4 * Copyright 1998 Bertho A. Stultiens
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.
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.
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
22 #include "wine/port.h"
31 #include "wine/unicode.h"
36 /* #define WANT_NEAR_INDICATION */
38 #ifdef WANT_NEAR_INDICATION
39 void make_print(char *str
)
50 static void generic_msg(const char *s
, const char *t
, const char *n
, va_list ap
)
52 fprintf(stderr
, "%s:%d:%d: %s: ", input_name
? input_name
: "stdin", line_number
, char_number
, t
);
53 vfprintf(stderr
, s
, ap
);
54 #ifdef WANT_NEAR_INDICATION
61 fprintf(stderr
, " near '%s'", cpy
);
69 int parser_error(const char *s
, ...)
73 generic_msg(s
, "Error", parser_text
, ap
);
74 fputc( '\n', stderr
);
80 int parser_warning(const char *s
, ...)
84 generic_msg(s
, "Warning", parser_text
, ap
);
89 void internal_error(const char *file
, int line
, const char *s
, ...)
93 fprintf(stderr
, "Internal error (please report) %s %d: ", file
, line
);
94 vfprintf(stderr
, s
, ap
);
99 void error(const char *s
, ...)
103 fprintf(stderr
, "Error: ");
104 vfprintf(stderr
, s
, ap
);
109 void warning(const char *s
, ...)
113 fprintf(stderr
, "Warning: ");
114 vfprintf(stderr
, s
, ap
);
118 void chat(const char *s
, ...)
120 if(debuglevel
& DEBUGLEVEL_CHAT
)
124 fprintf(stderr
, "FYI: ");
125 vfprintf(stderr
, s
, ap
);
130 char *dup_basename(const char *name
, const char *ext
)
133 int extlen
= strlen(ext
);
140 slash
= strrchr(name
, '/');
144 namelen
= strlen(name
);
146 /* +4 for later extension and +1 for '\0' */
147 base
= xmalloc(namelen
+4 +1);
149 if(!strcasecmp(name
+ namelen
-extlen
, ext
))
151 base
[namelen
- extlen
] = '\0';
156 void *xmalloc(size_t size
)
164 error("Virtual memory exhausted.\n");
166 memset(res
, 0x55, size
);
171 void *xrealloc(void *p
, size_t size
)
176 res
= realloc(p
, size
);
179 error("Virtual memory exhausted.\n");
184 char *xstrdup(const char *str
)
189 s
= xmalloc(strlen(str
)+1);
190 return strcpy(s
, str
);
195 *****************************************************************************
196 * Function : compare_name_id
197 * Syntax : int compare_name_id(const name_id_t *n1, const name_id_t *n2)
202 *****************************************************************************
204 int compare_name_id(const name_id_t
*n1
, const name_id_t
*n2
)
206 if(n1
->type
== name_ord
&& n2
->type
== name_ord
)
208 return n1
->name
.i_name
- n2
->name
.i_name
;
210 else if(n1
->type
== name_str
&& n2
->type
== name_str
)
212 if(n1
->name
.s_name
->type
== str_char
213 && n2
->name
.s_name
->type
== str_char
)
215 return strcasecmp(n1
