?  search:
summary | log | graphiclog1 | graphiclog2 | commit | commitdiff | tree | refs | edit | fork
blame | history | raw | HEAD
msvcrt: Remove MSVCRT_wchar_t type.
[wine.git] / tools / wrc / utils.c
blob78cc09c54b1e7ff1b375ff6ca52bbb9d489eb43c
1 /*
2 * Utility routines
3 *
4 * Copyright 1998 Bertho A. Stultiens
5 *
6 * This library is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
10 *
11 * This library is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
15 *
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with this library; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA
19 */
20
21 #include "config.h"
22 #include "wine/port.h"
23
24 #include <assert.h>
25 #include <stdio.h>
26 #include <stdlib.h>
27 #include <stdarg.h>
28 #include <string.h>
29 #include <ctype.h>
30
31 #include "wrc.h"
32 #include "utils.h"
33 #include "parser.h"
34
35 /* #define WANT_NEAR_INDICATION */
36
37 #ifdef WANT_NEAR_INDICATION
38 void make_print(char *str)
39 {
40 while(*str)
41 {
42 if(!isprint(*str))
43 *str = ' ';
44 str++;
45 }
46 }
47 #endif
48
49 static void generic_msg(const char *s, const char *t, const char *n, va_list ap)
50 {
51 fprintf(stderr, "%s:%d:%d: %s: ", input_name ? input_name : "stdin", line_number, char_number, t);
52 vfprintf(stderr, s, ap);
53 #ifdef WANT_NEAR_INDICATION
54 {
55 char *cpy;
56 if(n)
57 {
58 cpy = xstrdup(n);
59 make_print(cpy);
60 fprintf(stderr, " near '%s'", cpy);
61 free(cpy);
62 }
63 }
64 #endif
65 }
66
67
68 int parser_error(const char *s, ...)
69 {
70 va_list ap;
71 va_start(ap, s);
72 generic_msg(s, "Error", parser_text, ap);
73 fputc( '\n', stderr );
74 va_end(ap);
75 exit(1);
76 return 1;
77 }
78
79 int parser_warning(const char *s, ...)
80 {
81 va_list ap;
82 va_start(ap, s);
83 generic_msg(s, "Warning", parser_text, ap);
84 va_end(ap);
85 return 0;
86 }
87
88 void internal_error(const char *file, int line, const char *s, ...)
89 {
90 va_list ap;
91 va_start(ap, s);
92 fprintf(stderr, "Internal error (please report) %s %d: ", file, line);
93 vfprintf(stderr, s, ap);
94 va_end(ap);
95 exit(3);
96 }
97
98 void fatal_perror( const char *msg, ... )
99 {
100 va_list valist;
101 va_start( valist, msg );
102 fprintf(stderr, "Error: ");
103 vfprintf( stderr, msg, valist );
104 perror( " " );
105 va_end( valist );
106 exit(2);
107 }
108
109 void error(const char *s, ...)
110 {
111 va_list ap;
112 va_start(ap, s);
113 fprintf(stderr, "Error: ");
114 vfprintf(stderr, s, ap);
115 va_end(ap);
116 exit(2);
117 }
118
119 void warning(const char *s, ...)
120 {
121 va_list ap;
122 va_start(ap, s);
123 fprintf(stderr, "Warning: ");
124 vfprintf(stderr, s, ap);
125 va_end(ap);
126 }
127
128 void chat(const char *s, ...)
