1 /*
2 **********************************************************************
3 * Copyright (C) 1996-2011, 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 "unicode/uloc.h"
30 #include "cstring.h"
31 #include "cmemory.h"
32
33 #if defined(U_WINDOWS) && defined(_MSC_VER) && (_MSC_VER >= 1500)
34 #define USE_WINDOWS_LOCALE_API
35 #endif
36
37 #ifdef USE_WINDOWS_LOCALE_API
38 #include <windows.h>
39 #include <winnls.h>
40 #endif
41
42 /*
43 * Note:
44 * The mapping from Win32 locale ID numbers to POSIX locale strings should
45 * be the faster one.
46 *
47 * Many LCID values come from winnt.h
48 * Some also come from http://www.microsoft.com/globaldev/reference/lcid-all.mspx
49 */
50
51 /*
52 ////////////////////////////////////////////////
53 //
54 // Internal Classes for LCID <--> POSIX Mapping
55 //
56 /////////////////////////////////////////////////
57 */
58
59 typedef struct ILcidPosixElement
60 {
61 const uint32_t hostID;
62 const char * const posixID;
63 } ILcidPosixElement;
64
65 typedef struct ILcidPosixMap
66 {
67 const uint32_t numRegions;
68 const struct ILcidPosixElement* const regionMaps;
69 } ILcidPosixMap;
70
71
72 /*
73 /////////////////////////////////////////////////
74 //
75 // Easy macros to make the LCID <--> POSIX Mapping
76 //
77 /////////////////////////////////////////////////
78 */
79
80 /**
81 * The standard one language/one country mapping for LCID.
82 * The first element must be the language, and the following
83 * elements are the language with the country.
84 * @param hostID LCID in host format such as 0x044d
85 * @param languageID posix ID of just the language such as 'de'
86 * @param posixID posix ID of the language_TERRITORY such as 'de_CH'
87 */
88 #define ILCID_POSIX_ELEMENT_ARRAY(hostID, languageID, posixID) \
89 static const ILcidPosixElement locmap_ ## languageID [] = { \
90 {LANGUAGE_LCID(hostID), #languageID}, /* parent locale */ \
91 {hostID, #posixID}, \
92 };
93
94 /**
95 * Define a subtable by ID
96 * @param id the POSIX ID, either a language or language_TERRITORY
97 */
98 #define ILCID_POSIX_SUBTABLE(id) \
99 static const ILcidPosixElement locmap_ ## id [] =
100
101
102 /**
103 * Create the map for the posixID. This macro supposes that the language string
104 * name is the same as the global variable name, and that the first element
105 * in the ILcidPosixElement is just the language.
106 * @param _posixID the full POSIX ID for this entry.
107 */
108 #define ILCID_POSIX_MAP(_posixID) \
109 {sizeof(locmap_ ## _posixID)/sizeof(ILcidPosixElement), locmap_ ## _posixID}
110
111 /*
112 ////////////////////////////////////////////
113 //
114 // Create the table of LCID to POSIX Mapping
115 // None of it should be dynamically created.
116 //
117 // Keep static locale variables inside the function so that
118 // it can be created properly during static init.
119 //
120 // Note: This table should be updated periodically. Check the National Lanaguage Support API Reference Website.
121 // Microsoft is moving away from LCID in favor of locale name as of Vista. This table needs to be
122 // maintained for support of older Windows version.
123 // Update: Windows 7 (091130)
124 ////////////////////////////////////////////
125 */
126
127 ILCID_POSIX_ELEMENT_ARRAY(0x0436, af, af_ZA)
128
ILCID_POSIX_SUBTABLE(ar)129 ILCID_POSIX_SUBTABLE(ar) {
130 {0x01, "ar"},
131 {0x3801, "ar_AE"},
132 {0x3c01, "ar_BH"},
133 {0x1401, "ar_DZ"},
134 {0x0c01, "ar_EG"},
135 {0x0801, "ar_IQ"},
136 {0x2c01, "ar_JO"},
137 {0x3401, "ar_KW"},
138 {0x3001, "ar_LB"},
139 {0x1001, "ar_LY"},
140 {0x1801, "ar_MA"},
141 {0x1801, "ar_MO"},
142 {0x2001, "ar_OM"},
143 {0x4001, "ar_QA"},
144 {0x0401, "ar_SA"},
145 {0x2801, "ar_SY"},
146 {0x1c01, "ar_TN"},
147 {0x2401, "ar_YE"}
148 };
149
150 ILCID_POSIX_ELEMENT_ARRAY(0x044d, as, as_IN)
151 ILCID_POSIX_ELEMENT_ARRAY(0x045e, am, am_ET)
152 ILCID_POSIX_ELEMENT_ARRAY(0x047a, arn,arn_CL)
153
ILCID_POSIX_SUBTABLE(az)154 ILCID_POSIX_SUBTABLE(az) {
155 {0x2c, "az"},
156 {0x082c, "az_Cyrl_AZ"}, /* Cyrillic based */
