| |
1 /* |
| |
2 ********************************************************************** |
| |
3 * Copyright (C) 1996-2013, International Business Machines |
| |
4 * Corporation and others. All Rights Reserved. |
| |
5 ********************************************************************** |
| |
6 * |
| |
7 * Provides functionality for mapping between |
| |
8 * LCID and Posix IDs or ICU locale to codepage |
| |
9 * |
| |
10 * Note: All classes and code in this file are |
| |
11 * intended for internal use only. |
| |
12 * |
| |
13 * Methods of interest: |
| |
14 * unsigned long convertToLCID(const char*); |
| |
15 * const char* convertToPosix(unsigned long); |
| |
16 * |
| |
17 * Kathleen Wilson, 4/30/96 |
| |
18 * |
| |
19 * Date Name Description |
| |
20 * 3/11/97 aliu Fixed off-by-one bug in assignment operator. Added |
| |
21 * setId() method and safety check against |
| |
22 * MAX_ID_LENGTH. |
| |
23 * 04/23/99 stephen Added C wrapper for convertToPosix. |
| |
24 * 09/18/00 george Removed the memory leaks. |
| |
25 * 08/23/01 george Convert to C |
| |
26 */ |
| |
27 |
| |
28 #include "locmap.h" |
| |
29 #include "cstring.h" |
| |
30 #include "cmemory.h" |
| |
31 |
| |
32 #if U_PLATFORM == U_PF_WINDOWS && defined(_MSC_VER) && (_MSC_VER >= 1500) |
| |
33 /* |
| |
34 * TODO: It seems like we should widen this to |
| |
35 * either U_PLATFORM_USES_ONLY_WIN32_API (includes MinGW) |
| |
36 * or U_PLATFORM_HAS_WIN32_API (includes MinGW and Cygwin) |
| |
37 * but those use gcc and won't have defined(_MSC_VER). |
| |
38 * We might need to #include some Windows header and test for some version macro from there. |
| |
39 * Or call some Windows function and see what it returns. |
| |
40 */ |
| |
41 #define USE_WINDOWS_LOCALE_API |
| |
42 #endif |
| |
43 |
| |
44 #ifdef USE_WINDOWS_LOCALE_API |
| |
45 #include <windows.h> |
| |
46 #include <winnls.h> |
| |
47 #endif |
| |
48 |
| |
49 /* |
| |
50 * Note: |
| |
51 * The mapping from Win32 locale ID numbers to POSIX locale strings should |
| |
52 * be the faster one. |
| |
53 * |
| |
54 * Many LCID values come from winnt.h |
| |
55 * Some also come from http://www.microsoft.com/globaldev/reference/lcid-all.mspx |
| |
56 */ |
| |
57 |
| |
58 /* |
| |
59 //////////////////////////////////////////////// |
| |
60 // |
| |
61 // Internal Classes for LCID <--> POSIX Mapping |
| |
62 // |
| |
63 ///////////////////////////////////////////////// |
| |
64 */ |
| |
65 |
| |
66 typedef struct ILcidPosixElement |
| |
67 { |
| |
68 const uint32_t hostID; |
| |
69 const char * const posixID; |
| |
70 } ILcidPosixElement; |
| |
71 |
| |
72 typedef struct ILcidPosixMap |
| |
73 { |
| |
74 const uint32_t numRegions; |
| |
75 const struct ILcidPosixElement* const regionMaps; |
| |
76 } ILcidPosixMap; |
| |
77 |
| |
78 |
| |
79 /* |
| |
80 ///////////////////////////////////////////////// |
| |
81 // |
| |
82 // Easy macros to make the LCID <--> POSIX Mapping |
| |
83 // |
| |
84 ///////////////////////////////////////////////// |
| |
85 */ |
| |
86 |
| |
87 /** |
| |
88 * The standard one language/one country mapping for LCID. |
| |
89 * The first element must be the language, and the following |
| |
90 * elements are the language with the country. |
| |
91 * @param hostID LCID in host format such as 0x044d |
| |
92 * @param languageID posix ID of just the language such as 'de' |
| |
93 * @param posixID posix ID of the language_TERRITORY such as 'de_CH' |
| |
94 */ |
| |
95 #define ILCID_POSIX_ELEMENT_ARRAY(hostID, languageID, posixID) \ |
| |
96 static const ILcidPosixElement locmap_ ## languageID [] = { \ |
| |
97 {LANGUAGE_LCID(hostID), #languageID}, /* parent locale */ \ |
| |
98 {hostID, #posixID}, \ |
| |
99 }; |
| |
100 |
| |
101 /** |
| |
102 * Define a subtable by ID |
| |
103 * @param id the POSIX ID, either a language or language_TERRITORY |
| |
104 */ |
| |
105 #define ILCID_POSIX_SUBTABLE(id) \ |
| |
106 static const ILcidPosixElement locmap_ ## id [] = |
| |
107 |
| |
108 |
| |
109 /** |
| |
110 * Create the map for the posixID. This macro supposes that the language string |
| |
111 * name is the same as the global variable name, and that the first element |
| |
112 * in the ILcidPosixElement is just the language. |
| |
113 * @param _posixID the full POSIX ID for this entry. |
| |
114 */ |
| |
115 #define ILCID_POSIX_MAP(_posixID) \ |
| |
116 {sizeof(locmap_ ## _posixID)/sizeof(ILcidPosixElement), locmap_ ## _posixID} |
| |
117 |
| |
118 /* |
| |
119 //////////////////////////////////////////// |
| |
120 // |
| |
121 // Create the table of LCID to POSIX Mapping |
| |
122 // None of it should be dynamically created. |
| |
123 // |
| |
124 // Keep static locale variables inside the function so that |
| |
125 // it can be created properly during static init. |
| |
126 // |
| |
127 // Note: This table should be updated periodically. Check the National Lanaguage Support API Reference Website. |
| |
128 // Microsoft is moving away from LCID in favor of locale name as of Vista. This table needs to be |
| |
129 // maintained for support of older Windows version. |
| |
130 // Update: Windows 7 (091130) |
| |
131 // |
| |
132 // Note: Microsoft assign a different LCID if a locale has a sorting variant. POSIX IDs below may contain |
| |
133 // @collation=XXX, but no other keywords are allowed (at least for now). When uprv_convertToLCID() is |
