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_ja.c
26 * by moriyoshi koizumi <moriyoshi@php.net> on 4 dec 2002.
27 *
28 */
29
30 #ifdef HAVE_CONFIG_H
31 #include "config.h"
32 #endif
33
34 #include "mbfilter.h"
35 #include "mbfilter_euc_jp.h"
36
37 #include "unicode_table_cp932_ext.h"
38 #include "unicode_table_jis.h"
39
40 int mbfl_filt_ident_eucjp(int c, mbfl_identify_filter *filter);
41
42 const unsigned char mblen_table_eucjp[] = { /* 0xA1-0xFE */
43 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
44 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
45 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
46 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
47 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
48 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
49 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
50 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
51 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 3,
52 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
53 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
54 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
55 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
56 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
57 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
58 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1
59 };
60
61 static const char *mbfl_encoding_euc_jp_aliases[] = {"EUC", "EUC_JP", "eucJP", "x-euc-jp", NULL};
62
63 const mbfl_encoding mbfl_encoding_euc_jp = {
64 mbfl_no_encoding_euc_jp,
65 "EUC-JP",
66 "EUC-JP",
67 (const char *(*)[])&mbfl_encoding_euc_jp_aliases,
68 mblen_table_eucjp,
69 MBFL_ENCTYPE_MBCS,
70 &vtbl_eucjp_wchar,
71 &vtbl_wchar_eucjp
72 };
73
74 const struct mbfl_identify_vtbl vtbl_identify_eucjp = {
75 mbfl_no_encoding_euc_jp,
76 mbfl_filt_ident_common_ctor,
77 mbfl_filt_ident_common_dtor,
78 mbfl_filt_ident_eucjp
79 };
80
81 const struct mbfl_convert_vtbl vtbl_eucjp_wchar = {
82 mbfl_no_encoding_euc_jp,
83 mbfl_no_encoding_wchar,
84 mbfl_filt_conv_common_ctor,
85 mbfl_filt_conv_common_dtor,
86 mbfl_filt_conv_eucjp_wchar,
87 mbfl_filt_conv_common_flush
88 };
89
90 const struct mbfl_convert_vtbl vtbl_wchar_eucjp = {
91 mbfl_no_encoding_wchar,
92 mbfl_no_encoding_euc_jp,
93 mbfl_filt_conv_common_ctor,
94 mbfl_filt_conv_common_dtor,
95 mbfl_filt_conv_wchar_eucjp,
96 mbfl_filt_conv_common_flush
97 };
98
99 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
100
101 /*
102 * EUC-JP => wchar
103 */
104 int
mbfl_filt_conv_eucjp_wchar(int c,mbfl_convert_filter * filter)105 mbfl_filt_conv_eucjp_wchar(int c, mbfl_convert_filter *filter)
106 {
107 int c1, s, w;
108
109 switch (filter->status) {
110 case 0:
111 if (c >= 0 && c < 0x80) { /* latin */
112 CK((*filter->output_function)(c, filter->data));
113 } else if (c > 0xa0 && c < 0xff) { /* X 0208 first char */
114 filter->status = 1;
115 filter->cache = c;
116 } else if (c == 0x8e) { /* kana first char */
117 filter->status = 2;
118 } else if (c == 0x8f) { /* X 0212 first char */
119 filter->status = 3;
120 } else {
121 w = c & MBFL_WCSGROUP_MASK;
122 w |= MBFL_WCSGROUP_THROUGH;
123 CK((*filter->output_function)(w, filter->data));
124 }
125 break;
126
127 case 1: /* got first half */
128 filter->status = 0;
129 c1 = filter->cache;
130 if (c > 0xa0 && c < 0xff) {
131 s = (c1 - 0xa1)*94 + c - 0xa1;
132 if (s >= 0 && s < jisx0208_ucs_table_size) {
133 w = jisx0208_ucs_table[s];
134 } else {
135 w = 0;
136 }
137 if (w <= 0) {
138 w = ((c1 & 0x7f) << 8) | (c & 0x7f);
139 w &= MBFL_WCSPLANE_MASK;
140 w |= MBFL_WCSPLANE_JIS0208;
141 }
142 CK((*filter->output_function)(w, filter->data));
143 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
144 CK((*filter->output_function)(c, filter->data));
145 } else {
146 w = (c1 << 8) | c;
147 w &= MBFL_WCSGROUP_MASK;
148 w |= MBFL_WCSGROUP_THROUGH;
149 CK((*filter->output_function)(w, filter->data));
150 }
151 break;
152
153 case 2: /* got 0x8e */
154 filter->status = 0;
155 if (c > 0xa0 && c < 0xe0) {
156 w = 0xfec0 + c;
157 CK((*filter->output_function)(w, filter->data));
158 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
159 CK((*filter->output_function)(c, filter->data));
160 } else {
161 w = 0x8e00 | c;
162 w &= MBFL_WCSGROUP_MASK;
163 w |= MBFL_WCSGROUP_THROUGH;
164 CK((*filter->output_function)(w, filter->data));
165 }
166 break;
167
168 case 3: /* got 0x8f, X 0212 first char */
169 if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
