tests/test-c32toupper.c

   1 /* Test of c32toupper() function.
   2    Copyright (C) 2020-2024 Free Software Foundation, Inc.
   3
   4    This program is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU General Public License as published by
   6    the Free Software Foundation, either version 3 of the License, or
   7    (at your option) any later version.
   8
   9    This program is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU General Public License for more details.
  13
  14    You should have received a copy of the GNU General Public License
  15    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  16
  17 #include <config.h>
  18
  19 #include <uchar.h>
  20
  21 #include "signature.h"
  22 SIGNATURE_CHECK (c32toupper, wint_t, (wint_t));
  23
  24 #include <locale.h>
  25 #include <stdlib.h>
  26 #include <string.h>
  27 #include <wchar.h>
  28
  29 #include "macros.h"
  30
  31 /* Representation of a multibyte character.  */
  32 #define MBCHAR_BUF_SIZE 6
  33 struct multibyte
  34 {
  35   size_t nbytes;             /* number of bytes of current character, > 0 */
  36   char buf[MBCHAR_BUF_SIZE]; /* room for the bytes */
  37 };
  38
  39 /* Returns the value of c32toupper for the multibyte character s[0..n-1],
  40    as a multibyte character.  */
  41 static struct multibyte
  42 for_character (const char *s, size_t n)
  43 {
  44   mbstate_t state;
  45   char32_t wc;
  46   size_t ret;
  47   struct multibyte result;
  48
  49   memset (&state, '\0', sizeof (mbstate_t));
  50   wc = (char32_t) 0xBADFACE;
  51   ret = mbrtoc32 (&wc, s, n, &state);
  52   ASSERT (ret == n);
  53
  54   wc = c32toupper (wc);
  55   ASSERT (wc != WEOF);
  56
  57   memset (&state, '\0', sizeof (mbstate_t));
  58   ret = c32rtomb (result.buf, wc, &state);
  59   ASSERT (ret != 0);
  60   if (ret == (size_t)(-1))
  61     /* wc cannot be converted back to multibyte.  */
  62     result.nbytes = 0;
  63   else
  64     {
  65       ASSERT (ret <= MBCHAR_BUF_SIZE);
  66       result.nbytes = ret;
  67     }
  68   return result;
  69 }
  70
  71 int
  72 main (int argc, char *argv[])
  73 {
  74   wint_t wc;
  75   struct multibyte mb;
  76   char buf[4];
  77
  78   /* configure should already have checked that the locale is supported.  */
  79   if (setlocale (LC_ALL, "") == NULL)
  80     return 1;
  81
  82   /* Test WEOF.  */
  83   wc = c32toupper (WEOF);
  84   ASSERT (wc == WEOF);
  85
  86   /* Test single-byte characters.
  87      POSIX specifies in
  88        <https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap07.html>
  89      that
  90        - in all locales, the lowercase characters include the a ... z
  91          characters, and the corresponding characters A ... Z (if not in a
  92          Turkish locale) are uppercase,
  93        - in the "POSIX" locale (which is usually the same as the "C" locale),
  94          the lowercase characters include only the ASCII a ... z characters,
  95          and the corresponding characters A ... Z are uppercase.
  96    */
  97 #if defined __NetBSD__
  98   /* towupper is broken in the zh_CN.GB18030 locale on NetBSD 9.0.
