tests/test-c32isupper.c

   1 /* Test of c32isupper() 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 (c32isupper, 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 c32isupper 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 c32isupper (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 = c32isupper (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 uppercase characters include the A ... Z
  66          characters,
  67        - in the "POSIX" locale (which is usually the same as the "C" locale),
  68          the uppercase 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           /* U+00B5 MICRO SIGN */
 132           is = for_character ("\265", 1);
 133           ASSERT (is == 0);
 134           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 135           is = for_character ("\311", 1);
 136           ASSERT (is != 0);
 137         #if !defined __hpux
 138           /* U+00DF LATIN SMALL LETTER SHARP S */
 139           is = for_character ("\337", 1);
 140           ASSERT (is == 0);
 141         #endif
 142           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 143           is = for_character ("\351", 1);
 144           ASSERT (is == 0);
 145           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 146           is = for_character ("\377", 1);
 147           ASSERT (is == 0);
 148         }
 149         return 0;
 150
 151       case '2':
 152         /* Locale encoding is EUC-JP.  */
 153         {
 154         #if !((defined __APPLE__ && defined __MACH__) || defined __NetBSD__)
 155           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 156           is = for_character ("\217\252\261", 3);
 157           ASSERT (is != 0);
 158         #endif
 159           /* U+00DF LATIN SMALL LETTER SHARP S */
 160           is = for_character ("\217\251\316", 3);
 161           ASSERT (is == 0);
 162           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 163           is = for_character ("\217\253\261", 3);
 164           ASSERT (is == 0);
 165           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 166           is = for_character ("\217\253\363", 3);
 167           ASSERT (is == 0);
 168         #if !((defined __APPLE__ && defined __MACH__) || defined __NetBSD__)
 169           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 170           is = for_character ("\217\251\250", 3);
 171           ASSERT (is != 0);
 172         #endif
 173           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 174           is = for_character ("\217\251\310", 3);
 175           ASSERT (is == 0);
 176         #if !(defined __FreeBSD__ || defined __DragonFly__)
 177           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 178           is = for_character ("\247\273", 2);
 179           ASSERT (is != 0);
 180         #endif
 181           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 182           is = for_character ("\247\353", 2);
 183           ASSERT (is == 0);
 184           /* U+3073 HIRAGANA LETTER BI */
 185           is = for_character ("\244\323", 2);
 186           ASSERT (is == 0);
 187           /* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
 188           is = for_character ("\243\307", 2);
 189           ASSERT (is != 0);
 190         }
 191         return 0;
 192
 193       case '3':
 194         /* Locale encoding is UTF-8.  */
 195         {
 196           /* U+00B2 SUPERSCRIPT TWO */
 197           is = for_character ("\302\262", 2);
 198           ASSERT (is == 0);
 199           /* U+00B5 MICRO SIGN */
 200           is = for_character ("\302\265", 2);
 201           ASSERT (is == 0);
 202           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 203           is = for_character ("\303\211", 2);
 204           ASSERT (is != 0);
 205           /* U+00DF LATIN SMALL LETTER SHARP S */
 206           is = for_character ("\303\237", 2);
 207           ASSERT (is == 0);
 208           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 209           is = for_character ("\303\251", 2);
 210           ASSERT (is == 0);
 211           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 212           is = for_character ("\303\277", 2);
 213           ASSERT (is == 0);
 214           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 215           is = for_character ("\305\201", 2);
 216           ASSERT (is != 0);
 217           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 218           is = for_character ("\305\202", 2);
 219           ASSERT (is == 0);
 220           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 221           is = for_character ("\320\251", 2);
 222           ASSERT (is != 0);
 223           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 224           is = for_character ("\321\211", 2);
