tests/test-c32islower.c

   1 /* Test of c32islower() function.
   2    Copyright (C) 2020 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 (c32islower, int, (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 /* Returns the value of c32islower for the multibyte character s[0..n-1].  */
  32 static int
  33 for_character (const char *s, size_t n)
  34 {
  35   mbstate_t state;
  36   char32_t wc;
  37   size_t ret;
  38
  39   memset (&state, '\0', sizeof (mbstate_t));
  40   wc = (char32_t) 0xBADFACE;
  41   ret = mbrtoc32 (&wc, s, n, &state);
  42   ASSERT (ret == n);
  43
  44   return c32islower (wc);
  45 }
  46
  47 int
  48 main (int argc, char *argv[])
  49 {
  50   int is;
  51   char buf[4];
  52
  53   /* configure should already have checked that the locale is supported.  */
  54   if (setlocale (LC_ALL, "") == NULL)
  55     return 1;
  56
  57   /* Test WEOF.  */
  58   is = c32islower (WEOF);
  59   ASSERT (is == 0);
  60
  61   /* Test single-byte characters.
  62      POSIX specifies in
  63        <https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap07.html>
  64      that
  65        - in all locales, the lowercase characters include the a ... z
  66          characters,
  67        - in the "POSIX" locale (which is usually the same as the "C" locale),
  68          the lowercase characters include only the ASCII a ... z characters.
  69    */
  70   {
  71     int c;
  72
  73     for (c = 0; c < 0x100; c++)
  74       switch (c)
  75         {
  76         case '\t': case '\v': case '\f':
  77         case ' ': case '!': case '"': case '#': case '%':
  78         case '&': case '\'': case '(': case ')': case '*':
  79         case '+': case ',': case '-': case '.': case '/':
  80         case '0': case '1': case '2': case '3': case '4':
  81         case '5': case '6': case '7': case '8': case '9':
  82         case ':': case ';': case '<': case '=': case '>':
  83         case '?':
  84         case 'A': case 'B': case 'C': case 'D': case 'E':
  85         case 'F': case 'G': case 'H': case 'I': case 'J':
  86         case 'K': case 'L': case 'M': case 'N': case 'O':
  87         case 'P': case 'Q': case 'R': case 'S': case 'T':
  88         case 'U': case 'V': case 'W': case 'X': case 'Y':
  89         case 'Z':
  90         case '[': case '\\': case ']': case '^': case '_':
  91         case 'a': case 'b': case 'c': case 'd': case 'e':
  92         case 'f': case 'g': case 'h': case 'i': case 'j':
  93         case 'k': case 'l': case 'm': case 'n': case 'o':
  94         case 'p': case 'q': case 'r': case 's': case 't':
  95         case 'u': case 'v': case 'w': case 'x': case 'y':
  96         case 'z': case '{': case '|': case '}': case '~':
  97           /* c is in the ISO C "basic character set".  */
  98           buf[0] = (unsigned char) c;
  99           is = for_character (buf, 1);
 100           switch (c)
 101             {
 102             case 'a': case 'b': case 'c': case 'd': case 'e':
 103             case 'f': case 'g': case 'h': case 'i': case 'j':
 104             case 'k': case 'l': case 'm': case 'n': case 'o':
 105             case 'p': case 'q': case 'r': case 's': case 't':
 106             case 'u': case 'v': case 'w': case 'x': case 'y':
 107             case 'z':
 108               ASSERT (is != 0);
 109               break;
 110             default:
 111               ASSERT (is == 0);
 112               break;
 113             }
 114           break;
 115         }
 116   }
 117
 118   if (argc > 1)
 119     switch (argv[1][0])
 120       {
 121       case '0':
 122         /* C locale; tested above.  */
 123         return 0;
 124
 125       case '1':
 126         /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
 127         {
 128           /* U+00B2 SUPERSCRIPT TWO */
 129           is = for_character ("\262", 1);
 130           ASSERT (is == 0);
 131         #if !(defined __GLIBC__ || defined __sun || defined __CYGWIN__ || (defined _WIN32 && !defined __CYGWIN__))
 132           /* U+00B5 MICRO SIGN */
 133           is = for_character ("\265", 1);
 134           ASSERT (is == 0);
 135         #endif
 136           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 137           is = for_character ("\311", 1);
 138           ASSERT (is == 0);
 139         #if !defined __CYGWIN__
 140           /* U+00DF LATIN SMALL LETTER SHARP S */
 141           is = for_character ("\337", 1);
 142           ASSERT (is != 0);
 143         #endif
