tests/test-c32isblank.c

   1 /* Test of c32isblank() 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 (c32isblank, 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 c32isblank 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 c32isblank (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 = c32isblank (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 blank characters include the <space> and <tab>
  66          characters,
  67        - in the "POSIX" locale (which is usually the same as the "C" locale),
  68          the blank characters include only the ASCII <space> and <tab>
  69          characters.  */
  70   {
  71     int c;
  72
  73     for (c = 0; c < 0x100; c++)
  74       switch (c)
  75         {
  76         case '\t':
  77         #if !defined __NetBSD__
  78         case '\v':
  79         #endif
  80         case '\f':
  81         case ' ': case '!': case '"': case '#': case '%':
  82         case '&': case '\'': case '(': case ')': case '*':
  83         case '+': case ',': case '-': case '.': case '/':
  84         case '0': case '1': case '2': case '3': case '4':
  85         case '5': case '6': case '7': case '8': case '9':
  86         case ':': case ';': case '<': case '=': case '>':
  87         case '?':
  88         case 'A': case 'B': case 'C': case 'D': case 'E':
  89         case 'F': case 'G': case 'H': case 'I': case 'J':
  90         case 'K': case 'L': case 'M': case 'N': case 'O':
  91         case 'P': case 'Q': case 'R': case 'S': case 'T':
  92         case 'U': case 'V': case 'W': case 'X': case 'Y':
  93         case 'Z':
  94         case '[': case '\\': case ']': case '^': case '_':
  95         case 'a': case 'b': case 'c': case 'd': case 'e':
  96         case 'f': case 'g': case 'h': case 'i': case 'j':
  97         case 'k': case 'l': case 'm': case 'n': case 'o':
  98         case 'p': case 'q': case 'r': case 's': case 't':
  99         case 'u': case 'v': case 'w': case 'x': case 'y':
 100         case 'z': case '{': case '|': case '}': case '~':
 101           /* c is in the ISO C "basic character set".  */
 102           buf[0] = (unsigned char) c;
 103           is = for_character (buf, 1);
 104           if (c == '\t' || c == ' ')
 105             ASSERT (is != 0);
 106           else
 107             ASSERT (is == 0);
 108           break;
 109         }
 110   }
 111
 112   if (argc > 1)
 113     switch (argv[1][0])
 114       {
 115       case '0':
 116         /* C locale; tested above.  */
 117         return 0;
 118
 119       case '1':
 120         /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
 121         {
 122         #if defined __GLIBC__
 123           /* U+00A0 NO-BREAK SPACE */
 124           is = for_character ("\240", 1);
 125           ASSERT (is == 0);
 126         #endif
 127           /* U+00B7 MIDDLE DOT */
 128           is = for_character ("\267", 1);
 129           ASSERT (is == 0);
 130         }
 131         return 0;
 132
 133       case '2':
 134         /* Locale encoding is EUC-JP.  */
 135         {
 136           /* U+3002 IDEOGRAPHIC FULL STOP */
 137           is = for_character ("\241\243", 2);
 138           ASSERT (is == 0);
 139         }
 140         return 0;
 141
 142       case '3':
 143         /* Locale encoding is UTF-8.  */
 144         {
 145         #if defined __GLIBC__
 146           /* U+00A0 NO-BREAK SPACE */
 147           is = for_character ("\302\240", 2);
 148           ASSERT (is == 0);
 149         #endif
 150           /* U+00B7 MIDDLE DOT */
 151           is = for_character ("\302\267", 2);
 152           ASSERT (is == 0);
 153         #if defined __GLIBC__
 154           /* U+202F NARROW NO-BREAK SPACE */
 155           is = for_character ("\342\200\257", 3);
 156           ASSERT (is == 0);
 157         #endif
 158           /* U+3002 IDEOGRAPHIC FULL STOP */
 159           is = for_character ("\343\200\202", 3);
 160           ASSERT (is == 0);
 161           /* U+1D13D MUSICAL SYMBOL QUARTER REST */
 162           is = for_character ("\360\235\204\275", 4);
 163           ASSERT (is == 0);
 164           /* U+E0020 TAG SPACE */
 165           is = for_character ("\363\240\200\240", 4);
 166           ASSERT (is == 0);
 167         }
 168         return 0;
 169
 170       case '4':
 171         /* Locale encoding is GB18030.  */
 172         {
 173         #if defined __GLIBC__
 174           /* U+00A0 NO-BREAK SPACE */
 175           is = for_character ("\201\060\204\062", 4);
 176           ASSERT (is == 0);
 177         #endif
 178           /* U+00B7 MIDDLE DOT */
 179           is = for_character ("\241\244", 2);
 180           ASSERT (is == 0);
 181         #if defined __GLIBC__
 182           /* U+202F NARROW NO-BREAK SPACE */
 183           is = for_character ("\201\066\247\062", 4);
 184           ASSERT (is == 0);
 185         #endif
 186           /* U+3002 IDEOGRAPHIC FULL STOP */
 187           is = for_character ("\241\243", 2);
 188           ASSERT (is == 0);
 189           /* U+1D13D MUSICAL SYMBOL QUARTER REST */
 190           is = for_character ("\224\062\301\065", 4);
 191           ASSERT (is == 0);
 192           /* U+E0020 TAG SPACE */
 193           is = for_character ("\323\066\231\060", 4);
 194           ASSERT (is == 0);
 195         }
 196         return 0;
 197
 198       }
 199
 200   return 1;
 201 }