tools/wrc/utils.c

   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 "wine/unicode.h"
  32 #include "wrc.h"
  33 #include "utils.h"
  34 #include "parser.h"
  35
  36 /* #define WANT_NEAR_INDICATION */
  37
  38 #ifdef WANT_NEAR_INDICATION
  39 void make_print(char *str)
  40 {
  41         while(*str)
  42         {
  43                 if(!isprint(*str))
  44                         *str = ' ';
  45                 str++;
  46         }
  47 }
  48 #endif
  49
  50 static void generic_msg(const char *s, const char *t, const char *n, va_list ap)
  51 {
  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
  55         {
  56                 char *cpy;
  57                 if(n)
  58                 {
  59                         cpy = xstrdup(n);
  60                         make_print(cpy);
  61                         fprintf(stderr, " near '%s'", cpy);
  62                         free(cpy);
  63                 }
  64         }
  65 #endif
  66 }
  67
  68
  69 int parser_error(const char *s, ...)
  70 {
  71         va_list ap;
  72         va_start(ap, s);
  73         generic_msg(s, "Error", parser_text, ap);
  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 error(const char *s, ...)
  99 {
 100         va_list ap;
 101         va_start(ap, s);
 102         fprintf(stderr, "Error: ");
 103         vfprintf(stderr, s, ap);
 104         va_end(ap);
 105         exit(2);
 106 }
 107
 108 void warning(const char *s, ...)
 109 {
 110         va_list ap;
 111         va_start(ap, s);
 112         fprintf(stderr, "Warning: ");
 113         vfprintf(stderr, s, ap);
 114         va_end(ap);
 115 }
 116
 117 void chat(const char *s, ...)
 118 {
 119         if(debuglevel & DEBUGLEVEL_CHAT)
 120         {
 121                 va_list ap;
 122                 va_start(ap, s);
 123                 fprintf(stderr, "FYI: ");
 124                 vfprintf(stderr, s, ap);
 125                 va_end(ap);
 126         }
 127 }
 128
 129 char *dup_basename(const char *name, const char *ext)
 130 {
 131         int namelen;
 132         int extlen = strlen(ext);
 133         char *base;
 134         char *slash;
 135
 136         if(!name)
 137                 name = "wrc.tab";
 138
 139         slash = strrchr(name, '/');
 140         if (slash)
 141                 name = slash + 1;
 142
 143         namelen = strlen(name);
 144
 145         /* +4 for later extension and +1 for '\0' */
 146         base = xmalloc(namelen +4 +1);
 147         strcpy(base, name);
 148         if(!strcasecmp(name + namelen-extlen, ext))
 149         {
 150                 base[namelen - extlen] = '\0';
 151         }
 152         return base;
 153 }
 154
 155 void *xmalloc(size_t size)
 156 {
 157     void *res;
 158
 159     assert(size > 0);
 160     res = malloc(size);
 161     if(res == NULL)
 162     {
 163         error("Virtual memory exhausted.\n");
 164     }
 165     memset(res, 0x55, size);
 166     return res;
 167 }
 168
 169
 170 void *xrealloc(void *p, size_t size)
 171 {
 172     void *res;
 173
 174     assert(size > 0);
 175     res = realloc(p, size);
 176     if(res == NULL)
 177     {
 178         error("Virtual memory exhausted.\n");
 179     }
 180     return res;
 181 }
 182
 183 char *xstrdup(const char *str)
 184 {
 185         char *s;
 186
 187         assert(str != NULL);
 188         s = xmalloc(strlen(str)+1);
 189         return strcpy(s, str);
 190 }
 191
 192
 193 /*
 194  *****************************************************************************
 195  * Function     : compare_name_id
 196  * Syntax       : int compare_name_id(const name_id_t *n1, const name_id_t *n2)
 197  * Input        :
 198  * Output       :
 199  * Description  :
 200  * Remarks      :
 201  *****************************************************************************
 202 */
 203 int compare_name_id(const name_id_t *n1, const name_id_t *n2)
 204 {
 205         if(n1->type == name_ord && n2->type == name_ord)
 206         {
 207                 return n1->name.i_name - n2->name.i_name;
