xref: /PHP-7.4/ext/mbstring/libmbfl/mbfl/mbfl_ident.c (revision 6c1ff61a)
1 /*
2  * "streamable kanji code filter and converter"
3  * Copyright (c) 1998-2002 HappySize, Inc. All rights reserved.
4  *
5  * LICENSE NOTICES
6  *
7  * This file is part of "streamable kanji code filter and converter",
8  * which is distributed under the terms of GNU Lesser General Public
9  * License (version 2) as published by the Free Software Foundation.
10  *
11  * This software is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
14  * GNU Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with "streamable kanji code filter and converter";
18  * if not, write to the Free Software Foundation, Inc., 59 Temple Place,
19  * Suite 330, Boston, MA  02111-1307  USA
20  *
21  * The author of this file:
22  *
23  */
24 /*
25  * The source code included in this files was separated from mbfilter.c
26  * by Moriyoshi Koizumi <moriyoshi@php.net> on 20 Dec 2002. The file
27  * mbfilter.c is included in this package .
28  *
29  */
30 
31 #ifdef HAVE_CONFIG_H
32 #include "config.h"
33 #endif
34 
35 #include <stddef.h>
36 
37 #include "mbfl_ident.h"
38 #include "mbfl_allocators.h"
39 #include "mbfilter_pass.h"
40 #include "mbfilter_8bit.h"
41 #include "mbfilter_wchar.h"
42 
43 #include "filters/mbfilter_euc_cn.h"
44 #include "filters/mbfilter_hz.h"
45 #include "filters/mbfilter_euc_tw.h"
46 #include "filters/mbfilter_big5.h"
47 #include "filters/mbfilter_uhc.h"
48 #include "filters/mbfilter_euc_kr.h"
49 #include "filters/mbfilter_iso2022_kr.h"
50 #include "filters/mbfilter_sjis.h"
51 #include "filters/mbfilter_sjis_open.h"
52 #include "filters/mbfilter_sjis_mobile.h"
53 #include "filters/mbfilter_jis.h"
54 #include "filters/mbfilter_iso2022_jp_ms.h"
55 #include "filters/mbfilter_iso2022jp_2004.h"
56 #include "filters/mbfilter_iso2022jp_mobile.h"
57 #include "filters/mbfilter_euc_jp.h"
58 #include "filters/mbfilter_euc_jp_win.h"
59 #include "filters/mbfilter_euc_jp_2004.h"
60 #include "filters/mbfilter_utf8_mobile.h"
61 #include "filters/mbfilter_ascii.h"
62 #include "filters/mbfilter_koi8r.h"
63 #include "filters/mbfilter_koi8u.h"
64 #include "filters/mbfilter_cp866.h"
65 #include "filters/mbfilter_cp932.h"
66 #include "filters/mbfilter_cp936.h"
67 #include "filters/mbfilter_cp1251.h"
68 #include "filters/mbfilter_cp1252.h"
69 #include "filters/mbfilter_cp1254.h"
70 #include "filters/mbfilter_cp51932.h"
71 #include "filters/mbfilter_cp5022x.h"
72 #include "filters/mbfilter_gb18030.h"
73 #include "filters/mbfilter_iso8859_1.h"
74 #include "filters/mbfilter_iso8859_2.h"
75 #include "filters/mbfilter_iso8859_3.h"
76 #include "filters/mbfilter_iso8859_4.h"
77 #include "filters/mbfilter_iso8859_5.h"
78 #include "filters/mbfilter_iso8859_6.h"
79 #include "filters/mbfilter_iso8859_7.h"
80 #include "filters/mbfilter_iso8859_8.h"
81 #include "filters/mbfilter_iso8859_9.h"
82 #include "filters/mbfilter_iso8859_10.h"
83 #include "filters/mbfilter_iso8859_13.h"
84 #include "filters/mbfilter_iso8859_14.h"
85 #include "filters/mbfilter_iso8859_15.h"
86 #include "filters/mbfilter_base64.h"
87 #include "filters/mbfilter_qprint.h"
88 #include "filters/mbfilter_uuencode.h"