  99      See <https://gnats.netbsd.org/cgi-bin/query-pr-single.pl?number=57339>.  */
 100   if (!(argc > 1 && argv[1][0] == '4'))
 101 #endif
 102   {
 103     int c;
 104
 105     for (c = 0; c < 0x100; c++)
 106       switch (c)
 107         {
 108         case '\t': case '\v': case '\f':
 109         case ' ': case '!': case '"': case '#': case '%':
 110         case '&': case '\'': case '(': case ')': case '*':
 111         case '+': case ',': case '-': case '.': case '/':
 112         case '0': case '1': case '2': case '3': case '4':
 113         case '5': case '6': case '7': case '8': case '9':
 114         case ':': case ';': case '<': case '=': case '>':
 115         case '?':
 116         case 'A': case 'B': case 'C': case 'D': case 'E':
 117         case 'F': case 'G': case 'H': case 'I': case 'J':
 118         case 'K': case 'L': case 'M': case 'N': case 'O':
 119         case 'P': case 'Q': case 'R': case 'S': case 'T':
 120         case 'U': case 'V': case 'W': case 'X': case 'Y':
 121         case 'Z':
 122         case '[': case '\\': case ']': case '^': case '_':
 123         case 'a': case 'b': case 'c': case 'd': case 'e':
 124         case 'f': case 'g': case 'h': case 'i': case 'j':
 125         case 'k': case 'l': case 'm': case 'n': case 'o':
 126         case 'p': case 'q': case 'r': case 's': case 't':
 127         case 'u': case 'v': case 'w': case 'x': case 'y':
 128         case 'z': case '{': case '|': case '}': case '~':
 129           /* c is in the ISO C "basic character set".  */
 130           buf[0] = (unsigned char) c;
 131           mb = for_character (buf, 1);
 132           switch (c)
 133             {
 134             case 'a': case 'b': case 'c': case 'd': case 'e':
 135             case 'f': case 'g': case 'h': case 'i': case 'j':
 136             case 'k': case 'l': case 'm': case 'n': case 'o':
 137             case 'p': case 'q': case 'r': case 's': case 't':
 138             case 'u': case 'v': case 'w': case 'x': case 'y':
 139             case 'z':
 140               ASSERT (mb.nbytes == 1);
 141               ASSERT ((unsigned char) mb.buf[0] == (unsigned char) c - 'a' + 'A');
 142               break;
 143             default:
 144               ASSERT (mb.nbytes == 1);
 145               ASSERT ((unsigned char) mb.buf[0] == c);
 146               break;
 147             }
 148           break;
 149         }
 150   }
 151
 152   if (argc > 1)
 153     switch (argv[1][0])
 154       {
 155       case '0':
 156         /* C locale; tested above.  */
 157         return test_exit_status;
 158
 159       case '1':
 160         /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
 161         {
 162           /* U+00B2 SUPERSCRIPT TWO */
 163           mb = for_character ("\262", 1);
 164           ASSERT (mb.nbytes == 1);
 165           ASSERT (memcmp (mb.buf, "\262", 1) == 0);
 166         #if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __NetBSD__ || defined __sun || defined __CYGWIN__)
 167           /* U+00B5 MICRO SIGN */
 168           mb = for_character ("\265", 1);
 169           ASSERT (mb.nbytes == 1);
 170           ASSERT (memcmp (mb.buf, "\265", 1) == 0);
 171         #endif
 172           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 173           mb = for_character ("\311", 1);
 174           ASSERT (mb.nbytes == 1);
 175           ASSERT (memcmp (mb.buf, "\311", 1) == 0);
 176           /* U+00DF LATIN SMALL LETTER SHARP S */
 177           mb = for_character ("\337", 1);
 178           ASSERT (mb.nbytes == 1);
 179           ASSERT (memcmp (mb.buf, "\337", 1) == 0);
 180           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 181           mb = for_character ("\351", 1);
 182           ASSERT (mb.nbytes == 1);
 183           ASSERT (memcmp (mb.buf, "\311", 1) == 0);
 184         #if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun || defined __CYGWIN__ || (defined _WIN32 && !defined __CYGWIN__))
 185           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 186           mb = for_character ("\377", 1);
 187           ASSERT (mb.nbytes == 1);
 188           ASSERT (memcmp (mb.buf, "\377", 1) == 0);
 189         #endif
 190         }
 191         return test_exit_status;
 192
 193       case '2':
 194         /* Locale encoding is EUC-JP.  */
 195         {
 196           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 197           mb = for_character ("\217\252\261", 3);
