1 /**********************************************************************
2 utf16_be.c - Oniguruma (regular expression library)
3 **********************************************************************/
4 /*-
5 * Copyright (c) 2002-2016 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
is_valid_mbc_string(const UChar * s,const UChar * end)58 is_valid_mbc_string(const UChar* s, const UChar* end)
59 {
60 return onigenc_length_check_is_valid_mbc_string(ONIG_ENCODING_UTF16_BE, s, end);
61 }
62
63 static int
utf16be_is_mbc_newline(const UChar * p,const UChar * end)64 utf16be_is_mbc_newline(const UChar* p, const UChar* end)
65 {
66 if (p + 1 < end) {
67 if (*(p+1) == 0x0a && *p == 0x00)
68 return 1;
69 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
70 if ((
71 #ifndef USE_CRNL_AS_LINE_TERMINATOR
72 *(p+1) == 0x0d ||
73 #endif
74 *(p+1) == 0x85) && *p == 0x00)
75 return 1;
76
77 if (*p == 0x20 && (*(p+1) == 0x29 || *(p+1) == 0x28))
78 return 1;
79 #endif
80 }
81 return 0;
82 }
83
84 static OnigCodePoint
utf16be_mbc_to_code(const UChar * p,const UChar * end)85 utf16be_mbc_to_code(const UChar* p, const UChar* end)
86 {
87 OnigCodePoint code;
88
89 if (UTF16_IS_SURROGATE_FIRST(*p)) {
90 if (end - p < 4) return 0;
91 code = ((((p[0] - 0xd8) << 2) + ((p[1] & 0xc0) >> 6) + 1) << 16)
92 + ((((p[1] & 0x3f) << 2) + (p[2] - 0xdc)) << 8)
93 + p[3];
94 }
95 else {
96 if (end - p < 2) return 0;
97 code = p[0] * 256 + p[1];
98 }
99 return code;
100 }
101
102 static int
utf16be_code_to_mbclen(OnigCodePoint code)103 utf16be_code_to_mbclen(OnigCodePoint code)
104 {
105 return (code > 0xffff ? 4 : 2);
106 }
107
108 static int
utf16be_code_to_mbc(OnigCodePoint code,UChar * buf)109 utf16be_code_to_mbc(OnigCodePoint code, UChar *buf)
110 {
111 UChar* p = buf;
112
113 if (code > 0xffff) {
114 unsigned int plane, high;
115
116 plane = (code >> 16) - 1;
117 *p++ = (plane >> 2) + 0xd8;
118 high = (code & 0xff00) >> 8;
119 *p++ = ((plane & 0x03) << 6) + (high >> 2);
120 *p++ = (high & 0x03) + 0xdc;
121 *p = (UChar )(code & 0xff);
122 return 4;
123 }
124 else {
125 *p++ = (UChar )((code & 0xff00) >> 8);
126 *p++ = (UChar )(code & 0xff);
127 return 2;
128 }
129 }
130
131 static int
utf16be_mbc_case_fold(OnigCaseFoldType flag,const UChar ** pp,const UChar * end,UChar * fold)132 utf16be_mbc_case_fold(OnigCaseFoldType flag,
133 const UChar** pp, const UChar* end, UChar* fold)
134 {
135 const UChar* p = *pp;
136
137 if (ONIGENC_IS_ASCII_CODE(*(p+1)) && *p == 0) {
138 p++;
139 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
140 if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
141 if (*p == 0x49) {
142 *fold++ = 0x01;
143 *fold = 0x31;
144 (*pp) += 2;
145 return 2;
146 }
147 }
148 #endif
149
150 *fold++ = 0;
151 *fold = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
152 *pp += 2;
153 return 2;
154 }
155 else
156 return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF16_BE, flag,
157 pp, end, fold);
158 }
159
160 #if 0
161 static int
162 utf16be_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp, const UChar* end)
163 {
164 const UChar* p = *pp;
165
166 (*pp) += EncLen_UTF16[*p];
167
168 if (*p == 0) {
169 int c, v;
170
171 p++;
172 if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
173 return TRUE;
174 }
175
176 c = *p;
177 v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
178 (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
179
180 if ((v | BIT_CTYPE_LOWER) != 0) {
181 /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
182 if (c >= 0xaa && c <= 0xba)
183 return FALSE;
184 else
185 return TRUE;
186 }
187 return (v != 0 ? TRUE : FALSE);
188 }
189
190 return FALSE;
191 }
192 #endif
193
194 static UChar*
utf16be_left_adjust_char_head(const UChar * start,const UChar * s)195 utf16be_left_adjust_char_head(const UChar* start, const UChar* s)
196 {
197 if (s <= start) return (UChar* )s;
198
199 if ((s - start) % 2 == 1) {
200 s--;
201 }
202
203 if (UTF16_IS_SURROGATE_SECOND(*s) && s > start + 1)
204 s -= 2;
205
206 return (UChar* )s;
207 }
208
209 static int
utf16be_get_case_fold_codes_by_str(OnigCaseFoldType flag,const OnigUChar * p,const OnigUChar * end,OnigCaseFoldCodeItem items[])210 utf16be_get_case_fold_codes_by_str(OnigCaseFoldType flag,
211 const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
212 {
213 return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF16_BE,
214 flag, p, end, items);
215 }
216
217 OnigEncodingType OnigEncodingUTF16_BE = {
218 utf16be_mbc_enc_len,
219 "UTF-16BE", /* name */
220 4, /* max byte length */
221 2, /* min byte length */
222 utf16be_is_mbc_newline,
223 utf16be_mbc_to_code,
224 utf16be_code_to_mbclen,
225 utf16be_code_to_mbc,
226 utf16be_mbc_case_fold,
227 onigenc_unicode_apply_all_case_fold,
228 utf16be_get_case_fold_codes_by_str,
229 onigenc_unicode_property_name_to_ctype,
230 onigenc_unicode_is_code_ctype,
231 onigenc_utf16_32_get_ctype_code_range,
232 utf16be_left_adjust_char_head,
233 onigenc_always_false_is_allowed_reverse_match,
234 NULL, /* init */
235 NULL, /* is_initialized */
236 is_valid_mbc_string
237 };
238
