1 : /**********************************************************************
2 : utf16_be.c - Oniguruma (regular expression library)
3 : **********************************************************************/
4 : /*-
5 : * Copyright (c) 2002-2009 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
55 : utf16be_mbc_enc_len(const UChar* p)
56 0 : {
57 0 : return EncLen_UTF16[*p];
58 : }
59 :
60 : static int
61 : utf16be_is_mbc_newline(const UChar* p, const UChar* end)
62 0 : {
63 0 : if (p + 1 < end) {
64 0 : if (*(p+1) == 0x0a && *p == 0x00)
65 0 : 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 0 : return 0;
74 : }
75 :
76 : static OnigCodePoint
77 : utf16be_mbc_to_code(const UChar* p, const UChar* end)
78 0 : {
79 : OnigCodePoint code;
80 :
81 0 : if (UTF16_IS_SURROGATE_FIRST(*p)) {
82 0 : 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 0 : code = p[0] * 256 + p[1];
88 : }
89 0 : return code;
90 : }
91 :
92 : static int
93 : utf16be_code_to_mbclen(OnigCodePoint code)
94 0 : {
95 0 : return (code > 0xffff ? 4 : 2);
96 : }
97 :
98 : static int
99 : utf16be_code_to_mbc(OnigCodePoint code, UChar *buf)
100 0 : {
101 0 : UChar* p = buf;
102 :
103 0 : if (code > 0xffff) {
104 : unsigned int plane, high;
105 :
106 0 : plane = code >> 16;
107 0 : *p++ = (plane >> 2) + 0xd8;
108 0 : high = (code & 0xff00) >> 8;
109 0 : *p++ = ((plane & 0x03) << 6) + (high >> 2);
110 0 : *p++ = (high & 0x02) + 0xdc;
111 0 : *p = (UChar )(code & 0xff);
112 0 : return 4;
113 : }
114 : else {
115 0 : *p++ = (UChar )((code & 0xff00) >> 8);
116 0 : *p++ = (UChar )(code & 0xff);
117 0 : return 2;
118 : }
119 : }
120 :
121 : static int
122 : utf16be_mbc_to_normalize(OnigAmbigType flag, const UChar** pp, const UChar* end,
123 : UChar* lower)
124 0 : {
125 0 : const UChar* p = *pp;
126 :
127 0 : if (*p == 0) {
128 0 : p++;
129 0 : if (end > p + 2 &&
130 : (flag & ONIGENC_AMBIGUOUS_MATCH_COMPOUND) != 0 &&
131 : ((*p == 's' && *(p+2) == 's') ||
132 : ((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
133 : (*p == 'S' && *(p+2) == 'S'))) &&
134 : *(p+1) == 0) {
135 0 : *lower++ = '\0';
136 0 : *lower = 0xdf;
137 0 : (*pp) += 4;
138 0 : return 2;
139 : }
140 :
141 0 : *lower++ = '\0';
142 0 : if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
143 : ONIGENC_IS_MBC_ASCII(p)) ||
144 : ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
145 : !ONIGENC_IS_MBC_ASCII(p))) {
146 0 : *lower = ONIGENC_ISO_8859_1_TO_LOWER_CASE(*p);
147 : }
148 : else {
149 0 : *lower = *p;
150 : }
151 :
152 0 : (*pp) += 2;
153 0 : return 2; /* return byte length of converted char to lower */
154 : }
155 : else {
156 : int len;
157 0 : len = EncLen_UTF16[*p];
158 0 : if (lower != p) {
159 : int i;
160 0 : for (i = 0; i < len; i++) {
161 0 : *lower++ = *p++;
162 : }
163 : }
164 0 : (*pp) += len;
165 0 : return len; /* return byte length of converted char to lower */
166 : }
167 : }
168 :
169 : static int
170 : utf16be_is_mbc_ambiguous(OnigAmbigType flag, const UChar** pp, const UChar* end)
171 0 : {
172 0 : const UChar* p = *pp;
173 :
174 0 : (*pp) += EncLen_UTF16[*p];
175 :
176 0 : if (*p == 0) {
177 : int c, v;
178 :
179 0 : p++;
180 0 : if ((flag & ONIGENC_AMBIGUOUS_MATCH_COMPOUND) != 0) {
181 0 : if (end > p + 2 &&
182 : ((*p == 's' && *(p+2) == 's') ||
183 : ((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
184 : (*p == 'S' && *(p+2) == 'S'))) &&
185 : *(p+1) == 0) {
186 0 : (*pp) += 2;
187 0 : return TRUE;
188 : }
189 0 : else if (*p == 0xdf) {
190 0 : return TRUE;
191 : }
192 : }
193 :
194 0 : if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
195 : ONIGENC_IS_MBC_ASCII(p)) ||
196 : ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
197 : !ONIGENC_IS_MBC_ASCII(p))) {
198 0 : c = *p;
199 0 : v = ONIGENC_IS_UNICODE_ISO_8859_1_CTYPE(c,
200 : (ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
201 :
202 : if ((v | ONIGENC_CTYPE_LOWER) != 0) {
203 : /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
204 0 : if (c >= 0xaa && c <= 0xba)
205 0 : return FALSE;
206 : else
207 0 : return TRUE;
208 : }
209 : return (v != 0 ? TRUE : FALSE);
210 : }
211 : }
212 :
213 0 : return FALSE;
214 : }
215 :
216 : static UChar*
217 : utf16be_left_adjust_char_head(const UChar* start, const UChar* s)
218 0 : {
219 0 : if (s <= start) return (UChar* )s;
220 :
221 0 : if ((s - start) % 2 == 1) {
222 0 : s--;
223 : }
224 :
225 0 : if (UTF16_IS_SURROGATE_SECOND(*s) && s > start + 1)
226 0 : s -= 2;
227 :
228 0 : return (UChar* )s;
229 : }
230 :
231 : OnigEncodingType OnigEncodingUTF16_BE = {
232 : utf16be_mbc_enc_len,
233 : "UTF-16BE", /* name */
234 : 4, /* max byte length */
235 : 2, /* min byte length */
236 : (ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
237 : ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE |
238 : ONIGENC_AMBIGUOUS_MATCH_COMPOUND),
239 : {
240 : (OnigCodePoint )'\\' /* esc */
241 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.' */
242 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*' */
243 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
244 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
245 : , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
246 : },
247 : utf16be_is_mbc_newline,
248 : utf16be_mbc_to_code,
249 : utf16be_code_to_mbclen,
250 : utf16be_code_to_mbc,
251 : utf16be_mbc_to_normalize,
252 : utf16be_is_mbc_ambiguous,
253 : onigenc_iso_8859_1_get_all_pair_ambig_codes,
254 : onigenc_ess_tsett_get_all_comp_ambig_codes,
255 : onigenc_unicode_is_code_ctype,
256 : onigenc_unicode_get_ctype_code_range,
257 : utf16be_left_adjust_char_head,
258 : onigenc_always_false_is_allowed_reverse_match
259 : };
|