129 {
130 if(debuglevel & DEBUGLEVEL_CHAT)
131 {
132 va_list ap;
133 va_start(ap, s);
134 fprintf(stderr, "FYI: ");
135 vfprintf(stderr, s, ap);
136 va_end(ap);
137 }
138 }
139
140 char *dup_basename(const char *name, const char *ext)
141 {
142 int namelen;
143 int extlen = strlen(ext);
144 char *base;
145 char *slash;
146
147 if(!name)
148 name = "wrc.tab";
149
150 slash = strrchr(name, '/');
151 if (slash)
152 name = slash + 1;
153
154 namelen = strlen(name);
155
156 /* +4 for later extension and +1 for '\0' */
157 base = xmalloc(namelen +4 +1);
158 strcpy(base, name);
159 if(!strcasecmp(name + namelen-extlen, ext))
160 {
161 base[namelen - extlen] = '\0';
162 }
163 return base;
164 }
165
166 void *xmalloc(size_t size)
167 {
168 void *res;
169
170 assert(size > 0);
171 res = malloc(size);
172 if(res == NULL)
173 {
174 error("Virtual memory exhausted.\n");
175 }
176 memset(res, 0x55, size);
177 return res;
178 }
179
180
181 void *xrealloc(void *p, size_t size)
182 {
183 void *res;
184
185 assert(size > 0);
186 res = realloc(p, size);
187 if(res == NULL)
188 {
189 error("Virtual memory exhausted.\n");
190 }
191 return res;
192 }
193
194 char *strmake( const char* fmt, ... )
195 {
196 int n;
197 size_t size = 100;
198 va_list ap;
199
200 for (;;)
201 {
202 char *p = xmalloc( size );
203 va_start( ap, fmt );
204 n = vsnprintf( p, size, fmt, ap );
205 va_end( ap );
206 if (n == -1) size *= 2;
207 else if ((size_t)n >= size) size = n + 1;
208 else return p;
209 free( p );
210 }
211 }
212
213 char *xstrdup(const char *str)
214 {
215 char *s;
216
217 assert(str != NULL);
218 s = xmalloc(strlen(str)+1);
219 return strcpy(s, str);
220 }
221
222 int strendswith( const char *str, const char *end )
223 {
224 int l = strlen(str);
225 int m = strlen(end);
226 return l >= m && !strcmp( str + l - m, end );
227 }
228
229 int compare_striA( const char *str1, const char *str2 )
230 {
231 for (;;)
232 {
233 /* only the A-Z range is case-insensitive */
234 char ch1 = (*str1 >= 'a' && *str1 <= 'z') ? *str1 + 'A' - 'a' : *str1;
235 char ch2 = (*str2 >= 'a' && *str2 <= 'z') ? *str2 + 'A' - 'a' : *str2;
236 if (!ch1 || ch1 != ch2) return ch1 - ch2;
237 str1++;
238 str2++;
239 }
240 }
241
242 int compare_striW( const WCHAR *str1, const WCHAR *str2 )
243 {
244 for (;;)
245 {
246 /* only the A-Z range is case-insensitive */
247 WCHAR ch1 = (*str1 >= 'a' && *str1 <= 'z') ? *str1 + 'A' - 'a' : *str1;
248 WCHAR ch2 = (*str2 >= 'a' && *str2 <= 'z') ? *str2 + 'A' - 'a' : *str2;
249 if (!ch1 || ch1 != ch2) return ch1 - ch2;
250 str1++;
251 str2++;
252 }
253 }
254
255 /*
256 *****************************************************************************
257 * Function : compare_name_id
258 * Syntax : int compare_name_id(const name_id_t *n1, const name_id_t *n2)
259 * Input :