| |
134 // called from uloc_getLCID(), keywords other than collation are already removed. If we really need |
| |
135 // to support other keywords in this mapping data, we must update the implementation. |
| |
136 //////////////////////////////////////////// |
| |
137 */ |
| |
138 |
| |
139 ILCID_POSIX_ELEMENT_ARRAY(0x0436, af, af_ZA) |
| |
140 |
| |
141 ILCID_POSIX_SUBTABLE(ar) { |
| |
142 {0x01, "ar"}, |
| |
143 {0x3801, "ar_AE"}, |
| |
144 {0x3c01, "ar_BH"}, |
| |
145 {0x1401, "ar_DZ"}, |
| |
146 {0x0c01, "ar_EG"}, |
| |
147 {0x0801, "ar_IQ"}, |
| |
148 {0x2c01, "ar_JO"}, |
| |
149 {0x3401, "ar_KW"}, |
| |
150 {0x3001, "ar_LB"}, |
| |
151 {0x1001, "ar_LY"}, |
| |
152 {0x1801, "ar_MA"}, |
| |
153 {0x1801, "ar_MO"}, |
| |
154 {0x2001, "ar_OM"}, |
| |
155 {0x4001, "ar_QA"}, |
| |
156 {0x0401, "ar_SA"}, |
| |
157 {0x2801, "ar_SY"}, |
| |
158 {0x1c01, "ar_TN"}, |
| |
159 {0x2401, "ar_YE"} |
| |
160 }; |
| |
161 |
| |
162 ILCID_POSIX_ELEMENT_ARRAY(0x044d, as, as_IN) |
| |
163 ILCID_POSIX_ELEMENT_ARRAY(0x045e, am, am_ET) |
| |
164 ILCID_POSIX_ELEMENT_ARRAY(0x047a, arn,arn_CL) |
| |
165 |
| |
166 ILCID_POSIX_SUBTABLE(az) { |
| |
167 {0x2c, "az"}, |
| |
168 {0x082c, "az_Cyrl_AZ"}, /* Cyrillic based */ |
| |
169 {0x742c, "az_Cyrl"}, /* Cyrillic based */ |
| |
170 {0x042c, "az_Latn_AZ"}, /* Latin based */ |
| |
171 {0x782c, "az_Latn"}, /* Latin based */ |
| |
172 {0x042c, "az_AZ"} /* Latin based */ |
| |
173 }; |
| |
174 |
| |
175 ILCID_POSIX_ELEMENT_ARRAY(0x046d, ba, ba_RU) |
| |
176 ILCID_POSIX_ELEMENT_ARRAY(0x0423, be, be_BY) |
| |
177 |
| |
178 /*ILCID_POSIX_SUBTABLE(ber) { |
| |
179 {0x5f, "ber"}, |
| |
180 {0x045f, "ber_Arab_DZ"}, |
| |
181 {0x045f, "ber_Arab"}, |
| |
182 {0x085f, "ber_Latn_DZ"}, |
| |
183 {0x085f, "ber_Latn"} |
| |
184 };*/ |
| |
185 |
| |
186 ILCID_POSIX_ELEMENT_ARRAY(0x0402, bg, bg_BG) |
| |
187 |
| |
188 ILCID_POSIX_ELEMENT_ARRAY(0x0466, bin, bin_NG) |
| |
189 |
| |
190 ILCID_POSIX_SUBTABLE(bn) { |
| |
191 {0x45, "bn"}, |
| |
192 {0x0845, "bn_BD"}, |
| |
193 {0x0445, "bn_IN"} |
| |
194 }; |
| |
195 |
| |
196 ILCID_POSIX_SUBTABLE(bo) { |
| |
197 {0x51, "bo"}, |
| |
198 {0x0851, "bo_BT"}, |
| |
199 {0x0451, "bo_CN"} |
| |
200 }; |
| |
201 |
| |
202 ILCID_POSIX_ELEMENT_ARRAY(0x047e, br, br_FR) |
| |
203 |
| |
204 ILCID_POSIX_SUBTABLE(ca) { |
| |
205 {0x03, "ca"}, |
| |
206 {0x0403, "ca_ES"}, |
| |
207 {0x0803, "ca_ES_VALENCIA"} |
| |
208 }; |
| |
209 |
| |
210 ILCID_POSIX_ELEMENT_ARRAY(0x0483, co, co_FR) |
| |
211 ILCID_POSIX_ELEMENT_ARRAY(0x045c, chr,chr_US) |
| |
212 |
| |
213 ILCID_POSIX_SUBTABLE(ckb) { |
| |
214 {0x92, "ckb"}, |
| |
215 {0x92, "ku"}, |
| |
216 {0x7c92, "ckb_Arab"}, |
| |
217 {0x7c92, "ku_Arab"}, |
| |
218 {0x0492, "ckb_Arab_IQ"}, |
| |
219 {0x0492, "ku_Arab_IQ"} |
| |
220 }; |
| |
221 |
| |
222 /* Declared as cs_CZ to get around compiler errors on z/OS, which defines cs as a function */ |
| |
223 ILCID_POSIX_ELEMENT_ARRAY(0x0405, cs, cs_CZ) |
| |
224 |
| |
225 ILCID_POSIX_ELEMENT_ARRAY(0x0452, cy, cy_GB) |
| |
226 ILCID_POSIX_ELEMENT_ARRAY(0x0406, da, da_DK) |
| |
227 |
| |
228 ILCID_POSIX_SUBTABLE(de) { |
| |
229 {0x07, "de"}, |
| |
230 {0x0c07, "de_AT"}, |
| |
231 {0x0807, "de_CH"}, |
| |
232 {0x0407, "de_DE"}, |
| |
233 {0x1407, "de_LI"}, |
| |
234 {0x1007, "de_LU"}, |
| |
235 {0x10407,"de_DE@collation=phonebook"}, /*This is really de_DE_PHONEBOOK on Windows*/ |
| |
236 {0x10407,"de@collation=phonebook"} /*This is really de_DE_PHONEBOOK on Windows*/ |
| |
237 }; |
| |
238 |
| |
239 ILCID_POSIX_ELEMENT_ARRAY(0x0465, dv, dv_MV) |
| |
240 ILCID_POSIX_ELEMENT_ARRAY(0x0408, el, el_GR) |
| |
241 |
| |
242 ILCID_POSIX_SUBTABLE(en) { |
| |
243 {0x09, "en"}, |
| |
244 {0x0c09, "en_AU"}, |
| |
245 {0x2809, "en_BZ"}, |
| |
246 {0x1009, "en_CA"}, |
| |
247 {0x0809, "en_GB"}, |
| |
248 {0x3c09, "en_HK"}, |
| |
249 {0x3809, "en_ID"}, |
| |
250 {0x1809, "en_IE"}, |
| |
251 {0x4009, "en_IN"}, |
| |
252 {0x2009, "en_JM"}, |
| |
253 {0x4409, "en_MY"}, |
| |
254 {0x1409, "en_NZ"}, |
| |
255 {0x3409, "en_PH"}, |
| |
256 {0x4809, "en_SG"}, |
| |
257 {0x2C09, "en_TT"}, |
| |
258 {0x0409, "en_US"}, |
| |
259 {0x007f, "en_US_POSIX"}, /* duplicate for roundtripping */ |
| |
260 {0x2409, "en_VI"}, /* Virgin Islands AKA Caribbean Islands (en_CB). */ |
| |
261 {0x1c09, "en_ZA"}, |
| |
262 {0x3009, "en_ZW"}, |
| |
263 {0x2409, "en_029"}, |
| |
264 {0x0409, "en_AS"}, /* Alias for en_US. Leave last. */ |
| |
265 {0x0409, "en_GU"}, /* Alias for en_US. Leave last. */ |
| |
266 {0x0409, "en_MH"}, /* Alias for en_US. Leave last. */ |
| |
267 {0x0409, "en_MP"}, /* Alias for en_US. Leave last. */ |
| |
268 {0x0409, "en_UM"} /* Alias for en_US. Leave last. */ |
| |
269 }; |
| |
270 |
| |
271 ILCID_POSIX_SUBTABLE(en_US_POSIX) { |
| |
272 {0x007f, "en_US_POSIX"} /* duplicate for roundtripping */ |
| |
273 }; |
| |
274 |
| |
275 ILCID_POSIX_SUBTABLE(es) { |
| |
276 {0x0a, "es"}, |
| |
277 {0x2c0a, "es_AR"}, |
| |
278 {0x400a, "es_BO"}, |
| |
279 {0x340a, "es_CL"}, |
| |
280 {0x240a, "es_CO"}, |
| |
281 {0x140a, "es_CR"}, |
| |
282 {0x1c0a, "es_DO"}, |
| |
283 {0x300a, "es_EC"}, |
| |
284 {0x0c0a, "es_ES"}, /*Modern sort.*/ |
| |
285 {0x100a, "es_GT"}, |
| |
286 {0x480a, "es_HN"}, |
| |
287 {0x080a, "es_MX"}, |
| |
288 {0x4c0a, "es_NI"}, |
| |
289 {0x180a, "es_PA"}, |
| |
290 {0x280a, "es_PE"}, |
