aboutsummaryrefslogtreecommitdiff
path: root/posix/regex_internal.c
diff options
context:
space:
mode:
authorUlrich Drepper <drepper@redhat.com>2004-01-02 21:20:51 +0000
committerUlrich Drepper <drepper@redhat.com>2004-01-02 21:20:51 +0000
commit56b168be5d3d56f8a729acfb5072e0eca429157e (patch)
tree537ab5c65188e2890f815df6ab720f1f7895ffa6 /posix/regex_internal.c
parent8503c987b63bd8badff1e4c9286949b025cecdb3 (diff)
downloadglibc-56b168be5d3d56f8a729acfb5072e0eca429157e.tar
glibc-56b168be5d3d56f8a729acfb5072e0eca429157e.tar.gz
glibc-56b168be5d3d56f8a729acfb5072e0eca429157e.tar.bz2
glibc-56b168be5d3d56f8a729acfb5072e0eca429157e.zip
Update.
2004-01-02 Jakub Jelinek <jakub@redhat.com> * posix/regex_internal.c (re_node_set_insert): Remove unused variables. * posix/regex_internal.h (re_dfa_t): Add syntax field. * posix/regcomp.c (parse): Initialize dfa->syntax. * posix/regexec.c (acquire_init_state_context, prune_impossible_nodes, check_matching, check_halt_state_context, proceed_next_node, sift_states_iter_mb, sift_states_backward, update_cur_sifted_state, sift_states_bkref, transit_state, transit_state_sb, transit_state_mb, transit_state_bkref, get_subexp, get_subexp_sub, check_arrival, expand_bkref_cache, build_trtable): Remove preg argument, add dfa argument instead and remove dfa = preg->buffer initialization in the body. Adjust all callers. (check_node_accept_bytes, group_nodes_into_DFAstates, check_node_accept): Likewise. Use dfa->syntax instead of preg->syntax. (check_arrival_add_next_nodes): Remove preg argument. * posix/regex_internal.h (re_match_context_t): Make input re_string_t instead of a pointer to it. * posix/regex_internal.c (re_string_construct_common): Don't clear pstr here... (re_string_construct): ... but only here. * posix/regexec.c (match_ctx_init): Remove input argument. Don't initialize fields to zero. (re_search_internal): Move input into mctx.input. (acquire_init_state_context, check_matching, check_halt_state_context, proceed_next_node, clean_state_log_if_needed, sift_states_bkref, sift_states_iter_mb, transit_state, transit_state_sb, transit_state_mb, transit_state_bkref, get_subexp, check_arrival, check_arrival_add_next_nodes, check_node_accept, extend_buffers): Change mctx->input into &mctx->input and mctx->input->field into mctx->input.field. 2004-01-02 Jakub Jelinek <jakub@redhat.com> Paolo Bonzini <bonzini@gnu.org> * posix/regex_internal.h (re_const_bitset_ptr_t): New type. (re_string_t): Add newline_anchor, word_char and word_ops_used fields. (re_dfa_t): Change word_char type to bitset. Add word_ops_used field. (re_string_context_at, re_string_reconstruct): Remove last argument. * posix/regex_internal.c (re_string_allocate): Initialize pstr->word_char and pstr->word_ops_used. (re_string_context_at): Remove newline_anchor argument. Use input->newline_anchor instead, swap && conditions. Only use IS_WIDE_WORD_CHAR if input->word_ops_used != 0. Use input->word_char bitmap instead of IS_WORD_CHAR. (re_string_reconstruct): Likewise. Adjust re_string_context_at caller. * posix/regexec.c (acquire_init_state_context, check_halt_state_context, transit_state, transit_state_sb, transit_state_mb, transit_state_bkref, check_arrival, check_node_accept): Adjust re_string_context_at and re_string_reconstruct callers. (re_search_internal): Likewise. Set input.newline_anchor. (build_trtable): Use dfa->word_char bitmap instead of IS_WORD_CHAR. * posix/regcomp.c (init_word_char): Change return type to void. Set dfa->word_ops_used. (free_dfa_content): Don't free dfa->word_char. (parse_expression): Remove error handling for init_word_char.
