2003-11-14 04:52:55 +08:00
|
|
|
/* Regular expression tests.
|
2004-12-23 04:10:10 +08:00
|
|
|
Copyright (C) 2003 Free Software Foundation, Inc.
|
2003-11-14 04:52:55 +08:00
|
|
|
This file is part of the GNU C Library.
|
|
|
|
Contributed by Jakub Jelinek <jakub@redhat.com>, 2003.
|
|
|
|
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
|
|
modify it under the terms of the GNU Lesser General Public
|
|
|
|
License as published by the Free Software Foundation; either
|
|
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
|
|
Lesser General Public License for more details.
|
|
|
|
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
|
|
License along with the GNU C Library; if not, write to the Free
|
|
|
|
Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
|
|
|
|
02111-1307 USA. */
|
|
|
|
|
|
|
|
#include <sys/types.h>
|
|
|
|
#include <mcheck.h>
|
|
|
|
#include <regex.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <string.h>
|
|
|
|
#include <locale.h>
|
|
|
|
#include <getopt.h>
|
|
|
|
|
|
|
|
static void
|
|
|
|
replace_special_chars (char *str)
|
|
|
|
{
|
|
|
|
for (; (str = strpbrk (str, "NTSZ")) != NULL; ++str)
|
|
|
|
switch (*str)
|
|
|
|
{
|
|
|
|
case 'N': *str = '\n'; break;
|
|
|
|
case 'T': *str = '\t'; break;
|
|
|
|
case 'S': *str = ' '; break;
|
|
|
|
case 'Z': *str = '\0'; break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
|
|
|
glibc_re_syntax (char *str)
|
|
|
|
{
|
|
|
|
char *p, *end = strchr (str, '\0') + 1;
|
|
|
|
|
|
|
|
/* Replace [[:<:]] with \< and [[:>:]] with \>. */
|
|
|
|
for (p = str; (p = strstr (p, "[[:")) != NULL; )
|
|
|
|
if ((p[3] == '<' || p[3] == '>') && strncmp (p + 4, ":]]", 3) == 0)
|
|
|
|
{
|
|
|
|
p[0] = '\\';
|
|
|
|
p[1] = p[3];
|
|
|
|
memmove (p + 2, p + 7, end - p - 7);
|
|
|
|
end -= 5;
|
|
|
|
p += 2;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
p += 3;
|
|
|
|
}
|
|
|
|
|
|
|
|
static char *
|
|
|
|
mb_replace (char *dst, const char c)
|
|
|
|
{
|
|
|
|
switch (c)
|
|
|
|
{
|
|
|
|
/* Replace a with \'a and A with \'A. */
|
|
|
|
case 'a':
|
|
|
|
*dst++ = '\xc3';
|
|
|
|
*dst++ = '\xa1';
|
|
|
|
break;
|
|
|
|
case 'A':
|
|
|
|
*dst++ = '\xc3';
|
|
|
|
*dst++ = '\x81';
|
|
|
|
break;
|
|
|
|
/* Replace b with \v{c} and B with \v{C}. */
|
|
|
|
case 'b':
|
|
|
|
*dst++ = '\xc4';
|
|
|
|
*dst++ = '\x8d';
|
|
|
|
break;
|
|
|
|
case 'B':
|
|
|
|
*dst++ = '\xc4';
|
|
|
|
*dst++ = '\x8c';
|
|
|
|
break;
|
|
|
|
/* Replace c with \v{d} and C with \v{D}. */
|
|
|
|
case 'c':
|
|
|
|
*dst++ = '\xc4';
|
|
|
|
*dst++ = '\x8f';
|
|
|
|
break;
|
|
|
|
case 'C':
|
|
|
|
*dst++ = '\xc4';
|
|
|
|
*dst++ = '\x8e';
|
|
|
|
break;
|
|
|
|
/* Replace d with \'e and D with \'E. */
|
|
|
|
case 'd':
|
|
|
|
*dst++ = '\xc3';
|
|
|
|
*dst++ = '\xa9';
|
|
|
|
break;
|
|
|
|
case 'D':
|
|
|
|
*dst++ = '\xc3';
|
|
|
|
*dst++ = '\x89';
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return dst;
|
|
|
|
}
|
|
|
|
|
|
|
|
static char *
|
|
|
|
mb_frob_string (const char *str, const char *letters)
|
|
|
|
{
|
|
|
|
char *ret, *dst;
|
|
|
|
const char *src;
|
|
|
|
|
|
|
|