157 {0x742c, "az_Cyrl"}, /* Cyrillic based */
158 {0x042c, "az_Latn_AZ"}, /* Latin based */
159 {0x782c, "az_Latn"}, /* Latin based */
160 {0x042c, "az_AZ"} /* Latin based */
161 };
162
163 ILCID_POSIX_ELEMENT_ARRAY(0x046d, ba, ba_RU)
164 ILCID_POSIX_ELEMENT_ARRAY(0x0423, be, be_BY)
165
ILCID_POSIX_SUBTABLE(ber)166 ILCID_POSIX_SUBTABLE(ber) {
167 {0x5f, "ber"},
168 {0x045f, "ber_Arab_DZ"},
169 {0x045f, "ber_Arab"},
170 {0x085f, "ber_Latn_DZ"},
171 {0x085f, "ber_Latn"}
172 };
173
174 ILCID_POSIX_ELEMENT_ARRAY(0x0402, bg, bg_BG)
175
176 ILCID_POSIX_ELEMENT_ARRAY(0x0466, bin, bin_NG)
177
ILCID_POSIX_SUBTABLE(bn)178 ILCID_POSIX_SUBTABLE(bn) {
179 {0x45, "bn"},
180 {0x0845, "bn_BD"},
181 {0x0445, "bn_IN"}
182 };
183
ILCID_POSIX_SUBTABLE(bo)184 ILCID_POSIX_SUBTABLE(bo) {
185 {0x51, "bo"},
186 {0x0851, "bo_BT"},
187 {0x0451, "bo_CN"}
188 };
189
190 ILCID_POSIX_ELEMENT_ARRAY(0x047e, br, br_FR)
191 ILCID_POSIX_ELEMENT_ARRAY(0x0403, ca, ca_ES)
192 ILCID_POSIX_ELEMENT_ARRAY(0x0483, co, co_FR)
193 ILCID_POSIX_ELEMENT_ARRAY(0x045c, chr,chr_US)
194
195 /* Declared as cs_CZ to get around compiler errors on z/OS, which defines cs as a function */
196 ILCID_POSIX_ELEMENT_ARRAY(0x0405, cs, cs_CZ)
197
198 ILCID_POSIX_ELEMENT_ARRAY(0x0452, cy, cy_GB)
199 ILCID_POSIX_ELEMENT_ARRAY(0x0406, da, da_DK)
200
ILCID_POSIX_SUBTABLE(de)201 ILCID_POSIX_SUBTABLE(de) {
202 {0x07, "de"},
203 {0x0c07, "de_AT"},
204 {0x0807, "de_CH"},
205 {0x0407, "de_DE"},
206 {0x1407, "de_LI"},
207 {0x1007, "de_LU"},
208 {0x10407,"de_DE@collation=phonebook"}, /*This is really de_DE_PHONEBOOK on Windows*/
209 {0x10407,"de@collation=phonebook"} /*This is really de_DE_PHONEBOOK on Windows*/
210 };
211
212 ILCID_POSIX_ELEMENT_ARRAY(0x0465, dv, dv_MV)
213 ILCID_POSIX_ELEMENT_ARRAY(0x0408, el, el_GR)
214
ILCID_POSIX_SUBTABLE(en)215 ILCID_POSIX_SUBTABLE(en) {
216 {0x09, "en"},
217 {0x0c09, "en_AU"},
218 {0x2809, "en_BZ"},
219 {0x1009, "en_CA"},
220 {0x0809, "en_GB"},
221 {0x3c09, "en_HK"},
222 {0x3809, "en_ID"},
223 {0x1809, "en_IE"},
224 {0x4009, "en_IN"},
225 {0x2009, "en_JM"},
226 {0x4409, "en_MY"},
227 {0x1409, "en_NZ"},
228 {0x3409, "en_PH"},
229 {0x4809, "en_SG"},
230 {0x2C09, "en_TT"},
231 {0x0409, "en_US"},
232 {0x007f, "en_US_POSIX"}, /* duplicate for roundtripping */
233 {0x2409, "en_VI"}, /* Virgin Islands AKA Caribbean Islands (en_CB). */
234 {0x1c09, "en_ZA"},
235 {0x3009, "en_ZW"},
236 {0x2409, "en_029"},
237 {0x0409, "en_AS"}, /* Alias for en_US. Leave last. */
238 {0x0409, "en_GU"}, /* Alias for en_US. Leave last. */
239 {0x0409, "en_MH"}, /* Alias for en_US. Leave last. */
240 {0x0409, "en_MP"}, /* Alias for en_US. Leave last. */
241 {0x0409, "en_UM"} /* Alias for en_US. Leave last. */
242 };
243
ILCID_POSIX_SUBTABLE(en_US_POSIX)244 ILCID_POSIX_SUBTABLE(en_US_POSIX) {
245 {0x007f, "en_US_POSIX"} /* duplicate for roundtripping */
246 };
247
ILCID_POSIX_SUBTABLE(es)248 ILCID_POSIX_SUBTABLE(es) {
249 {0x0a, "es"},
250 {0x2c0a, "es_AR"},
251 {0x400a, "es_BO"},
252 {0x340a, "es_CL"},
253 {0x240a, "es_CO"},
254 {0x140a, "es_CR"},
255 {0x1c0a, "es_DO"},
256 {0x300a, "es_EC"},
257 {0x0c0a, "es_ES"}, /*Modern sort.*/
258 {0x100a, "es_GT"},
259 {0x480a, "es_HN"},
260 {0x080a, "es_MX"},
261 {0x4c0a, "es_NI"},
262 {0x180a, "es_PA"},
263 {0x280a, "es_PE"},
264 {0x500a, "es_PR"},
265 {0x3c0a, "es_PY"},
266 {0x440a, "es_SV"},
267 {0x540a, "es_US"},
268 {0x380a, "es_UY"},
269 {0x200a, "es_VE"},
270 {0xe40a, "es_419"},
271 {0x040a, "es_ES@collation=traditional"},
272 {0x040a, "es@collation=traditional"}
273 };
274
275 ILCID_POSIX_ELEMENT_ARRAY(0x0425, et, et_EE)
276 ILCID_POSIX_ELEMENT_ARRAY(0x042d, eu, eu_ES)
277
278 /* ISO-639 doesn't distinguish between Persian and Dari.*/
ILCID_POSIX_SUBTABLE(fa)279 ILCID_POSIX_SUBTABLE(fa) {
280 {0x29, "fa"},
281 {0x0429, "fa_IR"}, /* Persian/Farsi (Iran) */
282 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */
283 };
284
285 /* duplicate for roundtripping */
ILCID_POSIX_SUBTABLE(fa_AF)286 ILCID_POSIX_SUBTABLE(fa_AF) {