Diffstat (limited to 'posix/regex_internal.c')
-rw-r--r--posix/regex_internal.c40
1 files changed, 23 insertions, 17 deletions
diff --git a/posix/regex_internal.c b/posix/regex_internal.c
index f07d4a2e7f..2c6c407b02 100644
--- a/posix/regex_internal.c
+++ b/posix/regex_internal.c
@@ -67,6 +67,8 @@ re_string_allocate (pstr, str, len, init_len, trans, icase, dfa)
if (BE (ret != REG_NOERROR, 0))
return ret;
+ pstr->word_char = dfa->word_char;
+ pstr->word_ops_used = dfa->word_ops_used;
pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str;
pstr->valid_len = (pstr->mbs_allocated || dfa->mb_cur_max > 1) ? 0 : len;
pstr->valid_raw_len = pstr->valid_len;
@@ -84,6 +86,7 @@ re_string_construct (pstr, str, len, trans, icase, dfa)
const re_dfa_t *dfa;
{
reg_errcode_t ret;
+ memset (pstr, '\0', sizeof (re_string_t));
re_string_construct_common (str, len, pstr, trans, icase, dfa);
if (len > 0)
@@ -183,7 +186,6 @@ re_string_construct_common (str, len, pstr, trans, icase, dfa)
int icase;
const re_dfa_t *dfa;
{
- memset (pstr, '\0', sizeof (re_string_t));
pstr->raw_mbs = (const unsigned char *) str;
pstr->len = len;
pstr->raw_len = len;
@@ -572,9 +574,9 @@ re_string_translate_buffer (pstr)
convert to upper case in case of REG_ICASE, apply translation. */
static reg_errcode_t
-re_string_reconstruct (pstr, idx, eflags, newline)
+re_string_reconstruct (pstr, idx, eflags)
re_string_t *pstr;
- int idx, eflags, newline;
+ int idx, eflags;
{
int offset = idx - pstr->raw_mbs_idx;
if (offset < 0)
@@ -609,8 +611,7 @@ re_string_reconstruct (pstr, idx, eflags, newline)
)
{
/* Yes, move them to the front of the buffer. */
- pstr->tip_context = re_string_context_at (pstr, offset - 1, eflags,
- newline);
+ pstr->tip_context = re_string_context_at (pstr, offset - 1, eflags);
#ifdef RE_ENABLE_I18N
if (pstr->mb_cur_max > 1)
memmove (pstr->wcs, pstr->wcs + offset,
@@ -695,8 +696,11 @@ re_string_reconstruct (pstr, idx, eflags, newline)
memset (pstr->mbs, 255, pstr->valid_len);
}
pstr->valid_raw_len = pstr->valid_len;
- pstr->tip_context = (IS_WIDE_WORD_CHAR (wc) ? CONTEXT_WORD
- : ((newline && IS_WIDE_NEWLINE (wc))
+ pstr->tip_context = ((BE (pstr->word_ops_used != 0, 0)
+ && IS_WIDE_WORD_CHAR (wc))
+ ? CONTEXT_WORD
+ : ((IS_WIDE_NEWLINE (wc)
+ && pstr->newline_anchor)
? CONTEXT_NEWLINE : 0));
}
else
@@ -705,8 +709,9 @@ re_string_reconstruct (pstr, idx, eflags, newline)
int c = pstr->raw_mbs[pstr->raw_mbs_idx + offset - 1];
if (pstr->trans)
c = pstr->trans[c];
- pstr->tip_context = (IS_WORD_CHAR (c) ? CONTEXT_WORD
- : ((newline && IS_NEWLINE (c))
+ pstr->tip_context = (bitset_contain (pstr->word_char, c)
+ ? CONTEXT_WORD
+ : ((IS_NEWLINE (c) && pstr->newline_anchor)
? CONTEXT_NEWLINE : 0));
}
}
@@ -843,9 +848,9 @@ re_string_destruct (pstr)
/* Return the context at IDX in INPUT. */
static unsigned int
-re_string_context_at (input, idx, eflags, newline_anchor)
+re_string_context_at (input, idx, eflags)
const re_string_t *input;
- int idx, eflags, newline_anchor;
+ int idx, eflags;
{
int c;
if (idx < 0 || idx == input->len)
@@ -874,17 +879,18 @@ re_string_context_at (input, idx, eflags, newline_anchor)
return input->tip_context;
}
wc = input->wcs[wc_idx];
- if (IS_WIDE_WORD_CHAR (wc))
+ if (BE (input->word_ops_used != 0, 0) && IS_WIDE_WORD_CHAR (wc))
return CONTEXT_WORD;
- return (newline_anchor && IS_WIDE_NEWLINE (wc)) ? CONTEXT_NEWLINE : 0;
+ return (IS_WIDE_NEWLINE (wc) && input->newline_anchor
+ ? CONTEXT_NEWLINE : 0);
}
else
#endif
{
c = re_string_byte_at (input, idx);
- if (IS_WORD_CHAR (c))
+ if (bitset_contain (input->word_char, c))
return CONTEXT_WORD;
- return (newline_anchor && IS_NEWLINE (c)) ? CONTEXT_NEWLINE : 0;
+ return IS_NEWLINE (c) && input->newline_anchor ? CONTEXT_NEWLINE : 0;
}
}
@@ -1156,7 +1162,7 @@ re_node_set_insert (set, elem)
re_node_set *set;
int elem;
{
- int idx, right, mid;
+ int idx;
/* In case the set is empty. */
if (set->alloc == 0)
{
@@ -1206,7 +1212,7 @@ re_node_set_insert (set, elem)
}
/* Compare two node sets SET1 and SET2.
- return 1 if SET1 and SET2 are equivalent, retrun 0 otherwise. */
+ return 1 if SET1 and SET2 are equivalent, return 0 otherwise. */
static int
re_node_set_compare (set1, set2)