260 * Output :
261 * Description :
262 * Remarks :
263 *****************************************************************************
264 */
265 int compare_name_id(const name_id_t *n1, const name_id_t *n2)
266 {
267 if(n1->type == name_ord && n2->type == name_ord)
268 {
269 return n1->name.i_name - n2->name.i_name;
270 }
271 else if(n1->type == name_str && n2->type == name_str)
272 {
273 if(n1->name.s_name->type == str_char
274 && n2->name.s_name->type == str_char)
275 {
276 return compare_striA(n1->name.s_name->str.cstr, n2->name.s_name->str.cstr);
277 }
278 else if(n1->name.s_name->type == str_unicode
279 && n2->name.s_name->type == str_unicode)
280 {
281 return compare_striW(n1->name.s_name->str.wstr, n2->name.s_name->str.wstr);
282 }
283 else
284 {
285 internal_error(__FILE__, __LINE__, "Can't yet compare strings of mixed type\n");
286 }
287 }
288 else if(n1->type == name_ord && n2->type == name_str)
289 return 1;
290 else if(n1->type == name_str && n2->type == name_ord)
291 return -1;
292 else
293 internal_error(__FILE__, __LINE__, "Comparing name-ids with unknown types (%d, %d)\n",
294 n1->type, n2->type);
295
296 return 0; /* Keep the compiler happy */
297 }
298
299 #ifdef _WIN32
300
301 int is_valid_codepage(int id)
302 {
303 return IsValidCodePage( id );
304 }
305
306 static WCHAR *codepage_to_unicode( int codepage, const char *src, int srclen, int *dstlen )
307 {
308 WCHAR *dst = xmalloc( (srclen + 1) * sizeof(WCHAR) );
309 DWORD ret = MultiByteToWideChar( codepage, MB_ERR_INVALID_CHARS, src, srclen, dst, srclen );
310 if (!ret) return NULL;
311 dst[ret] = 0;
312 *dstlen = ret;
313 return dst;
314 }
315
316 #else /* _WIN32 */
317
318 struct nls_info
319 {
320 unsigned short codepage;
321 unsigned short unidef;
322 unsigned short trans_unidef;
323 unsigned short *cp2uni;
324 unsigned short *dbcs_offsets;
325 };
326
327 static struct nls_info nlsinfo[128];
328
329 static void init_nls_info( struct nls_info *info, unsigned short *ptr )
330 {
331 unsigned short hdr_size = ptr[0];
332
333 info->codepage = ptr[1];
334 info->unidef = ptr[4];
335 info->trans_unidef = ptr[6];
336 ptr += hdr_size;
337 info->cp2uni = ++ptr;
338 ptr += 256;
339 if (*ptr++) ptr += 256; /* glyph table */
340 info->dbcs_offsets = *ptr ? ptr + 1 : NULL;
341 }
342
343 static const struct nls_info *get_nls_info( unsigned int codepage )
344 {
345 struct stat st;
346 unsigned short *data;
347 char *path;
348 unsigned int i;
349 int fd;
350
351 for (i = 0; i < ARRAY_SIZE(nlsinfo) && nlsinfo[i].codepage; i++)
352 if (nlsinfo[i].codepage == codepage) return &nlsinfo[i];
353
354 assert( i < ARRAY_SIZE(nlsinfo) );
355
356 for (i = 0; nlsdirs[i]; i++)
357 {
358 path = strmake( "%s/c_%03u.nls", nlsdirs[i], codepage );
359 if ((fd = open( path, O_RDONLY )) != -1) break;
360 free( path );