89 #include "filters/mbfilter_7bit.h"
90 #include "filters/mbfilter_utf7.h"
91 #include "filters/mbfilter_utf7imap.h"
92 #include "filters/mbfilter_utf8.h"
93 #include "filters/mbfilter_utf16.h"
94 #include "filters/mbfilter_utf32.h"
95 #include "filters/mbfilter_byte2.h"
96 #include "filters/mbfilter_byte4.h"
97 #include "filters/mbfilter_ucs4.h"
98 #include "filters/mbfilter_ucs2.h"
99 #include "filters/mbfilter_htmlent.h"
100 #include "filters/mbfilter_armscii8.h"
101 #include "filters/mbfilter_cp850.h"
102 
103 static const struct mbfl_identify_vtbl vtbl_identify_false = {
104 	mbfl_no_encoding_pass,
105 	mbfl_filt_ident_false_ctor,
106 	mbfl_filt_ident_common_dtor,
107 	mbfl_filt_ident_false };
108 
109 
110 static const struct mbfl_identify_vtbl *mbfl_identify_filter_list[] = {
111 	&vtbl_identify_utf8,
112 	&vtbl_identify_utf7,
113 	&vtbl_identify_ascii,
114 	&vtbl_identify_eucjp,
115 	&vtbl_identify_sjis,
116 	&vtbl_identify_sjis_open,
117 	&vtbl_identify_eucjpwin,
118 	&vtbl_identify_eucjp2004,
119 	&vtbl_identify_cp932,
120 	&vtbl_identify_jis,
121 	&vtbl_identify_2022jp,
122 	&vtbl_identify_2022jpms,
123 	&vtbl_identify_2022jp_2004,
124 	&vtbl_identify_2022jp_kddi,
125 	&vtbl_identify_cp51932,
126 	&vtbl_identify_sjis_docomo,
127 	&vtbl_identify_sjis_kddi,
128 	&vtbl_identify_sjis_sb,
129 	&vtbl_identify_utf8_docomo,
130 	&vtbl_identify_utf8_kddi_a,
131 	&vtbl_identify_utf8_kddi_b,
132 	&vtbl_identify_utf8_sb,
133 	&vtbl_identify_euccn,
134 	&vtbl_identify_cp936,
135 	&vtbl_identify_hz,
136 	&vtbl_identify_euctw,
137 	&vtbl_identify_big5,
138 	&vtbl_identify_cp950,
139 	&vtbl_identify_euckr,
140 	&vtbl_identify_uhc,
141 	&vtbl_identify_2022kr,
142 	&vtbl_identify_cp1251,
143 	&vtbl_identify_cp866,
144 	&vtbl_identify_koi8r,
145 	&vtbl_identify_koi8u,
146 	&vtbl_identify_cp1252,
147 	&vtbl_identify_cp1254,
148 	&vtbl_identify_8859_1,
149 	&vtbl_identify_8859_2,
150 	&vtbl_identify_8859_3,
151 	&vtbl_identify_8859_4,
152 	&vtbl_identify_8859_5,
153 	&vtbl_identify_8859_6,
154 	&vtbl_identify_8859_7,
155 	&vtbl_identify_8859_8,
156 	&vtbl_identify_8859_9,
157 	&vtbl_identify_8859_10,
158 	&vtbl_identify_8859_13,
159 	&vtbl_identify_8859_14,
160 	&vtbl_identify_8859_15,
161 	&vtbl_identify_armscii8,
162 	&vtbl_identify_cp850,
163 	&vtbl_identify_jis_ms,
164 	&vtbl_identify_cp50220,
165 	&vtbl_identify_cp50221,
166 	&vtbl_identify_cp50222,
167 	&vtbl_identify_gb18030,
168 	&vtbl_identify_false,
169 	NULL
170 };
171 
172 
173 
174 /*
175  * identify filter
176  */
mbfl_identify_filter_get_vtbl(enum mbfl_no_encoding encoding)177 const struct mbfl_identify_vtbl * mbfl_identify_filter_get_vtbl(enum mbfl_no_encoding encoding)
178 {
179 	const struct mbfl_identify_vtbl * vtbl;
180 	int i;
181 
182 	i = 0;
183 	while ((vtbl = mbfl_identify_filter_list[i++]) != NULL) {
184 		if (vtbl->encoding == encoding) {
185 			break;
186 		}
187 	}
188 
189 	return vtbl;
190 }
191 
mbfl_identify_filter_new(enum mbfl_no_encoding encoding)192 mbfl_identify_filter *mbfl_identify_filter_new(enum mbfl_no_encoding encoding)
193 {
194 	mbfl_identify_filter *filter;
195 
196 	/* allocate */
197 	filter = (mbfl_identify_filter *)mbfl_malloc(sizeof(mbfl_identify_filter));