->name
.s_name
->str
.cstr
, n2
->name
.s_name
->str
.cstr
);
217 else if(n1
->name
.s_name
->type
== str_unicode
218 && n2
->name
.s_name
->type
== str_unicode
)
220 return strcmpiW(n1
->name
.s_name
->str
.wstr
, n2
->name
.s_name
->str
.wstr
);
224 internal_error(__FILE__
, __LINE__
, "Can't yet compare strings of mixed type\n");
227 else if(n1
->type
== name_ord
&& n2
->type
== name_str
)
229 else if(n1
->type
== name_str
&& n2
->type
== name_ord
)
232 internal_error(__FILE__
, __LINE__
, "Comparing name-ids with unknown types (%d, %d)\n",
235 return 0; /* Keep the compiler happy */
238 string_t
*convert_string(const string_t
*str
, enum str_e type
, int codepage
)
240 const union cptable
*cptable
= codepage
? wine_cp_get_table( codepage
) : NULL
;
241 string_t
*ret
= xmalloc(sizeof(*ret
));
244 if (!codepage
&& str
->type
!= type
)
245 parser_error( "Current language is Unicode only, cannot convert string" );
247 if((str
->type
== str_char
) && (type
== str_unicode
))
249 ret
->type
= str_unicode
;
250 ret
->size
= cptable
? wine_cp_mbstowcs( cptable
, 0, str
->str
.cstr
, str
->size
, NULL
, 0 )
251 : wine_utf8_mbstowcs( 0, str
->str
.cstr
, str
->size
, NULL
, 0 );
252 ret
->str
.wstr
= xmalloc( (ret
->size
+1) * sizeof(WCHAR
) );
254 res
= wine_cp_mbstowcs( cptable
, MB_ERR_INVALID_CHARS
, str
->str
.cstr
, str
->size
,
255 ret
->str
.wstr
, ret
->size
);
257 res
= wine_utf8_mbstowcs( MB_ERR_INVALID_CHARS
, str
->str
.cstr
, str
->size
,
258 ret
->str
.wstr
, ret
->size
);
260 parser_error( "Invalid character in string '%.*s' for codepage %u",
261 str
->size
, str
->str
.cstr
, codepage
);
262 ret
->str
.wstr
[ret
->size
] = 0;
264 else if((str
->type
== str_unicode
) && (type
== str_char
))
266 ret
->type
= str_char
;
267 ret
->size
= cptable
? wine_cp_wcstombs( cptable
, 0, str
->str
.wstr
, str
->size
, NULL
, 0, NULL
, NULL
)
268 : wine_utf8_wcstombs( 0, str
->str
.wstr
, str
->size
, NULL
, 0 );
269 ret
->str
.cstr
= xmalloc( ret
->size
+ 1 );
271 wine_cp_wcstombs( cptable
, 0, str
->str
.wstr
, str
->size
, ret
->str
.cstr
, ret
->size
, NULL
, NULL
);
273 wine_utf8_wcstombs( 0, str
->str
.wstr
, str
->size
, ret
->str
.cstr
, ret
->size
);
274 ret
->str
.cstr
[ret
->size
] = 0;
276 else if(str
->type
== str_unicode
)
278 ret
->type
= str_unicode
;
279 ret
->size
= str
->size
;
280 ret
->str
.wstr
= xmalloc(sizeof(WCHAR
)*(ret
->size
+1));
281 memcpy( ret
->str
.wstr
, str
->str
.wstr
, ret
->size
* sizeof(WCHAR
) );
282 ret
->str
.wstr
[ret
->size
] = 0;
284 else /* str->type == str_char */
286 ret
->type
= str_char
;
287 ret
->size
= str
->size
;
288 ret
->str
.cstr
= xmalloc( ret
