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 <assert.h>
  30 #include <ctype.h>
  31
  32 #include "wine/unicode.h"
  33 #include "wrc.h"
  34 #include "utils.h"
  35 #include "parser.h"
  36
  37 /* #define WANT_NEAR_INDICATION */
  38
  39 #ifdef WANT_NEAR_INDICATION
  40 void make_print(char *str)
  41 {
  42         while(*str)
  43         {
  44                 if(!isprint(*str))
  45                         *str = ' ';
  46                 str++;
  47         }
  48 }
  49 #endif
  50
  51 static void generic_msg(const char *s, const char *t, const char *n, va_list ap)
  52 {
  53         fprintf(stderr, "%s:%d:%d: %s: ", input_name ? input_name : "stdin", line_number, char_number, t);
  54         vfprintf(stderr, s, ap);
  55 #ifdef WANT_NEAR_INDICATION
  56         {
  57                 char *cpy;
  58                 if(n)
  59                 {
  60                         cpy = xstrdup(n);
  61                         make_print(cpy);
  62                         fprintf(stderr, " near '%s'", cpy);
  63                         free(cpy);
  64                 }
  65         }
  66 #endif
  67         fprintf(stderr, "\n");
  68 }
  69
  70
  71 int parser_error(const char *s, ...)
  72 {
  73         va_list ap;
  74         va_start(ap, s);
  75         generic_msg(s, "Error", parser_text, ap);
  76         va_end(ap);
  77         exit(1);
  78         return 1;
  79 }
  80
  81 int parser_warning(const char *s, ...)
  82 {
  83         va_list ap;
  84         va_start(ap, s);
  85         generic_msg(s, "Warning", parser_text, ap);
  86         va_end(ap);
  87         return 0;
  88 }
  89
  90 void internal_error(const char *file, int line, const char *s, ...)
  91 {
  92         va_list ap;
  93         va_start(ap, s);
  94         fprintf(stderr, "Internal error (please report) %s %d: ", file, line);
  95         vfprintf(stderr, s, ap);
  96         fprintf(stderr, "\n");
  97         va_end(ap);
  98         exit(3);
  99 }
 100
 101 void error(const char *s, ...)
 102 {
 103         va_list ap;
 104         va_start(ap, s);
 105         fprintf(stderr, "Error: ");
 106         vfprintf(stderr, s, ap);
 107         fprintf(stderr, "\n");
 108         va_end(ap);
 109         exit(2);
 110 }
 111
 112 void warning(const char *s, ...)
 113 {
 114         va_list ap;
 115         va_start(ap, s);
 116         fprintf(stderr, "Warning: ");
 117         vfprintf(stderr, s, ap);
 118         fprintf(stderr, "\n");
 119         va_end(ap);
 120 }
 121
 122 void chat(const char *s, ...)
 123 {
 124         if(debuglevel & DEBUGLEVEL_CHAT)
 125         {
 126                 va_list ap;
 127                 va_start(ap, s);
 128                 fprintf(stderr, "FYI: ");
 129                 vfprintf(stderr, s, ap);
 130                 fprintf(stderr, "\n");
 131                 va_end(ap);
 132         }
 133 }
 134
 135 char *dup_basename(const char *name, const char *ext)
 136 {
 137         int namelen;
 138         int extlen = strlen(ext);
 139         char *base;
 140         char *slash;
 141
 142         if(!name)
 143                 name = "wrc.tab";
 144
 145         slash = strrchr(name, '/');
 146         if (slash)
 147                 name = slash + 1;
 148
 149         namelen = strlen(name);
 150
 151         /* +4 for later extension and +1 for '\0' */
 152         base = xmalloc(namelen +4 +1);