if (str == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
ret = malloc (2 * strlen (str) + 1);
|
|
|
|
if (ret == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
for (src = str, dst = ret; *src; ++src)
|
|
|
|
if (strchr (letters, *src))
|
|
|
|
dst = mb_replace (dst, *src);
|
|
|
|
else
|
|
|
|
*dst++ = *src;
|
|
|
|
*dst = '\0';
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Like mb_frob_string, but don't replace anything between
|
2004-12-23 04:10:10 +08:00
|
|
|
[: and :], [. and .] or [= and =]. */
|
2003-11-14 04:52:55 +08:00
|
|
|
|
|
|
|
static char *
|
|
|
|
mb_frob_pattern (const char *str, const char *letters)
|
|
|
|
{
|
|
|
|
char *ret, *dst;
|
|
|
|
const char *src;
|
2004-12-23 04:10:10 +08:00
|
|
|
int in_class = 0;
|
2003-11-14 04:52:55 +08:00
|
|
|
|
|
|
|
if (str == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
ret = malloc (2 * strlen (str) + 1);
|
|
|
|
if (ret == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
for (src = str, dst = ret; *src; ++src)
|
2004-12-23 04:10:10 +08:00
|
|
|
if (!in_class && strchr (letters, *src))
|
2003-11-14 04:52:55 +08:00
|
|
|
dst = mb_replace (dst, *src);
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if (!in_class && *src == '[' && strchr (":.=", src[1]))
|
|
|
|
in_class = 1;
|
|
|
|
else if (in_class && *src == ']' && strchr (":.=", src[-1]))
|
|
|
|
in_class = 0;
|
|
|
|
*dst++ = *src;
|
|
|
|
}
|
|
|
|
*dst = '\0';
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
check_match (regmatch_t *rm, int idx, const char *string,
|
|
|
|
const char *match, const char *fail)
|
|
|
|
{
|
|
|
|
if (match[0] == '-' && match[1] == '\0')
|
|
|
|
{
|
|
|
|
if (rm[idx].rm_so == -1 && rm[idx].rm_eo == -1)
|
|
|
|
return 0;
|
|
|
|
printf ("%s rm[%d] unexpectedly matched\n", fail, idx);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (rm[idx].rm_so == -1 || rm[idx].rm_eo == -1)
|
|
|
|
{
|
|
|
|
printf ("%s rm[%d] unexpectedly did not match\n", fail, idx);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (match[0] == '@')
|
|
|
|
{
|
|
|
|
if (rm[idx].rm_so != rm[idx].rm_eo)
|
|
|
|
{
|
|
|
|
printf ("%s rm[%d] not empty\n", fail, idx);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2003-11-15 02:17:12 +08:00
|
|
|
if (strncmp (string + rm[idx].rm_so, match + 1, strlen (match + 1) ?: 1))
|
2003-11-14 04:52:55 +08:00
|
|
|
{
|
|
|
|
printf ("%s rm[%d] not matching %s\n", fail, idx, match);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (rm[idx].rm_eo - rm[idx].rm_so != strlen (match)
|
|
|
|
|| strncmp (string + rm[idx].rm_so, match,
|
|
|
|
rm[idx].rm_eo - rm[idx].rm_so))
|
|
|
|
{
|
|
|
|
printf ("%s rm[%d] not matching %s\n", fail, idx, match);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
test (const char *pattern, int cflags, const char *string, int eflags,
|
|
|
|
char *expect, char *matches, const char *fail)
|
|
|
|
{
|
|
|
|
regex_t re;
|
|
|
|
regmatch_t rm[10];
|
|
|
|
int n, ret = 0;
|
|
|
|
|
|
|
|
n = regcomp (&re, pattern, cflags);
|
|
|
|
if (n != 0)
|
|
|
|
{
|
Update.
2003-12-22 Jakub Jelinek <jakub@redhat.com>
* posix/regcomp.c: Remove C99-ism.
* posix/tst-rxspencer.c: Likewise.
