[279] | 1 | /**********************************************************************
|
---|
| 2 | regext.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 | static void
|
---|
| 34 | conv_ext0be32(const UChar* s, const UChar* end, UChar* conv)
|
---|
| 35 | {
|
---|
| 36 | while (s < end) {
|
---|
| 37 | *conv++ = '\0';
|
---|
| 38 | *conv++ = '\0';
|
---|
| 39 | *conv++ = '\0';
|
---|
| 40 | *conv++ = *s++;
|
---|
| 41 | }
|
---|
| 42 | }
|
---|
| 43 |
|
---|
| 44 | static void
|
---|
| 45 | conv_ext0le32(const UChar* s, const UChar* end, UChar* conv)
|
---|
| 46 | {
|
---|
| 47 | while (s < end) {
|
---|
| 48 | *conv++ = *s++;
|
---|
| 49 | *conv++ = '\0';
|
---|
| 50 | *conv++ = '\0';
|
---|
| 51 | *conv++ = '\0';
|
---|
| 52 | }
|
---|
| 53 | }
|
---|
| 54 |
|
---|
| 55 | static void
|
---|
| 56 | conv_ext0be(const UChar* s, const UChar* end, UChar* conv)
|
---|
| 57 | {
|
---|
| 58 | while (s < end) {
|
---|
| 59 | *conv++ = '\0';
|
---|
| 60 | *conv++ = *s++;
|
---|
| 61 | }
|
---|
| 62 | }
|
---|
| 63 |
|
---|
| 64 | static void
|
---|
| 65 | conv_ext0le(const UChar* s, const UChar* end, UChar* conv)
|
---|
| 66 | {
|
---|
| 67 | while (s < end) {
|
---|
| 68 | *conv++ = *s++;
|
---|
| 69 | *conv++ = '\0';
|
---|
| 70 | }
|
---|
| 71 | }
|
---|
| 72 |
|
---|
| 73 | static void
|
---|
| 74 | conv_swap4bytes(const UChar* s, const UChar* end, UChar* conv)
|
---|
| 75 | {
|
---|
| 76 | while (s < end) {
|
---|
| 77 | *conv++ = s[3];
|
---|
| 78 | *conv++ = s[2];
|
---|
| 79 | *conv++ = s[1];
|
---|
| 80 | *conv++ = s[0];
|
---|
| 81 | s += 4;
|
---|
| 82 | }
|
---|
| 83 | }
|
---|
| 84 |
|
---|
| 85 | static void
|
---|
| 86 | conv_swap2bytes(const UChar* s, const UChar* end, UChar* conv)
|
---|
| 87 | {
|
---|
| 88 | while (s < end) {
|
---|
| 89 | *conv++ = s[1];
|
---|
| 90 | *conv++ = s[0];
|
---|
| 91 | s += 2;
|
---|
| 92 | }
|
---|
| 93 | }
|
---|
| 94 |
|
---|
| 95 | static int
|
---|
| 96 | conv_encoding(OnigEncoding from, OnigEncoding to, const UChar* s, const UChar* end,
|
---|
| 97 | UChar** conv, UChar** conv_end)
|
---|
| 98 | {
|
---|
| 99 | ptrdiff_t len = end - s;
|
---|
| 100 |
|
---|
| 101 | if (to == ONIG_ENCODING_UTF16_BE) {
|
---|
| 102 | if (from == ONIG_ENCODING_ASCII || from == ONIG_ENCODING_ISO_8859_1) {
|
---|
| 103 | *conv = (UChar* )xmalloc(len * 2);
|
---|
| 104 | CHECK_NULL_RETURN_MEMERR(*conv);
|
---|
| 105 | *conv_end = *conv + (len * 2);
|
---|
| 106 | conv_ext0be(s, end, *conv);
|
---|
| 107 | return 0;
|
---|
| 108 | }
|
---|
| 109 | else if (from == ONIG_ENCODING_UTF16_LE) {
|
---|
| 110 | swap16:
|
---|
| 111 | *conv = (UChar* )xmalloc(len);
|
---|
| 112 | CHECK_NULL_RETURN_MEMERR(*conv);
|
---|
| 113 | *conv_end = *conv + len;
|
---|
| 114 | conv_swap2bytes(s, end, *conv);
|
---|
| 115 | return 0;
|
---|
| 116 | }
|
---|
| 117 | }
|
---|
| 118 | else if (to == ONIG_ENCODING_UTF16_LE) {
|
---|
| 119 | if (from == ONIG_ENCODING_ASCII || from == ONIG_ENCODING_ISO_8859_1) {
|
---|
| 120 | *conv = (UChar* )xmalloc(len * 2);
|
---|
| 121 | CHECK_NULL_RETURN_MEMERR(*conv);
|
---|
| 122 | *conv_end = *conv + (len * 2);
|
---|
| 123 | conv_ext0le(s, end, *conv);
|
---|
| 124 | return 0;
|
---|
| 125 | }
|
---|
| 126 | else if (from == ONIG_ENCODING_UTF16_BE) {
|
---|
| 127 | goto swap16;
|
---|
| 128 | }
|
---|
| 129 | }
|
---|
| 130 | if (to == ONIG_ENCODING_UTF32_BE) {