 144           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 145           is = for_character ("\351", 1);
 146           ASSERT (is != 0);
 147           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 148           is = for_character ("\377", 1);
 149           ASSERT (is != 0);
 150         }
 151         return 0;
 152
 153       case '2':
 154         /* Locale encoding is EUC-JP.  */
 155         {
 156           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 157           is = for_character ("\217\252\261", 3);
 158           ASSERT (is == 0);
 159         #if !((defined __APPLE__ && defined __MACH__) || defined __NetBSD__ || defined __CYGWIN__)
 160           /* U+00DF LATIN SMALL LETTER SHARP S */
 161           is = for_character ("\217\251\316", 3);
 162           ASSERT (is != 0);
 163         #endif
 164         #if !((defined __APPLE__ && defined __MACH__) || defined __NetBSD__)
 165           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 166           is = for_character ("\217\253\261", 3);
 167           ASSERT (is != 0);
 168           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 169           is = for_character ("\217\253\363", 3);
 170           ASSERT (is != 0);
 171         #endif
 172           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 173           is = for_character ("\217\251\250", 3);
 174           ASSERT (is == 0);
 175         #if !((defined __APPLE__ && defined __MACH__) || defined __NetBSD__)
 176           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 177           is = for_character ("\217\251\310", 3);
 178           ASSERT (is != 0);
 179         #endif
 180           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 181           is = for_character ("\247\273", 2);
 182           ASSERT (is == 0);
 183         #if !(defined __FreeBSD__ || defined __DragonFly__)
 184           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 185           is = for_character ("\247\353", 2);
 186           ASSERT (is != 0);
 187         #endif
 188           /* U+3073 HIRAGANA LETTER BI */
 189           is = for_character ("\244\323", 2);
 190           ASSERT (is == 0);
 191           /* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
 192           is = for_character ("\243\347", 2);
 193           ASSERT (is != 0);
 194         }
 195         return 0;
 196
 197       case '3':
 198         /* Locale encoding is UTF-8.  */
 199         {
 200           /* U+00B2 SUPERSCRIPT TWO */
 201           is = for_character ("\302\262", 2);
 202           ASSERT (is == 0);
 203         #if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined _AIX || defined __sun || defined __CYGWIN__ || (defined _WIN32 && !defined __CYGWIN__))
 204           /* U+00B5 MICRO SIGN */
 205           is = for_character ("\302\265", 2);
 206           ASSERT (is == 0);
 207         #endif
 208           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 209           is = for_character ("\303\211", 2);
 210           ASSERT (is == 0);
 211         #if !defined __CYGWIN__
 212           /* U+00DF LATIN SMALL LETTER SHARP S */
 213           is = for_character ("\303\237", 2);
 214           ASSERT (is != 0);
 215         #endif
 216           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 217           is = for_character ("\303\251", 2);
 218           ASSERT (is != 0);
 219           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 220           is = for_character ("\303\277", 2);
 221           ASSERT (is != 0);
 222           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 223           is = for_character ("\305\201", 2);
 224           ASSERT (is == 0);
 225           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 226           is = for_character ("\305\202", 2);
 227           ASSERT (is != 0);
 228           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 229           is = for_character ("\320\251", 2);
 230           ASSERT (is == 0);
 231           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 232           is = for_character ("\321\211", 2);
 233           ASSERT (is != 0);
 234           /* U+05D5 HEBREW LETTER VAV */
 235           is = for_character ("\327\225", 2);
 236           ASSERT (is == 0);
 237           /* U+3073 HIRAGANA LETTER BI */
 238           is = for_character ("\343\201\263", 3);
 239           ASSERT (is == 0);
 240           /* U+3162 HANGUL LETTER YI */
 241           is = for_character ("\343\205\242", 3);
 242           ASSERT (is == 0);
