1 /**********************************************************************
2 utf16_be.c - Oniguruma (regular expression library)
3 **********************************************************************/
4 /*-
5 * Copyright (c) 2002-2008 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 static const int EncLen_UTF16[] = {
33 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
34 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
35 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
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, 4, 4, 4, 4, 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 };
50
51 static int
utf16be_mbc_enc_len(const UChar * p)52 utf16be_mbc_enc_len(const UChar* p)
53 {
54 return EncLen_UTF16[*p];
55 }
56
57 static int
utf16be_is_mbc_newline(const UChar * p,const UChar * end)58 utf16be_is_mbc_newline(const UChar* p, const UChar* end)
59 {
60 if (p + 1 < end) {
61 if (*(p+1) == 0x0a && *p == 0x00)
62 return 1;
63 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
64 if ((
65 #ifndef USE_CRNL_AS_LINE_TERMINATOR
66 *(p+1) == 0x0d ||
67 #endif
68 *(p+1) == 0x85) && *p == 0x00)
69 return 1;
70 if (*p == 0x20 && (*(p+1) == 0x29 || *(p+1) == 0x28))
71 return 1;
72 #endif
73 }
74 return 0;
75 }
76
77 static OnigCodePoint
utf16be_mbc_to_code(const UChar * p,const UChar * end)78 utf16be_mbc_to_code(const UChar* p, const UChar* end)
79 {
80 OnigCodePoint code;
81
82 if (UTF16_IS_SURROGATE_FIRST(*p)) {
83 if (end - p < 4) return 0;
84 code = ((((p[0] - 0xd8) << 2) + ((p[1] & 0xc0) >> 6) + 1) << 16)
85 + ((((p[1] & 0x3f) << 2) + (p[2] - 0xdc)) << 8)
86 + p[3];
87 }
88 else {
89 if (end - p < 2) return 0;
90 code = p[0] * 256 + p[1];
91 }
92 return code;
93 }
94
95 static int
utf16be_code_to_mbclen(OnigCodePoint code)96 utf16be_code_to_mbclen(OnigCodePoint code)
97 {
98 return (code > 0xffff ? 4 : 2);
99 }
100
101 static int
utf16be_code_to_mbc(OnigCodePoint code,UChar * buf)102 utf16be_code_to_mbc(OnigCodePoint code, UChar *buf)
103 {
104 UChar* p = buf;
105
106 if (code > 0xffff) {
107 unsigned int plane, high;
108
109 plane = (code >> 16) - 1;
110 *p++ = (plane >> 2) + 0xd8;
111 high = (code & 0xff00) >> 8;
112 *p++ = ((plane & 0x03) << 6) + (high >> 2);
113 *p++ = (high & 0x03) + 0xdc;
114 *p = (UChar )(code & 0xff);
115 return 4;
116 }
117 else {
118 *p++ = (UChar )((code & 0xff00) >> 8);
119 *p++ = (UChar )(code & 0xff);
120 return 2;
121 }
122 }
123
124 static int
utf16be_mbc_case_fold(OnigCaseFoldType flag,const UChar ** pp,const UChar * end,UChar * fold)125 utf16be_mbc_case_fold(OnigCaseFoldType flag,
126 const UChar** pp, const UChar* end, UChar* fold)
127 {
128 const UChar* p = *pp;
129
130 if (ONIGENC_IS_ASCII_CODE(*(p+1)) && *p == 0) {
131 p++;
132 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
133 if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
134 if (*p == 0x49) {
135 *fold++ = 0x01;
136 *fold = 0x31;
137 (*pp) += 2;
138 return 2;
139 }
140 }
141 #endif
142
143 *fold++ = 0;
144 *fold = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
145 *pp += 2;
146 return 2;
147 }
148 else
149 return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF16_BE, flag,
150 pp, end, fold);
151 }
152
153 #if 0
154 static int
155 utf16be_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
156 {
157 const UChar* p = *pp;
158
159 (*pp) += EncLen_UTF16[*p];
160
161 if (*p == 0) {
162 int c, v;
163
164 p++;
165 if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
166 return TRUE;
167 }
168
169 c = *p;
170 v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
171 (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
172
173 if ((v | BIT_CTYPE_LOWER) != 0) {
174 /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
175 if (c >= 0xaa && c <= 0xba)
176 return FALSE;
177 else
178 return TRUE;
179 }
180 return (v != 0 ? TRUE : FALSE);
181 }
182
183 return FALSE;
184 }
185 #endif
186
187 static UChar*
utf16be_left_adjust_char_head(const UChar * start,const UChar * s)188 utf16be_left_adjust_char_head(const UChar* start, const UChar* s)
189 {
190 if (s <= start) return (UChar* )s;
191
192 if ((s - start) % 2 == 1) {
193 s--;
194 }
195
196 if (UTF16_IS_SURROGATE_SECOND(*s) && s > start + 1)
197 s -= 2;
198
199 return (UChar* )s;
200 }
201
202 static int
utf16be_get_case_fold_codes_by_str(OnigCaseFoldType flag,const OnigUChar * p,const OnigUChar * end,OnigCaseFoldCodeItem items[])203 utf16be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
204 const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
205 {
206 return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF16_BE,
207 flag, p, end, items);
208 }
209
210 OnigEncodingType OnigEncodingUTF16_BE = {
211 utf16be_mbc_enc_len,
212 "UTF-16BE", /* name */
213 4, /* max byte length */
214 2, /* min byte length */
215 utf16be_is_mbc_newline,
216 utf16be_mbc_to_code,
217 utf16be_code_to_mbclen,
218 utf16be_code_to_mbc,
219 utf16be_mbc_case_fold,
220 onigenc_unicode_apply_all_case_fold,
221 utf16be_get_case_fold_codes_by_str,
222 onigenc_unicode_property_name_to_ctype,
223 onigenc_unicode_is_code_ctype,
224 onigenc_utf16_32_get_ctype_code_range,
225 utf16be_left_adjust_char_head,
226 onigenc_always_false_is_allowed_reverse_match
227 };
228
