aboutsummaryrefslogtreecommitdiffstats
path: root/regcomp.c
diff options
context:
space:
mode:
Diffstat (limited to 'regcomp.c')
-rw-r--r--regcomp.c132
1 files changed, 70 insertions, 62 deletions
diff --git a/regcomp.c b/regcomp.c
index 55596968..6f0710cd 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -1,6 +1,5 @@
/* Extended regular expression matching and search library.
- Copyright (C) 2002,2003,2004,2005,2006,2007,2009
- Free Software Foundation, Inc.
+ Copyright (C) 2002-2007,2009,2010 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>.
@@ -397,7 +396,7 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
applies to multibyte character sets; for single byte character
sets, the SIMPLE_BRACKET again suffices. */
if (dfa->mb_cur_max > 1
- && (cset->nchar_classes || cset->non_match
+ && (cset->nchar_classes || cset->non_match || cset->nranges
# ifdef _LIBC
|| cset->nequiv_classes
# endif /* _LIBC */
@@ -430,8 +429,8 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state,
!= (size_t) -1)
re_set_fastmap (fastmap, false, *(unsigned char *) buf);
}
- }
- }
+ }
+ }
}
#endif /* RE_ENABLE_I18N */
else if (type == OP_PERIOD
@@ -635,7 +634,7 @@ free_dfa_content (re_dfa_t *dfa)
re_dfastate_t *state = entry->array[j];
free_state (state);
}
- re_free (entry->array);
+ re_free (entry->array);
}
re_free (dfa->state_table);
#ifdef RE_ENABLE_I18N
@@ -1044,7 +1043,11 @@ create_initial_state (re_dfa_t *dfa)
int dest_idx = dfa->edests[node_idx].elems[0];
if (!re_node_set_contains (&init_nodes, dest_idx))
{
- re_node_set_merge (&init_nodes, dfa->eclosures + dest_idx);
+ reg_errcode_t err = re_node_set_merge (&init_nodes,
+ dfa->eclosures
+ + dest_idx);
+ if (err != REG_NOERROR)
+ return err;
i = 0;
}
}
@@ -1110,8 +1113,8 @@ optimize_utf8 (re_dfa_t *dfa)
}
break;
case OP_PERIOD:
- has_period = 1;
- break;
+ has_period = 1;
+ break;
case OP_BACK_REF:
case OP_ALT:
case END_OF_RE:
@@ -1124,7 +1127,7 @@ optimize_utf8 (re_dfa_t *dfa)
case SIMPLE_BRACKET:
/* Just double check. The non-ASCII range starts at 0x80. */
assert (0x80 % BITSET_WORD_BITS == 0);
- for (i = 0x80 / BITSET_WORD_BITS; i < BITSET_WORDS; ++i)
+ for (i = 0x80 / BITSET_WORD_BITS; i < BITSET_WORDS; ++i)
if (dfa->nodes[node].opr.sbcset[i])
return;
break;
@@ -1205,7 +1208,7 @@ analyze (regex_t *preg)
{
dfa->inveclosures = re_malloc (re_node_set, dfa->nodes_len);
if (BE (dfa->inveclosures == NULL, 0))
- return REG_ESPACE;
+ return REG_ESPACE;
ret = calc_inveclosure (dfa);
}
@@ -1227,16 +1230,16 @@ postorder (bin_tree_t *root, reg_errcode_t (fn (void *, bin_tree_t *)),
if that's the only child). */
while (node->left || node->right)
if (node->left)
- node = node->left;
- else
- node = node->right;
+ node = node->left;
+ else
+ node = node->right;
do
{
reg_errcode_t err = fn (extra, node);
if (BE (err != REG_NOERROR, 0))
return err;
- if (node->parent == NULL)
+ if (node->parent == NULL)
return REG_NOERROR;
prev = node;
node = node->parent;
@@ -1270,7 +1273,7 @@ preorder (bin_tree_t *root, reg_errcode_t (fn (void *, bin_tree_t *)),
prev = node;
node = node->parent;
if (!node)
- return REG_NOERROR;
+ return REG_NOERROR;
}
node = node->right;
}
@@ -1293,13 +1296,13 @@ optimize_subexps (void *extra, bin_tree_t *node)
}
else if (node->token.type == SUBEXP
- && node->left && node->left->token.type == SUBEXP)
+ && node->left && node->left->token.type == SUBEXP)
{
int other_idx = node->left->token.opr.idx;
node->left = node->left->left;
if (node->left)
- node->left->parent = node;
+ node->left->parent = node;
dfa->subexp_map[other_idx] = dfa->subexp_map[node->token.opr.idx];
if (other_idx < BITSET_WORD_BITS)
@@ -1384,9 +1387,9 @@ calc_first (void *extra, bin_tree_t *node)
node->first = node;
node->node_idx = re_dfa_add_node (dfa, node->token);
if (BE (node->node_idx == -1, 0))
- return REG_ESPACE;
+ return REG_ESPACE;
if (node->token.type == ANCHOR)