Based on a patch by Alex Davis <alex14641@yahoo.com>.
2002-12-17 Paolo Bonzini <bonzini@gnu.org>
* posix/regex_internal.h [!_LIBC] (internal_function): Define.
(re_string_allocate, re_string_construct, re_string_reconstruct,
re_string_realloc_buffers, build_wcs_buffer,
build_wcs_upper_buffer, build_upper_buffer,
re_string_translate_buffer, re_string_destruct,
re_string_elem_size_at, re_string_char_size_at,
re_string_wchar_at, re_string_context_at,
re_node_set_alloc, re_node_set_init_1
re_node_set_init_2, re_node_set_init_copy,
re_node_set_add_intersect, re_node_set_init_union,
re_node_set_merge, re_node_set_insert
re_node_set_compare, re_node_set_contains
re_node_set_remove_at, re_dfa_add_node,
re_acquire_state, re_acquire_state_context,
free_state): Add internal_function to declaration.
* posix/regexec.c (match_ctx_init, match_ctx_clean,
match_ctx_free, match_ctx_free_subtops,
match_ctx_add_entry, search_cur_bkref_entry,
match_ctx_clear_flag, match_ctx_add_subtop,
match_ctx_add_sublast, sift_ctx_init,
re_search_internal, re_search_2_stub, re_search_stub,
re_copy_regs, acquire_init_state_context,
prune_impossible_nodes, check_matching,
check_halt_node_context, check_halt_state_context
update_regs, proceed_next_node, push_fail_stack,
pop_fail_stack, set_regs, free_fail_stack_return,
sift_states_iter_mb, sift_states_backward
update_cur_sifted_state, add_epsilon_src_nodes,
sub_epsilon_src_nodes, check_dst_limits,
check_dst_limits_calc_pos, check_subexp_limits,
sift_states_bkref, clean_state_log_if_need,
merge_state_array, transit_state,
check_subexp_matching_top, transit_state_sb,
transit_state_mb, transit_state_bkref,
get_subexp, get_subexp_sub, find_subexp_node,
check_arrival, check_arrival_add_next_nodes,
find_collation_sequence_value, check_arrival_expand_ecl,
check_arrival_expand_ecl_sub, expand_bkref_cache,
build_trtable, check_node_accept_bytes, extend_buffers,
group_nodes_into_DFAstates, check_node_accept): Likewise.
* posix/regex_internal.c (re_string_construct_common,
re_string_skip_chars, create_newstate_common,
register_state, create_ci_newstate, create_cd_newstate,
calc_state_hash): Likewise.
(re_string_peek_byte_case, re_fetch_byte_case): Change
declaration from ANSI to K&R.
2002-12-16 Paolo Bonzini <bonzini@gnu.org>
* posix/regexec.c (build_trtable): Don't allocate the trtable
until state->word_trtable is known. Don't hardcode UINT_BITS
iterations on each bitset item.
2003-12-23 10:29:44 +08:00
|
|
|
char buf[500];
|
2003-11-14 04:52:55 +08:00
|
|
|
if (eflags == -1)
|
|
|
|
{
|
|
|
|
static struct { reg_errcode_t code; const char *name; } codes []
|
|
|
|
#define C(x) { REG_##x, #x }
|
|
|
|
= { C(NOERROR), C(NOMATCH), C(BADPAT), C(ECOLLATE),
|
|
|
|
C(ECTYPE), C(EESCAPE), C(ESUBREG), C(EBRACK),
|
|
|
|
C(EPAREN), C(EBRACE), C(BADBR), C(ERANGE),
|
|
|
|
C(ESPACE), C(BADRPT) };
|
|
|
|
|
|
|
|
for (int i = 0; i < sizeof (codes) / sizeof (codes[0]); ++i)
|
|
|
|
if (n == codes[i].code)
|
|
|
|
{
|
|
|
|
if (strcmp (string, codes[i].name))
|
|
|
|
{
|
|
|
|
printf ("%s regcomp returned REG_%s (expected REG_%s)\n",
|
|
|
|
fail, codes[i].name, string);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
printf ("%s regcomp return value REG_%d\n", fail, n);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