170 CK((*filter->output_function)(c, filter->data));
171 filter->status = 0;
172 } else {
173 filter->status++;
174 filter->cache = c;
175 }
176 break;
177 case 4: /* got 0x8f, X 0212 second char */
178 filter->status = 0;
179 c1 = filter->cache;
180 if (c1 > 0xa0 && c1 < 0xff && c > 0xa0 && c < 0xff) {
181 s = (c1 - 0xa1)*94 + c - 0xa1;
182 if (s >= 0 && s < jisx0212_ucs_table_size) {
183 w = jisx0212_ucs_table[s];
184 } else {
185 w = 0;
186 }
187 if (w <= 0) {
188 w = ((c1 & 0x7f) << 8) | (c & 0x7f);
189 w &= MBFL_WCSPLANE_MASK;
190 w |= MBFL_WCSPLANE_JIS0212;
191 }
192 CK((*filter->output_function)(w, filter->data));
193 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
194 CK((*filter->output_function)(c, filter->data));
195 } else {
196 w = (c1 << 8) | c | 0x8f0000;
197 w &= MBFL_WCSGROUP_MASK;
198 w |= MBFL_WCSGROUP_THROUGH;
199 CK((*filter->output_function)(w, filter->data));
200 }
201 break;
202
203 default:
204 filter->status = 0;
205 break;
206 }
207
208 return c;
209 }
210
211 /*
212 * wchar => EUC-JP
213 */
214 int
mbfl_filt_conv_wchar_eucjp(int c,mbfl_convert_filter * filter)215 mbfl_filt_conv_wchar_eucjp(int c, mbfl_convert_filter *filter)
216 {
217 int c1, s;
218
219 s = 0;
220 if (c >= ucs_a1_jis_table_min && c < ucs_a1_jis_table_max) {
221 s = ucs_a1_jis_table[c - ucs_a1_jis_table_min];
222 } else if (c >= ucs_a2_jis_table_min && c < ucs_a2_jis_table_max) {
223 s = ucs_a2_jis_table[c - ucs_a2_jis_table_min];
224 } else if (c >= ucs_i_jis_table_min && c < ucs_i_jis_table_max) {
225 s = ucs_i_jis_table[c - ucs_i_jis_table_min];
226 } else if (c >= ucs_r_jis_table_min && c < ucs_r_jis_table_max) {
227 s = ucs_r_jis_table[c - ucs_r_jis_table_min];
228 }
229 if (s <= 0) {
230 c1 = c & ~MBFL_WCSPLANE_MASK;
231 if (c1 == MBFL_WCSPLANE_JIS0208) {
232 s = c & MBFL_WCSPLANE_MASK;
233 } else if (c1 == MBFL_WCSPLANE_JIS0212) {
234 s = c & MBFL_WCSPLANE_MASK;
235 s |= 0x8080;
236 } else if (c == 0xff3c) { /* FULLWIDTH REVERSE SOLIDUS */
237 s = 0x2140;
238 } else if (c == 0xff5e) { /* FULLWIDTH TILDE */
239 s = 0x2141;
240 } else if (c == 0x2225) { /* PARALLEL TO */
241 s = 0x2142;
242 } else if (c == 0xff0d) { /* FULLWIDTH HYPHEN-MINUS */
243 s = 0x215d;
244 } else if (c == 0xffe0) { /* FULLWIDTH CENT SIGN */
245 s = 0x2171;
246 } else if (c == 0xffe1) { /* FULLWIDTH POUND SIGN */
247 s = 0x2172;
248 } else if (c == 0xffe2) { /* FULLWIDTH NOT SIGN */
249 s = 0x224c;
250 }
251 if (c == 0) {
252 s = 0;
253 } else if (s <= 0) {
254 s = -1;
255 }
256 }
257 if (s >= 0) {
258 if (s < 0x80) { /* latin */
259 CK((*filter->output_function)(s, filter->data));
260 } else if (s < 0x100) { /* kana */
261 CK((*filter->output_function)(0x8e, filter->data));
262 CK((*filter->output_function)(s, filter->data));
263 } else if (s < 0x8080) { /* X 0208 */
264 CK((*filter->output_function)(((s >> 8) & 0xff) | 0x80, filter->data));
265 CK((*filter->output_function)((s & 0xff) | 0x80, filter->data));
266 } else { /* X 0212 */
267 CK((*filter->output_function)(0x8f, filter->data));
268 CK((*filter->output_function)(((s >> 8) & 0xff) | 0x80, filter->data));
269 CK((*filter->output_function)((s & 0xff) | 0x80, filter->data));
270 }
271 } else {
272 CK(mbfl_filt_conv_illegal_output(c, filter));
273 }
274
275 return c;
276 }
277
mbfl_filt_ident_eucjp(int c,mbfl_identify_filter * filter)278 int mbfl_filt_ident_eucjp(int c, mbfl_identify_filter *filter)
279 {
280 switch (filter->status) {
281 case 0: /* latin */
282 if (c >= 0 && c < 0x80) { /* ok */
283 ;
284 } else if (c > 0xa0 && c < 0xff) { /* kanji first char */
285 filter->status = 1;
286 } else if (c == 0x8e) { /* kana first char */
287 filter->status = 2;
288 } else if (c == 0x8f) { /* X 0212 first char */
289 filter->status = 3;
290 } else { /* bad */
291 filter->flag = 1;
292 }
293 break;
294
295 case 1: /* got first half */
296 if (c < 0xa1 || c > 0xfe) { /* bad */
297 filter->flag = 1;
298 }
299 filter->status = 0;
300 break;
301
302 case 2: /* got 0x8e */
303 if (c < 0xa1 || c > 0xdf) { /* bad */
304 filter->flag = 1;
305 }
306 filter->status = 0;
307 break;
308
309 case 3: /* got 0x8f */
310 if (c < 0xa1 || c > 0xfe) { /* bad */
311 filter->flag = 1;
312 }
313 filter->status++;
314 break;
315 case 4: /* got 0x8f */
316 if (c < 0xa1 || c > 0xfe) { /* bad */
317 filter->flag = 1;
318 }
319 filter->status = 0;
320 break;
321
322 default:
323 filter->status = 0;
324 break;
325 }
326
327 return c;
328 }
329