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: Rui Hirokawa <hirokawa@php.net>
22 *
23 */
24 /*
25 * The source code included in this files was separated from mbfilter_tw.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_tw.h"
36
37 #include "unicode_table_cns11643.h"
38
39 static int mbfl_filt_ident_euctw(int c, mbfl_identify_filter *filter);
40
41 static const unsigned char mblen_table_euctw[] = { /* 0xA1-0xFE */
42 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
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, 4, 1,
51 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
52 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
53 2, 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, 1
58 };
59
60
61 static const char *mbfl_encoding_euc_tw_aliases[] = {"EUC_TW", "eucTW", "x-euc-tw", NULL};
62
63 const mbfl_encoding mbfl_encoding_euc_tw = {
64 mbfl_no_encoding_euc_tw,
65 "EUC-TW",
66 "EUC-TW",
67 (const char *(*)[])&mbfl_encoding_euc_tw_aliases,
68 mblen_table_euctw,
69 MBFL_ENCTYPE_MBCS
70 };
71
72 const struct mbfl_identify_vtbl vtbl_identify_euctw = {
73 mbfl_no_encoding_euc_tw,
74 mbfl_filt_ident_common_ctor,
75 mbfl_filt_ident_common_dtor,
76 mbfl_filt_ident_euctw
77 };
78
79 const struct mbfl_convert_vtbl vtbl_euctw_wchar = {
80 mbfl_no_encoding_euc_tw,
81 mbfl_no_encoding_wchar,
82 mbfl_filt_conv_common_ctor,
83 mbfl_filt_conv_common_dtor,
84 mbfl_filt_conv_euctw_wchar,
85 mbfl_filt_conv_common_flush
86 };
87
88 const struct mbfl_convert_vtbl vtbl_wchar_euctw = {
89 mbfl_no_encoding_wchar,
90 mbfl_no_encoding_euc_tw,
91 mbfl_filt_conv_common_ctor,
92 mbfl_filt_conv_common_dtor,
93 mbfl_filt_conv_wchar_euctw,
94 mbfl_filt_conv_common_flush
95 };
96
97 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
98
99 /*
100 * EUC-TW => wchar
101 */
102 int
mbfl_filt_conv_euctw_wchar(int c,mbfl_convert_filter * filter)103 mbfl_filt_conv_euctw_wchar(int c, mbfl_convert_filter *filter)
104 {
105 int c1, s, w, plane;
106
107 switch (filter->status) {
108 case 0:
109 if (c >= 0 && c < 0x80) { /* latin */
110 CK((*filter->output_function)(c, filter->data));
111 } else if (c > 0xa0 && c < 0xff) { /* dbcs first byte */
112 filter->status = 1;
113 filter->cache = c;
114 } else if (c == 0x8e) { /* mbcs first byte */
115 filter->status = 2;
116 filter->cache = c;
117 } else {
118 w = c & MBFL_WCSGROUP_MASK;
119 w |= MBFL_WCSGROUP_THROUGH;
120 CK((*filter->output_function)(w, filter->data));
121 }
122 break;
123
124 case 1: /* mbcs second byte */
125 filter->status = 0;
126 c1 = filter->cache;
127 if (c > 0xa0 && c < 0xff) {
128 w = (c1 - 0xa1)*94 + (c - 0xa1);
129 if (w >= 0 && w < cns11643_1_ucs_table_size) {
130 w = cns11643_1_ucs_table[w];
131 } else {
132 w = 0;
133 }
134 if (w <= 0) {
135 w = (c1 << 8) | c;
136 w &= MBFL_WCSPLANE_MASK;
137 w |= MBFL_WCSPLANE_CNS11643;
138 }
139 CK((*filter->output_function)(w, filter->data));
140 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
141 CK((*filter->output_function)(c, filter->data));
142 } else {
143 w = (c1 << 8) | c;
144 w &= MBFL_WCSGROUP_MASK;
145 w |= MBFL_WCSGROUP_THROUGH;
146 CK((*filter->output_function)(w, filter->data));
147 }
148 break;
149
150 case 2: /* got 0x8e, first char */
151 c1 = filter->cache;
152 if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
153 CK((*filter->output_function)(c, filter->data));
154 filter->status = 0;
155 } else if (c > 0xa0 && c < 0xaf) {
156 filter->status = 3;
157 filter->cache = c - 0xa1;
158 } else {
159 w = (c1 << 8) | c;
160 w &= MBFL_WCSGROUP_MASK;
161 w |= MBFL_WCSGROUP_THROUGH;
162 CK((*filter->output_function)(w, filter->data));
163 }
164 break;
165
166 case 3: /* got 0x8e, third char */
167 filter->status = 0;
168 c1 = filter->cache;
169 if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
170 CK((*filter->output_function)(c, filter->data));
171 filter->status = 0;
172 } else if (c > 0xa0 && c < 0xff) {
173 filter->status = 4;
174 filter->cache = (c1 << 8) + c - 0xa1;
175 } else {