 153         strcpy(base, name);
 154         if(!strcasecmp(name + namelen-extlen, ext))
 155         {
 156                 base[namelen - extlen] = '\0';
 157         }
 158         return base;
 159 }
 160
 161 void *xmalloc(size_t size)
 162 {
 163     void *res;
 164
 165     assert(size > 0);
 166     res = malloc(size);
 167     if(res == NULL)
 168     {
 169         error("Virtual memory exhausted.\n");
 170     }
 171     memset(res, 0x55, size);
 172     return res;
 173 }
 174
 175
 176 void *xrealloc(void *p, size_t size)
 177 {
 178     void *res;
 179
 180     assert(size > 0);
 181     res = realloc(p, size);
 182     if(res == NULL)
 183     {
 184         error("Virtual memory exhausted.\n");
 185     }
 186     return res;
 187 }
 188
 189 char *xstrdup(const char *str)
 190 {
 191         char *s;
 192
 193         assert(str != NULL);
 194         s = xmalloc(strlen(str)+1);
 195         return strcpy(s, str);
 196 }
 197
 198
 199 /*
 200  *****************************************************************************
 201  * Function     : compare_name_id
 202  * Syntax       : int compare_name_id(const name_id_t *n1, const name_id_t *n2)
 203  * Input        :
 204  * Output       :
 205  * Description  :
 206  * Remarks      :
 207  *****************************************************************************
 208 */
 209 int compare_name_id(const name_id_t *n1, const name_id_t *n2)
 210 {
 211         if(n1->type == name_ord && n2->type == name_ord)
 212         {
 213                 return n1->name.i_name - n2->name.i_name;
 214         }
 215         else if(n1->type == name_str && n2->type == name_str)
 216         {
 217                 if(n1->name.s_name->type == str_char
 218                 && n2->name.s_name->type == str_char)
 219                 {
 220                         return strcasecmp(n1->name.s_name->str.cstr, n2->name.s_name->str.cstr);
 221                 }
 222                 else if(n1->name.s_name->type == str_unicode
 223                 && n2->name.s_name->type == str_unicode)
 224                 {
 225                         return strcmpiW(n1->name.s_name->str.wstr, n2->name.s_name->str.wstr);
 226                 }
 227                 else
 228                 {
 229                         internal_error(__FILE__, __LINE__, "Can't yet compare strings of mixed type");
 230                 }
 231         }
 232         else if(n1->type == name_ord && n2->type == name_str)
 233                 return 1;
 234         else if(n1->type == name_str && n2->type == name_ord)
 235                 return -1;
 236         else
 237                 internal_error(__FILE__, __LINE__, "Comparing name-ids with unknown types (%d, %d)",
 238                                 n1->type, n2->type);
 239
 240         return 0; /* Keep the compiler happy */
 241 }
 242
 243 string_t *convert_string(const string_t *str, enum str_e type, int codepage)
 244 {
 245     const union cptable *cptable = codepage ? wine_cp_get_table( codepage ) : NULL;
 246     string_t *ret = xmalloc(sizeof(*ret));
 247     int res;
 248
 249     if (!codepage && str->type != type)
 250         parser_error( "Current language is Unicode only, cannot convert string" );
 251
 252     if((str->type == str_char) && (type == str_unicode))
 253     {
 254         ret->type = str_unicode;
 255         ret->size = cptable ? wine_cp_mbstowcs( cptable, 0, str->str.cstr, str->size, NULL, 0 )
