[279] | 1 | /**********************************************************************
|
---|
| 2 | utf8.c - Oniguruma (regular expression library)
|
---|
| 3 | **********************************************************************/
|
---|
| 4 | /*-
|
---|
| 5 | * Copyright (c) 2002-2007 K.Kosako <sndgk393 AT ybb DOT ne DOT jp>
|
---|
| 6 | * All rights reserved.
|
---|
| 7 | *
|
---|
| 8 | * Redistribution and use in source and binary forms, with or without
|
---|
| 9 | * modification, are permitted provided that the following conditions
|
---|
| 10 | * are met:
|
---|
| 11 | * 1. Redistributions of source code must retain the above copyright
|
---|
| 12 | * notice, this list of conditions and the following disclaimer.
|
---|
| 13 | * 2. Redistributions in binary form must reproduce the above copyright
|
---|
| 14 | * notice, this list of conditions and the following disclaimer in the
|
---|
| 15 | * documentation and/or other materials provided with the distribution.
|
---|
| 16 | *
|
---|
| 17 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
---|
| 18 | * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
---|
| 19 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
---|
| 20 | * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
---|
| 21 | * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
---|
| 22 | * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
---|
| 23 | * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
---|
| 24 | * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
---|
| 25 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
---|
| 26 | * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
---|
| 27 | * SUCH DAMAGE.
|
---|
| 28 | */
|
---|
| 29 |
|
---|
| 30 | #include "regenc.h"
|
---|
| 31 |
|
---|
| 32 | #define USE_INVALID_CODE_SCHEME
|
---|
| 33 |
|
---|
| 34 | #ifdef USE_INVALID_CODE_SCHEME
|
---|
| 35 | /* virtual codepoint values for invalid encoding byte 0xfe and 0xff */
|
---|
| 36 | #define INVALID_CODE_FE 0xfffffffe
|
---|
| 37 | #define INVALID_CODE_FF 0xffffffff
|
---|
| 38 | #define VALID_CODE_LIMIT 0x7fffffff
|
---|
| 39 | #endif
|
---|
| 40 |
|
---|
| 41 | #define utf8_islead(c) ((UChar )((c) & 0xc0) != 0x80)
|
---|
| 42 |
|
---|
| 43 | static const int EncLen_UTF8[] = {
|
---|
| 44 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 45 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 46 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 47 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 48 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 49 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 50 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 51 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 52 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 53 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 54 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 55 | 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