- dfa->nodes[node->node_idx].constraint = node->token.opr.ctx_type;
+ dfa->nodes[node->node_idx].constraint = node->token.opr.ctx_type;
}
return REG_NOERROR;
}
@@ -1408,7 +1411,7 @@ calc_next (void *extra, bin_tree_t *node)
if (node->left)
node->left->next = node->next;
if (node->right)
- node->right->next = node->next;
+ node->right->next = node->next;
break;
}
return REG_NOERROR;
@@ -1459,7 +1462,7 @@ link_nfa_nodes (void *extra, bin_tree_t *node)
case OP_BACK_REF:
dfa->nexts[idx] = node->next->node_idx;
if (node->token.type == OP_BACK_REF)
- re_node_set_init_1 (dfa->edests + idx, dfa->nexts[idx]);
+ err = re_node_set_init_1 (dfa->edests + idx, dfa->nexts[idx]);
break;
default:
@@ -1687,9 +1690,10 @@ static reg_errcode_t
calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa, int node, int root)
{
reg_errcode_t err;
- int i, incomplete;
+ int i;
re_node_set eclosure;
- incomplete = 0;
+ int ret;
+ int incomplete = 0;
err = re_node_set_alloc (&eclosure, dfa->edests[node].nelem + 1);
if (BE (err != REG_NOERROR, 0))
return err;
@@ -1734,7 +1738,9 @@ calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa, int node, int root)
else
eclosure_elem = dfa->eclosures[edest];
/* Merge the epsilon closure of `edest'. */
- re_node_set_merge (&eclosure, &eclosure_elem);
+ err = re_node_set_merge (&eclosure, &eclosure_elem);
+ if (BE (err != REG_NOERROR, 0))
+ return err;
/* If the epsilon closure of `edest' is incomplete,
the epsilon closure of this node is also incomplete. */
if (dfa->eclosures[edest].nelem == 0)
@@ -1744,8 +1750,10 @@ calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa, int node, int root)
}
}
- /* Epsilon closures include itself. */
- re_node_set_insert (&eclosure, node);
+ /* An epsilon closure includes itself. */
+ ret = re_node_set_insert (&eclosure, node);
+ if (BE (ret < 0, 0))
+ return REG_ESPACE;
if (incomplete && !root)
dfa->eclosures[node].nelem = 0;
else
@@ -2331,7 +2339,7 @@ parse_expression (re_string_t *regexp, regex_t *preg, re_token_t *token,
&& dfa->word_ops_used == 0)
init_word_char (dfa);
if (token->opr.ctx_type == WORD_DELIM
- || token->opr.ctx_type == NOT_WORD_DELIM)
+ || token->opr.ctx_type == NOT_WORD_DELIM)
{
bin_tree_t *tree_first, *tree_last;
if (token->opr.ctx_type == WORD_DELIM)
@@ -2339,13 +2347,13 @@ parse_expression (re_string_t *regexp, regex_t *preg, re_token_t *token,
token->opr.ctx_type = WORD_FIRST;
tree_first = create_token_tree (dfa, NULL, NULL, token);
token->opr.ctx_type = WORD_LAST;
- }
- else
- {
+ }
+ else
+ {
token->opr.ctx_type = INSIDE_WORD;
tree_first = create_token_tree (dfa, NULL, NULL, token);
token->opr.ctx_type = INSIDE_NOTWORD;
- }
+ }
tree_last = create_token_tree (dfa, NULL, NULL, token);
tree = create_tree (dfa, tree_first, tree_last, OP_ALT);
if (BE (tree_first == NULL || tree_last == NULL || tree == NULL, 0))
@@ -2456,7 +2464,7 @@ parse_sub_exp (re_string_t *regexp, regex_t *preg, re_token_t *token,
{
tree = parse_reg_exp (regexp, preg, token, syntax, nest, err);
if (BE (*err == REG_NOERROR && token->type != OP_CLOSE_SUBEXP, 0))
- *err = REG_EPAREN;
+ *err = REG_EPAREN;
if (BE (*err != REG_NOERROR, 0))
return NULL;
}
@@ -2533,7 +2541,7 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa,
return elem;
}
- if (BE (end != -1 && start > end, 0))
+ if (BE ((end != -1 && start > end) || token->type != OP_CLOSE_DUP_NUM, 0))
{
/* First number greater than second. */
*err = REG_BADBR;
@@ -2593,11 +2601,11 @@ parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa,
elem = duplicate_tree (elem, dfa);
tree = create_tree (dfa, tree, elem, CONCAT);
if (BE (elem == NULL || tree == NULL, 0))
- goto parse_dup_op_espace;
+ goto parse_dup_op_espace;
tree = create_tree (dfa, tree, NULL, OP_ALT);
if (BE (tree == NULL, 0))
- goto parse_dup_op_espace;
+ goto parse_dup_op_espace;
}
if (old_tree)
@@ -2690,9 +2698,9 @@ build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem,