287 {0x8c, "fa_AF"}, /* Persian/Dari (Afghanistan) */
288 {0x048c, "fa_AF"} /* Persian/Dari (Afghanistan) */
289 };
290
291 ILCID_POSIX_ELEMENT_ARRAY(0x040b, fi, fi_FI)
292 ILCID_POSIX_ELEMENT_ARRAY(0x0464, fil,fil_PH)
293 ILCID_POSIX_ELEMENT_ARRAY(0x0438, fo, fo_FO)
294
ILCID_POSIX_SUBTABLE(fr)295 ILCID_POSIX_SUBTABLE(fr) {
296 {0x0c, "fr"},
297 {0x080c, "fr_BE"},
298 {0x0c0c, "fr_CA"},
299 {0x240c, "fr_CD"},
300 {0x240c, "fr_CG"},
301 {0x100c, "fr_CH"},
302 {0x300c, "fr_CI"},
303 {0x2c0c, "fr_CM"},
304 {0x040c, "fr_FR"},
305 {0x3c0c, "fr_HT"},
306 {0x140c, "fr_LU"},
307 {0x380c, "fr_MA"},
308 {0x180c, "fr_MC"},
309 {0x340c, "fr_ML"},
310 {0x200c, "fr_RE"},
311 {0x280c, "fr_SN"},
312 {0xe40c, "fr_015"},
313 {0x1c0c, "fr_029"}
314 };
315
316 ILCID_POSIX_ELEMENT_ARRAY(0x0467, fuv, fuv_NG)
317
318 ILCID_POSIX_ELEMENT_ARRAY(0x0462, fy, fy_NL)
319
ILCID_POSIX_SUBTABLE(ga)320 ILCID_POSIX_SUBTABLE(ga) { /* Gaelic (Ireland) */
321 {0x3c, "ga"},
322 {0x083c, "ga_IE"},
323 {0x043c, "gd_GB"}
324 };
325
ILCID_POSIX_SUBTABLE(gd)326 ILCID_POSIX_SUBTABLE(gd) { /* Gaelic (Scotland) */
327 {0x91, "gd"},
328 {0x0491, "gd_GB"}
329 };
330
331 ILCID_POSIX_ELEMENT_ARRAY(0x0456, gl, gl_ES)
332 ILCID_POSIX_ELEMENT_ARRAY(0x0447, gu, gu_IN)
333 ILCID_POSIX_ELEMENT_ARRAY(0x0474, gn, gn_PY)
334 ILCID_POSIX_ELEMENT_ARRAY(0x0484, gsw,gsw_FR)
335
ILCID_POSIX_SUBTABLE(ha)336 ILCID_POSIX_SUBTABLE(ha) {
337 {0x68, "ha"},
338 {0x7c68, "ha_Latn"},
339 {0x0468, "ha_Latn_NG"},
340 };
341
342 ILCID_POSIX_ELEMENT_ARRAY(0x0475, haw,haw_US)
343 ILCID_POSIX_ELEMENT_ARRAY(0x040d, he, he_IL)
344 ILCID_POSIX_ELEMENT_ARRAY(0x0439, hi, hi_IN)
345
346 /* This LCID is really four different locales.*/
ILCID_POSIX_SUBTABLE(hr)347 ILCID_POSIX_SUBTABLE(hr) {
348 {0x1a, "hr"},
349 {0x141a, "bs_Latn_BA"}, /* Bosnian, Bosnia and Herzegovina */
350 {0x681a, "bs_Latn"}, /* Bosnian, Bosnia and Herzegovina */
351 {0x141a, "bs_BA"}, /* Bosnian, Bosnia and Herzegovina */
352 {0x781a, "bs"}, /* Bosnian */
353 {0x201a, "bs_Cyrl_BA"}, /* Bosnian, Bosnia and Herzegovina */
354 {0x641a, "bs_Cyrl"}, /* Bosnian, Bosnia and Herzegovina */
355 {0x101a, "hr_BA"}, /* Croatian in Bosnia */
356 {0x041a, "hr_HR"}, /* Croatian*/
357 {0x2c1a, "sr_Latn_ME"},
358 {0x241a, "sr_Latn_RS"},
359 {0x181a, "sr_Latn_BA"}, /* Serbo-Croatian in Bosnia */
360 {0x081a, "sr_Latn_CS"}, /* Serbo-Croatian*/
361 {0x701a, "sr_Latn"}, /* It's 0x1a or 0x081a, pick one to make the test program happy. */
362 {0x1c1a, "sr_Cyrl_BA"}, /* Serbo-Croatian in Bosnia */
363 {0x0c1a, "sr_Cyrl_CS"}, /* Serbian*/
364 {0x301a, "sr_Cyrl_ME"},
365 {0x281a, "sr_Cyrl_RS"},
366 {0x6c1a, "sr_Cyrl"}, /* It's 0x1a or 0x0c1a, pick one to make the test program happy. */
367 {0x7c1a, "sr"} /* In CLDR sr is sr_Cyrl. */
368 };
369
370 ILCID_POSIX_ELEMENT_ARRAY(0x040e, hu, hu_HU)
371 ILCID_POSIX_ELEMENT_ARRAY(0x042b, hy, hy_AM)
372 ILCID_POSIX_ELEMENT_ARRAY(0x0469, ibb, ibb_NG)
373 ILCID_POSIX_ELEMENT_ARRAY(0x0421, id, id_ID)
374 ILCID_POSIX_ELEMENT_ARRAY(0x0470, ig, ig_NG)
375 ILCID_POSIX_ELEMENT_ARRAY(0x0478, ii, ii_CN)
376 ILCID_POSIX_ELEMENT_ARRAY(0x040f, is, is_IS)
377
ILCID_POSIX_SUBTABLE(it)378 ILCID_POSIX_SUBTABLE(it) {
379 {0x10, "it"},
380 {0x0810, "it_CH"},
381 {0x0410, "it_IT"}
382 };
383
ILCID_POSIX_SUBTABLE(iu)384 ILCID_POSIX_SUBTABLE(iu) {
385 {0x5d, "iu"},
386 {0x045d, "iu_Cans_CA"},
387 {0x785d, "iu_Cans"},
388 {0x085d, "iu_Latn_CA"},
389 {0x7c5d, "iu_Latn"}
390 };
391
392 ILCID_POSIX_ELEMENT_ARRAY(0x040d, iw, iw_IL) /*Left in for compatibility*/
393 ILCID_POSIX_ELEMENT_ARRAY(0x0411, ja, ja_JP)
394 ILCID_POSIX_ELEMENT_ARRAY(0x0437, ka, ka_GE)
395 ILCID_POSIX_ELEMENT_ARRAY(0x043f, kk, kk_KZ)
396 ILCID_POSIX_ELEMENT_ARRAY(0x046f, kl, kl_GL)
397 ILCID_POSIX_ELEMENT_ARRAY(0x0453, km, km_KH)
398 ILCID_POSIX_ELEMENT_ARRAY(0x044b, kn, kn_IN)
399
ILCID_POSIX_SUBTABLE(ko)400 ILCID_POSIX_SUBTABLE(ko) {
401 {0x12, "ko"},
402 {0x0812, "ko_KP"},
403 {0x0412, "ko_KR"}
404 };
405
406 ILCID_POSIX_ELEMENT_ARRAY(0x0457, kok, kok_IN)