---|
| 56 | 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
---|
| 57 | 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
---|
| 58 | 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
|
---|
| 59 | 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 6, 6, 1, 1
|
---|
| 60 | };
|
---|
| 61 |
|
---|
| 62 | static int
|
---|
| 63 | mbc_enc_len(const UChar* p)
|
---|
| 64 | {
|
---|
| 65 | return EncLen_UTF8[*p];
|
---|
| 66 | }
|
---|
| 67 |
|
---|
| 68 | static int
|
---|
| 69 | is_mbc_newline(const UChar* p, const UChar* end)
|
---|
| 70 | {
|
---|
| 71 | if (p < end) {
|
---|
| 72 | if (*p == 0x0a) return 1;
|
---|
| 73 |
|
---|
| 74 | #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
|
---|
| 75 | if (*p == 0x0b || *p == 0x0c || *p == 0x0d) return 1;
|
---|
| 76 | if (p + 1 < end) {
|
---|
| 77 | if (*(p+1) == 0x85 && *p == 0xc2) /* U+0085 */
|
---|
| 78 | return 1;
|
---|
| 79 | if (p + 2 < end) {
|
---|
| 80 | if ((*(p+2) == 0xa8 || *(p+2) == 0xa9)
|
---|
| 81 | && *(p+1) == 0x80 && *p == 0xe2) /* U+2028, U+2029 */
|
---|
| 82 | return 1;
|
---|
| 83 | }
|
---|
| 84 | }
|
---|
| 85 | #endif
|
---|
| 86 | }
|
---|
| 87 |
|
---|
| 88 | return 0;
|
---|
| 89 | }
|
---|
| 90 |
|
---|
| 91 | static OnigCodePoint
|
---|
| 92 | mbc_to_code(const UChar* p, const UChar* end ARG_UNUSED)
|
---|
| 93 | {
|
---|
| 94 | int c, len;
|
---|
| 95 | OnigCodePoint n;
|
---|
| 96 |
|
---|
| 97 | len = mbc_enc_len(p);
|
---|
| 98 | c = *p++;
|
---|
| 99 | if (len > 1) {
|
---|
| 100 | len--;
|
---|
| 101 | n = c & ((1 << (6 - len)) - 1);
|
---|
| 102 | while (len--) {
|
---|
| 103 | c = *p++;
|
---|
| 104 | n = (n << 6) | (c & ((1 << 6) - 1));
|
---|
| 105 | }
|
---|
| 106 | return n;
|
---|
| 107 | }
|
---|
| 108 | else {
|
---|
| 109 | #ifdef USE_INVALID_CODE_SCHEME
|
---|
| 110 | if (c > 0xfd) {
|
---|
| 111 | return ((c == 0xfe) ? INVALID_CODE_FE : INVALID_CODE_FF);
|
---|
| 112 | }
|
---|
| 113 | #endif
|
---|
| 114 | return (OnigCodePoint )c;
|
---|
| 115 | }
|
---|
| 116 | }
|
---|
| 117 |
|
---|
| 118 | static int
|
---|
| 119 | code_to_mbclen(OnigCodePoint code)
|
---|
| 120 | {
|
---|
| 121 | if ((code & 0xffffff80) == 0) return 1;
|
---|
| 122 | else if ((code & 0xfffff800) == 0) return 2;
|
---|
| 123 | else if ((code & 0xffff0000) == 0) return 3;
|
---|
| 124 | else if ((code & 0xffe00000) == 0) return 4;
|
---|
| 125 | else if ((code & 0xfc000000) == 0) return 5;
|
---|
| 126 | else if ((code & 0x80000000) == 0) return 6;
|
---|
| 127 | #ifdef USE_INVALID_CODE_SCHEME
|
---|
| 128 | else if (code == INVALID_CODE_FE) return 1;
|
---|
| 129 | else if (code == INVALID_CODE_FF) return 1;
|
---|
| 130 | #endif
|
---|
| 131 | else
|
---|
| 132 | return ONIGERR_INVALID_CODE_POINT_VALUE;
|
---|
| 133 | }
|
---|
| 134 |
|
---|
| 135 | static int
|
---|
| 136 | code_to_mbc(OnigCodePoint code, UChar *buf)
|
---|
| 137 | {
|
---|
