[279] | 1 | /**********************************************************************
|
---|
| 2 | reggnu.c - Onigmo (Oniguruma-mod) (regular expression library)
|
---|
| 3 | **********************************************************************/
|
---|
| 4 | /*-
|
---|
| 5 | * Copyright (c) 2002-2008 K.Kosako <sndgk393 AT ybb DOT ne DOT jp>
|
---|
| 6 | * Copyright (c) 2011 K.Takata <kentkt AT csc DOT jp>
|
---|
| 7 | * All rights reserved.
|
---|
| 8 | *
|
---|
| 9 | * Redistribution and use in source and binary forms, with or without
|
---|
| 10 | * modification, are permitted provided that the following conditions
|
---|
| 11 | * are met:
|
---|
| 12 | * 1. Redistributions of source code must retain the above copyright
|
---|
| 13 | * notice, this list of conditions and the following disclaimer.
|
---|
| 14 | * 2. Redistributions in binary form must reproduce the above copyright
|
---|
| 15 | * notice, this list of conditions and the following disclaimer in the
|
---|
| 16 | * documentation and/or other materials provided with the distribution.
|
---|
| 17 | *
|
---|
| 18 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
---|
| 19 | * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
---|
| 20 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
---|
| 21 | * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
---|
| 22 | * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
---|
| 23 | * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
---|
| 24 | * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
---|
| 25 | * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
---|
| 26 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
---|
| 27 | * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
---|
| 28 | * SUCH DAMAGE.
|
---|
| 29 | */
|
---|
| 30 |
|
---|
| 31 | #include "regint.h"
|
---|
| 32 |
|
---|
| 33 | #ifndef ONIGGNU_H
|
---|
| 34 | #include "oniggnu.h"
|
---|
| 35 | #endif
|
---|
| 36 |
|
---|
| 37 | extern void
|
---|
| 38 | re_free_registers(OnigRegion* r)
|
---|
| 39 | {
|
---|
| 40 | /* 0: don't free self */
|
---|
| 41 | onig_region_free(r, 0);
|
---|
| 42 | }
|
---|
| 43 |
|
---|
| 44 | extern int
|
---|
| 45 | re_adjust_startpos(regex_t* reg, const char* string, int size,
|
---|
| 46 | int startpos, int range)
|
---|
| 47 | {
|
---|
| 48 | if (startpos > 0 && ONIGENC_MBC_MAXLEN(reg->enc) != 1 && startpos < size) {
|
---|
| 49 | UChar *p;
|
---|
| 50 | UChar *s = (UChar* )string + startpos;
|
---|
| 51 |
|
---|
| 52 | if (range > 0) {
|
---|
| 53 | p = onigenc_get_right_adjust_char_head(reg->enc, (UChar* )string, s);
|
---|
| 54 | }
|
---|
| 55 | else {
|
---|
| 56 | p = ONIGENC_LEFT_ADJUST_CHAR_HEAD(reg->enc, (UChar* )string, s);
|
---|
| 57 | }
|
---|
| 58 | return (int )(p - (UChar* )string);
|
---|
| 59 | }
|
---|
| 60 |
|
---|
| 61 | return startpos;
|
---|
| 62 | }
|
---|
| 63 |
|
---|
| 64 | extern int
|
---|
| 65 | re_match(regex_t* reg, const char* str, int size, int pos,
|
---|
| 66 | struct re_registers* regs)
|
---|
| 67 | {
|
---|
| 68 | return (int )onig_match(reg, (UChar* )str, (UChar* )(str + size),
|
---|
| 69 | (UChar* )(str + pos), regs, ONIG_OPTION_NONE);
|
---|
| 70 | }
|
---|
| 71 |
|
---|
| 72 | extern int
|
---|
| 73 | re_search(regex_t* bufp, const char* string, int size, int startpos, int range,
|
---|
| 74 | struct re_registers* regs)
|
---|
| 75 | {
|
---|
| 76 | return (int )onig_search(bufp, (UChar* )string, (UChar* )(string + size),
|
---|
| 77 | (UChar* )(string + startpos),
|
---|
| 78 | (UChar* )(string + startpos + range),
|
---|
| 79 | regs, ONIG_OPTION_NONE);
|
---|
| 80 | }
|
---|
| 81 |
|
---|
| 82 | extern int
|
---|
| 83 | re_compile_pattern(const char* pattern, int size, regex_t* reg, char* ebuf)
|
---|
| 84 | {
|
---|
| 85 | int r;
|
---|
| 86 | OnigErrorInfo einfo;
|
---|
| 87 |
|
---|
| 88 | r = onig_compile(reg, (UChar* )pattern, (UChar* )(pattern + size), &einfo);
|
---|
| 89 | if (r != ONIG_NORMAL) {
|
---|
| 90 | if (IS_NOT_NULL(ebuf))
|
---|
| 91 | (void )onig_error_code_to_str((UChar* )ebuf, r, &einfo);
|
---|
| 92 | }
|
---|
| 93 |
|
---|
| 94 | return r;
|
---|
| 95 | }
|
---|
| 96 |
|
---|
| 97 | #ifdef USE_RECOMPILE_API
|
---|
| 98 | extern int
|
---|
| 99 | re_recompile_pattern(const char* pattern, int size, regex_t* reg, char* ebuf)
|
---|
| 100 | {
|
---|
| 101 | int r;
|
---|
| 102 | OnigErrorInfo einfo;
|
---|
| 103 | OnigEncoding enc;
|
---|
| 104 |
|
---|
| 105 | /* I think encoding and options should be arguments of this function.