407 ILCID_POSIX_ELEMENT_ARRAY(0x0471, kr, kr_NG)
408
ILCID_POSIX_SUBTABLE(ks)409 ILCID_POSIX_SUBTABLE(ks) { /* We could add PK and CN too */
410 {0x60, "ks"},
411 {0x0860, "ks_IN"}, /* Documentation doesn't mention script */
412 {0x0460, "ks_Arab_IN"},
413 {0x0860, "ks_Deva_IN"}
414 };
415
416 ILCID_POSIX_ELEMENT_ARRAY(0x0440, ky, ky_KG) /* Kyrgyz is spoken in Kyrgyzstan */
417 ILCID_POSIX_ELEMENT_ARRAY(0x0476, la, la_IT) /* TODO: Verify the country */
418 ILCID_POSIX_ELEMENT_ARRAY(0x046e, lb, lb_LU)
419 ILCID_POSIX_ELEMENT_ARRAY(0x0454, lo, lo_LA)
420 ILCID_POSIX_ELEMENT_ARRAY(0x0427, lt, lt_LT)
421 ILCID_POSIX_ELEMENT_ARRAY(0x0426, lv, lv_LV)
422 ILCID_POSIX_ELEMENT_ARRAY(0x0481, mi, mi_NZ)
423 ILCID_POSIX_ELEMENT_ARRAY(0x042f, mk, mk_MK)
424 ILCID_POSIX_ELEMENT_ARRAY(0x044c, ml, ml_IN)
425
ILCID_POSIX_SUBTABLE(mn)426 ILCID_POSIX_SUBTABLE(mn) {
427 {0x50, "mn"},
428 {0x0450, "mn_MN"},
429 {0x7c50, "mn_Mong"},
430 {0x0850, "mn_Mong_CN"},
431 {0x0850, "mn_CN"},
432 {0x7850, "mn_Cyrl"}
433 };
434
435 ILCID_POSIX_ELEMENT_ARRAY(0x0458, mni,mni_IN)
436 ILCID_POSIX_ELEMENT_ARRAY(0x047c, moh,moh_CA)
437 ILCID_POSIX_ELEMENT_ARRAY(0x044e, mr, mr_IN)
438
ILCID_POSIX_SUBTABLE(ms)439 ILCID_POSIX_SUBTABLE(ms) {
440 {0x3e, "ms"},
441 {0x083e, "ms_BN"}, /* Brunei Darussalam*/
442 {0x043e, "ms_MY"} /* Malaysia*/
443 };
444
445 ILCID_POSIX_ELEMENT_ARRAY(0x043a, mt, mt_MT)
446 ILCID_POSIX_ELEMENT_ARRAY(0x0455, my, my_MM)
447
ILCID_POSIX_SUBTABLE(ne)448 ILCID_POSIX_SUBTABLE(ne) {
449 {0x61, "ne"},
450 {0x0861, "ne_IN"}, /* India*/
451 {0x0461, "ne_NP"} /* Nepal*/
452 };
453
ILCID_POSIX_SUBTABLE(nl)454 ILCID_POSIX_SUBTABLE(nl) {
455 {0x13, "nl"},
456 {0x0813, "nl_BE"},
457 {0x0413, "nl_NL"}
458 };
459
460 /* The "no" locale split into nb and nn. By default in ICU, "no" is nb.*/
ILCID_POSIX_SUBTABLE(no)461 ILCID_POSIX_SUBTABLE(no) {
462 {0x14, "no"}, /* really nb_NO */
463 {0x7c14, "nb"}, /* really nb */
464 {0x0414, "nb_NO"}, /* really nb_NO. Keep first in the 414 list. */
465 {0x0414, "no_NO"}, /* really nb_NO */
466 {0x0814, "nn_NO"}, /* really nn_NO. Keep first in the 814 list. */
467 {0x7814, "nn"}, /* It's 0x14 or 0x814, pick one to make the test program happy. */
468 {0x0814, "no_NO_NY"}/* really nn_NO */
469 };
470
471 ILCID_POSIX_ELEMENT_ARRAY(0x046c, nso,nso_ZA) /* TODO: Verify the ISO-639 code */
472 ILCID_POSIX_ELEMENT_ARRAY(0x0482, oc, oc_FR)
473
ILCID_POSIX_SUBTABLE(om)474 ILCID_POSIX_SUBTABLE(om) { /* TODO: Verify the country */
475 {0x72, "om"},
476 {0x0472, "om_ET"},
477 {0x0472, "gaz_ET"}
478 };
479
480 /* Declared as or_IN to get around compiler errors*/
ILCID_POSIX_SUBTABLE(or_IN)481 ILCID_POSIX_SUBTABLE(or_IN) {
482 {0x48, "or"},
483 {0x0448, "or_IN"},
484 };
485
486
ILCID_POSIX_SUBTABLE(pa)487 ILCID_POSIX_SUBTABLE(pa) {
488 {0x46, "pa"},
489 {0x0446, "pa_IN"},
490 {0x0846, "pa_PK"}
491 };
492
493 ILCID_POSIX_ELEMENT_ARRAY(0x0479, pap, pap_AN)
494 ILCID_POSIX_ELEMENT_ARRAY(0x0415, pl, pl_PL)
495 ILCID_POSIX_ELEMENT_ARRAY(0x0463, ps, ps_AF)
496
ILCID_POSIX_SUBTABLE(pt)497 ILCID_POSIX_SUBTABLE(pt) {
498 {0x16, "pt"},
499 {0x0416, "pt_BR"},
500 {0x0816, "pt_PT"}
501 };
502
ILCID_POSIX_SUBTABLE(qu)503 ILCID_POSIX_SUBTABLE(qu) {
504 {0x6b, "qu"},
505 {0x046b, "qu_BO"},
506 {0x086b, "qu_EC"},
507 {0x0C6b, "qu_PE"},
508 {0x046b, "quz_BO"},
509 {0x086b, "quz_EC"},
510 {0x0C6b, "quz_PE"}
511 };
512
513 ILCID_POSIX_ELEMENT_ARRAY(0x0486, qut, qut_GT) /* qut is an ISO-639-3 code */
514 ILCID_POSIX_ELEMENT_ARRAY(0x0417, rm, rm_CH)
515
ILCID_POSIX_SUBTABLE(ro)516 ILCID_POSIX_SUBTABLE(ro) {
517 {0x18, "ro"},
518 {0x0418, "ro_RO"},
519 {0x0818, "ro_MD"}
520 };
521
ILCID_POSIX_SUBTABLE(root)522 ILCID_POSIX_SUBTABLE(root) {
523 {0x00, "root"}
524 };
525
ILCID_POSIX_SUBTABLE(ru)526 ILCID_POSIX_SUBTABLE(ru) {
527 {0x19, "ru"},
528 {0x0419, "ru_RU"},
529 {0x0819, "ru_MD"}
530 };
531
532 ILCID_POSIX_ELEMENT_ARRAY(0x0487, rw, rw_RW)
533 ILCID_POSIX_ELEMENT_ARRAY(0x044f, sa, sa_IN)
534 ILCID_POSIX_ELEMENT_ARRAY(0x0485, sah,sah_RU)
535
ILCID_POSIX_SUBTABLE(sd)536 ILCID_POSIX_SUBTABLE(sd) {