| |
291 {0x500a, "es_PR"}, |
| |
292 {0x3c0a, "es_PY"}, |
| |
293 {0x440a, "es_SV"}, |
| |
294 {0x540a, "es_US"}, |
| |
295 {0x380a, "es_UY"}, |
| |
296 {0x200a, "es_VE"}, |
| |
297 {0xe40a, "es_419"}, |
| |
298 {0x040a, "es_ES@collation=traditional"}, |
| |
299 {0x040a, "es@collation=traditional"} |
| |
300 }; |
| |
301 |
| |
302 ILCID_POSIX_ELEMENT_ARRAY(0x0425, et, et_EE) |
| |
303 ILCID_POSIX_ELEMENT_ARRAY(0x042d, eu, eu_ES) |
| |
304 |
| |
305 /* ISO-639 doesn't distinguish between Persian and Dari.*/ |
| |
306 ILCID_POSIX_SUBTABLE(fa) { |
| |
307 {0x29, "fa"}, |
| |
308 {0x0429, "fa_IR"}, /* Persian/Farsi (Iran) */ |
| |
309 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */ |
| |
310 }; |
| |
311 |
| |
312 /* duplicate for roundtripping */ |
| |
313 ILCID_POSIX_SUBTABLE(fa_AF) { |
| |
314 {0x8c, "fa_AF"}, /* Persian/Dari (Afghanistan) */ |
| |
315 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */ |
| |
316 }; |
| |
317 |
| |
318 ILCID_POSIX_SUBTABLE(ff) { |
| |
319 {0x67, "ff"}, |
| |
320 {0x7c67, "ff_Latn"}, |
| |
321 {0x0867, "ff_Latn_SN"} |
| |
322 }; |
| |
323 |
| |
324 ILCID_POSIX_ELEMENT_ARRAY(0x040b, fi, fi_FI) |
| |
325 ILCID_POSIX_ELEMENT_ARRAY(0x0464, fil,fil_PH) |
| |
326 ILCID_POSIX_ELEMENT_ARRAY(0x0438, fo, fo_FO) |
| |
327 |
| |
328 ILCID_POSIX_SUBTABLE(fr) { |
| |
329 {0x0c, "fr"}, |
| |
330 {0x080c, "fr_BE"}, |
| |
331 {0x0c0c, "fr_CA"}, |
| |
332 {0x240c, "fr_CD"}, |
| |
333 {0x240c, "fr_CG"}, |
| |
334 {0x100c, "fr_CH"}, |
| |
335 {0x300c, "fr_CI"}, |
| |
336 {0x2c0c, "fr_CM"}, |
| |
337 {0x040c, "fr_FR"}, |
| |
338 {0x3c0c, "fr_HT"}, |
| |
339 {0x140c, "fr_LU"}, |
| |
340 {0x380c, "fr_MA"}, |
| |
341 {0x180c, "fr_MC"}, |
| |
342 {0x340c, "fr_ML"}, |
| |
343 {0x200c, "fr_RE"}, |
| |
344 {0x280c, "fr_SN"}, |
| |
345 {0xe40c, "fr_015"}, |
| |
346 {0x1c0c, "fr_029"} |
| |
347 }; |
| |
348 |
| |
349 ILCID_POSIX_ELEMENT_ARRAY(0x0467, fuv, fuv_NG) |
| |
350 |
| |
351 ILCID_POSIX_ELEMENT_ARRAY(0x0462, fy, fy_NL) |
| |
352 |
| |
353 ILCID_POSIX_SUBTABLE(ga) { /* Gaelic (Ireland) */ |
| |
354 {0x3c, "ga"}, |
| |
355 {0x083c, "ga_IE"}, |
| |
356 {0x043c, "gd_GB"} |
| |
357 }; |
| |
358 |
| |
359 ILCID_POSIX_SUBTABLE(gd) { /* Gaelic (Scotland) */ |
| |
360 {0x91, "gd"}, |
| |
361 {0x0491, "gd_GB"} |
| |
362 }; |
| |
363 |
| |
364 ILCID_POSIX_ELEMENT_ARRAY(0x0456, gl, gl_ES) |
| |
365 ILCID_POSIX_ELEMENT_ARRAY(0x0447, gu, gu_IN) |
| |
366 ILCID_POSIX_ELEMENT_ARRAY(0x0474, gn, gn_PY) |
| |
367 ILCID_POSIX_ELEMENT_ARRAY(0x0484, gsw,gsw_FR) |
| |
368 |
| |
369 ILCID_POSIX_SUBTABLE(ha) { |
| |
370 {0x68, "ha"}, |
| |
371 {0x7c68, "ha_Latn"}, |
| |
372 {0x0468, "ha_Latn_NG"}, |
| |
373 }; |
| |
374 |
| |
375 ILCID_POSIX_ELEMENT_ARRAY(0x0475, haw,haw_US) |
| |
376 ILCID_POSIX_ELEMENT_ARRAY(0x040d, he, he_IL) |
| |
377 ILCID_POSIX_ELEMENT_ARRAY(0x0439, hi, hi_IN) |
| |
378 |
| |
379 /* This LCID is really four different locales.*/ |
| |
380 ILCID_POSIX_SUBTABLE(hr) { |
| |
381 {0x1a, "hr"}, |
| |
382 {0x141a, "bs_Latn_BA"}, /* Bosnian, Bosnia and Herzegovina */ |
| |
383 {0x681a, "bs_Latn"}, /* Bosnian, Bosnia and Herzegovina */ |
| |
384 {0x141a, "bs_BA"}, /* Bosnian, Bosnia and Herzegovina */ |
| |
385 {0x781a, "bs"}, /* Bosnian */ |
| |
386 {0x201a, "bs_Cyrl_BA"}, /* Bosnian, Bosnia and Herzegovina */ |
| |
387 {0x641a, "bs_Cyrl"}, /* Bosnian, Bosnia and Herzegovina */ |
| |
388 {0x101a, "hr_BA"}, /* Croatian in Bosnia */ |
| |
389 {0x041a, "hr_HR"}, /* Croatian*/ |
| |
390 {0x2c1a, "sr_Latn_ME"}, |
| |
391 {0x241a, "sr_Latn_RS"}, |
| |
392 {0x181a, "sr_Latn_BA"}, /* Serbo-Croatian in Bosnia */ |
| |
393 {0x081a, "sr_Latn_CS"}, /* Serbo-Croatian*/ |
| |
394 {0x701a, "sr_Latn"}, /* It's 0x1a or 0x081a, pick one to make the test program happy. */ |
| |
395 {0x1c1a, "sr_Cyrl_BA"}, /* Serbo-Croatian in Bosnia */ |
| |
396 {0x0c1a, "sr_Cyrl_CS"}, /* Serbian*/ |
| |
397 {0x301a, "sr_Cyrl_ME"}, |
| |
398 {0x281a, "sr_Cyrl_RS"}, |
| |
399 {0x6c1a, "sr_Cyrl"}, /* It's 0x1a or 0x0c1a, pick one to make the test program happy. */ |
| |
400 {0x7c1a, "sr"} /* In CLDR sr is sr_Cyrl. */ |
| |
401 }; |
| |
402 |
| |
403 ILCID_POSIX_ELEMENT_ARRAY(0x040e, hu, hu_HU) |
| |
404 ILCID_POSIX_ELEMENT_ARRAY(0x042b, hy, hy_AM) |
| |
405 ILCID_POSIX_ELEMENT_ARRAY(0x0469, ibb, ibb_NG) |
| |
406 ILCID_POSIX_ELEMENT_ARRAY(0x0421, id, id_ID) |
| |
407 ILCID_POSIX_ELEMENT_ARRAY(0x0470, ig, ig_NG) |
| |
408 ILCID_POSIX_ELEMENT_ARRAY(0x0478, ii, ii_CN) |
| |
409 ILCID_POSIX_ELEMENT_ARRAY(0x040f, is, is_IS) |
| |
410 |
| |
411 ILCID_POSIX_SUBTABLE(it) { |
| |
412 {0x10, "it"}, |
| |
413 {0x0810, "it_CH"}, |
| |
414 {0x0410, "it_IT"} |
| |
415 }; |
| |
416 |
| |
417 ILCID_POSIX_SUBTABLE(iu) { |
| |
418 {0x5d, "iu"}, |
| |
419 {0x045d, "iu_Cans_CA"}, |
| |
420 {0x785d, "iu_Cans"}, |
| |
421 {0x085d, "iu_Latn_CA"}, |
| |
422 {0x7c5d, "iu_Latn"} |
| |
423 }; |
| |
424 |
| |
425 ILCID_POSIX_ELEMENT_ARRAY(0x040d, iw, iw_IL) /*Left in for compatibility*/ |
| |
426 ILCID_POSIX_ELEMENT_ARRAY(0x0411, ja, ja_JP) |
| |
427 ILCID_POSIX_ELEMENT_ARRAY(0x0437, ka, ka_GE) |
| |
428 ILCID_POSIX_ELEMENT_ARRAY(0x043f, kk, kk_KZ) |
| |
429 ILCID_POSIX_ELEMENT_ARRAY(0x046f, kl, kl_GL) |
| |
430 ILCID_POSIX_ELEMENT_ARRAY(0x0453, km, km_KH) |
| |
431 ILCID_POSIX_ELEMENT_ARRAY(0x044b, kn, kn_IN) |
| |
432 |
| |
433 ILCID_POSIX_SUBTABLE(ko) { |
| |