|
---|
| 131 | if (from == ONIG_ENCODING_ASCII || from == ONIG_ENCODING_ISO_8859_1) {
|
---|
| 132 | *conv = (UChar* )xmalloc(len * 4);
|
---|
| 133 | CHECK_NULL_RETURN_MEMERR(*conv);
|
---|
| 134 | *conv_end = *conv + (len * 4);
|
---|
| 135 | conv_ext0be32(s, end, *conv);
|
---|
| 136 | return 0;
|
---|
| 137 | }
|
---|
| 138 | else if (from == ONIG_ENCODING_UTF32_LE) {
|
---|
| 139 | swap32:
|
---|
| 140 | *conv = (UChar* )xmalloc(len);
|
---|
| 141 | CHECK_NULL_RETURN_MEMERR(*conv);
|
---|
| 142 | *conv_end = *conv + len;
|
---|
| 143 | conv_swap4bytes(s, end, *conv);
|
---|
| 144 | return 0;
|
---|
| 145 | }
|
---|
| 146 | }
|
---|
| 147 | else if (to == ONIG_ENCODING_UTF32_LE) {
|
---|
| 148 | if (from == ONIG_ENCODING_ASCII || from == ONIG_ENCODING_ISO_8859_1) {
|
---|
| 149 | *conv = (UChar* )xmalloc(len * 4);
|
---|
| 150 | CHECK_NULL_RETURN_MEMERR(*conv);
|
---|
| 151 | *conv_end = *conv + (len * 4);
|
---|
| 152 | conv_ext0le32(s, end, *conv);
|
---|
| 153 | return 0;
|
---|
| 154 | }
|
---|
| 155 | else if (from == ONIG_ENCODING_UTF32_BE) {
|
---|
| 156 | goto swap32;
|
---|
| 157 | }
|
---|
| 158 | }
|
---|
| 159 |
|
---|
| 160 | return ONIGERR_NOT_SUPPORTED_ENCODING_COMBINATION;
|
---|
| 161 | }
|
---|
| 162 |
|
---|
| 163 | extern int
|
---|
| 164 | onig_new_deluxe(regex_t** reg, const UChar* pattern, const UChar* pattern_end,
|
---|
| 165 | OnigCompileInfo* ci, OnigErrorInfo* einfo)
|
---|
| 166 | {
|
---|
| 167 | int r;
|
---|
| 168 | UChar *cpat, *cpat_end;
|
---|
| 169 |
|
---|
| 170 | if (IS_NOT_NULL(einfo)) einfo->par = (UChar* )NULL;
|
---|
| 171 |
|
---|
| 172 | if (ci->pattern_enc != ci->target_enc) {
|
---|
| 173 | r = conv_encoding(ci->pattern_enc, ci->target_enc, pattern, pattern_end,
|
---|
| 174 | &cpat, &cpat_end);
|
---|
| 175 | if (r) return r;
|
---|
| 176 | }
|
---|
| 177 | else {
|
---|
| 178 | cpat = (UChar* )pattern;
|
---|
| 179 | cpat_end = (UChar* )pattern_end;
|
---|
| 180 | }
|
---|
| 181 |
|
---|
| 182 | *reg = (regex_t* )xmalloc(sizeof(regex_t));
|
---|
| 183 | if (IS_NULL(*reg)) {
|
---|
| 184 | r = ONIGERR_MEMORY;
|
---|
| 185 | goto err2;
|
---|
| 186 | }
|
---|
| 187 |
|
---|
| 188 | r = onig_reg_init(*reg, ci->option, ci->case_fold_flag, ci->target_enc,
|
---|
| 189 | ci->syntax);
|
---|
| 190 | if (r) goto err;
|
---|
| 191 |
|
---|
| 192 | r = onig_compile(*reg, cpat, cpat_end, einfo);
|
---|
| 193 | if (r) {
|
---|
| 194 | err:
|
---|
| 195 | onig_free(*reg);
|
---|
| 196 | *reg = NULL;
|
---|
| 197 | }
|
---|
| 198 |
|
---|
| 199 | err2:
|
---|
| 200 | if (cpat != pattern) xfree(cpat);
|
---|
| 201 |
|
---|
| 202 | return r;
|
---|
| 203 | }
|
---|
| 204 |
|
---|
| 205 | #ifdef USE_RECOMPILE_API
|
---|
| 206 | extern int
|
---|
| 207 | onig_recompile_deluxe(regex_t* reg, const UChar* pattern, const UChar* pattern_end,
|
---|
| 208 | OnigCompileInfo* ci, OnigErrorInfo* einfo)
|
---|
| 209 | {
|
---|
| 210 | int r;
|
---|
| 211 | regex_t *new_reg;
|
---|
| 212 |
|
---|
| 213 | r = onig_new_deluxe(&new_reg, pattern, pattern_end, ci, einfo);
|
---|
| 214 | if (r) return r;
|
---|
| 215 | if (ONIG_STATE(reg) == ONIG_STATE_NORMAL) {
|
---|
| 216 | onig_transfer(reg, new_reg);
|
---|
| 217 | }
|
---|
| 218 | else {
|
---|
| 219 | onig_chain_link_add(reg, new_reg);
|
---|
| 220 | }
|
---|
| 221 | return 0;
|
---|
| 222 | }
|
---|
| 223 | #endif
|
---|