 256                             : wine_utf8_mbstowcs( 0, str->str.cstr, str->size, NULL, 0 );
 257         ret->str.wstr = xmalloc( (ret->size+1) * sizeof(WCHAR) );
 258         if (cptable)
 259             res = wine_cp_mbstowcs( cptable, MB_ERR_INVALID_CHARS, str->str.cstr, str->size,
 260                                     ret->str.wstr, ret->size );
 261         else
 262             res = wine_utf8_mbstowcs( MB_ERR_INVALID_CHARS, str->str.cstr, str->size,
 263                                       ret->str.wstr, ret->size );
 264         if (res == -2)
 265             parser_error( "Invalid character in string '%.*s' for codepage %u\n",
 266                    str->size, str->str.cstr, codepage );
 267         ret->str.wstr[ret->size] = 0;
 268     }
 269     else if((str->type == str_unicode) && (type == str_char))
 270     {
 271         ret->type = str_char;
 272         ret->size = cptable ? wine_cp_wcstombs( cptable, 0, str->str.wstr, str->size, NULL, 0, NULL, NULL )
 273                             : wine_utf8_wcstombs( 0, str->str.wstr, str->size, NULL, 0 );
 274         ret->str.cstr = xmalloc( ret->size + 1 );
 275         if (cptable)
 276             wine_cp_wcstombs( cptable, 0, str->str.wstr, str->size, ret->str.cstr, ret->size, NULL, NULL );
 277         else
 278             wine_utf8_wcstombs( 0, str->str.wstr, str->size, ret->str.cstr, ret->size );
 279         ret->str.cstr[ret->size] = 0;
 280     }
 281     else if(str->type == str_unicode)
 282     {
 283         ret->type     = str_unicode;
 284         ret->size     = str->size;
 285         ret->str.wstr = xmalloc(sizeof(WCHAR)*(ret->size+1));
 286         memcpy( ret->str.wstr, str->str.wstr, ret->size * sizeof(WCHAR) );
 287         ret->str.wstr[ret->size] = 0;
 288     }
 289     else /* str->type == str_char */
 290     {
 291         ret->type     = str_char;
 292         ret->size     = str->size;
 293         ret->str.cstr = xmalloc( ret->size + 1 );
 294         memcpy( ret->str.cstr, str->str.cstr, ret->size );
 295         ret->str.cstr[ret->size] = 0;
 296     }
 297     return ret;
 298 }
 299
 300
 301 void free_string(string_t *str)
 302 {
 303     if (str->type == str_unicode) free( str->str.wstr );
 304     else free( str->str.cstr );
 305     free( str );
 306 }
 307
 308
 309 int check_unicode_conversion( const string_t *str_a, const string_t *str_w, int codepage )
 310 {
 311     int ok;
 312     string_t *teststr = convert_string( str_w, str_char, codepage );
 313
 314     ok = (teststr->size == str_a->size && !memcmp( teststr->str.cstr, str_a->str.cstr, str_a->size ));
 315
 316     if (!ok)
 317     {
 318         int i;
 319
 320         fprintf( stderr, "Source: %s", str_a->str.cstr );
 321         for (i = 0; i < str_a->size; i++)
 322             fprintf( stderr, " %02x", (unsigned char)str_a->str.cstr[i] );
 323         fprintf( stderr, "\nUnicode: " );
 324         for (i = 0; i < str_w->size; i++)
 325             fprintf( stderr, " %04x", str_w->str.wstr[i] );
 326         fprintf( stderr, "\nBack: %s", teststr->str.cstr );
 327         for (i = 0; i < teststr->size; i++)
 328             fprintf( stderr, " %02x", (unsigned char)teststr->str.cstr[i] );
 329         fprintf( stderr, "\n" );
 330     }
 331     free_string( teststr );
 332     return ok;
 333 }
 334
 335
 336 struct lang2cp
 337 {
 338     unsigned short lang;