361 }
362 if (!nlsdirs[i]) return NULL;
363
364 fstat( fd, &st );
365 data = xmalloc( st.st_size );
366 if (read( fd, data, st.st_size ) != st.st_size) error( "failed to load %s\n", path );
367 close( fd );
368 free( path );
369 init_nls_info( &nlsinfo[i], data );
370 return &nlsinfo[i];
371 }
372
373 int is_valid_codepage(int cp)
374 {
375 return cp == CP_UTF8 || get_nls_info( cp );
376 }
377
378 static WCHAR *codepage_to_unicode( int codepage, const char *src, int srclen, int *dstlen )
379 {
380 const struct nls_info *info = get_nls_info( codepage );
381 unsigned int i;
382 WCHAR dbch, *dst = xmalloc( (srclen + 1) * sizeof(WCHAR) );
383
384 if (!info) error( "codepage %u not supported\n", codepage );
385
386 if (info->dbcs_offsets)
387 {
388 for (i = 0; srclen; i++, srclen--, src++)
389 {
390 unsigned short off = info->dbcs_offsets[(unsigned char)*src];
391 if (off)
392 {
393 if (srclen == 1) return NULL;
394 dbch = (src[0] << 8) | (unsigned char)src[1];
395 src++;
396 srclen--;
397 dst[i] = info->dbcs_offsets[off + (unsigned char)*src];
398 if (dst[i] == info->unidef && dbch != info->trans_unidef) return NULL;
399 }
400 else
401 {
402 dst[i] = info->cp2uni[(unsigned char)*src];
403 if (dst[i] == info->unidef && *src != info->trans_unidef) return NULL;
404 }
405 }
406 }
407 else
408 {
409 for (i = 0; i < srclen; i++)
410 {
411 dst[i] = info->cp2uni[(unsigned char)src[i]];
412 if (dst[i] == info->unidef && src[i] != info->trans_unidef) return NULL;
413 }
414 }
415 dst[i] = 0;
416 *dstlen = i;
417 return dst;
418 }
419
420 #endif /* _WIN32 */
421
422 static WCHAR *utf8_to_unicode( const char *src, int srclen, int *dstlen )
423 {
424 static const char utf8_length[128] =
425 {
426 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0x80-0x8f */
427 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0x90-0x9f */
428 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0xa0-0xaf */
429 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0xb0-0xbf */
430 0,0,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* 0xc0-0xcf */
431 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* 0xd0-0xdf */
432 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* 0xe0-0xef */
433 3,3,3,3,3,0,0,0,0,0,0,0,0,0,0,0 /* 0xf0-0xff */
434 };
435 static const unsigned char utf8_mask[4] = { 0x7f, 0x1f, 0x0f, 0x07 };
436
437 const char *srcend = src + srclen;
438 int len, res;
439 WCHAR *ret, *dst;
440
441 dst = ret = xmalloc( (srclen + 1) * sizeof(WCHAR) );
442 while (src < srcend)
443 {
444 unsigned char ch = *src++;
445 if (ch < 0x80) /* special fast case for 7-bit ASCII */
446 {
447 *dst++ = ch;
448 continue;
449 }
450 len = utf8_length[ch - 0x80];
451 if (len && src + len <= srcend)
452 {
453 res = ch & utf8_mask[len];
454 switch (len)
455 {
456 case 3:
