1 /**********************************************************************
2 utf16_le.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
utf16le_code_to_mbclen(OnigCodePoint code)52 utf16le_code_to_mbclen(OnigCodePoint code)
53 {
54 return (code > 0xffff ? 4 : 2);
55 }
56
57 static int
utf16le_mbc_enc_len(const UChar * p)58 utf16le_mbc_enc_len(const UChar* p)
59 {
60 return EncLen_UTF16[*(p+1)];
61 }
62
63 static int
is_valid_mbc_string(const UChar * p,const UChar * end)64 is_valid_mbc_string(const UChar* p, const UChar* end)
65 {
66 const UChar* end1 = end - 1;
67
68 while (p < end1) {
69 p += utf16le_mbc_enc_len(p);
70 }
71
72 if (p != end)
73 return FALSE;
74 else
75 return TRUE;
76 }
77
78 static int
utf16le_is_mbc_newline(const UChar * p,const UChar * end)79 utf16le_is_mbc_newline(const UChar* p, const UChar* end)
80 {
81 if (p + 1 < end) {
82 if (*p == 0x0a && *(p+1) == 0x00)
83 return 1;
84 #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
85 if ((
86 #ifndef USE_CRNL_AS_LINE_TERMINATOR
87 *p == 0x0d ||
88 #endif
89 *p == 0x85) && *(p+1) == 0x00)
90 return 1;
91
92 if (*(p+1) == 0x20 && (*p == 0x29 || *p == 0x28))
93 return 1;
94 #endif
95 }
96 return 0;
97 }
98
99 static OnigCodePoint
utf16le_mbc_to_code(const UChar * p,const UChar * end)100 utf16le_mbc_to_code(const UChar* p, const UChar* end)
101 {
102 OnigCodePoint code;
103 UChar c0 = *p;
104 UChar c1 = *(p+1);
105
106 if (UTF16_IS_SURROGATE_FIRST(c1)) {
107 if (end - p < 4) return 0;
108 code = ((((c1 - 0xd8) << 2) + ((c0 & 0xc0) >> 6) + 1) << 16)
109 + ((((c0 & 0x3f) << 2) + (p[3] - 0xdc)) << 8)
110 + p[2];
111 }
112 else {
113 code = c1 * 256 + p[0];
114 }
115 return code;
116 }
117
118 static int
utf16le_code_to_mbc(OnigCodePoint code,UChar * buf)119 utf16le_code_to_mbc(OnigCodePoint code, UChar *buf)
120 {
121 UChar* p = buf;
122
123 if (code > 0xffff) {
124 unsigned int plane, high;
125
126 plane = (code >> 16) - 1;
127 high = (code & 0xff00) >> 8;
128
129 *p++ = ((plane & 0x03) << 6) + (high >> 2);
130 *p++ = (plane >> 2) + 0xd8;
131 *p++ = (UChar )(code & 0xff);
132 *p = (high & 0x03) + 0xdc;
133 return 4;
134 }
135 else {
136 *p++ = (UChar )(code & 0xff);
137 *p++ = (UChar )((code & 0xff00) >> 8);
138 return 2;
139 }
140 }
141
142 static int
utf16le_mbc_case_fold(OnigCaseFoldType flag,const UChar ** pp,const UChar * end,UChar * fold)143 utf16le_mbc_case_fold(OnigCaseFoldType flag,
144 const UChar** pp, const UChar* end, UChar* fold)
145 {
146 const UChar* p = *pp;
147
148 if (ONIGENC_IS_ASCII_CODE(*p) && *(p+1) == 0) {
149 #ifdef USE_UNICODE_CASE_FOLD_TURKISH_AZERI
150 if ((flag & ONIGENC_CASE_FOLD_TURKISH_AZERI) != 0) {
151 if (*p == 0x49) {
152 *fold++ = 0x31;
153 *fold = 0x01;
154 (*pp) += 2;
155 return 2;
156 }
157 }
158 #endif
159
160 *fold++ = ONIGENC_ASCII_CODE_TO_LOWER_CASE(*p);
161 *fold = 0;
162 *pp += 2;
163 return 2;
164 }
165 else
166 return onigenc_unicode_mbc_case_fold(ONIG_ENCODING_UTF16_LE, flag, pp, end,
167 fold);
168 }
169
170 #if 0
171 static int
172 utf16le_is_mbc_ambiguous(OnigCaseFoldType flag, const UChar** pp,
173 const UChar* end)
174 {
175 const UChar* p = *pp;
176
177 (*pp) += EncLen_UTF16[*(p+1)];
178
179 if (*(p+1) == 0) {
180 int c, v;
181
182 if (*p == 0xdf && (flag & INTERNAL_ONIGENC_CASE_FOLD_MULTI_CHAR) != 0) {
183 return TRUE;
184 }
185
186 c = *p;
187 v = ONIGENC_IS_UNICODE_ISO_8859_1_BIT_CTYPE(c,
188 (BIT_CTYPE_UPPER | BIT_CTYPE_LOWER));
189 if ((v | BIT_CTYPE_LOWER) != 0) {
190 /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
191 if (c >= 0xaa && c <= 0xba)
192 return FALSE;
193 else
194 return TRUE;
195 }
196 return (v != 0 ? TRUE : FALSE);
197 }
198
199 return FALSE;
200 }
201 #endif
202
203 static UChar*
utf16le_left_adjust_char_head(const UChar * start,const UChar * s)204 utf16le_left_adjust_char_head(const UChar* start, const UChar* s)
205 {
206 if (s <= start) return (UChar* )s;
207
208 if ((s - start) % 2 == 1) {
209 s--;
210 }
211
212 if (UTF16_IS_SURROGATE_SECOND(*(s+1)) && s > start + 1)
213 s -= 2;
214
215 return (UChar* )s;
216 }
217
218 static int
utf16le_get_case_fold_codes_by_str(OnigCaseFoldType flag,const OnigUChar * p,const OnigUChar * end,OnigCaseFoldCodeItem items[])219 utf16le_get_case_fold_codes_by_str(OnigCaseFoldType flag,
220 const OnigUChar* p, const OnigUChar* end, OnigCaseFoldCodeItem items[])
221 {
222 return onigenc_unicode_get_case_fold_codes_by_str(ONIG_ENCODING_UTF16_LE,
223 flag, p, end, items);
224 }
225
226 OnigEncodingType OnigEncodingUTF16_LE = {
227 utf16le_mbc_enc_len,
228 "UTF-16LE", /* name */
229 4, /* max byte length */
230 2, /* min byte length */
231 utf16le_is_mbc_newline,
232 utf16le_mbc_to_code,
233 utf16le_code_to_mbclen,
234 utf16le_code_to_mbc,
235 utf16le_mbc_case_fold,
236 onigenc_unicode_apply_all_case_fold,
237 utf16le_get_case_fold_codes_by_str,
238 onigenc_unicode_property_name_to_ctype,
239 onigenc_unicode_is_code_ctype,
240 onigenc_utf16_32_get_ctype_code_range,
241 utf16le_left_adjust_char_head,
242 onigenc_always_false_is_allowed_reverse_match,
243 NULL, /* init */
244 NULL, /* is_initialized */
245 is_valid_mbc_string
246 };
247