 225           ASSERT (is == 0);
 226           /* U+05D5 HEBREW LETTER VAV */
 227           is = for_character ("\327\225", 2);
 228           ASSERT (is == 0);
 229           /* U+3073 HIRAGANA LETTER BI */
 230           is = for_character ("\343\201\263", 3);
 231           ASSERT (is == 0);
 232           /* U+3162 HANGUL LETTER YI */
 233           is = for_character ("\343\205\242", 3);
 234           ASSERT (is == 0);
 235           /* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
 236           is = for_character ("\357\274\247", 3);
 237           ASSERT (is != 0);
 238           /* U+FFDB HALFWIDTH HANGUL LETTER YI */
 239           is = for_character ("\357\277\233", 3);
 240           ASSERT (is == 0);
 241         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 242           /* U+10419 DESERET CAPITAL LETTER EF */
 243           is = for_character ("\360\220\220\231", 4);
 244           ASSERT (is != 0);
 245         #endif
 246           /* U+10441 DESERET SMALL LETTER EF */
 247           is = for_character ("\360\220\221\201", 4);
 248           ASSERT (is == 0);
 249           /* U+E0041 TAG LATIN CAPITAL LETTER A */
 250           is = for_character ("\363\240\201\201", 4);
 251           ASSERT (is == 0);
 252           /* U+E0061 TAG LATIN SMALL LETTER A */
 253           is = for_character ("\363\240\201\241", 4);
 254           ASSERT (is == 0);
 255         }
 256         return 0;
 257
 258       case '4':
 259         /* Locale encoding is GB18030.  */
 260         {
 261           /* U+00B2 SUPERSCRIPT TWO */
 262           is = for_character ("\201\060\205\065", 4);
 263           ASSERT (is == 0);
 264           /* U+00B5 MICRO SIGN */
 265           is = for_character ("\201\060\205\070", 4);
 266           ASSERT (is == 0);
 267         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 268           /* U+00C9 LATIN CAPITAL LETTER E WITH ACUTE */
 269           is = for_character ("\201\060\207\067", 4);
 270           ASSERT (is != 0);
 271         #endif
 272           /* U+00DF LATIN SMALL LETTER SHARP S */
 273           is = for_character ("\201\060\211\070", 4);
 274           ASSERT (is == 0);
 275           /* U+00E9 LATIN SMALL LETTER E WITH ACUTE */
 276           is = for_character ("\250\246", 2);
 277           ASSERT (is == 0);
 278           /* U+00FF LATIN SMALL LETTER Y WITH DIAERESIS */
 279           is = for_character ("\201\060\213\067", 4);
 280           ASSERT (is == 0);
 281         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 282           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 283           is = for_character ("\201\060\221\071", 4);
 284           ASSERT (is != 0);
 285         #endif
 286           /* U+0142 LATIN SMALL LETTER L WITH STROKE */
 287           is = for_character ("\201\060\222\060", 4);
 288           ASSERT (is == 0);
 289         #if !(defined __FreeBSD__ || defined __DragonFly__)
 290           /* U+0429 CYRILLIC CAPITAL LETTER SHCHA */
 291           is = for_character ("\247\273", 2);
 292           ASSERT (is != 0);
 293         #endif
 294           /* U+0449 CYRILLIC SMALL LETTER SHCHA */
 295           is = for_character ("\247\353", 2);
 296           ASSERT (is == 0);
 297           /* U+05D5 HEBREW LETTER VAV */
 298           is = for_character ("\201\060\371\067", 4);
 299           ASSERT (is == 0);
 300           /* U+3073 HIRAGANA LETTER BI */
 301           is = for_character ("\244\323", 2);
 302           ASSERT (is == 0);
 303           /* U+3162 HANGUL LETTER YI */
 304           is = for_character ("\201\071\256\062", 4);
 305           ASSERT (is == 0);
 306           /* U+FF27 FULLWIDTH LATIN CAPITAL LETTER G */
 307           is = for_character ("\243\307", 2);
 308           ASSERT (is != 0);
 309           /* U+FFDB HALFWIDTH HANGUL LETTER YI */
 310           is = for_character ("\204\061\241\071", 4);
 311           ASSERT (is == 0);
 312         #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
 313           /* U+10419 DESERET CAPITAL LETTER EF */
 314           is = for_character ("\220\060\351\071", 4);
 315           ASSERT (is != 0);
 316         #endif
 317           /* U+10441 DESERET SMALL LETTER EF */
 318           is = for_character ("\220\060\355\071", 4);
 319           ASSERT (is == 0);
 320           /* U+E0041 TAG LATIN CAPITAL LETTER A */
 321           is = for_character ("\323\066\234\063", 4);
 322           ASSERT (is == 0);
 323           /* U+E0061 TAG LATIN SMALL LETTER A */
 324           is = for_character ("\323\066\237\065", 4);
 325           ASSERT (is == 0);
 326         }
 327         return 0;
 328
 329       }
 330
 331   return 1;
 332 }