457 if ((ch = *src ^ 0x80) >= 0x40) break;
458 res = (res << 6) | ch;
459 src++;
460 if (res < 0x10) break;
461 case 2:
462 if ((ch = *src ^ 0x80) >= 0x40) break;
463 res = (res << 6) | ch;
464 if (res >= 0x110000 >> 6) break;
465 src++;
466 if (res < 0x20) break;
467 if (res >= 0xd800 >> 6 && res <= 0xdfff >> 6) break;
468 case 1:
469 if ((ch = *src ^ 0x80) >= 0x40) break;
470 res = (res << 6) | ch;
471 src++;
472 if (res < 0x80) break;
473 if (res <= 0xffff) *dst++ = res;
474 else
475 {
476 res -= 0x10000;
477 *dst++ = 0xd800 | (res >> 10);
478 *dst++ = 0xdc00 | (res & 0x3ff);
479 }
480 continue;
481 }
482 }
483 *dst++ = 0xfffd;
484 }
485 *dst = 0;
486 *dstlen = dst - ret;
487 return ret;
488 }
489
490 static char *unicode_to_utf8( const WCHAR *src, int srclen, int *dstlen )
491 {
492 char *ret, *dst;
493
494 dst = ret = xmalloc( srclen * 3 + 1 );
495 for ( ; srclen; srclen--, src++)
496 {
497 unsigned int ch = *src;
498
499 if (ch < 0x80) /* 0x00-0x7f: 1 byte */
500 {
501 *dst++ = ch;
502 continue;
503 }
504 if (ch < 0x800) /* 0x80-0x7ff: 2 bytes */
505 {
506 dst[1] = 0x80 | (ch & 0x3f);
507 ch >>= 6;
508 dst[0] = 0xc0 | ch;
509 dst += 2;
510 continue;
511 }
512 if (ch >= 0xd800 && ch <= 0xdbff && srclen > 1 && src[1] >= 0xdc00 && src[1] <= 0xdfff)
513 {
514 /* 0x10000-0x10ffff: 4 bytes */
515 ch = 0x10000 + ((ch & 0x3ff) << 10) + (src[1] & 0x3ff);
516 dst[3] = 0x80 | (ch & 0x3f);
517 ch >>= 6;
518 dst[2] = 0x80 | (ch & 0x3f);
519 ch >>= 6;
520 dst[1] = 0x80 | (ch & 0x3f);
521 ch >>= 6;
522 dst[0] = 0xf0 | ch;
523 dst += 4;
524 src++;
525 srclen--;
526 continue;
527 }
528 if (ch >= 0xd800 && ch <= 0xdfff) ch = 0xfffd; /* invalid surrogate pair */
529
530 /* 0x800-0xffff: 3 bytes */
531 dst[2] = 0x80 | (ch & 0x3f);
532 ch >>= 6;
533 dst[1] = 0x80 | (ch & 0x3f);
534 ch >>= 6;
535 dst[0] = 0xe0 | ch;
536 dst += 3;
537 }
538 *dst = 0;
539 *dstlen = dst - ret;
540 return ret;
541 }
542
543 string_t *convert_string_unicode( const string_t *str, int codepage )
544 {
545 string_t *ret = xmalloc(sizeof(*ret));
546
547 ret->type = str_unicode;
548 ret->loc = str->loc;
549
550 if (str->type == str_char)
551 {
552 if (!codepage) parser_error( "Current language is Unicode only, cannot convert string" );
553
554 if (codepage == CP_UTF8)
555 ret->str.wstr = utf8_to_unicode( str->str.cstr, str->size, &ret->size );
556 else
557 ret->str.wstr = codepage_to_unicode( codepage, str->str.cstr, str->size, &ret->size );
558 if (!ret->str.wstr) parser_error( "Invalid character in string '%.*s' for codepage %u",
559 str->size, str->str.cstr, codepage );
560 }
561 else
562 {
563 ret->size = str->size;
564 ret->str.wstr = xmalloc(sizeof(WCHAR)*(ret->size+1));
565 memcpy( ret->str.wstr, str->str.wstr, ret->size * sizeof(WCHAR) );
566 ret->str.wstr[ret->size] = 0;
567 }