 208         }
 209         else if(n1->type == name_str && n2->type == name_str)
 210         {
 211                 if(n1->name.s_name->type == str_char
 212                 && n2->name.s_name->type == str_char)
 213                 {
 214                         return strcasecmp(n1->name.s_name->str.cstr, n2->name.s_name->str.cstr);
 215                 }
 216                 else if(n1->name.s_name->type == str_unicode
 217                 && n2->name.s_name->type == str_unicode)
 218                 {
 219                         return strcmpiW(n1->name.s_name->str.wstr, n2->name.s_name->str.wstr);
 220                 }
 221                 else
 222                 {
 223                         internal_error(__FILE__, __LINE__, "Can't yet compare strings of mixed type\n");
 224                 }
 225         }
 226         else if(n1->type == name_ord && n2->type == name_str)
 227                 return 1;
 228         else if(n1->type == name_str && n2->type == name_ord)
 229                 return -1;
 230         else
 231                 internal_error(__FILE__, __LINE__, "Comparing name-ids with unknown types (%d, %d)\n",
 232                                 n1->type, n2->type);
 233
 234         return 0; /* Keep the compiler happy */
 235 }
 236
 237 string_t *convert_string(const string_t *str, enum str_e type, int codepage)
 238 {
 239     const union cptable *cptable = codepage ? wine_cp_get_table( codepage ) : NULL;
 240     string_t *ret = xmalloc(sizeof(*ret));
 241     int res;
 242
 243     if (!codepage && str->type != type)
 244         parser_error( "Current language is Unicode only, cannot convert string\n" );
 245
 246     if((str->type == str_char) && (type == str_unicode))
 247     {
 248         ret->type = str_unicode;
 249         ret->size = cptable ? wine_cp_mbstowcs( cptable, 0, str->str.cstr, str->size, NULL, 0 )
 250                             : wine_utf8_mbstowcs( 0, str->str.cstr, str->size, NULL, 0 );
 251         ret->str.wstr = xmalloc( (ret->size+1) * sizeof(WCHAR) );
 252         if (cptable)
 253             res = wine_cp_mbstowcs( cptable, MB_ERR_INVALID_CHARS, str->str.cstr, str->size,
 254                                     ret->str.wstr, ret->size );
 255         else
 256             res = wine_utf8_mbstowcs( MB_ERR_INVALID_CHARS, str->str.cstr, str->size,
 257                                       ret->str.wstr, ret->size );
 258         if (res == -2)
 259             parser_error( "Invalid character in string '%.*s' for codepage %u\n",
 260                    str->size, str->str.cstr, codepage );
 261         ret->str.wstr[ret->size] = 0;
 262     }
 263     else if((str->type == str_unicode) && (type == str_char))
 264     {
 265         ret->type = str_char;
 266         ret->size = cptable ? wine_cp_wcstombs( cptable, 0, str->str.wstr, str->size, NULL, 0, NULL, NULL )
 267                             : wine_utf8_wcstombs( 0, str->str.wstr, str->size, NULL, 0 );
 268         ret->str.cstr = xmalloc( ret->size + 1 );
 269         if (cptable)
 270             wine_cp_wcstombs( cptable, 0, str->str.wstr, str->size, ret->str.cstr, ret->size, NULL, NULL );
 271         else
 272             wine_utf8_wcstombs( 0, str->str.wstr, str->size, ret->str.cstr, ret->size );
 273         ret->str.cstr[ret->size] = 0;
 274     }
 275     else if(str->type == str_unicode)
 276     {
 277         ret->type     = str_unicode;
 278         ret->size     = str->size;
 279         ret->str.wstr = xmalloc(sizeof(WCHAR)*(ret->size+1));
 280         memcpy( ret->str.wstr, str->str.wstr, ret->size * sizeof(WCHAR) );
 281         ret->str.wstr[ret->size] = 0;
 282     }
 283     else /* str->type == str_char */
 284     {
 285         ret->type     = str_char;
 286         ret->size     = str->size;
 287         ret->str.cstr = xmalloc( ret->size + 1 );
 288         memcpy( ret->str.cstr, str->str.cstr, ret->size );
 289         ret->str.cstr[ret->size] = 0;
 290     }
 291     return ret;
 292 }
 293
 294
