summaryrefslogtreecommitdiff
path: root/posix/regex_internal.h
diff options
context:
space:
mode:
authorUlrich Drepper <drepper@redhat.com>2003-11-29 06:13:09 +0000
committerUlrich Drepper <drepper@redhat.com>2003-11-29 06:13:09 +0000
commitbb3f4825c411e676c51479fea59643af540810b5 (patch)
treec16c5849da218c04f66b8ccc47b1e911d673493d /posix/regex_internal.h
parent46bf9de7b17d4539a19b69bd8407d5d2987b034b (diff)
Update.
2003-11-28 Ulrich Drepper <drepper@redhat.com> * sysdeps/x86_64/fpu/libm-test-ulps: Add some more minor changes to compensate other setup. 2003-11-27 Andreas Jaeger <aj@suse.de> * sysdeps/x86_64/fpu/libm-test-ulps: Add ulps for new atan2 test. * math/libm-test.inc (atan2_test): Add test that run infinitly. Reported by "Willus" <etc231etc231@willus.com>. 2003-11-27 Michael Matz <matz@suse.de> * sysdeps/ieee754/dbl-64/mpsqrt.c (fastiroot): Fix 64-bit problem with wrong types. 2003-11-28 Jakub Jelinek <jakub@redhat.com> * posix/regexec.c (acquire_init_state_context): Make inline. Add always_inline attribute. (check_matching): Add BE macro. Move if (cur_state->has_backref) into if (dfa->nbackref). (sift_states_backward): Fix comment. (transit_state): Add BE macro. Move if (next_state->has_backref) into if (dfa->nbackref && next_state). Don't check for next_state != NULL twice. * posix/regcomp.c (peek_token): Use opr.ctx_type instead of opr.idx for ANCHOR. (parse_expression): Only call init_word_char if word context will be needed. * posix/bug-regex11.c (tests): Add new tests. * posix/tst-regex.c: Include getopt.h. (timing): New variable. (main): Set timing to 1 if --timing argument is present. Add 2 new tests. (run_test, run_test_backwards): Handle timing. 2003-11-27 Jakub Jelinek <jakub@redhat.com> * posix/regex_internal.h (re_string_t): Remove mbs_case field. Add offsets, valid_raw_len, raw_len, raw_stop, mbs_allocated and offsets_needed fields. Change icase, is_utf8 and map_notascii type from int bitfield to unsigned char. (MBS_ALLOCATED, MBS_CASE_ALLOCATED): Remove. (build_wcs_upper_buffer): Change prototype to return int. (re_string_peek_byte_case, re_string_fetch_byte_case): Remove defines, add prototypes. * posix/regex_internal.c (re_string_allocate): Don't initialize stop here. Don't initialize mbs_case. Set valid_raw_len. Use mbs_allocated instead of MBS_* macros. (re_string_construct): Don't initialize stop and valid_len here. Don't initialize mbs_case. Use mbs_allocated instead of MBS_* macros. Reallocate buffers if build_wcs_upper_buffer converted too few bytes. Set valid_len to bufs_len only for single byte no translation and set in that case valid_raw_len as well. (re_string_realloc_buffers): Reallocate offsets if not NULL. Use mbs_allocated instead of MBS_ALLOCATED. Don't reallocate mbs_case. (re_string_construct_common): Initialize raw_len, mbs_allocated, stop and raw_stop. (build_wcs_buffer): Apply pstr->trans before mbrtowc instead of after it. Set valid_raw_len. Don't set mbs_case. (build_wcs_upper_buffer): Return REG_NOERROR or REG_ESPACE. Only use the fast path if !pstr->offsets_needed. Apply pstr->trans before mbrtowc instead of after it. If upper case character uses different number of bytes than lower case, goto to the slow path. Don't call towupper unnecessarily twice. Set valid_raw_len as well. Handle in the slow path the case if lower and upper case use different number of characters. Don't set mbs_case. (re_string_skip_chars): Use valid_raw_len instead of valid_len. (build_upper_buffer): Don't set mbs_case. Add BE macro. Set valid_raw_len. (re_string_translate_buffer): Set mbs instead of mbs_case. Set valid_raw_len. (re_string_reconstruct): Use raw_len/raw_stop to initialize len/stop. Clear valid_raw_len and offsets_needed when clearing valid_len. Use mbs_allocated instead of MBS_* macros. Check original offset against valid_raw_len instead of valid_len. Remove mbs_case handling. Adjust valid_raw_len together with valid_len. If is_utf8 and looking for tip context, apply pstr->trans first. If buffers start with partial multi-byte character, initialize mbs array as well if mbs_allocated. Check return value of build_wcs_upper_buffer. (re_string_peek_byte_case): New function. (re_string_fetch_byte_case): New function. (re_string_destruct): Use mbs_allocated instead of MBS_ALLOCATED. Don't free mbs_case. Free offsets. * posix/regcomp.c (init_dfa): Only check if charset name is UTF-8 if mb_cur_max == 6. * posix/regexec.c (re_search_internal): Initialize input.raw_stop as well. Use valid_raw_len instead of valid_len when looking through fastmap. Adjust registers through input.offsets. (extend_buffers): Allow build_wcs_upper_buffer to fail. * posix/bug-regex18.c (tests): Enable #ifdefed out tests. Add new tests.