537 {0x59, "sd"},
538 {0x0459, "sd_IN"},
539 {0x0859, "sd_PK"}
540 };
541
ILCID_POSIX_SUBTABLE(se)542 ILCID_POSIX_SUBTABLE(se) {
543 {0x3b, "se"},
544 {0x0c3b, "se_FI"},
545 {0x043b, "se_NO"},
546 {0x083b, "se_SE"},
547 {0x783b, "sma"},
548 {0x183b, "sma_NO"},
549 {0x1c3b, "sma_SE"},
550 {0x7c3b, "smj"},
551 {0x703b, "smn"},
552 {0x743b, "sms"},
553 {0x103b, "smj_NO"},
554 {0x143b, "smj_SE"},
555 {0x243b, "smn_FI"},
556 {0x203b, "sms_FI"},
557 };
558
559 ILCID_POSIX_ELEMENT_ARRAY(0x045b, si, si_LK)
560 ILCID_POSIX_ELEMENT_ARRAY(0x041b, sk, sk_SK)
561 ILCID_POSIX_ELEMENT_ARRAY(0x0424, sl, sl_SI)
562
ILCID_POSIX_SUBTABLE(so)563 ILCID_POSIX_SUBTABLE(so) { /* TODO: Verify the country */
564 {0x77, "so"},
565 {0x0477, "so_ET"},
566 {0x0477, "so_SO"}
567 };
568
569 ILCID_POSIX_ELEMENT_ARRAY(0x041c, sq, sq_AL)
570 ILCID_POSIX_ELEMENT_ARRAY(0x0430, st, st_ZA)
571
ILCID_POSIX_SUBTABLE(sv)572 ILCID_POSIX_SUBTABLE(sv) {
573 {0x1d, "sv"},
574 {0x081d, "sv_FI"},
575 {0x041d, "sv_SE"}
576 };
577
578 ILCID_POSIX_ELEMENT_ARRAY(0x0441, sw, sw_KE)
579 ILCID_POSIX_ELEMENT_ARRAY(0x045A, syr, syr_SY)
580 ILCID_POSIX_ELEMENT_ARRAY(0x0449, ta, ta_IN)
581 ILCID_POSIX_ELEMENT_ARRAY(0x044a, te, te_IN)
582
583 /* Cyrillic based by default */
ILCID_POSIX_SUBTABLE(tg)584 ILCID_POSIX_SUBTABLE(tg) {
585 {0x28, "tg"},
586 {0x7c28, "tg_Cyrl"},
587 {0x0428, "tg_Cyrl_TJ"}
588 };
589
590 ILCID_POSIX_ELEMENT_ARRAY(0x041e, th, th_TH)
591
ILCID_POSIX_SUBTABLE(ti)592 ILCID_POSIX_SUBTABLE(ti) {
593 {0x73, "ti"},
594 {0x0473, "ti_ER"},
595 {0x0873, "ti_ER"},
596 {0x0873, "ti_ET"},
597 {0x0473, "ti_ET"}
598 };
599
600 ILCID_POSIX_ELEMENT_ARRAY(0x0442, tk, tk_TM)
601
ILCID_POSIX_SUBTABLE(tn)602 ILCID_POSIX_SUBTABLE(tn) {
603 {0x32, "tn"},
604 {0x0432, "tn_BW"},
605 {0x0432, "tn_ZA"}
606 };
607
608 ILCID_POSIX_ELEMENT_ARRAY(0x041f, tr, tr_TR)
609 ILCID_POSIX_ELEMENT_ARRAY(0x0431, ts, ts_ZA)
610 ILCID_POSIX_ELEMENT_ARRAY(0x0444, tt, tt_RU)
611
ILCID_POSIX_SUBTABLE(tzm)612 ILCID_POSIX_SUBTABLE(tzm) {
613 {0x5f, "tzm"},
614 {0x7c5f, "tzm_Latn"},
615 {0x085f, "tzm_Latn_DZ"},
616 {0x045f, "tmz"}
617 };
618
ILCID_POSIX_SUBTABLE(ug)619 ILCID_POSIX_SUBTABLE(ug) {
620 {0x80, "ug"},
621 {0x0480, "ug_CN"},
622 {0x0480, "ug_Arab_CN"}
623 };
624
625 ILCID_POSIX_ELEMENT_ARRAY(0x0422, uk, uk_UA)
626
ILCID_POSIX_SUBTABLE(ur)627 ILCID_POSIX_SUBTABLE(ur) {
628 {0x20, "ur"},
629 {0x0820, "ur_IN"},
630 {0x0420, "ur_PK"}
631 };
632
ILCID_POSIX_SUBTABLE(uz)633 ILCID_POSIX_SUBTABLE(uz) {
634 {0x43, "uz"},
635 {0x0843, "uz_Cyrl_UZ"}, /* Cyrillic based */
636 {0x7843, "uz_Cyrl"}, /* Cyrillic based */
637 {0x0843, "uz_UZ"}, /* Cyrillic based */
638 {0x0443, "uz_Latn_UZ"}, /* Latin based */
639 {0x7c43, "uz_Latn"} /* Latin based */
640 };
641
ILCID_POSIX_SUBTABLE(ve)642 ILCID_POSIX_SUBTABLE(ve) { /* TODO: Verify the country */
643 {0x33, "ve"},
644 {0x0433, "ve_ZA"},
645 {0x0433, "ven_ZA"}
646 };
647
648 ILCID_POSIX_ELEMENT_ARRAY(0x042a, vi, vi_VN)
649
ILCID_POSIX_SUBTABLE(wen)650 ILCID_POSIX_SUBTABLE(wen) {
651 {0x2E, "wen"},
652 {0x042E, "wen_DE"},
653 {0x042E, "hsb_DE"},
654 {0x082E, "dsb_DE"},
655 {0x7C2E, "dsb"},
656 {0x2E, "hsb"}
657 };
658
659 ILCID_POSIX_ELEMENT_ARRAY(0x0488, wo, wo_SN)
660 ILCID_POSIX_ELEMENT_ARRAY(0x0434, xh, xh_ZA)
661 ILCID_POSIX_ELEMENT_ARRAY(0x043d, yi, yi)
662 ILCID_POSIX_ELEMENT_ARRAY(0x046a, yo, yo_NG)
663
ILCID_POSIX_SUBTABLE(zh)664 ILCID_POSIX_SUBTABLE(zh) {
665 {0x0004, "zh_Hans"},
666 {0x7804, "zh"},
667 {0x0804, "zh_CN"},
668 {0x0804, "zh_Hans_CN"},
669 {0x0c04, "zh_Hant_HK"},
670 {0x0c04, "zh_HK"},
671 {0x1404, "zh_Hant_MO"},
672 {0x1404, "zh_MO"},
673 {0x1004, "zh_Hans_SG"},
674 {0x1004, "zh_SG"},
675 {0x0404, "zh_Hant_TW"},
676 {0x7c04, "zh_Hant"},
677 {0x0404, "zh_TW"},
678 {0x30404,"zh_Hant_TW"}, /* Bopomofo order */
679 {0x30404,"zh_TW"}, /* Bopomofo order */
680 {0x20004,"zh@collation=stroke"},
681 {0x20404,"zh_Hant@collation=stroke"},
682 {0x20404,"zh_Hant_TW@collation=stroke"},
683 {0x20404,"zh_TW@collation=stroke"},