->size
+ 1 );
289 memcpy( ret
->str
.cstr
, str
->str
.cstr
, ret
->size
);
290 ret
->str
.cstr
[ret
->size
] = 0;
296 void free_string(string_t
*str
)
298 if (str
->type
== str_unicode
) free( str
->str
.wstr
);
299 else free( str
->str
.cstr
);
304 int check_unicode_conversion( const string_t
*str_a
, const string_t
*str_w
, int codepage
)
307 string_t
*teststr
= convert_string( str_w
, str_char
, codepage
);
309 ok
= (teststr
->size
== str_a
->size
&& !memcmp( teststr
->str
.cstr
, str_a
->str
.cstr
, str_a
->size
));
315 fprintf( stderr
, "Source: %s", str_a
->str
.cstr
);
316 for (i
= 0; i
< str_a
->size
; i
++)
317 fprintf( stderr
, " %02x", (unsigned char)str_a
->str
.cstr
[i
] );
318 fprintf( stderr
, "\nUnicode: " );
319 for (i
= 0; i
< str_w
->size
; i
++)
320 fprintf( stderr
, " %04x", str_w
->str
.wstr
[i
] );
321 fprintf( stderr
, "\nBack: %s", teststr
->str
.cstr
);
322 for (i
= 0; i
< teststr
->size
; i
++)
323 fprintf( stderr
, " %02x", (unsigned char)teststr
->str
.cstr
[i
] );
324 fprintf( stderr
, "\n" );
326 free_string( teststr
);
334 unsigned short sublang
;
338 /* language to codepage conversion table */
339 /* specific sublanguages need only be specified if their codepage */
340 /* differs from the default (SUBLANG_NEUTRAL) */
341 static const struct lang2cp lang2cps
[] =
343 { LANG_AFRIKAANS
, SUBLANG_NEUTRAL
, 1252 },
344 { LANG_ALBANIAN
, SUBLANG_NEUTRAL
, 1250 },
345 { LANG_ALSATIAN
, SUBLANG_NEUTRAL
, 1252 },
346 { LANG_AMHARIC
, SUBLANG_NEUTRAL
, 0 },
347 { LANG_ARABIC
, SUBLANG_NEUTRAL
, 1256 },
348 { LANG_ARMENIAN
, SUBLANG_NEUTRAL
, 0 },
349 { LANG_ASSAMESE
, SUBLANG_NEUTRAL
, 0 },
350 { LANG_AZERI
, SUBLANG_NEUTRAL
, 1254 },
351 { LANG_AZERI
, SUBLANG_AZERI_CYRILLIC
, 1251 },
352 { LANG_BASHKIR
, SUBLANG_NEUTRAL
, 1251 },
353 { LANG_BASQUE
, SUBLANG_NEUTRAL
, 1252 },
354 { LANG_BELARUSIAN
, SUBLANG_NEUTRAL
, 1251 },
355 { LANG_BENGALI
, SUBLANG_NEUTRAL
, 0 },
356 { LANG_BOSNIAN
, SUBLANG_NEUTRAL
, 1250 },
357 { LANG_BOSNIAN
, SUBLANG_BOSNIAN_BOSNIA_HERZEGOVINA_CYRILLIC
, 1251 },
358 { LANG_BRETON
, SUBLANG_NEUTRAL
, 1252 },
359 { LANG_BULGARIAN
, SUBLANG_NEUTRAL
, 1251 },
360 { LANG_CATALAN
, SUBLANG_NEUTRAL
, 1252 },
361 { LANG_CHINESE
, SUBLANG_NEUTRAL
, 950 },
362 { LANG_CHINESE
, SUBLANG_CHINESE_SIMPLIFIED
, 936 },
363 { LANG_CHINESE
, SUBLANG_CHINESE_SINGAPORE
, 936 },
365 { LANG_CORNISH
, SUBLANG_NEUTRAL
, 1252 },
366 #endif /* LANG_CORNISH */
367 { LANG_CORSICAN
, SUBLANG_NEUTRAL
, 1252 },
368 { LANG_CROATIAN
, SUBLANG_NEUTRAL
, 1250 },
369 { LANG_CZECH
, SUBLANG_NEUTRAL
, 1250 },
370 { LANG_DANISH
, SUBLANG_NEUTRAL
, 1252 },
371 { LANG_DARI
, SUBLANG_NEUTRAL
