posix/bug-regex34.c

   1 /* Test re_search with multi-byte characters in UTF-8.
   2    Copyright (C) 2013-2022 Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   4
   5    The GNU C Library is free software; you can redistribute it and/or
   6    modify it under the terms of the GNU Lesser General Public
   7    License as published by the Free Software Foundation; either
   8    version 2.1 of the License, or (at your option) any later version.
   9
  10    The GNU C Library is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public
  16    License along with the GNU C Library; if not, see
  17    <https://www.gnu.org/licenses/>.  */
  18
  19 #define _GNU_SOURCE 1
  20 #include <stdio.h>
  21 #include <string.h>
  22 #include <locale.h>
  23 #include <regex.h>
  24
  25 static int
  26 do_test (void)
  27 {
  28   struct re_pattern_buffer r;
  29   /* ကျွန်ုပ်x */
  30   const char *s = "\xe1\x80\x80\xe1\x80\xbb\xe1\x80\xbd\xe1\x80\x94\xe1\x80\xba\xe1\x80\xaf\xe1\x80\x95\xe1\x80\xbax";
  31
  32   if (setlocale (LC_ALL, "en_US.UTF-8") == NULL)
  33     {
  34       puts ("setlocale failed");
  35       return 1;
  36     }
  37   memset (&r, 0, sizeof (r));
  38
  39   re_compile_pattern ("[^x]x", 5, &r);
  40   /* This was triggering a buffer overflow.  */
  41   re_search (&r, s, strlen (s), 0, strlen (s), 0);
  42   return 0;
  43 }
  44
  45 #define TEST_FUNCTION do_test ()
  46 #include "../test-skeleton.c"