no MBCSET if dfa->mb_cur_max == 1. */
if (mbcset)
{
- /* Check the space of the arrays. */
- if (BE (*range_alloc == mbcset->nranges, 0))
- {
+ /* Check the space of the arrays. */
+ if (BE (*range_alloc == mbcset->nranges, 0))
+ {
/* There is not enough space, need realloc. */
wchar_t *new_array_start, *new_array_end;
int new_nranges;
@@ -2702,9 +2710,9 @@ build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem,
/* Use realloc since mbcset->range_starts and mbcset->range_ends
are NULL if *range_alloc == 0. */
new_array_start = re_realloc (mbcset->range_starts, wchar_t,
- new_nranges);
+ new_nranges);
new_array_end = re_realloc (mbcset->range_ends, wchar_t,
- new_nranges);
+ new_nranges);
if (BE (new_array_start == NULL || new_array_end == NULL, 0))
return REG_ESPACE;
@@ -2712,10 +2720,10 @@ build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem,
mbcset->range_starts = new_array_start;
mbcset->range_ends = new_array_end;
*range_alloc = new_nranges;
- }
+ }
- mbcset->range_starts[mbcset->nranges] = start_wc;
- mbcset->range_ends[mbcset->nranges++] = end_wc;
+ mbcset->range_starts[mbcset->nranges] = start_wc;
+ mbcset->range_ends[mbcset->nranges++] = end_wc;
}
/* Build the table for single byte characters. */
@@ -2934,8 +2942,8 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
build below suffices. */
if (nrules > 0 || dfa->mb_cur_max > 1)
{
- /* Check the space of the arrays. */
- if (BE (*range_alloc == mbcset->nranges, 0))
+ /* Check the space of the arrays. */
+ if (BE (*range_alloc == mbcset->nranges, 0))
{
/* There is not enough space, need realloc. */
uint32_t *new_array_start;
@@ -2947,18 +2955,18 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
new_array_start = re_realloc (mbcset->range_starts, uint32_t,
new_nranges);
new_array_end = re_realloc (mbcset->range_ends, uint32_t,
- new_nranges);
+ new_nranges);
if (BE (new_array_start == NULL || new_array_end == NULL, 0))
- return REG_ESPACE;
+ return REG_ESPACE;
mbcset->range_starts = new_array_start;
mbcset->range_ends = new_array_end;
*range_alloc = new_nranges;
}
- mbcset->range_starts[mbcset->nranges] = start_collseq;
- mbcset->range_ends[mbcset->nranges++] = end_collseq;
+ mbcset->range_starts[mbcset->nranges] = start_collseq;
+ mbcset->range_ends[mbcset->nranges++] = end_collseq;
}
/* Build the table for single byte characters. */
@@ -3291,17 +3299,17 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
of having both SIMPLE_BRACKET and COMPLEX_BRACKET. */
if (sbc_idx < BITSET_WORDS)
{
- /* Build a tree for simple bracket. */
- br_token.type = SIMPLE_BRACKET;
- br_token.opr.sbcset = sbcset;
- work_tree = create_token_tree (dfa, NULL, NULL, &br_token);
- if (BE (work_tree == NULL, 0))
- goto parse_bracket_exp_espace;
+ /* Build a tree for simple bracket. */
+ br_token.type = SIMPLE_BRACKET;
+ br_token.opr.sbcset = sbcset;
+ work_tree = create_token_tree (dfa, NULL, NULL, &br_token);
+ if (BE (work_tree == NULL, 0))
+ goto parse_bracket_exp_espace;
- /* Then join them by ALT node. */
- work_tree = create_tree (dfa, work_tree, mbc_tree, OP_ALT);
- if (BE (work_tree == NULL, 0))
- goto parse_bracket_exp_espace;
+ /* Then join them by ALT node. */
+ work_tree = create_tree (dfa, work_tree, mbc_tree, OP_ALT);
+ if (BE (work_tree == NULL, 0))
+ goto parse_bracket_exp_espace;
}
else
{
@@ -3320,7 +3328,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token,
br_token.opr.sbcset = sbcset;
work_tree = create_token_tree (dfa, NULL, NULL, &br_token);
if (BE (work_tree == NULL, 0))
- goto parse_bracket_exp_espace;
+ goto parse_bracket_exp_espace;
}
return work_tree;
@@ -3877,7 +3885,7 @@ duplicate_tree (const bin_tree_t *root, re_dfa_t *dfa)
node = node->parent;
dup_node = dup_node->parent;
if (!node)
- return dup_root;
+ return dup_root;
}
node = node->right;
p_new = &dup_node->right;
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-03 17:58:56 +0000