posix/bug-regex11.c

   1 /* Regular expression tests.
   2    Copyright (C) 2002-2023 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 #include <sys/types.h>
  20 #include <mcheck.h>
  21 #include <regex.h>
  22 #include <stdio.h>
  23 #include <stdlib.h>
  24
  25 /* Tests supposed to match.  */
  26 struct
  27 {
  28   const char *pattern;
  29   const char *string;
  30   int flags, nmatch;
  31   regmatch_t rm[5];
  32 } tests[] = {
  33   /* Test for newline handling in regex.  */
  34   { "[^~]*~", "\nx~y", 0, 2, { { 0, 3 }, { -1, -1 } } },
  35   /* Other tests.  */
  36   { "a(.*)b", "a b", REG_EXTENDED, 2, { { 0, 3 }, { 1, 2 } } },
  37   { ".*|\\([KIO]\\)\\([^|]*\\).*|?[KIO]", "10~.~|P|K0|I10|O16|?KSb", 0, 3,
  38     { { 0, 21 }, { 15, 16 }, { 16, 18 } } },
  39   { ".*|\\([KIO]\\)\\([^|]*\\).*|?\\1", "10~.~|P|K0|I10|O16|?KSb", 0, 3,
  40     { { 0, 21 }, { 8, 9 }, { 9, 10 } } },
  41   { "^\\(a*\\)\\1\\{9\\}\\(a\\{0,9\\}\\)\\([0-9]*;.*[^a]\\2\\([0-9]\\)\\)",
  42     "a1;;0a1aa2aaa3aaaa4aaaaa5aaaaaa6aaaaaaa7aaaaaaaa8aaaaaaaaa9aa2aa1a0", 0,
  43     5, { { 0, 67 }, { 0, 0 }, { 0, 1 }, { 1, 67 }, { 66, 67 } } },
  44   /* Test for BRE expression anchoring.  POSIX says just that this may match;
  45      in glibc regex it always matched, so avoid changing it.  */
  46   { "\\(^\\|foo\\)bar", "bar", 0, 2, { { 0, 3 }, { -1, -1 } } },
  47   { "\\(foo\\|^\\)bar", "bar", 0, 2, { { 0, 3 }, { -1, -1 } } },
  48   /* In ERE this must be treated as an anchor.  */
  49   { "(^|foo)bar", "bar", REG_EXTENDED, 2, { { 0, 3 }, { -1, -1 } } },
  50   { "(foo|^)bar", "bar", REG_EXTENDED, 2, { { 0, 3 }, { -1, -1 } } },
  51   /* Here ^ cannot be treated as an anchor according to POSIX.  */
  52   { "(^|foo)bar", "(^|foo)bar", 0, 2, { { 0, 10 }, { -1, -1 } } },
  53   { "(foo|^)bar", "(foo|^)bar", 0, 2, { { 0, 10 }, { -1, -1 } } },
  54   /* More tests on backreferences.  */
  55   { "()\\1", "x", REG_EXTENDED, 2, { { 0, 0 }, { 0, 0 } } },
  56   { "()x\\1", "x", REG_EXTENDED, 2, { { 0, 1 }, { 0, 0 } } },
  57   { "()\\1*\\1*", "", REG_EXTENDED, 2, { { 0, 0 }, { 0, 0 } } },
  58   { "([0-9]).*\\1(a*)", "7;7a6", REG_EXTENDED, 3, { { 0, 4 }, { 0, 1 }, { 3, 4 } } },
  59   { "([0-9]).*\\1(a*)", "7;7a", REG_EXTENDED, 3, { { 0, 4 }, { 0, 1 }, { 3, 4 } } },
  60   { "(b)()c\\1", "bcb", REG_EXTENDED, 3, { { 0, 3 }, { 0, 1 }, { 1, 1 } } },
  61   { "()(b)c\\2", "bcb", REG_EXTENDED, 3, { { 0, 3 }, { 0, 0 }, { 0, 1 } } },
  62   { "a(b)()c\\1", "abcb", REG_EXTENDED, 3, { { 0, 4 }, { 1, 2 }, { 2, 2 } } },
  63   { "a()(b)c\\2", "abcb", REG_EXTENDED, 3, { { 0, 4 }, { 1, 1 }, { 1, 2 } } },
  64   { "()(b)\\1c\\2", "bcb", REG_EXTENDED, 3, { { 0, 3 }, { 0, 0 }, { 0, 1 } } },
  65   { "(b())\\2\\1", "bbbb", REG_EXTENDED, 3, { { 0, 2 }, { 0, 1 }, { 1, 1 } } },
  66   { "a()(b)\\1c\\2", "abcb", REG_EXTENDED, 3, { { 0, 4 }, { 1, 1 }, { 1, 2 } } },