684 {0x20804,"zh_Hans@collation=stroke"},
685 {0x20804,"zh_Hans_CN@collation=stroke"},
686 {0x20804,"zh_CN@collation=stroke"}
687 };
688
689 ILCID_POSIX_ELEMENT_ARRAY(0x0435, zu, zu_ZA)
690
691 /* This must be static and grouped by LCID. */
692 static const ILcidPosixMap gPosixIDmap[] = {
693 ILCID_POSIX_MAP(af), /* af Afrikaans 0x36 */
694 ILCID_POSIX_MAP(am), /* am Amharic 0x5e */
695 ILCID_POSIX_MAP(ar), /* ar Arabic 0x01 */
696 ILCID_POSIX_MAP(arn), /* arn Araucanian/Mapudungun 0x7a */
697 ILCID_POSIX_MAP(as), /* as Assamese 0x4d */
698 ILCID_POSIX_MAP(az), /* az Azerbaijani 0x2c */
699 ILCID_POSIX_MAP(ba), /* ba Bashkir 0x6d */
700 ILCID_POSIX_MAP(be), /* be Belarusian 0x23 */
701 /* ILCID_POSIX_MAP(ber), ber Berber/Tamazight 0x5f */
702 ILCID_POSIX_MAP(bg), /* bg Bulgarian 0x02 */
703 ILCID_POSIX_MAP(bin), /* bin Edo 0x66 */
704 ILCID_POSIX_MAP(bn), /* bn Bengali; Bangla 0x45 */
705 ILCID_POSIX_MAP(bo), /* bo Tibetan 0x51 */
706 ILCID_POSIX_MAP(br), /* br Breton 0x7e */
707 ILCID_POSIX_MAP(ca), /* ca Catalan 0x03 */
708 ILCID_POSIX_MAP(chr), /* chr Cherokee 0x5c */
709 ILCID_POSIX_MAP(co), /* co Corsican 0x83 */
710 ILCID_POSIX_MAP(cs), /* cs Czech 0x05 */
711 ILCID_POSIX_MAP(cy), /* cy Welsh 0x52 */
712 ILCID_POSIX_MAP(da), /* da Danish 0x06 */
713 ILCID_POSIX_MAP(de), /* de German 0x07 */
714 ILCID_POSIX_MAP(dv), /* dv Divehi 0x65 */
715 ILCID_POSIX_MAP(el), /* el Greek 0x08 */
716 ILCID_POSIX_MAP(en), /* en English 0x09 */
717 ILCID_POSIX_MAP(en_US_POSIX), /* invariant 0x7f */
718 ILCID_POSIX_MAP(es), /* es Spanish 0x0a */
719 ILCID_POSIX_MAP(et), /* et Estonian 0x25 */
720 ILCID_POSIX_MAP(eu), /* eu Basque 0x2d */
721 ILCID_POSIX_MAP(fa), /* fa Persian/Farsi 0x29 */
722 ILCID_POSIX_MAP(fa_AF), /* fa Persian/Dari 0x8c */
723 ILCID_POSIX_MAP(fi), /* fi Finnish 0x0b */
724 ILCID_POSIX_MAP(fil), /* fil Filipino 0x64 */
725 ILCID_POSIX_MAP(fo), /* fo Faroese 0x38 */
726 ILCID_POSIX_MAP(fr), /* fr French 0x0c */
727 ILCID_POSIX_MAP(fuv), /* fuv Fulfulde - Nigeria 0x67 */
728 ILCID_POSIX_MAP(fy), /* fy Frisian 0x62 */
729 ILCID_POSIX_MAP(ga), /* * Gaelic (Ireland,Scotland) 0x3c */
730 ILCID_POSIX_MAP(gd), /* gd Gaelic (United Kingdom) 0x91 */
731 ILCID_POSIX_MAP(gl), /* gl Galician 0x56 */
732 ILCID_POSIX_MAP(gn), /* gn Guarani 0x74 */
733 ILCID_POSIX_MAP(gsw), /* gsw Alemanic/Alsatian/Swiss German 0x84 */
734 ILCID_POSIX_MAP(gu), /* gu Gujarati 0x47 */
735 ILCID_POSIX_MAP(ha), /* ha Hausa 0x68 */
736 ILCID_POSIX_MAP(haw), /* haw Hawaiian 0x75 */
737 ILCID_POSIX_MAP(he), /* he Hebrew (formerly iw) 0x0d */
738 ILCID_POSIX_MAP(hi), /* hi Hindi 0x39 */
739 ILCID_POSIX_MAP(hr), /* * Croatian and others 0x1a */
740 ILCID_POSIX_MAP(hu), /* hu Hungarian 0x0e */
741 ILCID_POSIX_MAP(hy), /* hy Armenian 0x2b */
742 ILCID_POSIX_MAP(ibb), /* ibb Ibibio - Nigeria 0x69 */
743 ILCID_POSIX_MAP(id), /* id Indonesian (formerly in) 0x21 */
744 ILCID_POSIX_MAP(ig), /* ig Igbo 0x70 */
745 ILCID_POSIX_MAP(ii), /* ii Sichuan Yi 0x78 */
746 ILCID_POSIX_MAP(is), /* is Icelandic 0x0f */
747 ILCID_POSIX_MAP(it), /* it Italian 0x10 */
748 ILCID_POSIX_MAP(iu), /* iu Inuktitut 0x5d */
749 ILCID_POSIX_MAP(iw), /* iw Hebrew 0x0d */
750 ILCID_POSIX_MAP(ja), /* ja Japanese 0x11 */
751 ILCID_POSIX_MAP(ka), /* ka Georgian 0x37 */
752 ILCID_POSIX_MAP(kk), /* kk Kazakh 0x3f */
753 ILCID_POSIX_MAP(kl), /* kl Kalaallisut 0x6f */
754 ILCID_POSIX_MAP(km), /* km Khmer 0x53 */
755 ILCID_POSIX_MAP(kn), /* kn Kannada 0x4b */
756 ILCID_POSIX_MAP(ko), /* ko Korean 0x12 */
757 ILCID_POSIX_MAP(kok), /* kok Konkani 0x57 */
758 ILCID_POSIX_MAP(kr), /* kr Kanuri 0x71 */
759 ILCID_POSIX_MAP(ks), /* ks Kashmiri 0x60 */
760 ILCID_POSIX_MAP(ky), /* ky Kyrgyz 0x40 */
761 ILCID_POSIX_MAP(lb), /* lb Luxembourgish 0x6e */
762 ILCID_POSIX_MAP(la), /* la Latin 0x76 */
763 ILCID_POSIX_MAP(lo), /* lo Lao 0x54 */
764 ILCID_POSIX_MAP(lt), /* lt Lithuanian 0x27 */
765 ILCID_POSIX_MAP(lv), /* lv Latvian, Lettish 0x26 */
766 ILCID_POSIX_MAP(mi), /* mi Maori 0x81 */
767 ILCID_POSIX_MAP(mk), /* mk Macedonian 0x2f */