568 return ret;
569 }
570
571 char *convert_string_utf8( const string_t *str, int codepage )
572 {
573 int len;
574 string_t *wstr = convert_string_unicode( str, codepage );
575 char *ret = unicode_to_utf8( wstr->str.wstr, wstr->size, &len );
576 free_string( wstr );
577 return ret;
578 }
579
580 void free_string(string_t *str)
581 {
582 if (str->type == str_unicode) free( str->str.wstr );
583 else free( str->str.cstr );
584 free( str );
585 }
586
587 /* check if the string is valid utf8 despite a different codepage being in use */
588 int check_valid_utf8( const string_t *str, int codepage )
589 {
590 int i, count;
591 WCHAR *wstr;
592
593 if (!check_utf8) return 0;
594 if (!codepage) return 0;
595 if (codepage == CP_UTF8) return 0;
596 if (!is_valid_codepage( codepage )) return 0;
597
598 for (i = count = 0; i < str->size; i++)
599 {
600 if ((unsigned char)str->str.cstr[i] >= 0xf5) goto done;
601 if ((unsigned char)str->str.cstr[i] >= 0xc2) { count++; continue; }
602 if ((unsigned char)str->str.cstr[i] >= 0x80) goto done;
603 }
604 if (!count) return 0; /* no 8-bit chars at all */
605
606 wstr = utf8_to_unicode( str->str.cstr, str->size, &count );
607 for (i = 0; i < count; i++) if (wstr[i] == 0xfffd) break;
608 free( wstr );
609 return (i == count);
610
611 done:
612 check_utf8 = 0; /* at least one 8-bit non-utf8 string found, stop checking */
613 return 0;
614 }
615
616
617 struct lang2cp
618 {
619 unsigned short lang;
620 unsigned short sublang;
621 unsigned int cp;
622 };
623
624 /* language to codepage conversion table */
625 /* specific sublanguages need only be specified if their codepage */
626 /* differs from the default (SUBLANG_NEUTRAL) */
627 static const struct lang2cp lang2cps[] =
628 {
629 { LANG_AFRIKAANS, SUBLANG_NEUTRAL, 1252 },
630 { LANG_ALBANIAN, SUBLANG_NEUTRAL, 1250 },
631 { LANG_ALSATIAN, SUBLANG_NEUTRAL, 1252 },
632 { LANG_AMHARIC, SUBLANG_NEUTRAL, 0 },
633 { LANG_ARABIC, SUBLANG_NEUTRAL, 1256 },
634 { LANG_ARMENIAN, SUBLANG_NEUTRAL, 0 },
635 { LANG_ASSAMESE, SUBLANG_NEUTRAL, 0 },
636 { LANG_ASTURIAN, SUBLANG_NEUTRAL, 1252 },
637 { LANG_AZERI, SUBLANG_NEUTRAL, 1254 },
638 { LANG_AZERI, SUBLANG_AZERI_CYRILLIC, 1251 },
639 { LANG_BASHKIR, SUBLANG_NEUTRAL, 1251 },
640 { LANG_BASQUE, SUBLANG_NEUTRAL, 1252 },
641 { LANG_BELARUSIAN, SUBLANG_NEUTRAL, 1251 },
642 { LANG_BENGALI, SUBLANG_NEUTRAL, 0 },
643 { LANG_BOSNIAN, SUBLANG_NEUTRAL, 1250 },
644 { LANG_BOSNIAN, SUBLANG_BOSNIAN_BOSNIA_HERZEGOVINA_CYRILLIC, 1251 },
645 { LANG_BRETON, SUBLANG_NEUTRAL, 1252 },
646 { LANG_BULGARIAN, SUBLANG_NEUTRAL, 1251 },
647 { LANG_CATALAN, SUBLANG_NEUTRAL, 1252 },
648 { LANG_CHINESE, SUBLANG_NEUTRAL, 950 },
649 { LANG_CHINESE, SUBLANG_CHINESE_SIMPLIFIED, 936 },
650 { LANG_CHINESE, SUBLANG_CHINESE_SINGAPORE, 936 },
651 #ifdef LANG_CORNISH
