1 /**********************************************************************
2 utf16_le.c - Oniguruma (regular expression library)
3 **********************************************************************/
4 /*-
5 * Copyright (c) 2002-2006 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 UTF16_IS_SURROGATE_FIRST(c) (c >= 0xd8 && c <= 0xdb)
33 #define UTF16_IS_SURROGATE_SECOND(c) (c >= 0xdc && c <= 0xdf)
34
35 static const int EncLen_UTF16[] = {
36 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
37 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
38 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
39 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
40 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
41 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
42 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
43 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
44 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
45 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
46 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
47 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
48 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
49 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 2, 2, 2, 2,
50 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
51 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
52 };
53
54 static int
utf16le_code_to_mbclen(OnigCodePoint code)55 utf16le_code_to_mbclen(OnigCodePoint code)
56 {
57 return (code > 0xffff ? 4 : 2);
58 }
59
60 static int
utf16le_mbc_enc_len(const UChar * p)61 utf16le_mbc_enc_len(const UChar* p)
62 {
63 return EncLen_UTF16[*(p+1)];
64 }
65
66 static int
utf16le_is_mbc_newline(const UChar * p,const UChar * end)67 utf16le_is_mbc_newline(const UChar* p, const UChar* end)
68 {
69 if (p + 1 < end) {
70 if (*p == 0x0a && *(p+1) == 0x00)
71 return 1;
72 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
73 if ((*p == 0x0d || *p == 0x85) && *(p+1) == 0x00)
74 return 1;
75 if (*(p+1) == 0x20 && (*p == 0x29 || *p == 0x28))
76 return 1;
77 #endif
78 }
79 return 0;
80 }
81
82 static OnigCodePoint
utf16le_mbc_to_code(const UChar * p,const UChar * end)83 utf16le_mbc_to_code(const UChar* p, const UChar* end)
84 {
85 OnigCodePoint code;
86 UChar c0 = *p;
87 UChar c1 = *(p+1);
88
89 if (UTF16_IS_SURROGATE_FIRST(c1)) {
90 code = ((((c1 - 0xd8) << 2) + ((c0 & 0xc0) >> 6) + 1) << 16)
91 + ((((c0 & 0x3f) << 2) + (p[3] - 0xdc)) << 8)
92 + p[2];
93 }
94 else {
95 code = c1 * 256 + p[0];
96 }
97 return code;
98 }
99
100 static int
utf16le_code_to_mbc(OnigCodePoint code,UChar * buf)101 utf16le_code_to_mbc(OnigCodePoint code, UChar *buf)
102 {
103 UChar* p = buf;
104
105 if (code > 0xffff) {
106 unsigned int plane, high;
107
108 plane = code >> 16;
109 high = (code & 0xff00) >> 8;
110
111 *p++ = ((plane & 0x03) << 6) + (high >> 2);
112 *p++ = (plane >> 2) + 0xd8;
113 *p++ = (UChar )(code & 0xff);
114 *p = (high & 0x02) + 0xdc;
115 return 4;
116 }
117 else {
118 *p++ = (UChar )(code & 0xff);
119 *p++ = (UChar )((code & 0xff00) >> 8);
120 return 2;
121 }
122 }
123
124 static int
utf16le_mbc_to_normalize(OnigAmbigType flag,const UChar ** pp,const UChar * end,UChar * lower)125 utf16le_mbc_to_normalize(OnigAmbigType flag, const UChar** pp, const UChar* end,
126 UChar* lower)
127 {
128 const UChar* p = *pp;
129
130 if (*(p+1) == 0) {
131 *(lower+1) = '\0';
132 if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
133 ONIGENC_IS_MBC_ASCII(p)) ||
134 ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
135 !ONIGENC_IS_MBC_ASCII(p))) {
136 *lower = ONIGENC_ISO_8859_1_TO_LOWER_CASE(*p);
137 }
138 else {
139 *lower = *p;
140 }
141 (*pp) += 2;
142 return 2; /* return byte length of converted char to lower */
143 }
144 else {
145 int len = EncLen_UTF16[*(p+1)];
146 if (lower != p) {
147 int i;
148 for (i = 0; i < len; i++) {
149 *lower++ = *p++;
150 }
151 }
152 (*pp) += len;
153 return len; /* return byte length of converted char to lower */
154 }
155 }
156
157 static int
utf16le_is_mbc_ambiguous(OnigAmbigType flag,const UChar ** pp,const UChar * end)158 utf16le_is_mbc_ambiguous(OnigAmbigType flag, const UChar** pp, const UChar* end)
159 {
160 const UChar* p = *pp;
161
162 (*pp) += EncLen_UTF16[*(p+1)];
163
164 if (*(p+1) == 0) {
165 int c, v;
166
167 if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
168 ONIGENC_IS_MBC_ASCII(p)) ||
169 ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
170 !ONIGENC_IS_MBC_ASCII(p))) {
171 c = *p;
172 v = ONIGENC_IS_UNICODE_ISO_8859_1_CTYPE(c,
173 (ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
174 if ((v | ONIGENC_CTYPE_LOWER) != 0) {
175 /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
176 if (c >= 0xaa && c <= 0xba)
177 return FALSE;
178 else
179 return TRUE;
180 }
181 return (v != 0 ? TRUE : FALSE);
182 }
183 }
184
185 return FALSE;
186 }
187
188 static UChar*
utf16le_left_adjust_char_head(const UChar * start,const UChar * s)189 utf16le_left_adjust_char_head(const UChar* start, const UChar* s)
190 {
191 if (s <= start) return (UChar* )s;
192
193 if ((s - start) % 2 == 1) {
194 s--;
195 }
196
197 if (UTF16_IS_SURROGATE_SECOND(*(s+1)) && s > start + 1)
198 s -= 2;
199
200 return (UChar* )s;
201 }
202
203 OnigEncodingType OnigEncodingUTF16_LE = {
204 utf16le_mbc_enc_len,
205 "UTF-16LE", /* name */
206 4, /* max byte length */
207 2, /* min byte length */
208 (ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
209 ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE ),
210 {
211 (OnigCodePoint )'\\' /* esc */
212 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.' */
213 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*' */
214 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
215 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
216 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
217 },
218 utf16le_is_mbc_newline,
219 utf16le_mbc_to_code,
220 utf16le_code_to_mbclen,
221 utf16le_code_to_mbc,
222 utf16le_mbc_to_normalize,
223 utf16le_is_mbc_ambiguous,
224 onigenc_iso_8859_1_get_all_pair_ambig_codes,
225 onigenc_ess_tsett_get_all_comp_ambig_codes,
226 onigenc_unicode_is_code_ctype,
227 onigenc_unicode_get_ctype_code_range,
228 utf16le_left_adjust_char_head,
229 onigenc_always_false_is_allowed_reverse_match
230 };
231