  67   { "a()d(b)\\1c\\2", "adbcb", REG_EXTENDED, 3, { { 0, 5 }, { 1, 1 }, { 2, 3 } } },
  68   { "a(b())\\2\\1", "abbbb", REG_EXTENDED, 3, { { 0, 3 }, { 1, 2 }, { 2, 2 } } },
  69   { "(bb())\\2\\1", "bbbb", REG_EXTENDED, 3, { { 0, 4 }, { 0, 2 }, { 2, 2 } } },
  70   { "^([^,]*),\\1,\\1$", "a,a,a", REG_EXTENDED, 2, { { 0, 5 }, { 0, 1 } } },
  71   { "^([^,]*),\\1,\\1$", "ab,ab,ab", REG_EXTENDED, 2, { { 0, 8 }, { 0, 2 } } },
  72   { "^([^,]*),\\1,\\1,\\1$", "abc,abc,abc,abc", REG_EXTENDED, 2,
  73     { { 0, 15 }, { 0, 3 } } },
  74   { "^(.?)(.?)(.?)(.?)(.?).?\\5\\4\\3\\2\\1$",
  75     "level", REG_NOSUB | REG_EXTENDED, 0, { { -1, -1 } } },
  76   { "^(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.).?\\9\\8\\7\\6\\5\\4\\3\\2\\1$|^.?$",
  77     "level", REG_NOSUB | REG_EXTENDED, 0, { { -1, -1 } } },
  78   { "^(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.).?\\9\\8\\7\\6\\5\\4\\3\\2\\1$|^.?$",
  79     "abcdedcba", REG_EXTENDED, 1, { { 0, 9 } } },
  80 #if 0
  81   /* XXX Not used since they fail so far.  */
  82   { "^(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.).?\\9\\8\\7\\6\\5\\4\\3\\2\\1$|^.?$",
  83     "ababababa", REG_EXTENDED, 1, { { 0, 9 } } },
  84   { "^(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?).?\\9\\8\\7\\6\\5\\4\\3\\2\\1$",
  85     "level", REG_NOSUB | REG_EXTENDED, 0, { { -1, -1 } } },
  86   { "^(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?)(.?).?\\9\\8\\7\\6\\5\\4\\3\\2\\1$",
  87     "ababababa", REG_EXTENDED, 1, { { 0, 9 } } },
  88 #endif
  89 };
  90
  91 int
  92 main (void)
  93 {
  94   regex_t re;
  95   regmatch_t rm[5];
  96   size_t i;
  97   int n, ret = 0;
  98
  99   mtrace ();
 100
 101   for (i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i)
 102     {
 103       n = regcomp (&re, tests[i].pattern, tests[i].flags);
 104       if (n != 0)
 105         {
 106           char buf[500];
 107           regerror (n, &re, buf, sizeof (buf));
 108           printf ("%s: regcomp %zd failed: %s\n", tests[i].pattern, i, buf);
 109           ret = 1;
 110           continue;
 111         }
 112
 113       if (regexec (&re, tests[i].string, tests[i].nmatch, rm, 0))
 114         {
 115           printf ("%s: regexec %zd failed\n", tests[i].pattern, i);
 116           ret = 1;
 117           regfree (&re);
 118           continue;
 119         }
 120
 121       for (n = 0; n < tests[i].nmatch; ++n)
 122         if (rm[n].rm_so != tests[i].rm[n].rm_so
 123               || rm[n].rm_eo != tests[i].rm[n].rm_eo)
 124           {
 125             if (tests[i].rm[n].rm_so == -1 && tests[i].rm[n].rm_eo == -1)
 126               break;
 127             printf ("%s: regexec %zd match failure rm[%d] %d..%d\n",
 128                     tests[i].pattern, i, n, rm[n].rm_so, rm[n].rm_eo);
 129             ret = 1;
 130             break;
 131           }
 132
 133       regfree (&re);
 134     }
 135
 136   return ret;
 137 }