434 {0x12, "ko"}, |
| |
435 {0x0812, "ko_KP"}, |
| |
436 {0x0412, "ko_KR"} |
| |
437 }; |
| |
438 |
| |
439 ILCID_POSIX_ELEMENT_ARRAY(0x0457, kok, kok_IN) |
| |
440 ILCID_POSIX_ELEMENT_ARRAY(0x0471, kr, kr_NG) |
| |
441 |
| |
442 ILCID_POSIX_SUBTABLE(ks) { /* We could add PK and CN too */ |
| |
443 {0x60, "ks"}, |
| |
444 {0x0860, "ks_IN"}, /* Documentation doesn't mention script */ |
| |
445 {0x0460, "ks_Arab_IN"}, |
| |
446 {0x0860, "ks_Deva_IN"} |
| |
447 }; |
| |
448 |
| |
449 ILCID_POSIX_ELEMENT_ARRAY(0x0440, ky, ky_KG) /* Kyrgyz is spoken in Kyrgyzstan */ |
| |
450 ILCID_POSIX_ELEMENT_ARRAY(0x0476, la, la_IT) /* TODO: Verify the country */ |
| |
451 ILCID_POSIX_ELEMENT_ARRAY(0x046e, lb, lb_LU) |
| |
452 ILCID_POSIX_ELEMENT_ARRAY(0x0454, lo, lo_LA) |
| |
453 ILCID_POSIX_ELEMENT_ARRAY(0x0427, lt, lt_LT) |
| |
454 ILCID_POSIX_ELEMENT_ARRAY(0x0426, lv, lv_LV) |
| |
455 ILCID_POSIX_ELEMENT_ARRAY(0x0481, mi, mi_NZ) |
| |
456 ILCID_POSIX_ELEMENT_ARRAY(0x042f, mk, mk_MK) |
| |
457 ILCID_POSIX_ELEMENT_ARRAY(0x044c, ml, ml_IN) |
| |
458 |
| |
459 ILCID_POSIX_SUBTABLE(mn) { |
| |
460 {0x50, "mn"}, |
| |
461 {0x0450, "mn_MN"}, |
| |
462 {0x7c50, "mn_Mong"}, |
| |
463 {0x0850, "mn_Mong_CN"}, |
| |
464 {0x0850, "mn_CN"}, |
| |
465 {0x7850, "mn_Cyrl"} |
| |
466 }; |
| |
467 |
| |
468 ILCID_POSIX_ELEMENT_ARRAY(0x0458, mni,mni_IN) |
| |
469 ILCID_POSIX_ELEMENT_ARRAY(0x047c, moh,moh_CA) |
| |
470 ILCID_POSIX_ELEMENT_ARRAY(0x044e, mr, mr_IN) |
| |
471 |
| |
472 ILCID_POSIX_SUBTABLE(ms) { |
| |
473 {0x3e, "ms"}, |
| |
474 {0x083e, "ms_BN"}, /* Brunei Darussalam*/ |
| |
475 {0x043e, "ms_MY"} /* Malaysia*/ |
| |
476 }; |
| |
477 |
| |
478 ILCID_POSIX_ELEMENT_ARRAY(0x043a, mt, mt_MT) |
| |
479 ILCID_POSIX_ELEMENT_ARRAY(0x0455, my, my_MM) |
| |
480 |
| |
481 ILCID_POSIX_SUBTABLE(ne) { |
| |
482 {0x61, "ne"}, |
| |
483 {0x0861, "ne_IN"}, /* India*/ |
| |
484 {0x0461, "ne_NP"} /* Nepal*/ |
| |
485 }; |
| |
486 |
| |
487 ILCID_POSIX_SUBTABLE(nl) { |
| |
488 {0x13, "nl"}, |
| |
489 {0x0813, "nl_BE"}, |
| |
490 {0x0413, "nl_NL"} |
| |
491 }; |
| |
492 |
| |
493 /* The "no" locale split into nb and nn. By default in ICU, "no" is nb.*/ |
| |
494 ILCID_POSIX_SUBTABLE(no) { |
| |
495 {0x14, "no"}, /* really nb_NO */ |
| |
496 {0x7c14, "nb"}, /* really nb */ |
| |
497 {0x0414, "nb_NO"}, /* really nb_NO. Keep first in the 414 list. */ |
| |
498 {0x0414, "no_NO"}, /* really nb_NO */ |
| |
499 {0x0814, "nn_NO"}, /* really nn_NO. Keep first in the 814 list. */ |
| |
500 {0x7814, "nn"}, /* It's 0x14 or 0x814, pick one to make the test program happy. */ |
| |
501 {0x0814, "no_NO_NY"}/* really nn_NO */ |
| |
502 }; |
| |
503 |
| |
504 ILCID_POSIX_ELEMENT_ARRAY(0x046c, nso,nso_ZA) /* TODO: Verify the ISO-639 code */ |
| |
505 ILCID_POSIX_ELEMENT_ARRAY(0x0482, oc, oc_FR) |
| |
506 |
| |
507 ILCID_POSIX_SUBTABLE(om) { /* TODO: Verify the country */ |
| |
508 {0x72, "om"}, |
| |
509 {0x0472, "om_ET"}, |
| |
510 {0x0472, "gaz_ET"} |
| |
511 }; |
| |
512 |
| |
513 /* Declared as or_IN to get around compiler errors*/ |
| |
514 ILCID_POSIX_SUBTABLE(or_IN) { |
| |
515 {0x48, "or"}, |
| |
516 {0x0448, "or_IN"}, |
| |
517 }; |
| |
518 |
| |
519 |
| |
520 ILCID_POSIX_SUBTABLE(pa) { |
| |
521 {0x46, "pa"}, |
| |
522 {0x0446, "pa_IN"}, |
| |
523 {0x0846, "pa_PK"}, |
| |
524 {0x0846, "pa_Arab_PK"} |
| |
525 }; |
| |
526 |
| |
527 ILCID_POSIX_ELEMENT_ARRAY(0x0479, pap, pap_AN) |
| |
528 ILCID_POSIX_ELEMENT_ARRAY(0x0415, pl, pl_PL) |
| |
529 ILCID_POSIX_ELEMENT_ARRAY(0x0463, ps, ps_AF) |
| |
530 |
| |
531 ILCID_POSIX_SUBTABLE(pt) { |
| |
532 {0x16, "pt"}, |
| |
533 {0x0416, "pt_BR"}, |
| |
534 {0x0816, "pt_PT"} |
| |
535 }; |
| |
536 |
| |
537 ILCID_POSIX_SUBTABLE(qu) { |
| |
538 {0x6b, "qu"}, |
| |
539 {0x046b, "qu_BO"}, |
| |
540 {0x086b, "qu_EC"}, |
| |
541 {0x0C6b, "qu_PE"}, |
| |
542 {0x046b, "quz_BO"}, |
| |
543 {0x086b, "quz_EC"}, |
| |
544 {0x0C6b, "quz_PE"} |
| |
545 }; |
| |
546 |
| |
547 ILCID_POSIX_ELEMENT_ARRAY(0x0486, qut, qut_GT) /* qut is an ISO-639-3 code */ |
| |
548 ILCID_POSIX_ELEMENT_ARRAY(0x0417, rm, rm_CH) |
| |
549 |
| |
550 ILCID_POSIX_SUBTABLE(ro) { |
| |
551 {0x18, "ro"}, |
| |
552 {0x0418, "ro_RO"}, |
| |
553 {0x0818, "ro_MD"} |
| |
554 }; |
| |
555 |
| |
556 ILCID_POSIX_SUBTABLE(root) { |
| |
557 {0x00, "root"} |
| |
558 }; |
| |
559 |
| |
560 ILCID_POSIX_SUBTABLE(ru) { |
| |
561 {0x19, "ru"}, |
| |
562 {0x0419, "ru_RU"}, |
| |
563 {0x0819, "ru_MD"} |
| |
564 }; |
| |
565 |
| |
566 ILCID_POSIX_ELEMENT_ARRAY(0x0487, rw, rw_RW) |
| |
567 ILCID_POSIX_ELEMENT_ARRAY(0x044f, sa, sa_IN) |
| |
568 ILCID_POSIX_ELEMENT_ARRAY(0x0485, sah,sah_RU) |
| |
569 |
| |
570 ILCID_POSIX_SUBTABLE(sd) { |
| |
571 {0x59, "sd"}, |
| |
572 {0x0459, "sd_IN"}, |
| |
573 {0x0859, "sd_PK"} |
| |
574 }; |
| |
575 |
| |
576 ILCID_POSIX_SUBTABLE(se) { |
| |
577 {0x3b, "se"}, |
| |
578 {0x0c3b, "se_FI"}, |
| |
579 {0x043b, "se_NO"}, |
| |
580 {0x083b, "se_SE"}, |
| |
581 {0x783b, "sma"}, |
| |
582 {0x183b, "sma_NO"}, |
| |
583 {0x1c3b, "sma_SE"}, |
| |
584 {0x7c3b, "smj"}, |
| |
585 {0x703b, "smn"}, |
| |
586 {0x743b, "sms"}, |
| |
587 {0x103b, "smj_NO"}, |
| |
588 {0x143b, "smj_SE"}, |
| |
589 {0x243b, "smn_FI"}, |
| |
590 {0x203b, "sms_FI"}, |
| |
591 }; |
| |
592 |
| |
593 ILCID_POSIX_ELEMENT_ARRAY(0x045b, si, si_LK) |
| |
594 ILCID_POSIX_ELEMENT_ARRAY(0x041b, sk, sk_SK) |
| |