regerror (n, &re, buf, sizeof (buf));
|
|
|
|
printf ("%s regcomp failed: %s\n", fail, buf);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (eflags == -1)
|
|
|
|
{
|
|
|
|
regfree (&re);
|
|
|
|
|
|
|
|
/* The test case file assumes something only guaranteed by the
|
|
|
|
rxspencer regex implementation. Namely that for empty
|
|
|
|
expressions regcomp() return REG_EMPTY. This is not the case
|
|
|
|
for us and so we ignore this error. */
|
|
|
|
if (strcmp (string, "EMPTY") == 0)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
printf ("%s regcomp unexpectedly succeeded\n", fail);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (regexec (&re, string, 10, rm, eflags))
|
|
|
|
{
|
|
|
|
regfree (&re);
|
|
|
|
if (expect == NULL)
|
|
|
|
return 0;
|
|
|
|
printf ("%s regexec failed\n", fail);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
regfree (&re);
|
|
|
|
|
|
|
|
if (expect == NULL)
|
|
|
|
{
|
|
|
|
printf ("%s regexec unexpectedly succeeded\n", fail);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (cflags & REG_NOSUB)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
ret = check_match (rm, 0, string, expect, fail);
|
|
|
|
if (matches == NULL)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
for (n = 1; ret == 0 && n < 10; ++n)
|
|
|
|
{
|
|
|
|
char *p = NULL;
|
|
|
|
|
|
|
|
if (matches)
|
|
|
|
{
|
|
|
|
p = strchr (matches, ',');
|
|
|
|
if (p != NULL)
|
|
|
|
*p = '\0';
|
|
|
|
}
|
|
|
|
ret = check_match (rm, n, string, matches ?: "-", fail);
|
|
|
|
if (p)
|
|
|
|
{
|
|
|
|
*p = ',';
|
|
|
|
matches = p + 1;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
matches = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
mb_test (const char *pattern, int cflags, const char *string, int eflags,
|
|
|
|
char *expect, const char *matches, const char *letters,
|
|
|
|
const char *fail)
|
|
|
|
{
|
|
|
|
char *pattern_mb = mb_frob_pattern (pattern, letters);
|
|
|
|
const char *string_mb
|
|
|
|
= eflags == -1 ? string : mb_frob_string (string, letters);
|
|
|
|
char *expect_mb = mb_frob_string (expect, letters);
|
|
|
|
char *matches_mb = mb_frob_string (matches, letters);
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
if (!pattern_mb || !string_mb
|
|
|
|
|| (expect && !expect_mb) || (matches && !matches_mb))
|
|
|
|
{
|
|
|
|
printf ("%s %m", fail);
|
|
|
|
ret = 1;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
ret = test (pattern_mb, cflags, string_mb, eflags, expect_mb,
|
|
|
|
matches_mb, fail);
|
|
|
|
|
|
|
|
free (matches_mb);
|
|
|
|
free (expect_mb);
|
|
|
|
if (string_mb != string)
|
|
|
|
free ((char *) string_mb);
|
|
|
|
free (pattern_mb);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
mb_tests (const char *pattern, int cflags, const char *string, int eflags,
|
|
|
|
char *expect, const char *matches)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
int i;
|
|
|
|
char letters[9], fail[20];
|
|
|
|
|
|
|
|
/* The tests aren't supposed to work with xdigit, since a-dA-D are
|
|
|
|
hex digits while \'a \'A \v{c}\v{C}\v{d}\v{D}\'e \'E are not. */
|
|
|
|
if (strstr (pattern, "[:xdigit:]"))
|
|
|
|
return 0;
|
|
|
|
|
2003-11-21 07:36:40 +08:00
|
|
|
/* XXX: regex ATM handles only single byte equivalence classes. */
|
|
|
|
if (strstr (pattern, "[[=b=]]"))
|
|
|
|
return 0;