652 { LANG_CORNISH, SUBLANG_NEUTRAL, 1252 },
653 #endif /* LANG_CORNISH */
654 { LANG_CORSICAN, SUBLANG_NEUTRAL, 1252 },
655 { LANG_CROATIAN, SUBLANG_NEUTRAL, 1250 },
656 { LANG_CZECH, SUBLANG_NEUTRAL, 1250 },
657 { LANG_DANISH, SUBLANG_NEUTRAL, 1252 },
658 { LANG_DARI, SUBLANG_NEUTRAL, 1256 },
659 { LANG_DIVEHI, SUBLANG_NEUTRAL, 0 },
660 { LANG_DUTCH, SUBLANG_NEUTRAL, 1252 },
661 { LANG_ENGLISH, SUBLANG_NEUTRAL, 1252 },
662 #ifdef LANG_ESPERANTO
663 { LANG_ESPERANTO, SUBLANG_NEUTRAL, 1252 },
664 #endif /* LANG_ESPERANTO */
665 { LANG_ESTONIAN, SUBLANG_NEUTRAL, 1257 },
666 { LANG_FAEROESE, SUBLANG_NEUTRAL, 1252 },
667 { LANG_FILIPINO, SUBLANG_NEUTRAL, 1252 },
668 { LANG_FINNISH, SUBLANG_NEUTRAL, 1252 },
669 { LANG_FRENCH, SUBLANG_NEUTRAL, 1252 },
670 { LANG_FRISIAN, SUBLANG_NEUTRAL, 1252 },
671 #ifdef LANG_MANX_GAELIC
672 { LANG_MANX_GAELIC, SUBLANG_NEUTRAL, 1252 },
673 #endif /* LANG_MANX_GAELIC */
674 { LANG_GALICIAN, SUBLANG_NEUTRAL, 1252 },
675 { LANG_GEORGIAN, SUBLANG_NEUTRAL, 0 },
676 { LANG_GERMAN, SUBLANG_NEUTRAL, 1252 },
677 { LANG_GREEK, SUBLANG_NEUTRAL, 1253 },
678 { LANG_GREENLANDIC, SUBLANG_NEUTRAL, 1252 },
679 { LANG_GUJARATI, SUBLANG_NEUTRAL, 0 },
680 { LANG_HAUSA, SUBLANG_NEUTRAL, 1252 },
681 { LANG_HEBREW, SUBLANG_NEUTRAL, 1255 },
682 { LANG_HINDI, SUBLANG_NEUTRAL, 0 },
683 { LANG_HUNGARIAN, SUBLANG_NEUTRAL, 1250 },
684 { LANG_ICELANDIC, SUBLANG_NEUTRAL, 1252 },
685 { LANG_IGBO, SUBLANG_NEUTRAL, 1252 },
686 { LANG_INDONESIAN, SUBLANG_NEUTRAL, 1252 },
687 { LANG_INUKTITUT, SUBLANG_NEUTRAL, 0 },
688 { LANG_INUKTITUT, SUBLANG_INUKTITUT_CANADA_LATIN, 0 },
689 { LANG_INVARIANT, SUBLANG_NEUTRAL, 0 },
690 { LANG_IRISH, SUBLANG_NEUTRAL, 1252 },
691 { LANG_ITALIAN, SUBLANG_NEUTRAL, 1252 },
692 { LANG_JAPANESE, SUBLANG_NEUTRAL, 932 },
693 { LANG_KANNADA, SUBLANG_NEUTRAL, 0 },
694 { LANG_KAZAK, SUBLANG_NEUTRAL, 1251 },
695 { LANG_KHMER, SUBLANG_NEUTRAL, 0 },
696 { LANG_KICHE, SUBLANG_NEUTRAL, 1252 },
697 { LANG_KINYARWANDA, SUBLANG_NEUTRAL, 1252 },
698 { LANG_KONKANI, SUBLANG_NEUTRAL, 0 },
699 { LANG_KOREAN, SUBLANG_NEUTRAL, 949 },
700 { LANG_KYRGYZ, SUBLANG_NEUTRAL, 1251 },
701 { LANG_LAO, SUBLANG_NEUTRAL, 0 },
702 { LANG_LATVIAN, SUBLANG_NEUTRAL, 1257 },
703 { LANG_LITHUANIAN, SUBLANG_NEUTRAL, 1257 },
704 { LANG_LOWER_SORBIAN, SUBLANG_NEUTRAL, 1252 },
705 { LANG_LUXEMBOURGISH, SUBLANG_NEUTRAL, 1252 },
706 { LANG_MACEDONIAN, SUBLANG_NEUTRAL, 1251 },
707 { LANG_MALAY, SUBLANG_NEUTRAL, 1252 },
708 { LANG_MALAYALAM, SUBLANG_NEUTRAL, 0 },
709 { LANG_MALTESE, SUBLANG_NEUTRAL, 0 },
710 { LANG_MAORI, SUBLANG_NEUTRAL, 0 },
711 { LANG_MAPUDUNGUN, SUBLANG_NEUTRAL, 1252 },
712 { LANG_MARATHI, SUBLANG_NEUTRAL, 0 },
713 { LANG_MOHAWK, SUBLANG_NEUTRAL, 1252 },
714 { LANG_MONGOLIAN, SUBLANG_NEUTRAL, 1251 },
715 { LANG_NEPALI, SUBLANG_NEUTRAL, 0 },