| 138 | #define UTF8_TRAILS(code, shift) (UChar )((((code) >> (shift)) & 0x3f) | 0x80)
|
---|
| 139 | #define UTF8_TRAIL0(code) (UChar )(((code) & 0x3f) | 0x80)
|
---|
| 140 |
|
---|
| 141 | if ((code & 0xffffff80) == 0) {
|
---|
| 142 | *buf = (UChar )code;
|
---|
| 143 | return 1;
|
---|
| 144 | }
|
---|
| 145 | else {
|
---|
| 146 | UChar *p = buf;
|
---|
| 147 |
|
---|
| 148 | if ((code & 0xfffff800) == 0) {
|
---|
| 149 | *p++ = (UChar )(((code>>6)& 0x1f) | 0xc0);
|
---|
| 150 | }
|
---|
| 151 | else if ((code & 0xffff0000) == 0) {
|
---|
| 152 | *p++ = (UChar )(((code>>12) & 0x0f) | 0xe0);
|
---|
| 153 | *p++ = UTF8_TRAILS(code, 6);
|
---|
| 154 | }
|
---|
| 155 | else if ((code & 0xffe00000) == 0) {
|
---|
| 156 | *p++ = (UChar )(((code>>18) & 0x07) | 0xf0);
|
---|
| 157 | *p++ = UTF8_TRAILS(code, 12);
|
---|
| 158 | *p++ = UTF8_TRAILS(code, 6);
|
---|
| 159 | }
|
---|
| 160 | else if ((code & 0xfc000000) == 0) {
|
---|
| 161 | *p++ = (UChar )(((code>>24) & 0x03) | 0xf8);
|
---|
| 162 | *p++ = UTF8_TRAILS(code, 18);
|
---|
| 163 | *p++ = UTF8_TRAILS(code, 12);
|
---|
| 164 | *p++ = UTF8_TRAILS(code, 6);
|
---|
| 165 | }
|
---|
| 166 | else if ((code & 0x80000000) == 0) {
|
---|
| 167 | *p++ = (UChar )(((code>>30) & 0x01) | 0xfc);
|
---|
| 168 | *p++ = UTF8_TRAILS(code, 24);
|
---|
| 169 | *p++ = UTF8_TRAILS(code, 18);
|
---|
| 170 | *p++ = UTF8_TRAILS(code, 12);
|
---|
| 171 | *p++ = UTF8_TRAILS(code, 6);
|
---|
| 172 | }
|
---|
| 173 | #ifdef USE_INVALID_CODE_SCHEME
|
---|
| 174 | else if (code == INVALID_CODE_FE) {
|
---|
| 175 | *p = 0xfe;
|
---|
| 176 | return 1;
|
---|
| 177 | }
|
---|
| 178 | else if (code == INVALID_CODE_FF) {
|
---|
| 179 | *p = 0xff;
|
---|
| 180 | return 1;
|
---|
| 181 | }
|
---|
| 182 | #endif
|
---|
| 183 | else {
|
---|
| 184 | return ONIGERR_TOO_BIG_WIDE_CHAR_VALUE;
|
---|
| 185 | }
|
---|
| 186 |
|
---|
| 187 | *p++ = UTF8_TRAIL0(code);
|
---|
| 188 | return (int )(p - buf);
|
---|
| 189 | }
|
---|
| 190 | }
|
---|
| 191 |
|
---|
| 192 | static int
|
---|
| 193 | mbc_case_fold(OnigCaseFoldType flag, const UChar** pp,
|
---|
| 194 | const UChar* end, UChar* fold)
|
---|
| 195 | {
|
---|
| 196 | const UChar* p = *pp;
|
---|
| 197 |
|
---|
| 198 | if (ONIGENC_IS_MBC_ASCII(p)) {
|
---|
| 199 | #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
|
---|
| 200 | if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
|
---|
| 201 | if (*p == 0x49) {
|
---|
| 202 | *fold++ = 0xc4;
|
---|
| 203 | *fold = 0xb1;
|
---|
| 204 | (*pp)++;
|
---|
| 205 | return 2;
|
---|
| 206 | }
|
---|
| 207 | }
|
---|
| 208 | #endif
|
---|
| 209 |
|
---|
| 210 | *fold = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
|
---|
| 211 | (*pp)++;
|
---|
| 212 | return 1; /* return byte length of converted char to lower */
|
---|
| 213 | }
|
---|
| 214 | else {
|
---|
| 215 | return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF8, flag,
|
---|
| 216 | pp, end, fold);
|
---|
| 217 | }
|
---|