|
|
|
|
|
2003-11-14 04:52:55 +08:00
|
|
|
for (i = 1; i < 16; ++i)
|
|
|
|
{
|
|
|
|
char *p = letters;
|
2003-11-21 17:20:45 +08:00
|
|
|
if (i & 1)
|
|
|
|
{
|
|
|
|
if (!strchr (pattern, 'a') && !strchr (string, 'a')
|
|
|
|
&& !strchr (pattern, 'A') && !strchr (string, 'A'))
|
|
|
|
continue;
|
|
|
|
*p++ = 'a', *p++ = 'A';
|
|
|
|
}
|
|
|
|
if (i & 2)
|
|
|
|
{
|
|
|
|
if (!strchr (pattern, 'b') && !strchr (string, 'b')
|
|
|
|
&& !strchr (pattern, 'B') && !strchr (string, 'B'))
|
|
|
|
continue;
|
|
|
|
*p++ = 'b', *p++ = 'B';
|
|
|
|
}
|
|
|
|
if (i & 4)
|
|
|
|
{
|
|
|
|
if (!strchr (pattern, 'c') && !strchr (string, 'c')
|
|
|
|
&& !strchr (pattern, 'C') && !strchr (string, 'C'))
|
|
|
|
continue;
|
|
|
|
*p++ = 'c', *p++ = 'C';
|
|
|
|
}
|
|
|
|
if (i & 8)
|
|
|
|
{
|
|
|
|
if (!strchr (pattern, 'd') && !strchr (string, 'd')
|
|
|
|
&& !strchr (pattern, 'D') && !strchr (string, 'D'))
|
|
|
|
continue;
|
|
|
|
*p++ = 'd', *p++ = 'D';
|
|
|
|
}
|
2003-11-14 04:52:55 +08:00
|
|
|
*p++ = '\0';
|
|
|
|
sprintf (fail, "UTF-8 %s FAIL", letters);
|
|
|
|
ret |= mb_test (pattern, cflags, string, eflags, expect, matches,
|
|
|
|
letters, fail);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int
|
|
|
|
main (int argc, char **argv)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
char *line = NULL;
|
|
|
|
size_t line_len = 0;
|
|
|
|
ssize_t len;
|
|
|
|
FILE *f;
|
|
|
|
static int test_utf8 = 0;
|
|
|
|
static const struct option options[] =
|
|
|
|
{
|
|
|
|
{"utf8", no_argument, &test_utf8, 1},
|
|
|
|
{NULL, 0, NULL, 0 }
|
|
|
|
};
|
|
|
|
|
Update.
2003-11-19 Jakub Jelinek <jakub@redhat.com>
* posix/regexec.c (extend_buffers): Don't allocate
twice as big state_log as needed. Don't modify pstr->valid_len
for mb_cur_max == 1 !icase !trans.
* posix/regcomp.c (free_bin_tree): Removed.
(create_tree): Add dfa argument. Don't call re_malloc for
each tree, instead allocate from str_tree_storage.
(re_dfa_add_tree_node): New function.
(free_dfa_content): Handle freeing if dfa->nodes == NULL
or dfa->state_table == NULL.
(re_compile_internal): Call free_dfa_content if init_dfa
fails. Call free_workarea_compile, re_string_destruct
and free_dfa_content for most of the other failure paths.
(init_dfa): Initialize str_tree_storage_idx.
Don't clear any fields on allocation failure.
(free_workarea_compile): Free str_tree_storage chunks
instead of free_bin_tree (dfa->str_tree).
(parse): Call re_dfa_add_tree_node instead of re_dfa_add_node
followed by create_tree. Add dfa argument to remaining
create_tree calls. Remove new_idx variable. Remove calls
to free_bin_tree.
(parse_reg_exp, parse_branch, parse_expression, parse_sub_exp,
parse_dup_op, parse_bracket_exp, build_charclass_op): Likewise.
(duplicate_tree): Remove calls to free_bin_tree, add dfa
argument to create_tree.
* posix/regex_internal.h (BIN_TREE_STORAGE_SIZE): Define.
(bin_tree_storage_t): New type.
(re_dfa_t): Add str_tree_storage and str_tree_storage_idx
fields.
* posix/Makefile (tests): Add bug-regex21.
(generated): Add bug-regex21-mem, bug-regex21.mtrace,
tst-rxspencer-mem and tst-rxspencer.mtrace.
(tests): Depend on $(objpfx)bug-regex21-mem
and $(objpfx)tst-rxspencer-mem.
(bug-regex21-ENV, tst-rxspencer-ENV): Set.
($(objpfx)bug-regex21-mem, $(objpfx)tst-rxspencer-mem): New.