, 1256 },
372 { LANG_DIVEHI
, SUBLANG_NEUTRAL
, 0 },
373 { LANG_DUTCH
, SUBLANG_NEUTRAL
, 1252 },
374 { LANG_ENGLISH
, SUBLANG_NEUTRAL
, 1252 },
375 #ifdef LANG_ESPERANTO
376 { LANG_ESPERANTO
, SUBLANG_NEUTRAL
, 1252 },
377 #endif /* LANG_ESPERANTO */
378 { LANG_ESTONIAN
, SUBLANG_NEUTRAL
, 1257 },
379 { LANG_FAEROESE
, SUBLANG_NEUTRAL
, 1252 },
380 { LANG_FILIPINO
, SUBLANG_NEUTRAL
, 1252 },
381 { LANG_FINNISH
, SUBLANG_NEUTRAL
, 1252 },
382 { LANG_FRENCH
, SUBLANG_NEUTRAL
, 1252 },
383 { LANG_FRISIAN
, SUBLANG_NEUTRAL
, 1252 },
385 { LANG_GAELIC
, SUBLANG_NEUTRAL
, 1252 },
386 #endif /* LANG_GAELIC */
387 { LANG_GALICIAN
, SUBLANG_NEUTRAL
, 1252 },
388 { LANG_GEORGIAN
, SUBLANG_NEUTRAL
, 0 },
389 { LANG_GERMAN
, SUBLANG_NEUTRAL
, 1252 },
390 { LANG_GREEK
, SUBLANG_NEUTRAL
, 1253 },
391 { LANG_GREENLANDIC
, SUBLANG_NEUTRAL
, 1252 },
392 { LANG_GUJARATI
, SUBLANG_NEUTRAL
, 0 },
393 { LANG_HAUSA
, SUBLANG_NEUTRAL
, 1252 },
394 { LANG_HEBREW
, SUBLANG_NEUTRAL
, 1255 },
395 { LANG_HINDI
, SUBLANG_NEUTRAL
, 0 },
396 { LANG_HUNGARIAN
, SUBLANG_NEUTRAL
, 1250 },
397 { LANG_ICELANDIC
, SUBLANG_NEUTRAL
, 1252 },
398 { LANG_IGBO
, SUBLANG_NEUTRAL
, 1252 },
399 { LANG_INDONESIAN
, SUBLANG_NEUTRAL
, 1252 },
400 { LANG_INUKTITUT
, SUBLANG_NEUTRAL
, 0 },
401 { LANG_INUKTITUT
, SUBLANG_INUKTITUT_CANADA_LATIN
, 0 },
402 { LANG_IRISH
, SUBLANG_NEUTRAL
, 1252 },
403 { LANG_ITALIAN
, SUBLANG_NEUTRAL
, 1252 },
404 { LANG_JAPANESE
, SUBLANG_NEUTRAL
, 932 },
405 { LANG_KANNADA
, SUBLANG_NEUTRAL
, 0 },
406 { LANG_KAZAK
, SUBLANG_NEUTRAL
, 1251 },
407 { LANG_KHMER
, SUBLANG_NEUTRAL
, 0 },
408 { LANG_KICHE
, SUBLANG_NEUTRAL
, 1252 },
409 { LANG_KINYARWANDA
, SUBLANG_NEUTRAL
, 1252 },
410 { LANG_KONKANI
, SUBLANG_NEUTRAL
, 0 },
411 { LANG_KOREAN
, SUBLANG_NEUTRAL
, 949 },
412 { LANG_KYRGYZ
, SUBLANG_NEUTRAL
, 1251 },
413 { LANG_LAO
, SUBLANG_NEUTRAL
, 0 },
414 { LANG_LATVIAN
, SUBLANG_NEUTRAL
, 1257 },
415 { LANG_LITHUANIAN
, SUBLANG_NEUTRAL
, 1257 },
416 { LANG_LOWER_SORBIAN
, SUBLANG_NEUTRAL
, 1252 },
417 { LANG_LUXEMBOURGISH
, SUBLANG_NEUTRAL
, 1252 },
418 { LANG_MACEDONIAN
, SUBLANG_NEUTRAL
, 1251 },
419 { LANG_MALAY
, SUBLANG_NEUTRAL
, 1252 },
420 { LANG_MALAYALAM
, SUBLANG_NEUTRAL
, 0 },
421 { LANG_MALTESE
, SUBLANG_NEUTRAL
, 0 },
422 { LANG_MAORI
, SUBLANG_NEUTRAL
, 0 },
423 { LANG_MAPUDUNGUN
, SUBLANG_NEUTRAL
, 1252 },
424 { LANG_MARATHI
, SUBLANG_NEUTRAL
, 0 },
425 { LANG_MOHAWK
, SUBLANG_NEUTRAL
, 1252 },
426 { LANG_MONGOLIAN
, SUBLANG_NEUTRAL
, 1251 },
427 { LANG_NEPALI
, SUBLANG_NEUTRAL
, 0 },
428 { LANG_NEUTRAL
, SUBLANG_NEUTRAL
, 1252 },
429 { LANG_NORWEGIAN
, SUBLANG_NEUTRAL
, 1252 },
430 { LANG_OCCITAN