716 { LANG_NEUTRAL, SUBLANG_NEUTRAL, 1252 },
717 { LANG_NORWEGIAN, SUBLANG_NEUTRAL, 1252 },
718 { LANG_OCCITAN, SUBLANG_NEUTRAL, 1252 },
719 { LANG_ORIYA, SUBLANG_NEUTRAL, 0 },
720 { LANG_PASHTO, SUBLANG_NEUTRAL, 0 },
721 { LANG_PERSIAN, SUBLANG_NEUTRAL, 1256 },
722 { LANG_POLISH, SUBLANG_NEUTRAL, 1250 },
723 { LANG_PORTUGUESE, SUBLANG_NEUTRAL, 1252 },
724 { LANG_PUNJABI, SUBLANG_NEUTRAL, 0 },
725 { LANG_QUECHUA, SUBLANG_NEUTRAL, 1252 },
726 { LANG_ROMANIAN, SUBLANG_NEUTRAL, 1250 },
727 { LANG_ROMANSH, SUBLANG_NEUTRAL, 1252 },
728 { LANG_RUSSIAN, SUBLANG_NEUTRAL, 1251 },
729 { LANG_SAMI, SUBLANG_NEUTRAL, 1252 },
730 { LANG_SANSKRIT, SUBLANG_NEUTRAL, 0 },
731 { LANG_SCOTTISH_GAELIC,SUBLANG_NEUTRAL, 1252 },
732 { LANG_SERBIAN, SUBLANG_NEUTRAL, 1250 },
733 { LANG_SERBIAN, SUBLANG_SERBIAN_CYRILLIC, 1251 },
734 { LANG_SINHALESE, SUBLANG_NEUTRAL, 0 },
735 { LANG_SLOVAK, SUBLANG_NEUTRAL, 1250 },
736 { LANG_SLOVENIAN, SUBLANG_NEUTRAL, 1250 },
737 { LANG_SOTHO, SUBLANG_NEUTRAL, 1252 },
738 { LANG_SPANISH, SUBLANG_NEUTRAL, 1252 },
739 { LANG_SWAHILI, SUBLANG_NEUTRAL, 1252 },
740 { LANG_SWEDISH, SUBLANG_NEUTRAL, 1252 },
741 { LANG_SYRIAC, SUBLANG_NEUTRAL, 0 },
742 { LANG_TAJIK, SUBLANG_NEUTRAL, 1251 },
743 { LANG_TAMAZIGHT, SUBLANG_NEUTRAL, 1252 },
744 { LANG_TAMIL, SUBLANG_NEUTRAL, 0 },
745 { LANG_TATAR, SUBLANG_NEUTRAL, 1251 },
746 { LANG_TELUGU, SUBLANG_NEUTRAL, 0 },
747 { LANG_THAI, SUBLANG_NEUTRAL, 874 },
748 { LANG_TIBETAN, SUBLANG_NEUTRAL, 0 },
749 { LANG_TSWANA, SUBLANG_NEUTRAL, 1252 },
750 { LANG_TURKISH, SUBLANG_NEUTRAL, 1254 },
751 { LANG_TURKMEN, SUBLANG_NEUTRAL, 1250 },
752 { LANG_UIGHUR, SUBLANG_NEUTRAL, 1256 },
753 { LANG_UKRAINIAN, SUBLANG_NEUTRAL, 1251 },
754 { LANG_UPPER_SORBIAN, SUBLANG_NEUTRAL, 1252 },
755 { LANG_URDU, SUBLANG_NEUTRAL, 1256 },
756 { LANG_UZBEK, SUBLANG_NEUTRAL, 1254 },
757 { LANG_UZBEK, SUBLANG_UZBEK_CYRILLIC, 1251 },
758 { LANG_VIETNAMESE, SUBLANG_NEUTRAL, 1258 },
759 #ifdef LANG_WALON
760 { LANG_WALON, SUBLANG_NEUTRAL, 1252 },
761 #endif /* LANG_WALON */
762 { LANG_WELSH, SUBLANG_NEUTRAL, 1252 },
763 { LANG_WOLOF, SUBLANG_NEUTRAL, 1252 },
764 { LANG_XHOSA, SUBLANG_NEUTRAL, 1252 },
765 { LANG_YAKUT, SUBLANG_NEUTRAL, 1251 },
766 { LANG_YI, SUBLANG_NEUTRAL, 0 },
767 { LANG_YORUBA, SUBLANG_NEUTRAL, 1252 },
768 { LANG_ZULU, SUBLANG_NEUTRAL, 1252 }
769 };
770
771 int get_language_codepage( unsigned short lang, unsigned short sublang )
772 {
773 unsigned int i;
774 int cp = -1, defcp = -1;
775
776 for (i = 0; i < ARRAY_SIZE(lang2cps); i++)
777 {
778 if (lang2cps[i].lang != lang) continue;
779 if (lang2cps[i].sublang == sublang)
780 {
781 cp = lang2cps[i].cp;
782 break;
783 }
784 if (lang2cps[i].sublang == SUBLANG_NEUTRAL) defcp = lang2cps[i].cp;
785 }
786
787 if (cp == -1) cp = defcp;
788 return cp;
789 }
Windows API implementation