176 w = (c1 << 8) | c;
177 w &= MBFL_WCSGROUP_MASK;
178 w |= MBFL_WCSGROUP_THROUGH;
179 CK((*filter->output_function)(w, filter->data));
180 }
181 break;
182
183 case 4: /* mbcs fourth char */
184 filter->status = 0;
185 c1 = filter->cache;
186 if (c1 >= 0x100 && c1 <= 0xdff && c > 0xa0 && c < 0xff) {
187 plane = (c1 & 0xf00) >> 8;
188 s = (c1 & 0xff)*94 + c - 0xa1;
189 w = 0;
190 if (s >= 0) {
191 if (plane == 1 && s < cns11643_2_ucs_table_size) {
192 w = cns11643_2_ucs_table[s];
193 }
194 if (plane == 13 && s < cns11643_14_ucs_table_size) {
195 w = cns11643_14_ucs_table[s];
196 }
197 }
198 if (w <= 0) {
199 w = ((c1 & 0x7f) << 8) | (c & 0x7f);
200 w &= MBFL_WCSPLANE_MASK;
201 w |= MBFL_WCSPLANE_CNS11643;
202 }
203 CK((*filter->output_function)(w, filter->data));
204 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
205 CK((*filter->output_function)(c, filter->data));
206 } else {
207 w = (c1 << 8) | c | 0x8e0000;
208 w &= MBFL_WCSGROUP_MASK;
209 w |= MBFL_WCSGROUP_THROUGH;
210 CK((*filter->output_function)(w, filter->data));
211 }
212 break;
213
214 default:
215 filter->status = 0;
216 break;
217 }
218
219 return c;
220 }
221
222 /*
223 * wchar => EUC-TW
224 */
225 int
mbfl_filt_conv_wchar_euctw(int c,mbfl_convert_filter * filter)226 mbfl_filt_conv_wchar_euctw(int c, mbfl_convert_filter *filter)
227 {
228 int c1, s, plane;
229
230 s = 0;
231 if (c >= ucs_a1_cns11643_table_min && c < ucs_a1_cns11643_table_max) {
232 s = ucs_a1_cns11643_table[c - ucs_a1_cns11643_table_min];
233 } else if (c >= ucs_a2_cns11643_table_min && c < ucs_a2_cns11643_table_max) {
234 s = ucs_a2_cns11643_table[c - ucs_a2_cns11643_table_min];
235 } else if (c >= ucs_a3_cns11643_table_min && c < ucs_a3_cns11643_table_max) {
236 s = ucs_a3_cns11643_table[c - ucs_a3_cns11643_table_min];
237 } else if (c >= ucs_i_cns11643_table_min && c < ucs_i_cns11643_table_max) {
238 s = ucs_i_cns11643_table[c - ucs_i_cns11643_table_min];
239 } else if (c >= ucs_r_cns11643_table_min && c < ucs_r_cns11643_table_max) {
240 s = ucs_r_cns11643_table[c - ucs_r_cns11643_table_min];
241 }
242 if (s <= 0) {
243 c1 = c & ~MBFL_WCSPLANE_MASK;
244 if (c1 == MBFL_WCSPLANE_CNS11643) {
245 s = c & MBFL_WCSPLANE_MASK;
246 }
247 if (c == 0) {
248 s = 0;
249 } else if (s <= 0) {
250 s = -1;
251 }
252 }
253 if (s >= 0) {
254 plane = (s & 0x1f0000) >> 16;
255 if (plane <= 1){
256 if (s < 0x80) { /* latin */
257 CK((*filter->output_function)(s, filter->data));
258 } else {
259 s = (s & 0xffff) | 0x8080;
260 CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
261 CK((*filter->output_function)(s & 0xff, filter->data));
262 }
263 } else {
264 s = (0x8ea00000 + (plane << 16)) | ((s & 0xffff) | 0x8080);
265 CK((*filter->output_function)(0x8e , filter->data));
266 CK((*filter->output_function)((s >> 16) & 0xff, filter->data));
267 CK((*filter->output_function)((s >> 8) & 0xff, filter->data));
268 CK((*filter->output_function)(s & 0xff, filter->data));
269 }
270 } else {
271 if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
272 CK(mbfl_filt_conv_illegal_output(c, filter));
273 }
274 }
275 return c;
276 }
277
mbfl_filt_ident_euctw(int c,mbfl_identify_filter * filter)278 static int mbfl_filt_ident_euctw(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) { /* DBCS lead byte */
285 filter->status = 1;
286 } else if (c == 0x8e) { /* DBCS lead byte */
287 filter->status = 2;
288 } else { /* bad */
289 filter->flag = 1;
290 }
291 break;
292
293 case 1: /* got lead byte */
294 if (c < 0xa1 || c > 0xfe) { /* bad */
295 filter->flag = 1;
296 }
297 filter->status = 0;
298 break;
299
300 case 2: /* got lead byte */
301 if (c >= 0xa1 && c < 0xaf) { /* ok */
302 filter->status = 3;
303 } else {
304 filter->flag = 1; /* bad */
305 }
306 break;
307
308 case 3: /* got lead byte */
309 if (c < 0xa1 || c > 0xfe) { /* bad */
310 filter->flag = 1;
311 }
312 filter->status = 4;
313 break;
314
315 case 4: /* got lead byte */
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
330