 198           ASSERT (mb.nbytes == 3);
 199           ASSERT (memcmp (mb.buf, "\217\252\261", 3) == 0);
 200         #if !defined __NetBSD__
 201           /* U+00DF LATIN SMALL LETTER SHARP S */
 202           mb = for_character ("\217\251\316", 3);
 203           ASSERT (mb.nbytes == 3);
 204           ASSERT (memcmp (mb.buf, "\217\251\316", 3) == 0);
 205         #endif
 206         #if !((defined __APPLE__ && defined __MACH__) || defined __DragonFly__)
 207           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 208           mb = for_character ("\217\253\261", 3);
 209           ASSERT (mb.nbytes == 3);
 210           ASSERT (memcmp (mb.buf, "\217\252\261", 3) == 0);
 211         #endif
 212         #if !((defined __APPLE__ && defined __MACH__) || defined __DragonFly__ || defined __NetBSD__)
 213           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 214           mb = for_character ("\217\253\363", 3);
 215           ASSERT (mb.nbytes == 3);
 216           ASSERT (memcmp (mb.buf, "\217\252\363", 3) == 0);
 217         #endif
 218           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 219           mb = for_character ("\217\251\250", 3);
 220           ASSERT (mb.nbytes == 3);
 221           ASSERT (memcmp (mb.buf, "\217\251\250", 3) == 0);
 222         #if !((defined __APPLE__ && defined __MACH__) || defined __DragonFly__)
 223           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 224           mb = for_character ("\217\251\310", 3);
 225           ASSERT (mb.nbytes == 3);
 226           ASSERT (memcmp (mb.buf, "\217\251\250", 3) == 0);
 227         #endif
 228           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 229           mb = for_character ("\247\273", 2);
 230           ASSERT (mb.nbytes == 2);
 231           ASSERT (memcmp (mb.buf, "\247\273", 2) == 0);
 232         #if !defined __DragonFly__
 233           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 234           mb = for_character ("\247\353", 2);
 235           ASSERT (mb.nbytes == 2);
 236           ASSERT (memcmp (mb.buf, "\247\273", 2) == 0);
 237         #endif
 238           /* U+3073 HIRAGANA LETTER BI */
 239           mb = for_character ("\244\323", 2);
 240           ASSERT (mb.nbytes == 2);
 241           ASSERT (memcmp (mb.buf, "\244\323", 2) == 0);
 242           /* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
 243           mb = for_character ("\243\307", 2);
 244           ASSERT (mb.nbytes == 2);
 245           ASSERT (memcmp (mb.buf, "\243\307", 2) == 0);
 246         #if !defined __DragonFly__
 247           /* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
 248           mb = for_character ("\243\347", 2);
 249           ASSERT (mb.nbytes == 2);
 250           ASSERT (memcmp (mb.buf, "\243\307", 2) == 0);
 251         #endif
 252         }
 253         return test_exit_status;
 254
 255       case '3':
 256         /* Locale encoding is UTF-8.  */
 257         {
 258           /* U+00B2 SUPERSCRIPT TWO */
 259           mb = for_character ("\302\262", 2);
 260           ASSERT (mb.nbytes == 2);
 261           ASSERT (memcmp (mb.buf, "\302\262", 2) == 0);
 262         #if !(defined __GLIBC__ || defined MUSL_LIBC || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined _AIX || defined __sun || defined __CYGWIN__)
 263           /* U+00B5 MICRO SIGN */
 264           mb = for_character ("\302\265", 2);
 265           ASSERT (mb.nbytes == 2);
 266           ASSERT (memcmp (mb.buf, "\302\265", 2) == 0);
 267         #endif
 268           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 269           mb = for_character ("\303\211", 2);
 270           ASSERT (mb.nbytes == 2);
 271           ASSERT (memcmp (mb.buf, "\303\211", 2) == 0);
 272         #if !defined MUSL_LIBC
 273           /* U+00DF LATIN SMALL LETTER SHARP S */
 274           mb = for_character ("\303\237", 2);
 275           ASSERT (mb.nbytes == 2);
 276           ASSERT (memcmp (mb.buf, "\303\237", 2) == 0);
 277         #endif
 278         #if !(defined _WIN32 && !defined __CYGWIN__)
 279           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 280           mb = for_character ("\303\251", 2);
 281           ASSERT (mb.nbytes == 2);
 282           ASSERT (memcmp (mb.buf, "\303\211", 2) == 0);
 283           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 284           mb = for_character ("\303\277", 2);
 285           ASSERT (mb.nbytes == 2);
