posix/bug-regex18.c

   1 /* Turkish regular expression tests.
   2    Copyright (C) 2002-2017 Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   4    Contributed by Jakub Jelinek <jakub@redhat.com>, 2002.
   5
   6    The GNU C 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    The GNU C 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 the GNU C Library; if not, see
  18    <http://www.gnu.org/licenses/>.  */
  19
  20 #include <sys/types.h>
  21 #include <mcheck.h>
  22 #include <regex.h>
  23 #include <stdio.h>
  24 #include <stdlib.h>
  25 #include <locale.h>
  26
  27 /* Tests supposed to match.  */
  28 struct
  29 {
  30   const char *pattern;
  31   const char *string;
  32   int flags, nmatch;
  33   regmatch_t rm[5];
  34 } tests[] = {
  35   /* \xc4\xb0           LATIN CAPITAL LETTER I WITH DOT ABOVE
  36      \xc4\xb1           LATIN SMALL LETTER DOTLESS I
  37      \xe2\x80\x94       EM DASH  */
  38   { "\xc4\xb0I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2,
  39     { { 2, 8 }, { -1, -1 } } },
  40   { "[\xc4\xb0x]I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2,
  41     { { 2, 8 }, { -1, -1 } } },
  42   { "[^x]I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2,
  43     { { 2, 8 }, { -1, -1 } } },
  44   { "([[:alpha:]]i[[:xdigit:]])(\xc4\xb1*)(\xc4\xb0{2})",
  45     "\xe2\x80\x94\xc4\xb1\xc4\xb0""fIi\xc4\xb0ii", REG_ICASE | REG_EXTENDED,
  46     4, { { 3, 12 }, { 3, 8 }, { 8, 9 }, { 9, 12 } } },
  47   { "\xc4\xb1i(i)*()(\\s\xc4\xb0|\\SI)", "SIi\xc4\xb0\xc4\xb0 is",
  48     REG_ICASE | REG_EXTENDED, 4, { { 1, 9 }, { 5, 7 }, { 7, 7 }, { 7, 9 } } },
  49   { "\xc4\xb1i(i)*()(\\s\xc4\xb0|\\SI)", "\xc4\xb1\xc4\xb0\xc4\xb0iJ\xc4\xb1",
  50     REG_ICASE | REG_EXTENDED, 4,
  51     { { 0, 10 }, { 6, 7 }, { 7, 7 }, { 7, 10 } } },
  52 };
  53
  54 int
  55 main (void)
  56 {
  57   regex_t re;
  58   regmatch_t rm[5];
  59   size_t i;
  60   int n, ret = 0;
  61
  62   setlocale (LC_ALL, "tr_TR.UTF-8");
  63   for (i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i)
  64     {
  65       n = regcomp (&re, tests[i].pattern, tests[i].flags);
  66       if (n != 0)
  67         {
  68           char buf[500];
  69           regerror (n, &re, buf, sizeof (buf));
  70           printf ("regcomp %zd failed: %s\n", i, buf);
  71           ret = 1;
  72           continue;
  73         }
  74
  75       if (regexec (&re, tests[i].string, tests[i].nmatch, rm, 0))
  76         {
  77           printf ("regexec %zd failed\n", i);
  78           ret = 1;
  79           regfree (&re);
  80           continue;
  81         }
  82
  83       for (n = 0; n < tests[i].nmatch; ++n)
  84         if (rm[n].rm_so != tests[i].rm[n].rm_so
  85               || rm[n].rm_eo != tests[i].rm[n].rm_eo)
  86           {
  87             if (tests[i].rm[n].rm_so == -1 && tests[i].rm[n].rm_eo == -1)
  88               break;
  89             printf ("regexec match failure rm[%d] %d..%d\n",
  90                     n, rm[n].rm_so, rm[n].rm_eo);
  91             ret = 1;
  92             break;
  93           }
  94
  95       regfree (&re);
  96     }
  97
  98   return ret;
  99 }