1: /* Turkish regular expression tests.
    2:    Copyright (C) 2002, 2003 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, write to the Free
   18:    Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
   19:    02111-1307 USA.  */
   20: 
   21: #include <sys/types.h>
   22: #include <mcheck.h>
   23: #include <regex.h>
   24: #include <stdio.h>
   25: #include <stdlib.h>
   26: #include <locale.h>
   27: 
   28: /* Tests supposed to match.  */
   29: struct
   30: {
   31:   const char *pattern;
   32:   const char *string;
   33:   int flags, nmatch;
   34:   regmatch_t rm[5];
   35: } tests[] = {
   36:   /* \xc4\xb0           LATIN CAPITAL LETTER I WITH DOT ABOVE
   37:      \xc4\xb1           LATIN SMALL LETTER DOTLESS I
   38:      \xe2\x80\x94       EM DASH  */
   39:   { "\xc4\xb0I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2,
   40:     { { 2, 8 }, { -1, -1 } } },
   41:   { "[\xc4\xb0x]I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2,
   42:     { { 2, 8 }, { -1, -1 } } },
   43:   { "[^x]I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2,
   44:     { { 2, 8 }, { -1, -1 } } },
   45:   { "([[:alpha:]]i[[:xdigit:]])(\xc4\xb1*)(\xc4\xb0{2})",
   46:     "\xe2\x80\x94\xc4\xb1\xc4\xb0""fIi\xc4\xb0ii", REG_ICASE | REG_EXTENDED,
   47:     4, { { 3, 12 }, { 3, 8 }, { 8, 9 }, { 9, 12 } } },
   48:   { "\xc4\xb1i(i)*()(\\s\xc4\xb0|\\SI)", "SIi\xc4\xb0\xc4\xb0 is",
   49:     REG_ICASE | REG_EXTENDED, 4, { { 1, 9 }, { 5, 7 }, { 7, 7 }, { 7, 9 } } },
   50:   { "\xc4\xb1i(i)*()(\\s\xc4\xb0|\\SI)", "\xc4\xb1\xc4\xb0\xc4\xb0iJ\xc4\xb1",
   51:     REG_ICASE | REG_EXTENDED, 4,
   52:     { { 0, 10 }, { 6, 7 }, { 7, 7 }, { 7, 10 } } },
   53: };
   54: 
   55: int
   56: main (void)
   57: {
   58:   regex_t re;
   59:   regmatch_t rm[5];
   60:   size_t i;
   61:   int n, ret = 0;
   62: 
   63:   setlocale (LC_ALL, "tr_TR.UTF-8");
   64:   for (i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i)
   65:     {
   66:       n = regcomp (&re, tests[i].pattern, tests[i].flags);
   67:       if (n != 0)
   68:         {
   69:           char buf[500];
   70:           regerror (n, &re, buf, sizeof (buf));
   71:           printf ("regcomp %zd failed: %s\n", i, buf);
   72:           ret = 1;
   73:           continue;
   74:         }
   75: 
   76:       if (regexec (&re, tests[i].string, tests[i].nmatch, rm, 0))
   77:         {
   78:           printf ("regexec %zd failed\n", i);
   79:           ret = 1;
   80:           regfree (&re);
   81:           continue;
   82:         }
   83: 
   84:       for (n = 0; n < tests[i].nmatch; ++n)
   85:         if (rm[n].rm_so != tests[i].rm[n].rm_so
   86:               || rm[n].rm_eo != tests[i].rm[n].rm_eo)
   87:           {
   88:             if (tests[i].rm[n].rm_so == -1 && tests[i].rm[n].rm_eo == -1)
   89:               break;
   90:             printf ("regexec match failure rm[%d] %d..%d\n",
   91:                     n, rm[n].rm_so, rm[n].rm_eo);
   92:             ret = 1;
   93:             break;
   94:           }
   95: 
   96:       regfree (&re);
   97:     }
   98: 
   99:   return ret;
  100: }