 286           ASSERT (memcmp (mb.buf, "\305\270", 2) == 0);
 287         #endif
 288           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 289           mb = for_character ("\305\201", 2);
 290           ASSERT (mb.nbytes == 2);
 291           ASSERT (memcmp (mb.buf, "\305\201", 2) == 0);
 292           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 293           mb = for_character ("\305\202", 2);
 294           ASSERT (mb.nbytes == 2);
 295           ASSERT (memcmp (mb.buf, "\305\201", 2) == 0);
 296           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 297           mb = for_character ("\320\251", 2);
 298           ASSERT (mb.nbytes == 2);
 299           ASSERT (memcmp (mb.buf, "\320\251", 2) == 0);
 300           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 301           mb = for_character ("\321\211", 2);
 302           ASSERT (mb.nbytes == 2);
 303           ASSERT (memcmp (mb.buf, "\320\251", 2) == 0);
 304           /* U+05D5 HEBREW LETTER VAV */
 305           mb = for_character ("\327\225", 2);
 306           ASSERT (mb.nbytes == 2);
 307           ASSERT (memcmp (mb.buf, "\327\225", 2) == 0);
 308           /* U+3073 HIRAGANA LETTER BI */
 309           mb = for_character ("\343\201\263", 3);
 310           ASSERT (mb.nbytes == 3);
 311           ASSERT (memcmp (mb.buf, "\343\201\263", 3) == 0);
 312           /* U+3162 HANGUL LETTER YI */
 313           mb = for_character ("\343\205\242", 3);
 314           ASSERT (mb.nbytes == 3);
 315           ASSERT (memcmp (mb.buf, "\343\205\242", 3) == 0);
 316           /* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
 317           mb = for_character ("\357\274\247", 3);
 318           ASSERT (mb.nbytes == 3);
 319           ASSERT (memcmp (mb.buf, "\357\274\247", 3) == 0);
 320           /* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
 321           mb = for_character ("\357\275\207", 3);
 322           ASSERT (mb.nbytes == 3);
 323           ASSERT (memcmp (mb.buf, "\357\274\247", 3) == 0);
 324           /* U+FFDB HALFWIDTH HANGUL LETTER YI */
 325           mb = for_character ("\357\277\233", 3);
 326           ASSERT (mb.nbytes == 3);
 327           ASSERT (memcmp (mb.buf, "\357\277\233", 3) == 0);
 328           /* U+10419 DESERET CAPITAL LETTER EF */
 329           mb = for_character ("\360\220\220\231", 4);
 330           ASSERT (mb.nbytes == 4);
 331           ASSERT (memcmp (mb.buf, "\360\220\220\231", 4) == 0);
 332         #if !(defined __DragonFly__ || defined __sun)
 333           /* U+10441 DESERET SMALL LETTER EF */
 334           mb = for_character ("\360\220\221\201", 4);
 335           ASSERT (mb.nbytes == 4);
 336           ASSERT (memcmp (mb.buf, "\360\220\220\231", 4) == 0);
 337         #endif
 338           /* U+E0041 TAG LATIN CAPITAL LETTER A */
 339           mb = for_character ("\363\240\201\201", 4);
 340           ASSERT (mb.nbytes == 4);
 341           ASSERT (memcmp (mb.buf, "\363\240\201\201", 4) == 0);
 342           /* U+E0061 TAG LATIN SMALL LETTER A */
 343           mb = for_character ("\363\240\201\241", 4);
 344           ASSERT (mb.nbytes == 4);
 345           ASSERT (memcmp (mb.buf, "\363\240\201\241", 4) == 0);
 346         }
 347         return test_exit_status;
 348
 349       case '4':
 350         /* Locale encoding is GB18030.  */
 351         #if (defined __GLIBC__ && __GLIBC__ == 2 && __GLIBC_MINOR__ >= 13 && __GLIBC_MINOR__ <= 15) || (GL_CHAR32_T_IS_UNICODE && (defined __FreeBSD__ || defined __NetBSD__ || defined __sun))
 352         if (test_exit_status != EXIT_SUCCESS)
 353           return test_exit_status;
 354         fputs ("Skipping test: The GB18030 converter in this system's iconv is broken.\n", stderr);
 355         return 77;
 356         #endif
 357         {
 358           /* U+00B2 SUPERSCRIPT TWO */
 359           mb = for_character ("\201\060\205\065", 4);
 360           ASSERT (mb.nbytes == 4);
 361           ASSERT (memcmp (mb.buf, "\201\060\205\065", 4) == 0);
 362         #if !(defined __GLIBC__ || defined __FreeBSD__ || (defined __APPLE__ && defined __MACH__) || defined __NetBSD__ || defined __CYGWIN__)
 363           /* U+00B5 MICRO SIGN */
 364           mb = for_character ("\201\060\205\070", 4);
 365           ASSERT (mb.nbytes == 4);
 366           ASSERT (memcmp (mb.buf, "\201\060\205\070", 4) == 0);
 367         #endif
 368           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 369           mb = for_character ("\201\060\207\067", 4);