595 ILCID_POSIX_ELEMENT_ARRAY(0x0424, sl, sl_SI) |
| |
596 |
| |
597 ILCID_POSIX_SUBTABLE(so) { /* TODO: Verify the country */ |
| |
598 {0x77, "so"}, |
| |
599 {0x0477, "so_ET"}, |
| |
600 {0x0477, "so_SO"} |
| |
601 }; |
| |
602 |
| |
603 ILCID_POSIX_ELEMENT_ARRAY(0x041c, sq, sq_AL) |
| |
604 ILCID_POSIX_ELEMENT_ARRAY(0x0430, st, st_ZA) |
| |
605 |
| |
606 ILCID_POSIX_SUBTABLE(sv) { |
| |
607 {0x1d, "sv"}, |
| |
608 {0x081d, "sv_FI"}, |
| |
609 {0x041d, "sv_SE"} |
| |
610 }; |
| |
611 |
| |
612 ILCID_POSIX_ELEMENT_ARRAY(0x0441, sw, sw_KE) |
| |
613 ILCID_POSIX_ELEMENT_ARRAY(0x045A, syr, syr_SY) |
| |
614 |
| |
615 ILCID_POSIX_SUBTABLE(ta) { |
| |
616 {0x49, "ta"}, |
| |
617 {0x0449, "ta_IN"}, |
| |
618 {0x0849, "ta_LK"} |
| |
619 }; |
| |
620 |
| |
621 ILCID_POSIX_ELEMENT_ARRAY(0x044a, te, te_IN) |
| |
622 |
| |
623 /* Cyrillic based by default */ |
| |
624 ILCID_POSIX_SUBTABLE(tg) { |
| |
625 {0x28, "tg"}, |
| |
626 {0x7c28, "tg_Cyrl"}, |
| |
627 {0x0428, "tg_Cyrl_TJ"} |
| |
628 }; |
| |
629 |
| |
630 ILCID_POSIX_ELEMENT_ARRAY(0x041e, th, th_TH) |
| |
631 |
| |
632 ILCID_POSIX_SUBTABLE(ti) { |
| |
633 {0x73, "ti"}, |
| |
634 {0x0873, "ti_ER"}, |
| |
635 {0x0473, "ti_ET"} |
| |
636 }; |
| |
637 |
| |
638 ILCID_POSIX_ELEMENT_ARRAY(0x0442, tk, tk_TM) |
| |
639 |
| |
640 ILCID_POSIX_SUBTABLE(tn) { |
| |
641 {0x32, "tn"}, |
| |
642 {0x0832, "tn_BW"}, |
| |
643 {0x0432, "tn_ZA"} |
| |
644 }; |
| |
645 |
| |
646 ILCID_POSIX_ELEMENT_ARRAY(0x041f, tr, tr_TR) |
| |
647 ILCID_POSIX_ELEMENT_ARRAY(0x0431, ts, ts_ZA) |
| |
648 ILCID_POSIX_ELEMENT_ARRAY(0x0444, tt, tt_RU) |
| |
649 |
| |
650 ILCID_POSIX_SUBTABLE(tzm) { |
| |
651 {0x5f, "tzm"}, |
| |
652 {0x7c5f, "tzm_Latn"}, |
| |
653 {0x085f, "tzm_Latn_DZ"}, |
| |
654 {0x105f, "tzm_Tfng_MA"}, |
| |
655 {0x045f, "tmz"} |
| |
656 }; |
| |
657 |
| |
658 ILCID_POSIX_SUBTABLE(ug) { |
| |
659 {0x80, "ug"}, |
| |
660 {0x0480, "ug_CN"}, |
| |
661 {0x0480, "ug_Arab_CN"} |
| |
662 }; |
| |
663 |
| |
664 ILCID_POSIX_ELEMENT_ARRAY(0x0422, uk, uk_UA) |
| |
665 |
| |
666 ILCID_POSIX_SUBTABLE(ur) { |
| |
667 {0x20, "ur"}, |
| |
668 {0x0820, "ur_IN"}, |
| |
669 {0x0420, "ur_PK"} |
| |
670 }; |
| |
671 |
| |
672 ILCID_POSIX_SUBTABLE(uz) { |
| |
673 {0x43, "uz"}, |
| |
674 {0x0843, "uz_Cyrl_UZ"}, /* Cyrillic based */ |
| |
675 {0x7843, "uz_Cyrl"}, /* Cyrillic based */ |
| |
676 {0x0843, "uz_UZ"}, /* Cyrillic based */ |
| |
677 {0x0443, "uz_Latn_UZ"}, /* Latin based */ |
| |
678 {0x7c43, "uz_Latn"} /* Latin based */ |
| |
679 }; |
| |
680 |
| |
681 ILCID_POSIX_SUBTABLE(ve) { /* TODO: Verify the country */ |
| |
682 {0x33, "ve"}, |
| |
683 {0x0433, "ve_ZA"}, |
| |
684 {0x0433, "ven_ZA"} |
| |
685 }; |
| |
686 |
| |
687 ILCID_POSIX_ELEMENT_ARRAY(0x042a, vi, vi_VN) |
| |
688 |
| |
689 ILCID_POSIX_SUBTABLE(wen) { |
| |
690 {0x2E, "wen"}, |
| |
691 {0x042E, "wen_DE"}, |
| |
692 {0x042E, "hsb_DE"}, |
| |
693 {0x082E, "dsb_DE"}, |
| |
694 {0x7C2E, "dsb"}, |
| |
695 {0x2E, "hsb"} |
| |
696 }; |
| |
697 |
| |
698 ILCID_POSIX_ELEMENT_ARRAY(0x0488, wo, wo_SN) |
| |
699 ILCID_POSIX_ELEMENT_ARRAY(0x0434, xh, xh_ZA) |
| |
700 ILCID_POSIX_ELEMENT_ARRAY(0x043d, yi, yi) |
| |
701 ILCID_POSIX_ELEMENT_ARRAY(0x046a, yo, yo_NG) |
| |
702 |
| |
703 ILCID_POSIX_SUBTABLE(zh) { |
| |
704 {0x0004, "zh_Hans"}, |
| |
705 {0x7804, "zh"}, |
| |
706 {0x0804, "zh_CN"}, |
| |
707 {0x0804, "zh_Hans_CN"}, |
| |
708 {0x0c04, "zh_Hant_HK"}, |
| |
709 {0x0c04, "zh_HK"}, |
| |
710 {0x1404, "zh_Hant_MO"}, |
| |
711 {0x1404, "zh_MO"}, |
| |
712 {0x1004, "zh_Hans_SG"}, |
| |
713 {0x1004, "zh_SG"}, |
| |
714 {0x0404, "zh_Hant_TW"}, |
| |
715 {0x7c04, "zh_Hant"}, |
| |
716 {0x0404, "zh_TW"}, |
| |
717 {0x30404,"zh_Hant_TW"}, /* Bopomofo order */ |
| |
718 {0x30404,"zh_TW"}, /* Bopomofo order */ |
| |
719 {0x20004,"zh@collation=stroke"}, |
| |
720 {0x20404,"zh_Hant@collation=stroke"}, |
| |
721 {0x20404,"zh_Hant_TW@collation=stroke"}, |
| |
722 {0x20404,"zh_TW@collation=stroke"}, |
| |
723 {0x20804,"zh_Hans@collation=stroke"}, |
| |
724 {0x20804,"zh_Hans_CN@collation=stroke"}, |
| |
725 {0x20804,"zh_CN@collation=stroke"} |
| |
726 }; |
| |
727 |
| |
728 ILCID_POSIX_ELEMENT_ARRAY(0x0435, zu, zu_ZA) |
| |
729 |
| |
730 /* This must be static and grouped by LCID. */ |
| |
731 static const ILcidPosixMap gPosixIDmap[] = { |
| |
732 ILCID_POSIX_MAP(af), /* af Afrikaans 0x36 */ |
| |
733 ILCID_POSIX_MAP(am), /* am Amharic 0x5e */ |
| |
734 ILCID_POSIX_MAP(ar), /* ar Arabic 0x01 */ |
| |
735 ILCID_POSIX_MAP(arn), /* arn Araucanian/Mapudungun 0x7a */ |
| |
736 ILCID_POSIX_MAP(as), /* as Assamese 0x4d */ |
| |
737 ILCID_POSIX_MAP(az), /* az Azerbaijani 0x2c */ |
| |
738 ILCID_POSIX_MAP(ba), /* ba Bashkir 0x6d */ |
| |
739 ILCID_POSIX_MAP(be), /* be Belarusian 0x23 */ |
| |
740 /* ILCID_POSIX_MAP(ber), ber Berber/Tamazight 0x5f */ |
| |
741 ILCID_POSIX_MAP(bg), /* bg Bulgarian 0x02 */ |
| |
742 ILCID_POSIX_MAP(bin), /* bin Edo 0x66 */ |
| |
743 ILCID_POSIX_MAP(bn), /* bn Bengali; Bangla 0x45 */ |
| |
744 ILCID_POSIX_MAP(bo), /* bo Tibetan 0x51 */ |
| |
745 ILCID_POSIX_MAP(br), /* br Breton 0x7e */ |
| |
746 ILCID_POSIX_MAP(ca), /* ca Catalan 0x03 */ |
| |
747 ILCID_POSIX_MAP(chr), /* chr Cherokee 0x5c */ |
| |
748 ILCID_POSIX_MAP(ckb), /* ckb Sorani (Central Kurdish) 0x92 */ |
| |
749 ILCID_POSIX_MAP(co), /* co Corsican 0x83 */ |
| |
750 ILCID_POSIX_MAP(cs), /* cs Czech 0x05 */ |
