summaryrefslogtreecommitdiff
path: root/lib/regcomp.c
diff options
context:
space:
mode:
authorIgor Pashev <pashev.igor@gmail.com>2014-09-30 18:22:48 +0400
committerIgor Pashev <pashev.igor@gmail.com>2014-09-30 18:22:48 +0400
commitc18578632fd3c9e513e613a86ba2b7c4ebee6c45 (patch)
tree377f4d4e3f0a6471a5012126078fcd97f4c67242 /lib/regcomp.c
parent974ab3dd887985e3aa347f3c6521f819296396a0 (diff)
downloadcoreutils-c18578632fd3c9e513e613a86ba2b7c4ebee6c45.tar.gz
Imported Upstream version 8.23upstream/8.23
Diffstat (limited to 'lib/regcomp.c')
-rw-r--r--lib/regcomp.c119
1 files changed, 60 insertions, 59 deletions
diff --git a/lib/regcomp.c b/lib/regcomp.c
index 62dcbed7..a9640922 100644
--- a/lib/regcomp.c
+++ b/lib/regcomp.c
@@ -1,5 +1,5 @@
/* Extended regular expression matching and search library.
- Copyright (C) 2002-2013 Free Software Foundation, Inc.
+ Copyright (C) 2002-2014 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>.
@@ -292,7 +292,7 @@ weak_alias (__re_compile_fastmap, re_compile_fastmap)
#endif
static inline void
-__attribute ((always_inline))
+__attribute__ ((always_inline))
re_set_fastmap (char *fastmap, bool icase, int ch)
{
fastmap[ch] = 1;
@@ -586,7 +586,7 @@ weak_alias (__regerror, regerror)
static const bitset_t utf8_sb_map =
{
/* Set the first 128 bits. */
-# ifdef __GNUC__
+# if defined __GNUC__ && !defined __STRICT_ANSI__
[0 ... 0x80 / BITSET_WORD_BITS - 1] = BITSET_WORD_MAX
# else
# if 4 * BITSET_WORD_BITS < ASCII_CHARS
@@ -663,7 +663,10 @@ regfree (preg)
{
re_dfa_t *dfa = preg->buffer;
if (BE (dfa != NULL, 1))
- free_dfa_content (dfa);
+ {
+ lock_fini (dfa->lock);
+ free_dfa_content (dfa);
+ }
preg->buffer = NULL;
preg->allocated = 0;
@@ -784,6 +787,8 @@ re_compile_internal (regex_t *preg, const char * pattern, size_t length,
preg->used = sizeof (re_dfa_t);
err = init_dfa (dfa, length);
+ if (BE (err == REG_NOERROR && lock_init (dfa->lock) != 0, 0))
+ err = REG_ESPACE;
if (BE (err != REG_NOERROR, 0))
{
free_dfa_content (dfa);
@@ -797,8 +802,6 @@ re_compile_internal (regex_t *preg, const char * pattern, size_t length,
strncpy (dfa->re_str, pattern, length + 1);
#endif
- __libc_lock_init (dfa->lock);
-
err = re_string_construct (&regexp, pattern, length, preg->translate,
(syntax & RE_ICASE) != 0, dfa);
if (BE (err != REG_NOERROR, 0))
@@ -806,6 +809,7 @@ re_compile_internal (regex_t *preg, const char * pattern, size_t length,
re_compile_internal_free_return:
free_workarea_compile (preg);
re_string_destruct (&regexp);
+ lock_fini (dfa->lock);
free_dfa_content (dfa);
preg->buffer = NULL;
preg->allocated = 0;
@@ -838,6 +842,7 @@ re_compile_internal (regex_t *preg, const char * pattern, size_t length,
if (BE (err != REG_NOERROR, 0))
{
+ lock_fini (dfa->lock);
free_dfa_content (dfa);
preg->buffer = NULL;
preg->allocated = 0;
@@ -2194,7 +2199,11 @@ parse_reg_exp (re_string_t *regexp, regex_t *preg, re_token_t *token,
{
branch = parse_branch (regexp, preg, token, syntax, nest, err);
if (BE (*err != REG_NOERROR && branch == NULL, 0))
- return NULL;
+ {
+ if (tree != NULL)
+ postorder (tree, free_tree, NULL);
+ return NULL;
+ }
}
else
branch = NULL;
@@ -2455,14 +2464,22 @@ parse_expression (re_string_t *regexp, regex_t *preg, re_token_t *token,
while (token->type == OP_DUP_ASTERISK || token->type == OP_DUP_PLUS
|| token->type == OP_DUP_QUESTION || token->type == OP_OPEN_DUP_NUM)
{
- tree = parse_dup_op (tree, regexp, dfa, token, syntax, err);
- if (BE (*err != REG_NOERROR && tree == NULL, 0))
- return NULL;
+ bin_tree_t *dup_tree = parse_dup_op (tree, regexp, dfa, token,
+ syntax, err);
+ if (BE (*err != REG_NOERROR && dup_tree == NULL, 0))
+ {
+ if (tree != NULL)
+ postorder (tree, free_tree, NULL);
+ return NULL;
+ }
+ tree = dup_tree;
/* In BRE consecutive duplications are not allowed. */
if ((syntax & RE_CONTEXT_INVALID_DUP)
&& (token->type == OP_DUP_ASTERISK
|| token->type == OP_OPEN_DUP_NUM))
{
+ if (tree != NULL)
+ postorder (tree, free_tree, NULL);
*err = REG_BADRPT;
return NULL;
}
@@ -2618,6 +2635,8 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa,
/* Duplicate ELEM before it is marked optional. */
elem = duplicate_tree (elem, dfa);
+ if (BE (elem == NULL, 0))
+ goto parse_dup_op_espace;
old_tree = tree;
}
else
@@ -2837,40 +2856,29 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
/* Local function for parse_bracket_exp used in _LIBC environment.