* posix/tst-rxspencer.c (main): Add call to mtrace.
Free line at the end.
* posix/bug-regex21.c: New test.
* posix/regexec.c (get_subexp): After calling get_subexp_sub
2003-11-20 03:37:31 +08:00
|
|
|
mtrace ();
|
|
|
|
|
2003-11-14 07:39:31 +08:00
|
|
|
while (getopt_long (argc, argv, "", options, NULL) >= 0);
|
2003-11-14 04:52:55 +08:00
|
|
|
|
|
|
|
if (optind + 1 != argc)
|
|
|
|
{
|
|
|
|
fprintf (stderr, "Missing test filename\n");
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
f = fopen (argv[optind], "r");
|
|
|
|
if (f == NULL)
|
|
|
|
{
|
2003-11-15 02:17:12 +08:00
|
|
|
fprintf (stderr, "Couldn't open %s\n", argv[optind]);
|
2003-11-14 04:52:55 +08:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
while ((len = getline (&line, &line_len, f)) > 0)
|
|
|
|
{
|
|
|
|
char *pattern, *flagstr, *string, *expect, *matches, *p;
|
|
|
|
int cflags = REG_EXTENDED, eflags = 0, try_bre_ere = 0;
|
|
|
|
|
|
|
|
if (line[len - 1] == '\n')
|
|
|
|
line[len - 1] = '\0';
|
|
|
|
|
|
|
|
/* Skip comments and empty lines. */
|
|
|
|
if (*line == '#' || *line == '\0')
|
|
|
|
continue;
|
|
|
|
|
|
|
|
puts (line);
|
|
|
|
fflush (stdout);
|
|
|
|
|
|
|
|
pattern = strtok (line, "\t");
|
|
|
|
if (pattern == NULL)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (strcmp (pattern, "\"\"") == 0)
|
|
|
|
pattern += 2;
|
|
|
|
|
|
|
|
flagstr = strtok (NULL, "\t");
|
|
|
|
if (flagstr == NULL)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
string = strtok (NULL, "\t");
|
|
|
|
if (string == NULL)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (strcmp (string, "\"\"") == 0)
|
|
|
|
string += 2;
|
|
|
|
|
|
|
|
for (p = flagstr; *p; ++p)
|
|
|
|
switch (*p)
|
|
|
|
{
|
|
|
|
case '-':
|
|
|
|
break;
|
|
|
|
case 'b':
|
|
|
|
cflags &= ~REG_EXTENDED;
|
|
|
|
break;
|
|
|
|
case '&':
|
|
|
|
try_bre_ere = 1;
|
|
|
|
break;
|
|
|
|
case 'C':
|
|
|
|
eflags = -1;
|
|
|
|
break;
|
|
|
|
case 'i':
|
|
|
|
cflags |= REG_ICASE;
|
|
|
|
break;
|
|
|
|
case 's':
|
|
|
|
cflags |= REG_NOSUB;
|
|
|
|
break;
|
|
|
|
case 'n':
|
|
|
|
cflags |= REG_NEWLINE;
|
|
|
|
break;
|
|
|
|
case '^':
|
|
|
|
eflags |= REG_NOTBOL;
|
|
|
|
break;
|
|
|
|
case '$':
|
|
|
|
eflags |= REG_NOTEOL;
|
|
|
|
break;
|
|
|
|
case 'm':
|
|
|
|
case 'p':
|
|
|
|
case '#':
|
|
|
|
/* Not supported. */
|
|
|
|
flagstr = NULL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (flagstr == NULL)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
replace_special_chars (pattern);
|
|
|
|
glibc_re_syntax (pattern);
|
|
|
|
if (eflags != -1)
|
|
|
|
replace_special_chars (string);
|
|
|
|
|
|
|
|
expect = strtok (NULL, "\t");
|
|
|
|
matches = NULL;
|
|
|
|
if (expect != NULL)
|
|
|
|
{
|
|
|
|
replace_special_chars (expect);
|
|
|
|
matches = strtok (NULL, "\t");
|
|
|
|
if (matches != NULL)
|
|
|
|
replace_special_chars (matches);
|
|
|
|
}
|
|
|
|
|
2003-11-21 07:36:40 +08:00
|
|
|
if (setlocale (LC_ALL, "C") == NULL)
|
|
|
|
{
|
|
|
|
puts ("setlocale C failed");
|
|
|
|
ret = 1;