768 ILCID_POSIX_MAP(ml), /* ml Malayalam 0x4c */
769 ILCID_POSIX_MAP(mn), /* mn Mongolian 0x50 */
770 ILCID_POSIX_MAP(mni), /* mni Manipuri 0x58 */
771 ILCID_POSIX_MAP(moh), /* moh Mohawk 0x7c */
772 ILCID_POSIX_MAP(mr), /* mr Marathi 0x4e */
773 ILCID_POSIX_MAP(ms), /* ms Malay 0x3e */
774 ILCID_POSIX_MAP(mt), /* mt Maltese 0x3a */
775 ILCID_POSIX_MAP(my), /* my Burmese 0x55 */
776 /* ILCID_POSIX_MAP(nb), // no Norwegian 0x14 */
777 ILCID_POSIX_MAP(ne), /* ne Nepali 0x61 */
778 ILCID_POSIX_MAP(nl), /* nl Dutch 0x13 */
779 /* ILCID_POSIX_MAP(nn), // no Norwegian 0x14 */
780 ILCID_POSIX_MAP(no), /* * Norwegian 0x14 */
781 ILCID_POSIX_MAP(nso), /* nso Sotho, Northern (Sepedi dialect) 0x6c */
782 ILCID_POSIX_MAP(oc), /* oc Occitan 0x82 */
783 ILCID_POSIX_MAP(om), /* om Oromo 0x72 */
784 ILCID_POSIX_MAP(or_IN), /* or Oriya 0x48 */
785 ILCID_POSIX_MAP(pa), /* pa Punjabi 0x46 */
786 ILCID_POSIX_MAP(pap), /* pap Papiamentu 0x79 */
787 ILCID_POSIX_MAP(pl), /* pl Polish 0x15 */
788 ILCID_POSIX_MAP(ps), /* ps Pashto 0x63 */
789 ILCID_POSIX_MAP(pt), /* pt Portuguese 0x16 */
790 ILCID_POSIX_MAP(qu), /* qu Quechua 0x6B */
791 ILCID_POSIX_MAP(qut), /* qut K'iche 0x86 */
792 ILCID_POSIX_MAP(rm), /* rm Raeto-Romance/Romansh 0x17 */
793 ILCID_POSIX_MAP(ro), /* ro Romanian 0x18 */
794 ILCID_POSIX_MAP(root), /* root 0x00 */
795 ILCID_POSIX_MAP(ru), /* ru Russian 0x19 */
796 ILCID_POSIX_MAP(rw), /* rw Kinyarwanda 0x87 */
797 ILCID_POSIX_MAP(sa), /* sa Sanskrit 0x4f */
798 ILCID_POSIX_MAP(sah), /* sah Yakut 0x85 */
799 ILCID_POSIX_MAP(sd), /* sd Sindhi 0x59 */
800 ILCID_POSIX_MAP(se), /* se Sami 0x3b */
801 /* ILCID_POSIX_MAP(sh), // sh Serbo-Croatian 0x1a */
802 ILCID_POSIX_MAP(si), /* si Sinhalese 0x5b */
803 ILCID_POSIX_MAP(sk), /* sk Slovak 0x1b */
804 ILCID_POSIX_MAP(sl), /* sl Slovenian 0x24 */
805 ILCID_POSIX_MAP(so), /* so Somali 0x77 */
806 ILCID_POSIX_MAP(sq), /* sq Albanian 0x1c */
807 /* ILCID_POSIX_MAP(sr), // sr Serbian 0x1a */
808 ILCID_POSIX_MAP(st), /* st Sutu 0x30 */
809 ILCID_POSIX_MAP(sv), /* sv Swedish 0x1d */
810 ILCID_POSIX_MAP(sw), /* sw Swahili 0x41 */
811 ILCID_POSIX_MAP(syr), /* syr Syriac 0x5A */
812 ILCID_POSIX_MAP(ta), /* ta Tamil 0x49 */
813 ILCID_POSIX_MAP(te), /* te Telugu 0x4a */
814 ILCID_POSIX_MAP(tg), /* tg Tajik 0x28 */
815 ILCID_POSIX_MAP(th), /* th Thai 0x1e */
816 ILCID_POSIX_MAP(ti), /* ti Tigrigna 0x73 */
817 ILCID_POSIX_MAP(tk), /* tk Turkmen 0x42 */
818 ILCID_POSIX_MAP(tn), /* tn Tswana 0x32 */
819 ILCID_POSIX_MAP(tr), /* tr Turkish 0x1f */
820 ILCID_POSIX_MAP(ts), /* ts Tsonga 0x31 */
821 ILCID_POSIX_MAP(tt), /* tt Tatar 0x44 */
822 ILCID_POSIX_MAP(tzm), /* tzm Tamazight 0x5f */
823 ILCID_POSIX_MAP(ug), /* ug Uighur 0x80 */
824 ILCID_POSIX_MAP(uk), /* uk Ukrainian 0x22 */
825 ILCID_POSIX_MAP(ur), /* ur Urdu 0x20 */
826 ILCID_POSIX_MAP(uz), /* uz Uzbek 0x43 */
827 ILCID_POSIX_MAP(ve), /* ve Venda 0x33 */
828 ILCID_POSIX_MAP(vi), /* vi Vietnamese 0x2a */
829 ILCID_POSIX_MAP(wen), /* wen Sorbian 0x2e */
830 ILCID_POSIX_MAP(wo), /* wo Wolof 0x88 */
831 ILCID_POSIX_MAP(xh), /* xh Xhosa 0x34 */
832 ILCID_POSIX_MAP(yi), /* yi Yiddish 0x3d */
833 ILCID_POSIX_MAP(yo), /* yo Yoruba 0x6a */
834 ILCID_POSIX_MAP(zh), /* zh Chinese 0x04 */
835 ILCID_POSIX_MAP(zu), /* zu Zulu 0x35 */
836 };
837
838 static const uint32_t gLocaleCount = sizeof(gPosixIDmap)/sizeof(ILcidPosixMap);
839
840 /**
841 * Do not call this function. It is called by hostID.
842 * The function is not private because this struct must stay as a C struct,
843 * and this is an internal class.
844 */
845 static int32_t
idCmp(const char * id1,const char * id2)846 idCmp(const char* id1, const char* id2)
847 {
848 int32_t diffIdx = 0;
849 while (*id1 == *id2 && *id1 != 0) {
850 diffIdx++;
851 id1++;
852 id2++;
853 }
854 return diffIdx;
855 }
856
857 /**
858 * Searches for a Windows LCID
859 *
860 * @param posixid the Posix style locale id.
861 * @param status gets set to U_ILLEGAL_ARGUMENT_ERROR when the Posix ID has
862 * no equivalent Windows LCID.