 243           /* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
 244           is = for_character ("\357\275\207", 3);
 245           ASSERT (is != 0);
 246           /* U+FFDB HALFWIDTH HANGUL LETTER YI */
 247           is = for_character ("\357\277\233", 3);
 248           ASSERT (is == 0);
 249           /* U+10419 DESERET CAPITAL LETTER EF */
 250           is = for_character ("\360\220\220\231", 4);
 251           ASSERT (is == 0);
 252         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 253           /* U+10441 DESERET SMALL LETTER EF */
 254           is = for_character ("\360\220\221\201", 4);
 255           ASSERT (is != 0);
 256         #endif
 257           /* U+E0041 TAG LATIN CAPITAL LETTER A */
 258           is = for_character ("\363\240\201\201", 4);
 259           ASSERT (is == 0);
 260           /* U+E0061 TAG LATIN SMALL LETTER A */
 261           is = for_character ("\363\240\201\241", 4);
 262           ASSERT (is == 0);
 263         }
 264         return 0;
 265
 266       case '4':
 267         /* Locale encoding is GB18030.  */
 268         {
 269           /* U+00B2 SUPERSCRIPT TWO */
 270           is = for_character ("\201\060\205\065", 4);
 271           ASSERT (is == 0);
 272         #if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __NetBSD__)
 273           /* U+00B5 MICRO SIGN */
 274           is = for_character ("\201\060\205\070", 4);
 275           ASSERT (is == 0);
 276         #endif
 277           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 278           is = for_character ("\201\060\207\067", 4);
 279           ASSERT (is == 0);
 280         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 281           /* U+00DF LATIN SMALL LETTER SHARP S */
 282           is = for_character ("\201\060\211\070", 4);
 283           ASSERT (is != 0);
 284         #endif
 285           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 286           is = for_character ("\250\246", 2);
 287           ASSERT (is != 0);
 288         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 289           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 290           is = for_character ("\201\060\213\067", 4);
 291           ASSERT (is != 0);
 292         #endif
 293           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 294           is = for_character ("\201\060\221\071", 4);
 295           ASSERT (is == 0);
 296         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 297           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 298           is = for_character ("\201\060\222\060", 4);
 299           ASSERT (is != 0);
 300         #endif
 301           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 302           is = for_character ("\247\273", 2);
 303           ASSERT (is == 0);
 304         #if !(defined __FreeBSD__ || defined __DragonFly__)
 305           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 306           is = for_character ("\247\353", 2);
 307           ASSERT (is != 0);
 308         #endif
 309           /* U+05D5 HEBREW LETTER VAV */
 310           is = for_character ("\201\060\371\067", 4);
 311           ASSERT (is == 0);
 312           /* U+3073 HIRAGANA LETTER BI */
 313           is = for_character ("\244\323", 2);
 314           ASSERT (is == 0);
 315           /* U+3162 HANGUL LETTER YI */
 316           is = for_character ("\201\071\256\062", 4);
 317           ASSERT (is == 0);
 318           /* U+FF47 FULLWIDTH LATIN SMALL LETTER G */
 319           is = for_character ("\243\347", 2);
 320           ASSERT (is != 0);
 321           /* U+FFDB HALFWIDTH HANGUL LETTER YI */
 322           is = for_character ("\204\061\241\071", 4);
 323           ASSERT (is == 0);
 324           /* U+10419 DESERET CAPITAL LETTER EF */
 325           is = for_character ("\220\060\351\071", 4);
 326           ASSERT (is == 0);
 327         #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
 328           /* U+10441 DESERET SMALL LETTER EF */
 329           is = for_character ("\220\060\355\071", 4);
 330           ASSERT (is != 0);
 331         #endif
 332           /* U+E0041 TAG LATIN CAPITAL LETTER A */
 333           is = for_character ("\323\066\234\063", 4);
 334           ASSERT (is == 0);
 335           /* U+E0061 TAG LATIN SMALL LETTER A */
 336           is = for_character ("\323\066\237\065", 4);
 337           ASSERT (is == 0);
 338         }
 339         return 0;
 340
 341       }
 342
 343   return 1;
 344 }