 370           ASSERT (mb.nbytes == 4);
 371           ASSERT (memcmp (mb.buf, "\201\060\207\067", 4) == 0);
 372           /* U+00DF LATIN SMALL LETTER SHARP S */
 373           mb = for_character ("\201\060\211\070", 4);
 374           ASSERT (mb.nbytes == 4);
 375           ASSERT (memcmp (mb.buf, "\201\060\211\070", 4) == 0);
 376         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 377           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 378           mb = for_character ("\250\246", 2);
 379           ASSERT (mb.nbytes == 4);
 380           ASSERT (memcmp (mb.buf, "\201\060\207\067", 4) == 0);
 381           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 382           mb = for_character ("\201\060\213\067", 4);
 383           ASSERT (mb.nbytes == 4);
 384           ASSERT (memcmp (mb.buf, "\201\060\227\060", 4) == 0);
 385         #endif
 386           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 387           mb = for_character ("\201\060\221\071", 4);
 388           ASSERT (mb.nbytes == 4);
 389           ASSERT (memcmp (mb.buf, "\201\060\221\071", 4) == 0);
 390         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 391           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 392           mb = for_character ("\201\060\222\060", 4);
 393           ASSERT (mb.nbytes == 4);
 394           ASSERT (memcmp (mb.buf, "\201\060\221\071", 4) == 0);
 395         #endif
 396           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 397           mb = for_character ("\247\273", 2);
 398           ASSERT (mb.nbytes == 2);
 399           ASSERT (memcmp (mb.buf, "\247\273", 2) == 0);
 400         #if !(defined __FreeBSD__ || defined __DragonFly__)
 401           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 402           mb = for_character ("\247\353", 2);
 403           ASSERT (mb.nbytes == 2);
 404           ASSERT (memcmp (mb.buf, "\247\273", 2) == 0);
 405         #endif
 406           /* U+05D5 HEBREW LETTER VAV */
 407           mb = for_character ("\201\060\371\067", 4);
 408           ASSERT (mb.nbytes == 4);
 409           ASSERT (memcmp (mb.buf, "\201\060\371\067", 4) == 0);
 410           /* U+3073 HIRAGANA LETTER BI */
 411           mb = for_character ("\244\323", 2);
 412           ASSERT (mb.nbytes == 2);
 413           ASSERT (memcmp (mb.buf, "\244\323", 2) == 0);
 414           /* U+3162 HANGUL LETTER YI */
 415           mb = for_character ("\201\071\256\062", 4);
 416           ASSERT (mb.nbytes == 4);
 417           ASSERT (memcmp (mb.buf, "\201\071\256\062", 4) == 0);
 418           /* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
 419           mb = for_character ("\243\307", 2);
 420           ASSERT (mb.nbytes == 2);
 421           ASSERT (memcmp (mb.buf, "\243\307", 2) == 0);
 422         #if !defined __DragonFly__
 423           /* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
 424           mb = for_character ("\243\347", 2);
 425           ASSERT (mb.nbytes == 2);
 426           ASSERT (memcmp (mb.buf, "\243\307", 2) == 0);
 427         #endif
 428           /* U+FFDB HALFWIDTH HANGUL LETTER YI */
 429           mb = for_character ("\204\061\241\071", 4);
 430           ASSERT (mb.nbytes == 4);
 431           ASSERT (memcmp (mb.buf, "\204\061\241\071", 4) == 0);
 432           /* U+10419 DESERET CAPITAL LETTER EF */
 433           mb = for_character ("\220\060\351\071", 4);
 434           ASSERT (mb.nbytes == 4);
 435           ASSERT (memcmp (mb.buf, "\220\060\351\071", 4) == 0);
 436         #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
 437           /* U+10441 DESERET SMALL LETTER EF */
 438           mb = for_character ("\220\060\355\071", 4);
 439           ASSERT (mb.nbytes == 4);
 440           ASSERT (memcmp (mb.buf, "\220\060\351\071", 4) == 0);
 441         #endif
 442           /* U+E0041 TAG LATIN CAPITAL LETTER A */
 443           mb = for_character ("\323\066\234\063", 4);
 444           ASSERT (mb.nbytes == 4);
 445           ASSERT (memcmp (mb.buf, "\323\066\234\063", 4) == 0);
 446           /* U+E0061 TAG LATIN SMALL LETTER A */
 447           mb = for_character ("\323\066\237\065", 4);
 448           ASSERT (mb.nbytes == 4);
 449           ASSERT (memcmp (mb.buf, "\323\066\237\065", 4) == 0);
 450         }
 451         return test_exit_status;
 452
 453       }
 454
 455   return 1;
 456 }