|
|
|
|
}
|
2003-11-14 04:52:55 +08:00
|
|
|
if (test (pattern, cflags, string, eflags, expect, matches, "FAIL")
|
|
|
|
|| (try_bre_ere
|
|
|
|
&& test (pattern, cflags & ~REG_EXTENDED, string, eflags,
|
|
|
|
expect, matches, "FAIL")))
|
|
|
|
ret = 1;
|
|
|
|
else if (test_utf8)
|
|
|
|
{
|
2003-11-21 07:36:40 +08:00
|
|
|
if (setlocale (LC_ALL, "cs_CZ.UTF-8") == NULL)
|
|
|
|
{
|
|
|
|
puts ("setlocale cs_CZ.UTF-8 failed");
|
|
|
|
ret = 1;
|
|
|
|
}
|
|
|
|
else if (test (pattern, cflags, string, eflags, expect, matches,
|
|
|
|
"UTF-8 FAIL")
|
|
|
|
|| (try_bre_ere
|
|
|
|
&& test (pattern, cflags & ~REG_EXTENDED, string,
|
|
|
|
eflags, expect, matches, "UTF-8 FAIL")))
|
2003-11-14 04:52:55 +08:00
|
|
|
ret = 1;
|
|
|
|
else if (mb_tests (pattern, cflags, string, eflags, expect, matches)
|
|
|
|
|| (try_bre_ere
|
|
|
|
&& mb_tests (pattern, cflags & ~REG_EXTENDED, string,
|
|
|
|
eflags, expect, matches)))
|
|
|
|
ret = 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
Update.
2003-11-19 Jakub Jelinek <jakub@redhat.com>
* posix/regexec.c (extend_buffers): Don't allocate
twice as big state_log as needed. Don't modify pstr->valid_len
for mb_cur_max == 1 !icase !trans.
* posix/regcomp.c (free_bin_tree): Removed.
(create_tree): Add dfa argument. Don't call re_malloc for
each tree, instead allocate from str_tree_storage.
(re_dfa_add_tree_node): New function.
(free_dfa_content): Handle freeing if dfa->nodes == NULL
or dfa->state_table == NULL.
(re_compile_internal): Call free_dfa_content if init_dfa
fails. Call free_workarea_compile, re_string_destruct
and free_dfa_content for most of the other failure paths.
(init_dfa): Initialize str_tree_storage_idx.
Don't clear any fields on allocation failure.
(free_workarea_compile): Free str_tree_storage chunks
instead of free_bin_tree (dfa->str_tree).
(parse): Call re_dfa_add_tree_node instead of re_dfa_add_node
followed by create_tree. Add dfa argument to remaining
create_tree calls. Remove new_idx variable. Remove calls
to free_bin_tree.
(parse_reg_exp, parse_branch, parse_expression, parse_sub_exp,
parse_dup_op, parse_bracket_exp, build_charclass_op): Likewise.
(duplicate_tree): Remove calls to free_bin_tree, add dfa
argument to create_tree.
* posix/regex_internal.h (BIN_TREE_STORAGE_SIZE): Define.
(bin_tree_storage_t): New type.
(re_dfa_t): Add str_tree_storage and str_tree_storage_idx
fields.
* posix/Makefile (tests): Add bug-regex21.
(generated): Add bug-regex21-mem, bug-regex21.mtrace,
tst-rxspencer-mem and tst-rxspencer.mtrace.
(tests): Depend on $(objpfx)bug-regex21-mem
and $(objpfx)tst-rxspencer-mem.
(bug-regex21-ENV, tst-rxspencer-ENV): Set.
($(objpfx)bug-regex21-mem, $(objpfx)tst-rxspencer-mem): New.
* posix/tst-rxspencer.c (main): Add call to mtrace.
Free line at the end.
* posix/bug-regex21.c: New test.
* posix/regexec.c (get_subexp): After calling get_subexp_sub
2003-11-20 03:37:31 +08:00
|
|
|
free (line);
|
2003-11-14 04:52:55 +08:00
|
|
|
fclose (f);
|
|
|
|
return ret;
|
|
|
|
}
|