1 /**********************************************************************
2 utf16_be.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
utf16be_mbc_enc_len(const UChar * p)55 utf16be_mbc_enc_len(const UChar* p)
56 {
57 return EncLen_UTF16[*p];
58 }
59
60 static int
utf16be_is_mbc_newline(const UChar * p,const UChar * end)61 utf16be_is_mbc_newline(const UChar* p, const UChar* end)
62 {
63 if (p + 1 < end) {
64 if (*(p+1) == 0x0a && *p == 0x00)
65 return 1;
66 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
67 if ((*(p+1) == 0x0d || *(p+1) == 0x85) && *p == 0x00)
68 return 1;
69 if (*p == 0x20 && (*(p+1) == 0x29 || *(p+1) == 0x28))
70 return 1;
71 #endif
72 }
73 return 0;
74 }
75
76 static OnigCodePoint
utf16be_mbc_to_code(const UChar * p,const UChar * end)77 utf16be_mbc_to_code(const UChar* p, const UChar* end)
78 {
79 OnigCodePoint code;
80
81 if (UTF16_IS_SURROGATE_FIRST(*p)) {
82 code = ((((p[0] - 0xd8) << 2) + ((p[1] & 0xc0) >> 6) + 1) << 16)
83 + ((((p[1] & 0x3f) << 2) + (p[2] - 0xdc)) << 8)
84 + p[3];
85 }
86 else {
87 code = p[0] * 256 + p[1];
88 }
89 return code;
90 }
91
92 static int
utf16be_code_to_mbclen(OnigCodePoint code)93 utf16be_code_to_mbclen(OnigCodePoint code)
94 {
95 return (code > 0xffff ? 4 : 2);
96 }
97
98 static int
utf16be_code_to_mbc(OnigCodePoint code,UChar * buf)99 utf16be_code_to_mbc(OnigCodePoint code, UChar *buf)
100 {
101 UChar* p = buf;
102
103 if (code > 0xffff) {
104 unsigned int plane, high;
105
106 plane = code >> 16;
107 *p++ = (plane >> 2) + 0xd8;
108 high = (code & 0xff00) >> 8;
109 *p++ = ((plane & 0x03) << 6) + (high >> 2);
110 *p++ = (high & 0x02) + 0xdc;
111 *p = (UChar )(code & 0xff);
112 return 4;
113 }
114 else {
115 *p++ = (UChar )((code & 0xff00) >> 8);
116 *p++ = (UChar )(code & 0xff);
117 return 2;
118 }
119 }
120
121 static int
utf16be_mbc_to_normalize(OnigAmbigType flag,const UChar ** pp,const UChar * end,UChar * lower)122 utf16be_mbc_to_normalize(OnigAmbigType flag, const UChar** pp, const UChar* end,
123 UChar* lower)
124 {
125 const UChar* p = *pp;
126
127 if (*p == 0) {
128 p++;
129 *lower++ = '\0';
130 if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
131 ONIGENC_IS_MBC_ASCII(p)) ||
132 ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
133 !ONIGENC_IS_MBC_ASCII(p))) {
134 *lower = ONIGENC_ISO_8859_1_TO_LOWER_CASE(*p);
135 }
136 else {
137 *lower = *p;
138 }
139
140 (*pp) += 2;
141 return 2; /* return byte length of converted char to lower */
142 }
143 else {
144 int len;
145 len = EncLen_UTF16[*p];
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
utf16be_is_mbc_ambiguous(OnigAmbigType flag,const UChar ** pp,const UChar * end)158 utf16be_is_mbc_ambiguous(OnigAmbigType flag, const UChar** pp, const UChar* end)
159 {
160 const UChar* p = *pp;
161
162 (*pp) += EncLen_UTF16[*p];
163
164 if (*p == 0) {
165 int c, v;
166
167 p++;
168 if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
169 ONIGENC_IS_MBC_ASCII(p)) ||
170 ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
171 !ONIGENC_IS_MBC_ASCII(p))) {
172 c = *p;
173 v = ONIGENC_IS_UNICODE_ISO_8859_1_CTYPE(c,
174 (ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
175
176 if ((v | ONIGENC_CTYPE_LOWER) != 0) {
177 /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
178 if (c >= 0xaa && c <= 0xba)
179 return FALSE;
180 else
181 return TRUE;
182 }
183 return (v != 0 ? TRUE : FALSE);
184 }
185 }
186
187 return FALSE;
188 }
189
190 static UChar*
utf16be_left_adjust_char_head(const UChar * start,const UChar * s)191 utf16be_left_adjust_char_head(const UChar* start, const UChar* s)
192 {
193 if (s <= start) return (UChar* )s;
194
195 if ((s - start) % 2 == 1) {
196 s--;
197 }
198
199 if (UTF16_IS_SURROGATE_SECOND(*s) && s > start + 1)
200 s -= 2;
201
202 return (UChar* )s;
203 }
204
205 OnigEncodingType OnigEncodingUTF16_BE = {
206 utf16be_mbc_enc_len,
207 "UTF-16BE", /* name */
208 4, /* max byte length */
209 2, /* min byte length */
210 (ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
211 ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE ),
212 {
213 (OnigCodePoint )'\\' /* esc */
214 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.' */
215 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*' */
216 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
217 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
218 , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
219 },
220 utf16be_is_mbc_newline,
221 utf16be_mbc_to_code,
222 utf16be_code_to_mbclen,
223 utf16be_code_to_mbc,
224 utf16be_mbc_to_normalize,
225 utf16be_is_mbc_ambiguous,
226 onigenc_iso_8859_1_get_all_pair_ambig_codes,
227 onigenc_ess_tsett_get_all_comp_ambig_codes,
228 onigenc_unicode_is_code_ctype,
229 onigenc_unicode_get_ctype_code_range,
230 utf16be_left_adjust_char_head,
231 onigenc_always_false_is_allowed_reverse_match
232 };
233