Seek the collating symbol entry corresponding to NAME.
- Return the index of the symbol in the SYMB_TABLE. */
+ Return the index of the symbol in the SYMB_TABLE,
+ or -1 if not found. */
auto inline int32_t
- __attribute ((always_inline))
- seek_collating_symbol_entry (name, name_len)
- const unsigned char *name;
- size_t name_len;
+ __attribute__ ((always_inline))
+ seek_collating_symbol_entry (const unsigned char *name, size_t name_len)
{
- int32_t hash = elem_hash ((const char *) name, name_len);
- int32_t elem = hash % table_size;
- if (symb_table[2 * elem] != 0)
- {
- int32_t second = hash % (table_size - 2) + 1;
-
- do
- {
- /* First compare the hashing value. */
- if (symb_table[2 * elem] == hash
- /* Compare the length of the name. */
- && name_len == extra[symb_table[2 * elem + 1]]
- /* Compare the name. */
- && memcmp (name, &extra[symb_table[2 * elem + 1] + 1],
- name_len) == 0)
- {
- /* Yep, this is the entry. */
- break;
- }
+ int32_t elem;
- /* Next entry. */
- elem += second;
- }
- while (symb_table[2 * elem] != 0);
- }
- return elem;
+ for (elem = 0; elem < table_size; elem++)
+ if (symb_table[2 * elem] != 0)
+ {
+ int32_t idx = symb_table[2 * elem + 1];
+ /* Skip the name of collating element name. */
+ idx += 1 + extra[idx];
+ if (/* Compare the length of the name. */
+ name_len == extra[idx]
+ /* Compare the name. */
+ && memcmp (name, &extra[idx + 1], name_len) == 0)
+ /* Yep, this is the entry. */
+ return elem;
+ }
+ return -1;
}
/* Local function for parse_bracket_exp used in _LIBC environment.
@@ -2878,9 +2886,8 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
Return the value if succeeded, UINT_MAX otherwise. */
auto inline unsigned int
- __attribute ((always_inline))
- lookup_collation_sequence_value (br_elem)
- bracket_elem_t *br_elem;
+ __attribute__ ((always_inline))
+ lookup_collation_sequence_value (bracket_elem_t *br_elem)
{
if (br_elem->type == SB_CHAR)
{
@@ -2908,7 +2915,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
int32_t elem, idx;
elem = seek_collating_symbol_entry (br_elem->opr.name,
sym_name_len);
- if (symb_table[2 * elem] != 0)
+ if (elem != -1)
{
/* We found the entry. */
idx = symb_table[2 * elem + 1];
@@ -2926,7 +2933,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
/* Return the collation sequence value. */
return *(unsigned int *) (extra + idx);
}
- else if (symb_table[2 * elem] == 0 && sym_name_len == 1)
+ else if (sym_name_len == 1)
{
/* No valid character. Match it as a single byte
character. */
@@ -2947,12 +2954,9 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
update it. */
auto inline reg_errcode_t
- __attribute ((always_inline))
- build_range_exp (sbcset, mbcset, range_alloc, start_elem, end_elem)
- re_charset_t *mbcset;
- Idx *range_alloc;
- bitset_t sbcset;
- bracket_elem_t *start_elem, *end_elem;
+ __attribute__ ((always_inline))
+ build_range_exp (bitset_t sbcset, re_charset_t *mbcset, int *range_alloc,
+ bracket_elem_t *start_elem, bracket_elem_t *end_elem)
{
unsigned int ch;
uint32_t start_collseq;
@@ -3031,26 +3035,23 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
pointer argument since we may update it. */
auto inline reg_errcode_t
- __attribute ((always_inline))
- build_collating_symbol (sbcset, mbcset, coll_sym_alloc, name)
- re_charset_t *mbcset;
- Idx *coll_sym_alloc;
- bitset_t sbcset;
- const unsigned char *name;
+ __attribute__ ((always_inline))
+ build_collating_symbol (bitset_t sbcset, re_charset_t *mbcset,
+ Idx *coll_sym_alloc, const unsigned char *name)
{
int32_t elem, idx;
size_t name_len = strlen ((const char *) name);
if (nrules != 0)
{
elem = seek_collating_symbol_entry (name, name_len);
- if (symb_table[2 * elem] != 0)
+ if (elem != -1)
{
/* We found the entry. */
idx = symb_table[2 * elem + 1];
/* Skip the name of collating element name. */
idx += 1 + extra[idx];
}
- else if (symb_table[2 * elem] == 0 && name_len == 1)
+ else if (name_len == 1)
{
/* No valid character, treat it as a normal
character. */