 339     unsigned short sublang;
 340     unsigned int   cp;
 341 } lang2cp_t;
 342
 343 /* language to codepage conversion table */
 344 /* specific sublanguages need only be specified if their codepage */
 345 /* differs from the default (SUBLANG_NEUTRAL) */
 346 static const struct lang2cp lang2cps[] =
 347 {
 348     { LANG_AFRIKAANS,      SUBLANG_NEUTRAL,              1252 },
 349     { LANG_ALBANIAN,       SUBLANG_NEUTRAL,              1250 },
 350     { LANG_ARABIC,         SUBLANG_NEUTRAL,              1256 },
 351     { LANG_ARMENIAN,       SUBLANG_NEUTRAL,              0    },
 352     { LANG_AZERI,          SUBLANG_NEUTRAL,              1254 },
 353     { LANG_AZERI,          SUBLANG_AZERI_CYRILLIC,       1251 },
 354     { LANG_BASQUE,         SUBLANG_NEUTRAL,              1252 },
 355     { LANG_BELARUSIAN,     SUBLANG_NEUTRAL,              1251 },
 356 #ifdef LANG_BRETON
 357     { LANG_BRETON,         SUBLANG_NEUTRAL,              1252 },
 358 #endif /* LANG_BRETON */
 359     { LANG_BULGARIAN,      SUBLANG_NEUTRAL,              1251 },
 360     { LANG_CATALAN,        SUBLANG_NEUTRAL,              1252 },
 361     { LANG_CHINESE,        SUBLANG_NEUTRAL,              950  },
 362     { LANG_CHINESE,        SUBLANG_CHINESE_SINGAPORE,    936  },
 363     { LANG_CHINESE,        SUBLANG_CHINESE_SIMPLIFIED,   936  },
 364 #ifdef LANG_CORNISH
 365     { LANG_CORNISH,        SUBLANG_NEUTRAL,              1252 },
 366 #endif /* LANG_CORNISH */
 367     { LANG_CROATIAN,       SUBLANG_NEUTRAL,              1250 },
 368     { LANG_CZECH,          SUBLANG_NEUTRAL,              1250 },
 369     { LANG_DANISH,         SUBLANG_NEUTRAL,              1252 },
 370     { LANG_DIVEHI,         SUBLANG_NEUTRAL,              0    },
 371     { LANG_DUTCH,          SUBLANG_NEUTRAL,              1252 },
 372     { LANG_ENGLISH,        SUBLANG_NEUTRAL,              1252 },
 373 #ifdef LANG_ESPERANTO
 374     { LANG_ESPERANTO,      SUBLANG_NEUTRAL,              1252 },
 375 #endif /* LANG_ESPERANTO */
 376     { LANG_ESTONIAN,       SUBLANG_NEUTRAL,              1257 },
 377     { LANG_FAEROESE,       SUBLANG_NEUTRAL,              1252 },
 378     { LANG_FARSI,          SUBLANG_NEUTRAL,              1256 },
 379     { LANG_FINNISH,        SUBLANG_NEUTRAL,              1252 },
 380     { LANG_FRENCH,         SUBLANG_NEUTRAL,              1252 },
 381 #ifdef LANG_GAELIC
 382     { LANG_GAELIC,         SUBLANG_NEUTRAL,              1252 },
 383 #endif /* LANG_GAELIC */
 384     { LANG_GALICIAN,       SUBLANG_NEUTRAL,              1252 },
 385     { LANG_GEORGIAN,       SUBLANG_NEUTRAL,              0    },
 386     { LANG_GERMAN,         SUBLANG_NEUTRAL,              1252 },
 387     { LANG_GREEK,          SUBLANG_NEUTRAL,              1253 },
 388     { LANG_GUJARATI,       SUBLANG_NEUTRAL,              0    },
 389     { LANG_HEBREW,         SUBLANG_NEUTRAL,              1255 },
 390     { LANG_HINDI,          SUBLANG_NEUTRAL,              0    },
 391     { LANG_HUNGARIAN,      SUBLANG_NEUTRAL,              1250 },
 392     { LANG_ICELANDIC,      SUBLANG_NEUTRAL,              1252 },
 393     { LANG_INDONESIAN,     SUBLANG_NEUTRAL,              1252 },
 394     { LANG_ITALIAN,        SUBLANG_NEUTRAL,              1252 },
 395     { LANG_JAPANESE,       SUBLANG_NEUTRAL,              932  },
 396     { LANG_KANNADA,        SUBLANG_NEUTRAL,              0    },