 295 void free_string(string_t *str)
 296 {
 297     if (str->type == str_unicode) free( str->str.wstr );
 298     else free( str->str.cstr );
 299     free( str );
 300 }
 301
 302
 303 int check_unicode_conversion( const string_t *str_a, const string_t *str_w, int codepage )
 304 {
 305     int ok;
 306     string_t *teststr = convert_string( str_w, str_char, codepage );
 307
 308     ok = (teststr->size == str_a->size && !memcmp( teststr->str.cstr, str_a->str.cstr, str_a->size ));
 309
 310     if (!ok)
 311     {
 312         int i;
 313
 314         fprintf( stderr, "Source: %s", str_a->str.cstr );
 315         for (i = 0; i < str_a->size; i++)
 316             fprintf( stderr, " %02x", (unsigned char)str_a->str.cstr[i] );
 317         fprintf( stderr, "\nUnicode: " );
 318         for (i = 0; i < str_w->size; i++)
 319             fprintf( stderr, " %04x", str_w->str.wstr[i] );
 320         fprintf( stderr, "\nBack: %s", teststr->str.cstr );
 321         for (i = 0; i < teststr->size; i++)
 322             fprintf( stderr, " %02x", (unsigned char)teststr->str.cstr[i] );
 323         fprintf( stderr, "\n" );
 324     }
 325     free_string( teststr );
 326     return ok;
 327 }
 328
 329
 330 struct lang2cp
 331 {
 332     unsigned short lang;
 333     unsigned short sublang;
 334     unsigned int   cp;
 335 } lang2cp_t;
 336
 337 /* language to codepage conversion table */
 338 /* specific sublanguages need only be specified if their codepage */
 339 /* differs from the default (SUBLANG_NEUTRAL) */
 340 static const struct lang2cp lang2cps[] =
 341 {
 342     { LANG_AFRIKAANS,      SUBLANG_NEUTRAL,              1252 },
 343     { LANG_ALBANIAN,       SUBLANG_NEUTRAL,              1250 },
 344     { LANG_ARABIC,         SUBLANG_NEUTRAL,              1256 },
 345     { LANG_ARMENIAN,       SUBLANG_NEUTRAL,              0    },
 346     { LANG_AZERI,          SUBLANG_NEUTRAL,              1254 },
 347     { LANG_AZERI,          SUBLANG_AZERI_CYRILLIC,       1251 },
 348     { LANG_BASQUE,         SUBLANG_NEUTRAL,              1252 },
 349     { LANG_BELARUSIAN,     SUBLANG_NEUTRAL,              1251 },
 350 #ifdef LANG_BRETON
 351     { LANG_BRETON,         SUBLANG_NEUTRAL,              1252 },
 352 #endif /* LANG_BRETON */
 353     { LANG_BULGARIAN,      SUBLANG_NEUTRAL,              1251 },
 354     { LANG_CATALAN,        SUBLANG_NEUTRAL,              1252 },
 355     { LANG_CHINESE,        SUBLANG_NEUTRAL,              950  },
 356     { LANG_CHINESE,        SUBLANG_CHINESE_SINGAPORE,    936  },
 357     { LANG_CHINESE,        SUBLANG_CHINESE_SIMPLIFIED,   936  },
 358 #ifdef LANG_CORNISH
 359     { LANG_CORNISH,        SUBLANG_NEUTRAL,              1252 },
 360 #endif /* LANG_CORNISH */
 361     { LANG_CROATIAN,       SUBLANG_NEUTRAL,              1250 },
 362     { LANG_CZECH,          SUBLANG_NEUTRAL,              1250 },
 363     { LANG_DANISH,         SUBLANG_NEUTRAL,              1252 },
 364     { LANG_DIVEHI,         SUBLANG_NEUTRAL,              0    },
 365     { LANG_DUTCH,          SUBLANG_NEUTRAL,              1252 },
 366     { LANG_ENGLISH,        SUBLANG_NEUTRAL,              1252 },
 367 #ifdef LANG_ESPERANTO
 368     { LANG_ESPERANTO,      SUBLANG_NEUTRAL,              1252 },
 369 #endif /* LANG_ESPERANTO */
 370     { LANG_ESTONIAN,       SUBLANG_NEUTRAL,              1257 },
 371     { LANG_FAEROESE,       SUBLANG_NEUTRAL,              1252 },
 372     { LANG_FARSI,          SUBLANG_NEUTRAL,              1256 },
 373     { LANG_FINNISH,        SUBLANG_NEUTRAL,              1252 },
 374     { LANG_FRENCH,         SUBLANG_NEUTRAL,              1252 },
 375 #ifdef LANG_GAELIC
 376     { LANG_GAELIC,         SUBLANG_NEUTRAL,              1252 },
 377 #endif /* LANG_GAELIC */
 378     { LANG_GALICIAN,       SUBLANG_NEUTRAL,              1252 },
 379     { LANG_GEORGIAN,       SUBLANG_NEUTRAL,              0    },
 380     { LANG_GERMAN,         SUBLANG_NEUTRAL,              1252 },
 381     { LANG_GREEK,          SUBLANG_NEUTRAL,              1253 },