| |
751 ILCID_POSIX_MAP(cy), /* cy Welsh 0x52 */ |
| |
752 ILCID_POSIX_MAP(da), /* da Danish 0x06 */ |
| |
753 ILCID_POSIX_MAP(de), /* de German 0x07 */ |
| |
754 ILCID_POSIX_MAP(dv), /* dv Divehi 0x65 */ |
| |
755 ILCID_POSIX_MAP(el), /* el Greek 0x08 */ |
| |
756 ILCID_POSIX_MAP(en), /* en English 0x09 */ |
| |
757 ILCID_POSIX_MAP(en_US_POSIX), /* invariant 0x7f */ |
| |
758 ILCID_POSIX_MAP(es), /* es Spanish 0x0a */ |
| |
759 ILCID_POSIX_MAP(et), /* et Estonian 0x25 */ |
| |
760 ILCID_POSIX_MAP(eu), /* eu Basque 0x2d */ |
| |
761 ILCID_POSIX_MAP(fa), /* fa Persian/Farsi 0x29 */ |
| |
762 ILCID_POSIX_MAP(fa_AF), /* fa Persian/Dari 0x8c */ |
| |
763 ILCID_POSIX_MAP(ff), /* ff Fula 0x67 */ |
| |
764 ILCID_POSIX_MAP(fi), /* fi Finnish 0x0b */ |
| |
765 ILCID_POSIX_MAP(fil), /* fil Filipino 0x64 */ |
| |
766 ILCID_POSIX_MAP(fo), /* fo Faroese 0x38 */ |
| |
767 ILCID_POSIX_MAP(fr), /* fr French 0x0c */ |
| |
768 ILCID_POSIX_MAP(fuv), /* fuv Fulfulde - Nigeria 0x67 */ |
| |
769 ILCID_POSIX_MAP(fy), /* fy Frisian 0x62 */ |
| |
770 ILCID_POSIX_MAP(ga), /* * Gaelic (Ireland,Scotland) 0x3c */ |
| |
771 ILCID_POSIX_MAP(gd), /* gd Gaelic (United Kingdom) 0x91 */ |
| |
772 ILCID_POSIX_MAP(gl), /* gl Galician 0x56 */ |
| |
773 ILCID_POSIX_MAP(gn), /* gn Guarani 0x74 */ |
| |
774 ILCID_POSIX_MAP(gsw), /* gsw Alemanic/Alsatian/Swiss German 0x84 */ |
| |
775 ILCID_POSIX_MAP(gu), /* gu Gujarati 0x47 */ |
| |
776 ILCID_POSIX_MAP(ha), /* ha Hausa 0x68 */ |
| |
777 ILCID_POSIX_MAP(haw), /* haw Hawaiian 0x75 */ |
| |
778 ILCID_POSIX_MAP(he), /* he Hebrew (formerly iw) 0x0d */ |
| |
779 ILCID_POSIX_MAP(hi), /* hi Hindi 0x39 */ |
| |
780 ILCID_POSIX_MAP(hr), /* * Croatian and others 0x1a */ |
| |
781 ILCID_POSIX_MAP(hu), /* hu Hungarian 0x0e */ |
| |
782 ILCID_POSIX_MAP(hy), /* hy Armenian 0x2b */ |
| |
783 ILCID_POSIX_MAP(ibb), /* ibb Ibibio - Nigeria 0x69 */ |
| |
784 ILCID_POSIX_MAP(id), /* id Indonesian (formerly in) 0x21 */ |
| |
785 ILCID_POSIX_MAP(ig), /* ig Igbo 0x70 */ |
| |
786 ILCID_POSIX_MAP(ii), /* ii Sichuan Yi 0x78 */ |
| |
787 ILCID_POSIX_MAP(is), /* is Icelandic 0x0f */ |
| |
788 ILCID_POSIX_MAP(it), /* it Italian 0x10 */ |
| |
789 ILCID_POSIX_MAP(iu), /* iu Inuktitut 0x5d */ |
| |
790 ILCID_POSIX_MAP(iw), /* iw Hebrew 0x0d */ |
| |
791 ILCID_POSIX_MAP(ja), /* ja Japanese 0x11 */ |
| |
792 ILCID_POSIX_MAP(ka), /* ka Georgian 0x37 */ |
| |
793 ILCID_POSIX_MAP(kk), /* kk Kazakh 0x3f */ |
| |
794 ILCID_POSIX_MAP(kl), /* kl Kalaallisut 0x6f */ |
| |
795 ILCID_POSIX_MAP(km), /* km Khmer 0x53 */ |
| |
796 ILCID_POSIX_MAP(kn), /* kn Kannada 0x4b */ |
| |
797 ILCID_POSIX_MAP(ko), /* ko Korean 0x12 */ |
| |
798 ILCID_POSIX_MAP(kok), /* kok Konkani 0x57 */ |
| |
799 ILCID_POSIX_MAP(kr), /* kr Kanuri 0x71 */ |
| |
800 ILCID_POSIX_MAP(ks), /* ks Kashmiri 0x60 */ |
| |
801 ILCID_POSIX_MAP(ky), /* ky Kyrgyz 0x40 */ |
| |
802 ILCID_POSIX_MAP(lb), /* lb Luxembourgish 0x6e */ |
| |
803 ILCID_POSIX_MAP(la), /* la Latin 0x76 */ |
| |
804 ILCID_POSIX_MAP(lo), /* lo Lao 0x54 */ |
| |
805 ILCID_POSIX_MAP(lt), /* lt Lithuanian 0x27 */ |
| |
806 ILCID_POSIX_MAP(lv), /* lv Latvian, Lettish 0x26 */ |
| |
807 ILCID_POSIX_MAP(mi), /* mi Maori 0x81 */ |
| |
808 ILCID_POSIX_MAP(mk), /* mk Macedonian 0x2f */ |
| |
809 ILCID_POSIX_MAP(ml), /* ml Malayalam 0x4c */ |
| |
810 ILCID_POSIX_MAP(mn), /* mn Mongolian 0x50 */ |
| |
811 ILCID_POSIX_MAP(mni), /* mni Manipuri 0x58 */ |
| |
812 ILCID_POSIX_MAP(moh), /* moh Mohawk 0x7c */ |
| |
813 ILCID_POSIX_MAP(mr), /* mr Marathi 0x4e */ |
| |
814 ILCID_POSIX_MAP(ms), /* ms Malay 0x3e */ |
| |
815 ILCID_POSIX_MAP(mt), /* mt Maltese 0x3a */ |
| |
816 ILCID_POSIX_MAP(my), /* my Burmese 0x55 */ |
| |
817 /* ILCID_POSIX_MAP(nb), // no Norwegian 0x14 */ |
| |
818 ILCID_POSIX_MAP(ne), /* ne Nepali 0x61 */ |
| |
819 ILCID_POSIX_MAP(nl), /* nl Dutch 0x13 */ |
| |
820 /* ILCID_POSIX_MAP(nn), // no Norwegian 0x14 */ |
| |
821 ILCID_POSIX_MAP(no), /* * Norwegian 0x14 */ |
| |
822 ILCID_POSIX_MAP(nso), /* nso Sotho, Northern (Sepedi dialect) 0x6c */ |
| |
823 ILCID_POSIX_MAP(oc), /* oc Occitan 0x82 */ |
| |
824 ILCID_POSIX_MAP(om), /* om Oromo 0x72 */ |
| |
825 ILCID_POSIX_MAP(or_IN), /* or Oriya 0x48 */ |
| |
826 ILCID_POSIX_MAP(pa), /* pa Punjabi 0x46 */ |
| |
827 ILCID_POSIX_MAP(pap), /* pap Papiamentu 0x79 */ |
| |
828 ILCID_POSIX_MAP(pl), /* pl Polish 0x15 */ |
| |
829 ILCID_POSIX_MAP(ps), /* ps Pashto 0x63 */ |
| |
830 ILCID_POSIX_MAP(pt), /* pt Portuguese 0x16 */ |
| |
831 ILCID_POSIX_MAP(qu), /* qu Quechua 0x6B */ |
| |
832 ILCID_POSIX_MAP(qut), /* qut K'iche 0x86 */ |
| |
833 ILCID_POSIX_MAP(rm), /* rm Raeto-Romance/Romansh 0x17 */ |
| |
834 ILCID_POSIX_MAP(ro), /* ro Romanian 0x18 */ |
| |
835 ILCID_POSIX_MAP(root), /* root 0x00 */ |
| |
836 ILCID_POSIX_MAP(ru), /* ru Russian 0x19 */ |
| |
837 ILCID_POSIX_MAP(rw), /* rw Kinyarwanda 0x87 */ |
| |
838 ILCID_POSIX_MAP(sa), /* sa Sanskrit 0x4f */ |
| |
839 ILCID_POSIX_MAP(sah), /* sah Yakut 0x85 */ |
| |
840 ILCID_POSIX_MAP(sd), /* sd Sindhi 0x59 */ |
| |
841 ILCID_POSIX_MAP(se), /* se Sami 0x3b */ |
| |
842 /* ILCID_POSIX_MAP(sh), // sh Serbo-Croatian 0x1a */ |
| |
843 ILCID_POSIX_MAP(si), /* si Sinhalese 0x5b */ |
| |
844 ILCID_POSIX_MAP(sk), /* sk Slovak 0x1b */ |
| |
845 ILCID_POSIX_MAP(sl), /* sl Slovenian 0x24 */ |
| |
846 ILCID_POSIX_MAP(so), /* so Somali 0x77 */ |
