ( aLowerLang.equalsAscii( pEntry->maLangStr ) )
879         {
880             if ( !aUpperCountry.getLength() ||
881                  aUpperCountry.equalsAscii( pEntry->maCountry ) )
882                 return pEntry->mnLang;
883             if ( !pFirstLang )
884                 pFirstLang = pEntry;
885             else if ( !*pEntry->maCountry )
886                 pFirstLang = pEntry;
887         }
888         ++pEntry;
889     }
890     while ( pEntry->mnLang != LANGUAGE_DONTKNOW );
891 
892     // some eng countries should be mapped to a specific english language
893     if ( aLowerLang.equalsAscii( "en" ) )
894     {
895         const IsoLangEngEntry* pEngEntry = aImplIsoLangEngEntries;
896         do
897         {
898             if ( aUpperCountry.equalsAscii( pEngEntry->maCountry ) )
899                 return pEngEntry->mnLang;
900             ++pEngEntry;
901         }
902         while ( pEngEntry->mnLang != LANGUAGE_DONTKNOW );
903     }
904 
905     // test for specific languages which are not used standard ISO 3166 codes
906     const IsoLangNoneStdEntry* pNoneStdEntry = aImplIsoNoneStdLangEntries;
907     do
908     {
909         if ( aLowerLang.equalsAscii( pNoneStdEntry->maLangStr ) )
910         {
911             // The countries in this table are not all in upper case
912             if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
913                 return pNoneStdEntry->mnLang;
914         }
915         ++pNoneStdEntry;
916     }
917     while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
918     pNoneStdEntry = aImplIsoNoneStdLangEntries2;
919     do
920     {
921         if ( aLowerLang.equalsAscii( pNoneStdEntry->maLangStr ) )
922         {
923             // The countries in this table are not all in upper case
924             if ( aUpperCountry.equalsIgnoreAsciiCaseAscii( pNoneStdEntry->maCountry ) )
925                 return pNoneStdEntry->mnLang;
926         }
927         ++pNoneStdEntry;
928     }
929     while ( pNoneStdEntry->mnLang != LANGUAGE_DONTKNOW );
930 
931     // If the language is correct, than we return the default language
932     if ( pFirstLang )
933         return pFirstLang->mnLang;
934 
935     //  if only the country is set, look for any entry matching the country
936     //  (to allow reading country and language in separate steps, in any order)
937     if ( rCountry.getLength() && !rLang.getLength() )
938     {
939         const IsoLangEntry* pEntry2 = aImplIsoLangEntries;
940         do
941         {
942             if ( aUpperCountry.equalsAscii( pEntry2->maCountry ) )
943                 return pEntry2->mnLang;
944             ++pEntry2;
945         }
946         while ( pEntry2->mnLang != LANGUAGE_DONTKNOW );
947 
948         aLowerLang = aUpperCountry.toAsciiLowerCase();
949     }
950 
951     // Now look for all other definitions, which are not standard
952     const IsoLangOtherEntry* pOtherEntry = aImplOtherEntries;
953     do
954     {
955         if ( aLowerLang.equalsAscii( pOtherEntry->mpLangStr ) )
956             return pOtherEntry->mnLang;
957         ++pOtherEntry;
958     }
959     while ( pOtherEntry->mnLang != LANGUAGE_DONTKNOW );
960 
961     return LANGUAGE_DONTKNOW;
962 }
963 
964 // -----------------------------------------------------------------------
965 
966 // static
convertIsoNamesToLanguage(const rtl::OString & rLang,const rtl::OString & rCountry)967 LanguageType MsLangId::convertIsoNamesToLanguage( const rtl::OString& rLang,
968         const rtl::OString& rCountry )
969 {
970     rtl::OUString aLang = OStringToOUString( rLang, RTL_TEXTENCODING_ASCII_US);
971     rtl::OUString aCountry = OStringToOUString( rCountry, RTL_TEXTENCODING_ASCII_US);
972     return convertIsoNamesToLanguage( aLang, aCountry);
973 }
974 
975 // -----------------------------------------------------------------------
976 
977 // static
convertIsoStringToLanguage(const rtl::OUString & rString,sal_Unicode cSep)978 LanguageType MsLangId::convertIsoStringToLanguage(
979         const rtl::OUString& rString, sal_Unicode cSep )
980 {
981     rtl::OUString   aLang;
982     rtl::OUString   aCountry;
983     sal_Int32  nSepPos = rString.indexOf( cSep );
984     if ( nSepPos >= 0 )
985     {
986         aLang = rString.copy( 0, nSepPos );
987         aCountry = rString.copy( nSepPos+1 );
988     }
989     else
990         aLang = rString;
991 
992     return convertIsoNamesToLanguage( aLang, aCountry );
993 }
994 
995 // -----------------------------------------------------------------------
996 
997 // static
convertIsoByteStringToLanguage(const rtl::OString & rString,sal_Char cSep)998 LanguageType MsLangId::convertIsoByteStringToLanguage(
