From 56b168be5d3d56f8a729acfb5072e0eca429157e Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Fri, 2 Jan 2004 21:20:51 +0000 Subject: Update. 2004-01-02 Jakub Jelinek * 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 Paolo Bonzini * 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. --- posix/regex_internal.h | 40 +++++++++++++++++++++++++++------------- 1 file changed, 27 insertions(+), 13 deletions(-) (limited to 'posix/regex_internal.h') diff --git a/posix/regex_internal.h b/posix/regex_internal.h index c2824ed977..8113914925 100644 --- a/posix/regex_internal.h +++ b/posix/regex_internal.h @@ -121,6 +121,7 @@ extern const size_t __re_error_msgid_idx[] attribute_hidden; #define BITSET_UINTS ((SBC_MAX + UINT_BITS - 1) / UINT_BITS) typedef unsigned int bitset[BITSET_UINTS]; typedef unsigned int *re_bitset_ptr_t; +typedef const unsigned int *re_const_bitset_ptr_t; #define bitset_set(set,i) (set[i / UINT_BITS] |= 1 << i % UINT_BITS) #define bitset_clear(set,i) (set[i / UINT_BITS] &= ~(1 << i % UINT_BITS)) @@ -337,12 +338,16 @@ struct re_string_t unsigned int tip_context; /* The translation passed as a part of an argument of re_compile_pattern. */ RE_TRANSLATE_TYPE trans; + /* Copy of re_dfa_t's word_char. */ + re_const_bitset_ptr_t word_char; /* 1 if REG_ICASE. */ unsigned char icase; unsigned char is_utf8; unsigned char map_notascii; unsigned char mbs_allocated; unsigned char offsets_needed; + unsigned char newline_anchor; + unsigned char word_ops_used; int mb_cur_max; }; typedef struct re_string_t re_string_t; @@ -363,14 +368,17 @@ typedef struct re_dfa_t re_dfa_t; static reg_errcode_t re_string_allocate (re_string_t *pstr, const char *str, int len, int init_len, RE_TRANSLATE_TYPE trans, int icase, - const re_dfa_t *dfa) internal_function; + const re_dfa_t *dfa) + internal_function; static reg_errcode_t re_string_construct (re_string_t *pstr, const char *str, int len, RE_TRANSLATE_TYPE trans, - int icase, const re_dfa_t *dfa) internal_function; + int icase, const re_dfa_t *dfa) + internal_function; static reg_errcode_t re_string_reconstruct (re_string_t *pstr, int idx, - int eflags, int newline) internal_function; + int eflags) internal_function; static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr, - int new_buf_len) internal_function; + int new_buf_len) + internal_function; # ifdef RE_ENABLE_I18N static void build_wcs_buffer (re_string_t *pstr) internal_function; static int build_wcs_upper_buffer (re_string_t *pstr) internal_function; @@ -379,15 +387,19 @@ static void build_upper_buffer (re_string_t *pstr) internal_function; static void re_string_translate_buffer (re_string_t *pstr) internal_function; static void re_string_destruct (re_string_t *pstr) internal_function; # ifdef RE_ENABLE_I18N -static int re_string_elem_size_at (const re_string_t *pstr, int idx) internal_function; -static inline int re_string_char_size_at (const re_string_t *pstr, int idx) internal_function; -static inline wint_t re_string_wchar_at (const re_string_t *pstr, int idx) internal_function; +static int re_string_elem_size_at (const re_string_t *pstr, int idx) + internal_function; +static inline int re_string_char_size_at (const re_string_t *pstr, int idx) + internal_function; +static inline wint_t re_string_wchar_at (const re_string_t *pstr, int idx) + internal_function; # endif /* RE_ENABLE_I18N */ static unsigned int re_string_context_at (const re_string_t *input, int idx, - int eflags, int newline_anchor) internal_function; + int eflags) internal_function; static unsigned char re_string_peek_byte_case (const re_string_t *pstr, int idx) internal_function; -static unsigned char re_string_fetch_byte_case (re_string_t *pstr) internal_function; +static unsigned char re_string_fetch_byte_case (re_string_t *pstr) + internal_function; #endif #define re_string_peek_byte(pstr, offset) \ ((pstr)->mbs[(pstr)->cur_idx + offset]) @@ -471,7 +483,7 @@ struct re_dfastate_t re_node_set nodes; re_node_set *entrance_nodes; struct re_dfastate_t **trtable; - unsigned int context : 10; + unsigned int context : 4; unsigned int halt : 1; /* If this state can accept `multi byte'. Note that we refer to multibyte characters, and multi character @@ -542,13 +554,13 @@ struct re_backref_cache_entry typedef struct { + /* The string object corresponding to the input string. */ + re_string_t input; /* EFLAGS of the argument of regexec. */ int eflags; /* Where the matching ends. */ int match_last; int last_node; - /* The string object corresponding to the input string. */ - re_string_t *input; /* The state log used by the matcher. */ re_dfastate_t **state_log; int state_log_top; @@ -594,7 +606,6 @@ struct re_fail_stack_t struct re_dfa_t { - re_bitset_ptr_t word_char; re_subexp_t *subexps; re_token_t *nodes; int nodes_alloc; @@ -629,7 +640,10 @@ struct re_dfa_t unsigned int has_mb_node : 1; unsigned int is_utf8 : 1; unsigned int map_notascii : 1; + unsigned int word_ops_used : 1; int mb_cur_max; + bitset word_char; + reg_syntax_t syntax; #ifdef DEBUG char* re_str; #endif -- cgit v1.2.3