| |
847 ILCID_POSIX_MAP(sq), /* sq Albanian 0x1c */ |
| |
848 /* ILCID_POSIX_MAP(sr), // sr Serbian 0x1a */ |
| |
849 ILCID_POSIX_MAP(st), /* st Sutu 0x30 */ |
| |
850 ILCID_POSIX_MAP(sv), /* sv Swedish 0x1d */ |
| |
851 ILCID_POSIX_MAP(sw), /* sw Swahili 0x41 */ |
| |
852 ILCID_POSIX_MAP(syr), /* syr Syriac 0x5A */ |
| |
853 ILCID_POSIX_MAP(ta), /* ta Tamil 0x49 */ |
| |
854 ILCID_POSIX_MAP(te), /* te Telugu 0x4a */ |
| |
855 ILCID_POSIX_MAP(tg), /* tg Tajik 0x28 */ |
| |
856 ILCID_POSIX_MAP(th), /* th Thai 0x1e */ |
| |
857 ILCID_POSIX_MAP(ti), /* ti Tigrigna 0x73 */ |
| |
858 ILCID_POSIX_MAP(tk), /* tk Turkmen 0x42 */ |
| |
859 ILCID_POSIX_MAP(tn), /* tn Tswana 0x32 */ |
| |
860 ILCID_POSIX_MAP(tr), /* tr Turkish 0x1f */ |
| |
861 ILCID_POSIX_MAP(ts), /* ts Tsonga 0x31 */ |
| |
862 ILCID_POSIX_MAP(tt), /* tt Tatar 0x44 */ |
| |
863 ILCID_POSIX_MAP(tzm), /* tzm Tamazight 0x5f */ |
| |
864 ILCID_POSIX_MAP(ug), /* ug Uighur 0x80 */ |
| |
865 ILCID_POSIX_MAP(uk), /* uk Ukrainian 0x22 */ |
| |
866 ILCID_POSIX_MAP(ur), /* ur Urdu 0x20 */ |
| |
867 ILCID_POSIX_MAP(uz), /* uz Uzbek 0x43 */ |
| |
868 ILCID_POSIX_MAP(ve), /* ve Venda 0x33 */ |
| |
869 ILCID_POSIX_MAP(vi), /* vi Vietnamese 0x2a */ |
| |
870 ILCID_POSIX_MAP(wen), /* wen Sorbian 0x2e */ |
| |
871 ILCID_POSIX_MAP(wo), /* wo Wolof 0x88 */ |
| |
872 ILCID_POSIX_MAP(xh), /* xh Xhosa 0x34 */ |
| |
873 ILCID_POSIX_MAP(yi), /* yi Yiddish 0x3d */ |
| |
874 ILCID_POSIX_MAP(yo), /* yo Yoruba 0x6a */ |
| |
875 ILCID_POSIX_MAP(zh), /* zh Chinese 0x04 */ |
| |
876 ILCID_POSIX_MAP(zu), /* zu Zulu 0x35 */ |
| |
877 }; |
| |
878 |
| |
879 static const uint32_t gLocaleCount = sizeof(gPosixIDmap)/sizeof(ILcidPosixMap); |
| |
880 |
| |
881 /** |
| |
882 * Do not call this function. It is called by hostID. |
| |
883 * The function is not private because this struct must stay as a C struct, |
| |
884 * and this is an internal class. |
| |
885 */ |
| |
886 static int32_t |
| |
887 idCmp(const char* id1, const char* id2) |
| |
888 { |
| |
889 int32_t diffIdx = 0; |
| |
890 while (*id1 == *id2 && *id1 != 0) { |
| |
891 diffIdx++; |
| |
892 id1++; |
| |
893 id2++; |
| |
894 } |
| |
895 return diffIdx; |
| |
896 } |
| |
897 |
| |
898 /** |
| |
899 * Searches for a Windows LCID |
| |
900 * |
| |
901 * @param posixid the Posix style locale id. |
| |
902 * @param status gets set to U_ILLEGAL_ARGUMENT_ERROR when the Posix ID has |
| |
903 * no equivalent Windows LCID. |
| |
904 * @return the LCID |
| |
905 */ |
| |
906 static uint32_t |
| |
907 getHostID(const ILcidPosixMap *this_0, const char* posixID, UErrorCode* status) |
| |
908 { |
| |
909 int32_t bestIdx = 0; |
| |
910 int32_t bestIdxDiff = 0; |
| |
911 int32_t posixIDlen = (int32_t)uprv_strlen(posixID); |
| |
912 uint32_t idx; |
| |
913 |
| |
914 for (idx = 0; idx < this_0->numRegions; idx++ ) { |
| |
915 int32_t sameChars = idCmp(posixID, this_0->regionMaps[idx].posixID); |
| |
916 if (sameChars > bestIdxDiff && this_0->regionMaps[idx].posixID[sameChars] == 0) { |
| |
917 if (posixIDlen == sameChars) { |
| |
918 /* Exact match */ |
| |
919 return this_0->regionMaps[idx].hostID; |
| |
920 } |
| |
921 bestIdxDiff = sameChars; |
| |
922 bestIdx = idx; |
| |
923 } |
| |
924 } |
| |
925 /* We asked for something unusual, like en_ZZ, and we try to return the number for the same language. */ |
| |
926 /* We also have to make sure that sid and si and similar string subsets don't match. */ |
| |
927 if ((posixID[bestIdxDiff] == '_' || posixID[bestIdxDiff] == '@') |
| |
928 && this_0->regionMaps[bestIdx].posixID[bestIdxDiff] == 0) |
| |
929 { |
| |
930 *status = U_USING_FALLBACK_WARNING; |
| |
931 return this_0->regionMaps[bestIdx].hostID; |
| |
932 } |
| |
933 |
| |
934 /*no match found */ |
| |
935 *status = U_ILLEGAL_ARGUMENT_ERROR; |
| |
936 return this_0->regionMaps->hostID; |
| |
937 } |
| |
938 |
| |
939 static const char* |
| |
940 getPosixID(const ILcidPosixMap *this_0, uint32_t hostID) |
| |
941 { |
| |
942 uint32_t i; |
| |
943 for (i = 0; i <= this_0->numRegions; i++) |
| |
944 { |
| |
945 if (this_0->regionMaps[i].hostID == hostID) |
| |
946 { |
| |
947 return this_0->regionMaps[i].posixID; |
| |
948 } |
| |
949 } |
| |
950 |
| |
951 /* If you get here, then no matching region was found, |
| |
952 so return the language id with the wild card region. */ |
| |
953 return this_0->regionMaps[0].posixID; |
| |
954 } |
| |
955 |
| |
956 /* |
| |
957 ////////////////////////////////////// |
| |
958 // |
| |
959 // LCID --> POSIX |
| |
960 // |
| |
961 ///////////////////////////////////// |
| |
962 */ |
| |
963 #ifdef USE_WINDOWS_LOCALE_API |
| |
964 /* |
| |
965 * Various language tags needs to be changed: |
| |
966 * quz -> qu |
| |
967 * prs -> fa |
| |
968 */ |
| |
969 #define FIX_LANGUAGE_ID_TAG(buffer, len) \ |
| |
970 if (len >= 3) { \ |
| |
971 if (buffer[0] == 'q' && buffer[1] == 'u' && buffer[2] == 'z') {\ |
| |
972 buffer[2] = 0; \ |
| |
973 uprv_strcat(buffer, buffer+3); \ |
| |
974 } else if (buffer[0] == 'p' && buffer[1] == 'r' && buffer[2] == 's') {\ |
| |
975 buffer[0] = 'f'; buffer[1] = 'a'; buffer[2] = 0; \ |
| |
976 uprv_strcat(buffer, buffer+3); \ |
| |
977 } \ |
| |
978 } |
| |
979 |
| |
980 #endif |
| |
981 U_CAPI int32_t |
| |
982 uprv_convertToPosix(uint32_t hostid, char *posixID, int32_t posixIDCapacity, UErrorCode* status) |