 382     { LANG_GUJARATI,       SUBLANG_NEUTRAL,              0    },
 383     { LANG_HEBREW,         SUBLANG_NEUTRAL,              1255 },
 384     { LANG_HINDI,          SUBLANG_NEUTRAL,              0    },
 385     { LANG_HUNGARIAN,      SUBLANG_NEUTRAL,              1250 },
 386     { LANG_ICELANDIC,      SUBLANG_NEUTRAL,              1252 },
 387     { LANG_INDONESIAN,     SUBLANG_NEUTRAL,              1252 },
 388     { LANG_ITALIAN,        SUBLANG_NEUTRAL,              1252 },
 389     { LANG_JAPANESE,       SUBLANG_NEUTRAL,              932  },
 390     { LANG_KANNADA,        SUBLANG_NEUTRAL,              0    },
 391     { LANG_KAZAK,          SUBLANG_NEUTRAL,              1251 },
 392     { LANG_KONKANI,        SUBLANG_NEUTRAL,              0    },
 393     { LANG_KOREAN,         SUBLANG_NEUTRAL,              949  },
 394     { LANG_KYRGYZ,         SUBLANG_NEUTRAL,              1251 },
 395     { LANG_LATVIAN,        SUBLANG_NEUTRAL,              1257 },
 396     { LANG_LITHUANIAN,     SUBLANG_NEUTRAL,              1257 },
 397     { LANG_MACEDONIAN,     SUBLANG_NEUTRAL,              1251 },
 398     { LANG_MALAY,          SUBLANG_NEUTRAL,              1252 },
 399     { LANG_MARATHI,        SUBLANG_NEUTRAL,              0    },
 400     { LANG_MONGOLIAN,      SUBLANG_NEUTRAL,              1251 },
 401     { LANG_NEUTRAL,        SUBLANG_NEUTRAL,              1252 },
 402     { LANG_NORWEGIAN,      SUBLANG_NEUTRAL,              1252 },
 403     { LANG_POLISH,         SUBLANG_NEUTRAL,              1250 },
 404     { LANG_PORTUGUESE,     SUBLANG_NEUTRAL,              1252 },
 405     { LANG_PUNJABI,        SUBLANG_NEUTRAL,              0    },
 406     { LANG_ROMANIAN,       SUBLANG_NEUTRAL,              1250 },
 407     { LANG_RUSSIAN,        SUBLANG_NEUTRAL,              1251 },
 408     { LANG_SANSKRIT,       SUBLANG_NEUTRAL,              0    },
 409     { LANG_SERBIAN,        SUBLANG_NEUTRAL,              1250 },
 410     { LANG_SERBIAN,        SUBLANG_SERBIAN_CYRILLIC,     1251 },
 411     { LANG_SLOVAK,         SUBLANG_NEUTRAL,              1250 },
 412     { LANG_SLOVENIAN,      SUBLANG_NEUTRAL,              1250 },
 413     { LANG_SPANISH,        SUBLANG_NEUTRAL,              1252 },
 414     { LANG_SWAHILI,        SUBLANG_NEUTRAL,              1252 },
 415     { LANG_SWEDISH,        SUBLANG_NEUTRAL,              1252 },
 416     { LANG_SYRIAC,         SUBLANG_NEUTRAL,              0    },
 417     { LANG_TAMIL,          SUBLANG_NEUTRAL,              0    },
 418     { LANG_TATAR,          SUBLANG_NEUTRAL,              1251 },
 419     { LANG_TELUGU,         SUBLANG_NEUTRAL,              0    },
 420     { LANG_THAI,           SUBLANG_NEUTRAL,              874  },
 421     { LANG_TURKISH,        SUBLANG_NEUTRAL,              1254 },
 422     { LANG_UKRAINIAN,      SUBLANG_NEUTRAL,              1251 },
 423     { LANG_URDU,           SUBLANG_NEUTRAL,              1256 },
 424     { LANG_UZBEK,          SUBLANG_NEUTRAL,              1254 },
 425     { LANG_UZBEK,          SUBLANG_UZBEK_CYRILLIC,       1251 },
 426     { LANG_VIETNAMESE,     SUBLANG_NEUTRAL,              1258 }
 427 #ifdef LANG_WALON
 428     , { LANG_WALON,          SUBLANG_NEUTRAL,              1252 }
 429 #endif /* LANG_WALON */
 430 #ifdef LANG_WELSH
 431     , { LANG_WELSH,          SUBLANG_NEUTRAL,              1252 }
 432 #endif /* LANG_WELSH */
 433 };
 434
 435 int get_language_codepage( unsigned short lang, unsigned short sublang )
 436 {
 437     unsigned int i;
 438     int cp = -1, defcp = -1;
 439
 440     for (i = 0; i < sizeof(lang2cps)/sizeof(lang2cps[0]); i++)
 441     {
 442         if (lang2cps[i].lang != lang) continue;
 443         if (lang2cps[i].sublang == sublang)
 444         {
 445             cp = lang2cps[i].cp;
 446             break;
 447         }
 448         if (lang2cps[i].sublang == SUBLANG_NEUTRAL) defcp = lang2cps[i].cp;
 449     }
 450
 451     if (cp == -1) cp = defcp;
 452     assert( cp <= 0 || wine_cp_get_table(cp) );
 453     return cp;
 454 }