863 * @return the LCID
864 */
865 static uint32_t
getHostID(const ILcidPosixMap * this_0,const char * posixID,UErrorCode * status)866 getHostID(const ILcidPosixMap *this_0, const char* posixID, UErrorCode* status)
867 {
868 int32_t bestIdx = 0;
869 int32_t bestIdxDiff = 0;
870 int32_t posixIDlen = (int32_t)uprv_strlen(posixID);
871 uint32_t idx;
872
873 for (idx = 0; idx < this_0->numRegions; idx++ ) {
874 int32_t sameChars = idCmp(posixID, this_0->regionMaps[idx].posixID);
875 if (sameChars > bestIdxDiff && this_0->regionMaps[idx].posixID[sameChars] == 0) {
876 if (posixIDlen == sameChars) {
877 /* Exact match */
878 return this_0->regionMaps[idx].hostID;
879 }
880 bestIdxDiff = sameChars;
881 bestIdx = idx;
882 }
883 }
884 /* We asked for something unusual, like en_ZZ, and we try to return the number for the same language. */
885 /* We also have to make sure that sid and si and similar string subsets don't match. */
886 if ((posixID[bestIdxDiff] == '_' || posixID[bestIdxDiff] == '@')
887 && this_0->regionMaps[bestIdx].posixID[bestIdxDiff] == 0)
888 {
889 *status = U_USING_FALLBACK_WARNING;
890 return this_0->regionMaps[bestIdx].hostID;
891 }
892
893 /*no match found */
894 *status = U_ILLEGAL_ARGUMENT_ERROR;
895 return this_0->regionMaps->hostID;
896 }
897
898 static const char*
getPosixID(const ILcidPosixMap * this_0,uint32_t hostID)899 getPosixID(const ILcidPosixMap *this_0, uint32_t hostID)
900 {
901 uint32_t i;
902 for (i = 0; i <= this_0->numRegions; i++)
903 {
904 if (this_0->regionMaps[i].hostID == hostID)
905 {
906 return this_0->regionMaps[i].posixID;
907 }
908 }
909
910 /* If you get here, then no matching region was found,
911 so return the language id with the wild card region. */
912 return this_0->regionMaps[0].posixID;
913 }
914
915 /*
916 //////////////////////////////////////
917 //
918 // LCID --> POSIX
919 //
920 /////////////////////////////////////
921 */
922 #ifdef USE_WINDOWS_LOCALE_API
923 /*
924 * Change the tag separator from '-' to '_'
925 */
926 #define FIX_LOCALE_ID_TAG_SEPARATOR(buffer, len, i) \
927 for(i = 0; i < len; i++) \
928 if (buffer[i] == '-') buffer[i] = '_';
929
930 /*
931 * Various language tags needs to be changed:
932 * quz -> qu
933 * prs -> fa
934 */
935 #define FIX_LANGUAGE_ID_TAG(buffer, len) \
936 if (len >= 3) { \
937 if (buffer[0] == 'q' && buffer[1] == 'u' && buffer[2] == 'z') {\
938 buffer[2] = 0; \
939 uprv_strcat(buffer, buffer+3); \
940 } else if (buffer[0] == 'p' && buffer[1] == 'r' && buffer[2] == 's') {\
941 buffer[0] = 'f'; buffer[1] = 'a'; buffer[2] = 0; \
942 uprv_strcat(buffer, buffer+3); \
943 } \
944 }
945
946 static char gPosixFromLCID[ULOC_FULLNAME_CAPACITY];
947 #endif
948 U_CAPI const char *
uprv_convertToPosix(uint32_t hostid,UErrorCode * status)949 uprv_convertToPosix(uint32_t hostid, UErrorCode* status)
950 {
951 uint16_t langID;
952 uint32_t localeIndex;
953 #ifdef USE_WINDOWS_LOCALE_API
954 int32_t ret = 0;
955
956 uprv_memset(gPosixFromLCID, 0, sizeof(gPosixFromLCID));
957
958 ret = GetLocaleInfoA(hostid, LOCALE_SNAME, (LPSTR)gPosixFromLCID, sizeof(gPosixFromLCID));
959 if (ret > 1) {
960 FIX_LOCALE_ID_TAG_SEPARATOR(gPosixFromLCID, (uint32_t)ret, localeIndex)
961 FIX_LANGUAGE_ID_TAG(gPosixFromLCID, ret)
962
963 return gPosixFromLCID;
964 }
965 #endif
966 langID = LANGUAGE_LCID(hostid);
967
968 for (localeIndex = 0; localeIndex < gLocaleCount; localeIndex++)
969 {
970 if (langID == gPosixIDmap[localeIndex].regionMaps->hostID)
971 {
972 return getPosixID(&gPosixIDmap[localeIndex], hostid);
973 }
974 }
975
976 /* no match found */
977 *status = U_ILLEGAL_ARGUMENT_ERROR;
978 return NULL;
979 }
980
981 /*
982 //////////////////////////////////////
983 //
984 // POSIX --> LCID
985 // This should only be called from uloc_getLCID.
986 // The locale ID must be in canonical form.
987 // langID is separate so that this file doesn't depend on the uloc_* API.
988 //
989 /////////////////////////////////////
990 */
991
992 U_CAPI uint32_t
uprv_convertToLCID(const char * langID,const char * posixID,UErrorCode * status)993 uprv_convertToLCID(const char *langID, const char* posixID, UErrorCode* status)
994 {
995
996 uint32_t low = 0;
997 uint32_t high = gLocaleCount;
998 uint32_t mid = high;
999 uint32_t oldmid = 0;
1000 int32_t compVal;
1001
1002 uint32_t value = 0;
1003 uint32_t fallbackValue = (uint32_t)-1;
1004 UErrorCode myStatus;
1005 uint32_t idx;
1006
1007 /* Check for incomplete id. */
1008 if (!langID || !posixID || uprv_strlen(langID) < 2 || uprv_strlen(posixID) < 2) {
1009 return 0;
1010 }
1011
1012 /*Binary search for the map entry for normal cases */
1013
1014 while (high > low) /*binary search*/{
1015
1016 mid = (high+low) >> 1; /*Finds median*/
1017
1018 if (mid == oldmid)
1019 break;
1020
1021 compVal = uprv_strcmp(langID, gPosixIDmap[mid].regionMaps->posixID);
1022 if (compVal < 0){
1023 high = mid;
1024 }
1025 else if (compVal > 0){
1026 low = mid;
1027 }
1028 else /*we found it*/{
1029 return getHostID(&gPosixIDmap[mid], posixID, status);
1030 }
1031 oldmid = mid;
1032 }
1033
1034 /*
1035 * Sometimes we can't do a binary search on posixID because some LCIDs
1036 * go to different locales. We hit one of those special cases.
1037 */
1038 for (idx = 0; idx < gLocaleCount; idx++ ) {
1039 myStatus = U_ZERO_ERROR;
1040 value = getHostID(&gPosixIDmap[idx], posixID, &myStatus);
1041 if (myStatus == U_ZERO_ERROR) {
1042 return value;
1043 }
1044 else if (myStatus == U_USING_FALLBACK_WARNING) {
1045 fallbackValue = value;
1046 }
1047 }
1048
1049 if (fallbackValue != (uint32_t)-1) {
1050 *status = U_USING_FALLBACK_WARNING;
1051 return fallbackValue;
1052 }
1053
1054 /* no match found */
1055 *status = U_ILLEGAL_ARGUMENT_ERROR;
1056 return 0; /* return international (root) */
1057 }
1058
1059