| |
983 { |
| |
984 uint16_t langID; |
| |
985 uint32_t localeIndex; |
| |
986 UBool bLookup = TRUE; |
| |
987 const char *pPosixID = NULL; |
| |
988 |
| |
989 #ifdef USE_WINDOWS_LOCALE_API |
| |
990 int32_t tmpLen = 0; |
| |
991 char locName[157]; /* ULOC_FULLNAME_CAPACITY */ |
| |
992 |
| |
993 tmpLen = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)locName, sizeof(locName)/sizeof(locName[0])); |
| |
994 if (tmpLen > 1) { |
| |
995 /* Windows locale name may contain sorting variant, such as "es-ES_tradnl". |
| |
996 In such case, we need special mapping data found in the hardcoded table |
| |
997 in this source file. */ |
| |
998 char *p = uprv_strchr(locName, '_'); |
| |
999 if (p) { |
| |
1000 /* Keep the base locale, without variant */ |
| |
1001 *p = 0; |
| |
1002 tmpLen = uprv_strlen(locName); |
| |
1003 } else { |
| |
1004 /* No hardcoded table lookup necessary */ |
| |
1005 bLookup = FALSE; |
| |
1006 } |
| |
1007 /* Change the tag separator from '-' to '_' */ |
| |
1008 p = locName; |
| |
1009 while (*p) { |
| |
1010 if (*p == '-') { |
| |
1011 *p = '_'; |
| |
1012 } |
| |
1013 p++; |
| |
1014 } |
| |
1015 FIX_LANGUAGE_ID_TAG(locName, tmpLen); |
| |
1016 pPosixID = locName; |
| |
1017 } |
| |
1018 #endif |
| |
1019 if (bLookup) { |
| |
1020 const char *pCandidate = NULL; |
| |
1021 langID = LANGUAGE_LCID(hostid); |
| |
1022 |
| |
1023 for (localeIndex = 0; localeIndex < gLocaleCount; localeIndex++) { |
| |
1024 if (langID == gPosixIDmap[localeIndex].regionMaps->hostID) { |
| |
1025 pCandidate = getPosixID(&gPosixIDmap[localeIndex], hostid); |
| |
1026 break; |
| |
1027 } |
| |
1028 } |
| |
1029 |
| |
1030 /* On Windows, when locale name has a variant, we still look up the hardcoded table. |
| |
1031 If a match in the hardcoded table is longer than the Windows locale name without |
| |
1032 variant, we use the one as the result */ |
| |
1033 if (pCandidate && (pPosixID == NULL || uprv_strlen(pCandidate) > uprv_strlen(pPosixID))) { |
| |
1034 pPosixID = pCandidate; |
| |
1035 } |
| |
1036 } |
| |
1037 |
| |
1038 if (pPosixID) { |
| |
1039 int32_t resLen = uprv_strlen(pPosixID); |
| |
1040 int32_t copyLen = resLen <= posixIDCapacity ? resLen : posixIDCapacity; |
| |
1041 uprv_memcpy(posixID, pPosixID, copyLen); |
| |
1042 if (resLen < posixIDCapacity) { |
| |
1043 posixID[resLen] = 0; |
| |
1044 if (*status == U_STRING_NOT_TERMINATED_WARNING) { |
| |
1045 *status = U_ZERO_ERROR; |
| |
1046 } |
| |
1047 } else if (resLen == posixIDCapacity) { |
| |
1048 *status = U_STRING_NOT_TERMINATED_WARNING; |
| |
1049 } else { |
| |
1050 *status = U_BUFFER_OVERFLOW_ERROR; |
| |
1051 } |
| |
1052 return resLen; |
| |
1053 } |
| |
1054 |
| |
1055 /* no match found */ |
| |
1056 *status = U_ILLEGAL_ARGUMENT_ERROR; |
| |
1057 return -1; |
| |
1058 } |
| |
1059 |
| |
1060 /* |
| |
1061 ////////////////////////////////////// |
| |
1062 // |
| |
1063 // POSIX --> LCID |
| |
1064 // This should only be called from uloc_getLCID. |
| |
1065 // The locale ID must be in canonical form. |
| |
1066 // langID is separate so that this file doesn't depend on the uloc_* API. |
| |
1067 // |
| |
1068 ///////////////////////////////////// |
| |
1069 */ |
| |
1070 |
| |
1071 U_CAPI uint32_t |
| |
1072 uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status) |
| |
1073 { |
| |
1074 |
| |
1075 uint32_t low = 0; |
| |
1076 uint32_t high = gLocaleCount; |
| |
1077 uint32_t mid; |
| |
1078 uint32_t oldmid = 0; |
| |
1079 int32_t compVal; |
| |
1080 |
| |
1081 uint32_t value = 0; |
| |
1082 uint32_t fallbackValue = (uint32_t)-1; |
| |
1083 UErrorCode myStatus; |
| |
1084 uint32_t idx; |
| |
1085 |
| |
1086 /* Check for incomplete id. */ |
| |
1087 if (!langID || !posixID || uprv_strlen(langID) < 2 || uprv_strlen(posixID) < 2) { |
| |
1088 return 0; |
| |
1089 } |
| |
1090 |
| |
1091 /*Binary search for the map entry for normal cases */ |
| |
1092 |
| |
1093 while (high > low) /*binary search*/{ |
| |
1094 |
| |
1095 mid = (high+low) >> 1; /*Finds median*/ |
| |
1096 |
| |
1097 if (mid == oldmid) |
| |
1098 break; |
| |
1099 |
| |
1100 compVal = uprv_strcmp(langID, gPosixIDmap[mid].regionMaps->posixID); |
| |
1101 if (compVal < 0){ |
| |
1102 high = mid; |
| |
1103 } |
| |
1104 else if (compVal > 0){ |
| |
1105 low = mid; |
| |
1106 } |
| |
1107 else /*we found it*/{ |
| |
1108 return getHostID(&gPosixIDmap[mid], posixID, status); |
| |
1109 } |
| |
1110 oldmid = mid; |
| |
1111 } |
| |
1112 |
| |
1113 /* |
| |
1114 * Sometimes we can't do a binary search on posixID because some LCIDs |
| |
1115 * go to different locales. We hit one of those special cases. |
| |
1116 */ |
| |
1117 for (idx = 0; idx < gLocaleCount; idx++ ) { |
| |
1118 myStatus = U_ZERO_ERROR; |
| |
1119 value = getHostID(&gPosixIDmap[idx], posixID, &myStatus); |
| |
1120 if (myStatus == U_ZERO_ERROR) { |
| |
1121 return value; |
| |
1122 } |
| |
1123 else if (myStatus == U_USING_FALLBACK_WARNING) { |
| |
1124 fallbackValue = value; |
| |
1125 } |
| |
1126 } |
| |
1127 |
| |
1128 if (fallbackValue != (uint32_t)-1) { |
| |
1129 *status = U_USING_FALLBACK_WARNING; |
| |
1130 return fallbackValue; |
| |
1131 } |
| |
1132 |
| |
1133 /* no match found */ |
| |
1134 *status = U_ILLEGAL_ARGUMENT_ERROR; |
| |
1135 return 0; /* return international (root) */ |
| |
1136 } |
| |
1137 |