| 218 | }
|
---|
| 219 |
|
---|
| 220 | #if 0
|
---|
| 221 | static int
|
---|
| 222 | is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
|
---|
| 223 | {
|
---|
| 224 | const UChar* p = *pp;
|
---|
| 225 |
|
---|
| 226 | if (ONIGENC_IS_MBC_ASCII(p)) {
|
---|
| 227 | (*pp)++;
|
---|
| 228 | return ONIGENC_IS_ASCII_CODE_CASE_AMBIG(*p);
|
---|
| 229 | }
|
---|
| 230 | else {
|
---|
| 231 | (*pp) += mbc_enc_len(p);
|
---|
| 232 |
|
---|
| 233 | if (*p == 0xc3) {
|
---|
| 234 | int c = *(p + 1);
|
---|
| 235 | if (c >= 0x80) {
|
---|
| 236 | if (c <= (UChar )0x9e) { /* upper */
|
---|
| 237 | if (c == (UChar )0x97) return FALSE;
|
---|
| 238 | return TRUE;
|
---|
| 239 | }
|
---|
| 240 | else if (c >= (UChar )0xa0 && c <= (UChar )0xbe) { /* lower */
|
---|
| 241 | if (c == (UChar )'\267') return FALSE;
|
---|
| 242 | return TRUE;
|
---|
| 243 | }
|
---|
| 244 | else if (c == (UChar )0x9f &&
|
---|
| 245 | (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
|
---|
| 246 | return TRUE;
|
---|
| 247 | }
|
---|
| 248 | }
|
---|
| 249 | }
|
---|
| 250 | }
|
---|
| 251 |
|
---|
| 252 | return FALSE;
|
---|
| 253 | }
|
---|
| 254 | #endif
|
---|
| 255 |
|
---|
| 256 |
|
---|
| 257 | static int
|
---|
| 258 | get_ctype_code_range(OnigCtype ctype, OnigCodePoint *sb_out,
|
---|
| 259 | const OnigCodePoint* ranges[])
|
---|
| 260 | {
|
---|
| 261 | *sb_out = 0x80;
|
---|
| 262 | return onigenc_unicode_ctype_code_range(ctype, ranges);
|
---|
| 263 | }
|
---|
| 264 |
|
---|
| 265 |
|
---|
| 266 | static UChar*
|
---|
| 267 | left_adjust_char_head(const UChar* start, const UChar* s)
|
---|
| 268 | {
|
---|
| 269 | const UChar *p;
|
---|
| 270 |
|
---|
| 271 | if (s <= start) return (UChar* )s;
|
---|
| 272 | p = s;
|
---|
| 273 |
|
---|
| 274 | while (!utf8_islead(*p) && p > start) p--;
|
---|
| 275 | return (UChar* )p;
|
---|
| 276 | }
|
---|
| 277 |
|
---|
| 278 | static int
|
---|
| 279 | get_case_fold_codes_by_str(OnigCaseFoldType flag,
|
---|
| 280 | const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
|
---|
| 281 | {
|
---|
| 282 | return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF8,
|
---|
| 283 | flag, p, end, items);
|
---|
| 284 | }
|
---|
| 285 |
|
---|
| 286 | OnigEncodingType OnigEncodingUTF8 = {
|
---|
| 287 | mbc_enc_len,
|
---|
| 288 | "UTF-8", /* name */
|
---|
| 289 | 6, /* max byte length */
|
---|
| 290 | 1, /* min byte length */
|
---|
| 291 | is_mbc_newline,
|
---|
| 292 | mbc_to_code,
|
---|
| 293 | code_to_mbclen,
|
---|
| 294 | code_to_mbc,
|
---|
| 295 | mbc_case_fold,
|
---|
| 296 | onigenc_unicode_apply_all_case_fold,
|
---|
| 297 | get_case_fold_codes_by_str,
|
---|
| 298 | onigenc_unicode_property_name_to_ctype,
|
---|
| 299 | onigenc_unicode_is_code_ctype,
|
---|
| 300 | get_ctype_code_range,
|
---|
| 301 | left_adjust_char_head,
|
---|
| 302 | onigenc_always_true_is_allowed_reverse_match,
|
---|
| 303 | ONIGENC_FLAG_UNICODE,
|
---|
| 304 | };
|
---|