Diffstat (limited to 'posix/regex_internal.h')
-rw-r--r--posix/regex_internal.h37
1 files changed, 18 insertions, 19 deletions
diff --git a/posix/regex_internal.h b/posix/regex_internal.h
index f8e99ee06a..214f7af6c0 100644
--- a/posix/regex_internal.h
+++ b/posix/regex_internal.h
@@ -302,13 +302,10 @@ struct re_string_t
REG_ICASE, upper cases of the string are stored, otherwise MBS points
the same address that RAW_MBS points. */
unsigned char *mbs;
- /* Store the case sensitive multibyte string. In case of
- "case insensitive mode", the original string are stored,
- otherwise MBS_CASE points the same address that MBS points. */
- unsigned char *mbs_case;
#ifdef RE_ENABLE_I18N
/* Store the wide character string which is corresponding to MBS. */
wint_t *wcs;
+ int *offsets;
mbstate_t cur_state;
#endif
/* Index in RAW_MBS. Each character mbs[i] corresponds to
@@ -316,15 +313,21 @@ struct re_string_t
int raw_mbs_idx;
/* The length of the valid characters in the buffers. */
int valid_len;
- /* The length of the buffers MBS, MBS_CASE, and WCS. */
+ /* The corresponding number of bytes in raw_mbs array. */
+ int valid_raw_len;
+ /* The length of the buffers MBS and WCS. */
int bufs_len;
/* The index in MBS, which is updated by re_string_fetch_byte. */
int cur_idx;
- /* This is length_of_RAW_MBS - RAW_MBS_IDX. */
+ /* length of RAW_MBS array. */
+ int raw_len;
+ /* This is RAW_LEN - RAW_MBS_IDX + VALID_LEN - VALID_RAW_LEN. */
int len;
/* End of the buffer may be shorter than its length in the cases such
as re_match_2, re_search_2. Then, we use STOP for end of the buffer
instead of LEN. */
+ int raw_stop;
+ /* This is RAW_STOP - RAW_MBS_IDX adjusted through OFFSETS. */
int stop;
/* The context of mbs[0]. We store the context independently, since
@@ -334,17 +337,14 @@ struct re_string_t
/* The translation passed as a part of an argument of re_compile_pattern. */
RE_TRANSLATE_TYPE trans;
/* 1 if REG_ICASE. */
- unsigned int icase : 1;
- unsigned int is_utf8 : 1;
- unsigned int map_notascii : 1;
+ unsigned char icase;
+ unsigned char is_utf8;
+ unsigned char map_notascii;
+ unsigned char mbs_allocated;
+ unsigned char offsets_needed;
int mb_cur_max;
};
typedef struct re_string_t re_string_t;
-/* In case of REG_ICASE, we allocate the buffer dynamically for mbs. */
-#define MBS_ALLOCATED(pstr) (pstr->icase)
-/* In case that we need translation, we allocate the buffer dynamically
- for mbs_case. Note that mbs == mbs_case if not REG_ICASE. */
-#define MBS_CASE_ALLOCATED(pstr) (pstr->trans != NULL)
struct re_dfa_t;
@@ -363,7 +363,7 @@ static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr,
int new_buf_len);
# ifdef RE_ENABLE_I18N
static void build_wcs_buffer (re_string_t *pstr);
-static void build_wcs_upper_buffer (re_string_t *pstr);
+static int build_wcs_upper_buffer (re_string_t *pstr);
# endif /* RE_ENABLE_I18N */
static void build_upper_buffer (re_string_t *pstr);
static void re_string_translate_buffer (re_string_t *pstr);
@@ -375,15 +375,14 @@ static inline wint_t re_string_wchar_at (const re_string_t *pstr, int idx);
# endif /* RE_ENABLE_I18N */
static unsigned int re_string_context_at (const re_string_t *input, int idx,
int eflags, int newline_anchor);
+static unsigned char re_string_peek_byte_case (const re_string_t *pstr,
+ int idx);
+static unsigned char re_string_fetch_byte_case (re_string_t *pstr);
#endif
#define re_string_peek_byte(pstr, offset) \
((pstr)->mbs[(pstr)->cur_idx + offset])
-#define re_string_peek_byte_case(pstr, offset) \
- ((pstr)->mbs_case[(pstr)->cur_idx + offset])
#define re_string_fetch_byte(pstr) \
((pstr)->mbs[(pstr)->cur_idx++])
-#define re_string_fetch_byte_case(pstr) \
- ((pstr)->mbs_case[(pstr)->cur_idx++])
#define re_string_first_byte(pstr, idx) \
((idx) == (pstr)->valid_len || (pstr)->wcs[idx] != WEOF)
#define re_string_is_single_byte_char(pstr, idx) \