|
---|
| 106 | But this is adapted to present re.c. (2002/11/29)
|
---|
| 107 | */
|
---|
| 108 | enc = OnigEncDefaultCharEncoding;
|
---|
| 109 |
|
---|
| 110 | r = onig_recompile(reg, (UChar* )pattern, (UChar* )(pattern + size),
|
---|
| 111 | reg->options, enc, OnigDefaultSyntax, &einfo);
|
---|
| 112 | if (r != ONIG_NORMAL) {
|
---|
| 113 | if (IS_NOT_NULL(ebuf))
|
---|
| 114 | (void )onig_error_code_to_str((UChar* )ebuf, r, &einfo);
|
---|
| 115 | }
|
---|
| 116 | return r;
|
---|
| 117 | }
|
---|
| 118 | #endif
|
---|
| 119 |
|
---|
| 120 | extern void
|
---|
| 121 | re_free_pattern(regex_t* reg)
|
---|
| 122 | {
|
---|
| 123 | onig_free(reg);
|
---|
| 124 | }
|
---|
| 125 |
|
---|
| 126 | extern int
|
---|
| 127 | re_alloc_pattern(regex_t** reg)
|
---|
| 128 | {
|
---|
| 129 | *reg = (regex_t* )xmalloc(sizeof(regex_t));
|
---|
| 130 | if (IS_NULL(*reg)) return ONIGERR_MEMORY;
|
---|
| 131 |
|
---|
| 132 | return onig_reg_init(*reg, ONIG_OPTION_DEFAULT,
|
---|
| 133 | ONIGENC_CASE_FOLD_DEFAULT,
|
---|
| 134 | OnigEncDefaultCharEncoding,
|
---|
| 135 | OnigDefaultSyntax);
|
---|
| 136 | }
|
---|
| 137 |
|
---|
| 138 | extern void
|
---|
| 139 | re_set_casetable(const char* table)
|
---|
| 140 | {
|
---|
| 141 | onigenc_set_default_caseconv_table((UChar* )table);
|
---|
| 142 | }
|
---|
| 143 |
|
---|
| 144 | extern void
|
---|
| 145 | re_mbcinit(int mb_code)
|
---|
| 146 | {
|
---|
| 147 | OnigEncoding enc;
|
---|
| 148 |
|
---|
| 149 | switch (mb_code) {
|
---|
| 150 | case RE_MBCTYPE_ASCII:
|
---|
| 151 | enc = ONIG_ENCODING_ASCII;
|
---|
| 152 | break;
|
---|
| 153 | #if 0
|
---|
| 154 | case RE_MBCTYPE_EUC:
|
---|
| 155 | enc = ONIG_ENCODING_EUC_JP;
|
---|
| 156 | break;
|
---|
| 157 | case RE_MBCTYPE_SJIS:
|
---|
| 158 | enc = ONIG_ENCODING_SJIS;
|
---|
| 159 | break;
|
---|
| 160 | #endif
|
---|
| 161 | case RE_MBCTYPE_UTF8:
|
---|
| 162 | enc = ONIG_ENCODING_UTF8;
|
---|
| 163 | break;
|
---|
| 164 | default:
|
---|
| 165 | return ;
|
---|
| 166 | break;
|
---|
| 167 | }
|
---|
| 168 |
|
---|
| 169 | onigenc_set_default_encoding(enc);
|
---|
| 170 | }
|
---|