999         const rtl::OString& rString, sal_Char cSep )
1000 {
1001     rtl::OString  aLang;
1002     rtl::OString  aCountry;
1003     sal_Int32  nSepPos = rString.indexOf( cSep );
1004     if ( nSepPos >= 0 )
1005     {
1006         aLang = rString.copy( 0, nSepPos );
1007         aCountry = rString.copy( nSepPos+1 );
1008     }
1009     else
1010         aLang = rString;
1011 
1012     return convertIsoNamesToLanguage( aLang, aCountry );
1013 }
1014 
1015 // -----------------------------------------------------------------------
1016 
1017 struct IsoLangGLIBCModifiersEntry
1018 {
1019     LanguageType  mnLang;
1020     sal_Char      maLangStr[4];
1021     sal_Char      maCountry[3];
1022     sal_Char      maAtString[9];
1023 };
1024 
1025 static IsoLangGLIBCModifiersEntry const aImplIsoLangGLIBCModifiersEntries[] =
1026 {
1027     // MS-LANGID codes               ISO639-1/2/3 ISO3166            glibc modifier
1028     { LANGUAGE_BOSNIAN_CYRILLIC_BOSNIA_HERZEGOVINA, "bs", "BA", "cyrillic" },
1029     { LANGUAGE_USER_SERBIAN_LATIN_SERBIA,           "sr", "RS", "latin" },   // Serbian Latin in Serbia
1030     { LANGUAGE_SERBIAN_LATIN,                       "sr", "CS", "latin" },   // Serbian Latin in Serbia and Montenegro
1031     { LANGUAGE_USER_SERBIAN_LATIN_MONTENEGRO,       "sr", "ME", "latin" },   // Serbian Latin in Montenegro
1032     { LANGUAGE_SERBIAN_LATIN_NEUTRAL,               "sr", "",   "latin" },
1033     { LANGUAGE_AZERI_CYRILLIC,                      "az", "AZ", "cyrillic" },
1034     { LANGUAGE_UZBEK_CYRILLIC,                      "uz", "UZ", "cyrillic" },
1035     { LANGUAGE_DONTKNOW,                            "",   "",   ""   }       // marks end of table
1036 };
1037 
1038 // convert a unix locale string into LanguageType
1039 
1040 // static
convertUnxByteStringToLanguage(const rtl::OString & rString)1041 LanguageType MsLangId::convertUnxByteStringToLanguage(
1042         const rtl::OString& rString )
1043 {
1044     rtl::OString  aLang;
1045     rtl::OString  aCountry;
1046     rtl::OString  aAtString;
1047 
1048     sal_Int32  nLangSepPos    = rString.indexOf( (sal_Char)'_' );
1049     sal_Int32  nCountrySepPos = rString.indexOf( (sal_Char)'.' );
1050     sal_Int32  nAtPos         = rString.indexOf( (sal_Char)'@' );
1051 
1052     if (nCountrySepPos < 0)
1053         nCountrySepPos = nAtPos;
1054     if (nCountrySepPos < 0)
1055         nCountrySepPos = rString.getLength();
1056 
1057     if (nAtPos >= 0)
1058         aAtString = rString.copy( nAtPos+1 );
1059 
1060     if (   ((nLangSepPos >= 0) && (nLangSepPos > nCountrySepPos))
1061         || ((nLangSepPos < 0)) )
1062     {
1063         // eg. "el.sun_eu_greek", "tchinese", "es.ISO8859-15"
1064         aLang    = rString.copy( 0, nCountrySepPos );
1065     }
1066     else if ( nLangSepPos >= 0 )
1067     {
1068         // well formed iso names like "en_US.UTF-8", "sh_BA.ISO8859-2@bosnia"
1069         aLang    = rString.copy( 0, nLangSepPos );
1070         aCountry = rString.copy( nLangSepPos+1, nCountrySepPos - nLangSepPos - 1);
1071     }
1072 
1073     //  if there is a glibc modifier, first look for exact match in modifier table
1074     if (aAtString.getLength())
1075     {
1076         // language is lower case in table
1077         rtl::OString aLowerLang = aLang.toAsciiLowerCase();
1078         // country is upper case in table
1079         rtl::OString aUpperCountry = aCountry.toAsciiUpperCase();
1080         const IsoLangGLIBCModifiersEntry* pGLIBCModifiersEntry = aImplIsoLangGLIBCModifiersEntries;
1081         do
1082         {
1083             if (( aLowerLang.equals( pGLIBCModifiersEntry->maLangStr ) ) &&
1084                ( aAtString.equals( pGLIBCModifiersEntry->maAtString ) ))
1085             {
1086                 if ( !aUpperCountry.getLength() ||
1087                      aUpperCountry.equals( pGLIBCModifiersEntry->maCountry ) )
1088                {
1089                     return pGLIBCModifiersEntry->mnLang;
1090                }
1091             }
1092             ++pGLIBCModifiersEntry;
1093         }
1094         while ( pGLIBCModifiersEntry->mnLang != LANGUAGE_DONTKNOW );
1095     }
1096 
1097     return convertIsoNamesToLanguage( aLang, aCountry );
1098 }
1099 
1100 // -----------------------------------------------------------------------
1101 // pass one IsoLangEntry to the outer world of the resource compiler
1102 
1103 // static
getIsoLangEntry(size_t nIndex)1104 const MsLangId::IsoLangEntry* MsLangId::getIsoLangEntry( size_t nIndex )
1105 {
1106     if (nIndex < sizeof( aImplIsoLangEntries) / sizeof( IsoLangEntry))
1107         return &aImplIsoLangEntries[ nIndex];
1108     return 0;
1109 }
1110