, SUBLANG_NEUTRAL
, 1252 },
431 { LANG_ORIYA
, SUBLANG_NEUTRAL
, 0 },
432 { LANG_PASHTO
, SUBLANG_NEUTRAL
, 0 },
433 { LANG_PERSIAN
, SUBLANG_NEUTRAL
, 1256 },
434 { LANG_POLISH
, SUBLANG_NEUTRAL
, 1250 },
435 { LANG_PORTUGUESE
, SUBLANG_NEUTRAL
, 1252 },
436 { LANG_PUNJABI
, SUBLANG_NEUTRAL
, 0 },
437 { LANG_QUECHUA
, SUBLANG_NEUTRAL
, 1252 },
438 { LANG_ROMANIAN
, SUBLANG_NEUTRAL
, 1250 },
439 { LANG_ROMANSH
, SUBLANG_NEUTRAL
, 1252 },
440 { LANG_RUSSIAN
, SUBLANG_NEUTRAL
, 1251 },
441 { LANG_SAMI
, SUBLANG_NEUTRAL
, 1252 },
442 { LANG_SANSKRIT
, SUBLANG_NEUTRAL
, 0 },
443 { LANG_SERBIAN
, SUBLANG_NEUTRAL
, 1250 },
444 { LANG_SERBIAN
, SUBLANG_SERBIAN_CYRILLIC
, 1251 },
445 { LANG_SINHALESE
, SUBLANG_NEUTRAL
, 0 },
446 { LANG_SLOVAK
, SUBLANG_NEUTRAL
, 1250 },
447 { LANG_SLOVENIAN
, SUBLANG_NEUTRAL
, 1250 },
448 { LANG_SOTHO
, SUBLANG_NEUTRAL
, 1252 },
449 { LANG_SPANISH
, SUBLANG_NEUTRAL
, 1252 },
450 { LANG_SWAHILI
, SUBLANG_NEUTRAL
, 1252 },
451 { LANG_SWEDISH
, SUBLANG_NEUTRAL
, 1252 },
452 { LANG_SYRIAC
, SUBLANG_NEUTRAL
, 0 },
453 { LANG_TAJIK
, SUBLANG_NEUTRAL
, 1251 },
454 { LANG_TAMAZIGHT
, SUBLANG_NEUTRAL
, 1252 },
455 { LANG_TAMIL
, SUBLANG_NEUTRAL
, 0 },
456 { LANG_TATAR
, SUBLANG_NEUTRAL
, 1251 },
457 { LANG_TELUGU
, SUBLANG_NEUTRAL
, 0 },
458 { LANG_THAI
, SUBLANG_NEUTRAL
, 874 },
459 { LANG_TIBETAN
, SUBLANG_NEUTRAL
, 0 },
460 { LANG_TSWANA
, SUBLANG_NEUTRAL
, 1252 },
461 { LANG_TURKISH
, SUBLANG_NEUTRAL
, 1254 },
462 { LANG_TURKMEN
, SUBLANG_NEUTRAL
, 1250 },
463 { LANG_UIGHUR
, SUBLANG_NEUTRAL
, 1256 },
464 { LANG_UKRAINIAN
, SUBLANG_NEUTRAL
, 1251 },
465 { LANG_UPPER_SORBIAN
, SUBLANG_NEUTRAL
, 1252 },
466 { LANG_URDU
, SUBLANG_NEUTRAL
, 1256 },
467 { LANG_UZBEK
, SUBLANG_NEUTRAL
, 1254 },
468 { LANG_UZBEK
, SUBLANG_UZBEK_CYRILLIC
, 1251 },
469 { LANG_VIETNAMESE
, SUBLANG_NEUTRAL
, 1258 },
471 { LANG_WALON
, SUBLANG_NEUTRAL
, 1252 },
472 #endif /* LANG_WALON */
473 { LANG_WELSH
, SUBLANG_NEUTRAL
, 1252 },
474 { LANG_WOLOF
, SUBLANG_NEUTRAL
, 1252 },
475 { LANG_XHOSA
, SUBLANG_NEUTRAL
, 1252 },
476 { LANG_YAKUT
, SUBLANG_NEUTRAL
, 1251 },
477 { LANG_YI
, SUBLANG_NEUTRAL
, 0 },
478 { LANG_YORUBA
, SUBLANG_NEUTRAL
, 1252 },
479 { LANG_ZULU
, SUBLANG_NEUTRAL
, 1252 }
482 int get_language_codepage( unsigned short lang
, unsigned short sublang
)
485 int cp
= -1, defcp
= -1;
487 for (i
= 0; i
< sizeof(lang2cps
)/sizeof(lang2cps
[0]); i
++)
489 if (lang2cps
[i
].lang
!= lang
) continue;
490 if (lang2cps
[i
].sublang
== sublang
)
495 if (lang2cps
[i
].sublang
== SUBLANG_NEUTRAL
) defcp
= lang2cps
[i
].cp
;
498 if (cp
== -1) cp
= defcp
;
499 assert( cp
<= 0 || wine_cp_get_table(cp
) );