 397     { LANG_KAZAK,          SUBLANG_NEUTRAL,              1251 },
 398     { LANG_KONKANI,        SUBLANG_NEUTRAL,              0    },
 399     { LANG_KOREAN,         SUBLANG_NEUTRAL,              949  },
 400     { LANG_KYRGYZ,         SUBLANG_NEUTRAL,              1251 },
 401     { LANG_LATVIAN,        SUBLANG_NEUTRAL,              1257 },
 402     { LANG_LITHUANIAN,     SUBLANG_NEUTRAL,              1257 },
 403     { LANG_MACEDONIAN,     SUBLANG_NEUTRAL,              1251 },
 404     { LANG_MALAY,          SUBLANG_NEUTRAL,              1252 },
 405     { LANG_MARATHI,        SUBLANG_NEUTRAL,              0    },
 406     { LANG_MONGOLIAN,      SUBLANG_NEUTRAL,              1251 },
 407     { LANG_NEUTRAL,        SUBLANG_NEUTRAL,              1252 },
 408     { LANG_NORWEGIAN,      SUBLANG_NEUTRAL,              1252 },
 409     { LANG_POLISH,         SUBLANG_NEUTRAL,              1250 },
 410     { LANG_PORTUGUESE,     SUBLANG_NEUTRAL,              1252 },
 411     { LANG_PUNJABI,        SUBLANG_NEUTRAL,              0    },
 412     { LANG_ROMANIAN,       SUBLANG_NEUTRAL,              1250 },
 413     { LANG_RUSSIAN,        SUBLANG_NEUTRAL,              1251 },
 414     { LANG_SANSKRIT,       SUBLANG_NEUTRAL,              0    },
 415     { LANG_SERBIAN,        SUBLANG_NEUTRAL,              1250 },
 416     { LANG_SERBIAN,        SUBLANG_SERBIAN_CYRILLIC,     1251 },
 417     { LANG_SLOVAK,         SUBLANG_NEUTRAL,              1250 },
 418     { LANG_SLOVENIAN,      SUBLANG_NEUTRAL,              1250 },
 419     { LANG_SPANISH,        SUBLANG_NEUTRAL,              1252 },
 420     { LANG_SWAHILI,        SUBLANG_NEUTRAL,              1252 },
 421     { LANG_SWEDISH,        SUBLANG_NEUTRAL,              1252 },
 422     { LANG_SYRIAC,         SUBLANG_NEUTRAL,              0    },
 423     { LANG_TAMIL,          SUBLANG_NEUTRAL,              0    },
 424     { LANG_TATAR,          SUBLANG_NEUTRAL,              1251 },
 425     { LANG_TELUGU,         SUBLANG_NEUTRAL,              0    },
 426     { LANG_THAI,           SUBLANG_NEUTRAL,              874  },
 427     { LANG_TURKISH,        SUBLANG_NEUTRAL,              1254 },
 428     { LANG_UKRAINIAN,      SUBLANG_NEUTRAL,              1251 },
 429     { LANG_URDU,           SUBLANG_NEUTRAL,              1256 },
 430     { LANG_UZBEK,          SUBLANG_NEUTRAL,              1254 },
 431     { LANG_UZBEK,          SUBLANG_UZBEK_CYRILLIC,       1251 },
 432     { LANG_VIETNAMESE,     SUBLANG_NEUTRAL,              1258 }
 433 #ifdef LANG_WALON
 434     , { LANG_WALON,          SUBLANG_NEUTRAL,              1252 }
 435 #endif /* LANG_WALON */
 436 #ifdef LANG_WELSH
 437     , { LANG_WELSH,          SUBLANG_NEUTRAL,              1252 }
 438 #endif /* LANG_WELSH */
 439 };
 440
 441 int get_language_codepage( unsigned short lang, unsigned short sublang )
 442 {
 443     unsigned int i;
 444     int cp = -1, defcp = -1;
 445
 446     for (i = 0; i < sizeof(lang2cps)/sizeof(lang2cps[0]); i++)
 447     {
 448         if (lang2cps[i].lang != lang) continue;
 449         if (lang2cps[i].sublang == sublang)
 450         {
 451             cp = lang2cps[i].cp;
 452             break;
 453         }
 454         if (lang2cps[i].sublang == SUBLANG_NEUTRAL) defcp = lang2cps[i].cp;
 455     }
 456
 457     if (cp == -1) cp = defcp;
 458     assert( cp <= 0 || wine_cp_get_table(cp) );
 459     return cp;
 460 }