198 	if (filter == NULL) {
199 		return NULL;
200 	}
201 
202 	if (mbfl_identify_filter_init(filter, encoding)) {
203 		mbfl_free(filter);
204 		return NULL;
205 	}
206 
207 	return filter;
208 }
209 
mbfl_identify_filter_new2(const mbfl_encoding * encoding)210 mbfl_identify_filter *mbfl_identify_filter_new2(const mbfl_encoding *encoding)
211 {
212 	mbfl_identify_filter *filter;
213 
214 	/* allocate */
215 	filter = (mbfl_identify_filter *)mbfl_malloc(sizeof(mbfl_identify_filter));
216 	if (filter == NULL) {
217 		return NULL;
218 	}
219 
220 	if (mbfl_identify_filter_init2(filter, encoding)) {
221 		mbfl_free(filter);
222 		return NULL;
223 	}
224 
225 	return filter;
226 }
227 
228 
mbfl_identify_filter_init(mbfl_identify_filter * filter,enum mbfl_no_encoding encoding)229 int mbfl_identify_filter_init(mbfl_identify_filter *filter, enum mbfl_no_encoding encoding)
230 {
231 	const mbfl_encoding *enc = mbfl_no2encoding(encoding);
232 	return mbfl_identify_filter_init2(filter, enc ? enc: &mbfl_encoding_pass);
233 }
234 
mbfl_identify_filter_init2(mbfl_identify_filter * filter,const mbfl_encoding * encoding)235 int mbfl_identify_filter_init2(mbfl_identify_filter *filter, const mbfl_encoding *encoding)
236 {
237 	const struct mbfl_identify_vtbl *vtbl;
238 
239 	/* encoding structure */
240 	filter->encoding = encoding;
241 
242 	filter->status = 0;
243 	filter->flag = 0;
244 	filter->score = 0;
245 
246 	/* setup the function table */
247 	vtbl = mbfl_identify_filter_get_vtbl(filter->encoding->no_encoding);
248 	if (vtbl == NULL) {
249 		vtbl = &vtbl_identify_false;
250 	}
251 	filter->filter_ctor = vtbl->filter_ctor;
252 	filter->filter_dtor = vtbl->filter_dtor;
253 	filter->filter_function = vtbl->filter_function;
254 
255 	/* constructor */
256 	(*filter->filter_ctor)(filter);
257 
258 	return 0;
259 }
260 
mbfl_identify_filter_delete(mbfl_identify_filter * filter)261 void mbfl_identify_filter_delete(mbfl_identify_filter *filter)
262 {
263 	if (filter == NULL) {
264 		return;
265 	}
266 
267 	mbfl_identify_filter_cleanup(filter);
268 	mbfl_free((void*)filter);
269 }
270 
mbfl_identify_filter_cleanup(mbfl_identify_filter * filter)271 void mbfl_identify_filter_cleanup(mbfl_identify_filter *filter)
272 {
273 	(*filter->filter_dtor)(filter);
274 }
275 
mbfl_filt_ident_common_ctor(mbfl_identify_filter * filter)276 void mbfl_filt_ident_common_ctor(mbfl_identify_filter *filter)
277 {
278 	filter->status = 0;
279 	filter->flag = 0;
280 }
281 
mbfl_filt_ident_common_dtor(mbfl_identify_filter * filter)282 void mbfl_filt_ident_common_dtor(mbfl_identify_filter *filter)
283 {
284 	filter->status = 0;
285 }
286 
mbfl_filt_ident_false(int c,mbfl_identify_filter * filter)287 int mbfl_filt_ident_false(int c, mbfl_identify_filter *filter)
288 {
289 	filter->flag = 1;	/* bad */
290 	return c;
291 }
292 
mbfl_filt_ident_false_ctor(mbfl_identify_filter * filter)293 void mbfl_filt_ident_false_ctor(mbfl_identify_filter *filter)
294 {
295 	filter->status = 0;
296 	filter->flag = 1;
297 }
298 
mbfl_filt_ident_true(int c,mbfl_identify_filter * filter)299 int mbfl_filt_ident_true(int c, mbfl_identify_filter *filter)
300 {
301 	return c;
302 }
303