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_win.h"
36
37 #include "unicode_table_cp932_ext.h"
38 #include "unicode_table_jis.h"
39 #include "cp932_table.h"
40
41 static int mbfl_filt_ident_eucjp_win(int c, mbfl_identify_filter *filter);
42
43 static const unsigned char mblen_table_eucjp[] = { /* 0xA1-0xFE */
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, 1, 1,
52 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 3,
53 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
54 1, 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, 2,
59 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1
60 };
61
62
63 static const char *mbfl_encoding_eucjp_win_aliases[] = {"eucJP-open",
64 "eucJP-ms", NULL};
65
66 const struct mbfl_identify_vtbl vtbl_identify_eucjpwin = {
67 mbfl_no_encoding_eucjp_win,
68 mbfl_filt_ident_common_ctor,
69 mbfl_filt_ident_common_dtor,
70 mbfl_filt_ident_eucjp_win
71 };
72
73 const mbfl_encoding mbfl_encoding_eucjp_win = {
74 mbfl_no_encoding_eucjp_win,
75 "eucJP-win",
76 "EUC-JP",
77 (const char *(*)[])&mbfl_encoding_eucjp_win_aliases,
78 mblen_table_eucjp,
79 MBFL_ENCTYPE_MBCS
80 };
81
82 const struct mbfl_convert_vtbl vtbl_eucjpwin_wchar = {
83 mbfl_no_encoding_eucjp_win,
84 mbfl_no_encoding_wchar,
85 mbfl_filt_conv_common_ctor,
86 mbfl_filt_conv_common_dtor,
87 mbfl_filt_conv_eucjpwin_wchar,
88 mbfl_filt_conv_common_flush
89 };
90
91 const struct mbfl_convert_vtbl vtbl_wchar_eucjpwin = {
92 mbfl_no_encoding_wchar,
93 mbfl_no_encoding_eucjp_win,
94 mbfl_filt_conv_common_ctor,
95 mbfl_filt_conv_common_dtor,
96 mbfl_filt_conv_wchar_eucjpwin,
97 mbfl_filt_conv_common_flush
98 };
99
100 #define CK(statement) do { if ((statement) < 0) return (-1); } while (0)
101
102 /*
103 * eucJP-win => wchar
104 */
105 int
mbfl_filt_conv_eucjpwin_wchar(int c,mbfl_convert_filter * filter)106 mbfl_filt_conv_eucjpwin_wchar(int c, mbfl_convert_filter *filter)
107 {
108 int c1, s, w, n;
109
110 switch (filter->status) {
111 case 0:
112 if (c >= 0 && c < 0x80) { /* latin */
113 CK((*filter->output_function)(c, filter->data));
114 } else if (c > 0xa0 && c < 0xff) { /* CP932 first char */
115 filter->status = 1;
116 filter->cache = c;
117 } else if (c == 0x8e) { /* kana first char */
118 filter->status = 2;
119 } else if (c == 0x8f) { /* X 0212 first char */
120 filter->status = 3;
121 } else {
122 w = c & MBFL_WCSGROUP_MASK;
123 w |= MBFL_WCSGROUP_THROUGH;
124 CK((*filter->output_function)(w, filter->data));
125 }
126 break;
127
128 case 1: /* got first half */
129 filter->status = 0;
130 c1 = filter->cache;
131 if (c > 0xa0 && c < 0xff) {
132 w = 0;
133 s = (c1 - 0xa1)*94 + c - 0xa1;
134 if (s <= 137) {
135 if (s == 31) {
136 w = 0xff3c; /* FULLWIDTH REVERSE SOLIDUS */
137 } else if (s == 32) {
138 w = 0xff5e; /* FULLWIDTH TILDE */
139 } else if (s == 33) {
140 w = 0x2225; /* PARALLEL TO */
141 } else if (s == 60) {
142 w = 0xff0d; /* FULLWIDTH HYPHEN-MINUS */
143 } else if (s == 80) {
144 w = 0xffe0; /* FULLWIDTH CENT SIGN */
145 } else if (s == 81) {
146 w = 0xffe1; /* FULLWIDTH POUND SIGN */
147 } else if (s == 137) {
148 w = 0xffe2; /* FULLWIDTH NOT SIGN */
149 }
150 }
151 if (w == 0) {
152 if (s >= cp932ext1_ucs_table_min && s < cp932ext1_ucs_table_max) { /* vendor ext1 (13ku) */
153 w = cp932ext1_ucs_table[s - cp932ext1_ucs_table_min];
154 } else if (s >= 0 && s < jisx0208_ucs_table_size) { /* X 0208 */
155 w = jisx0208_ucs_table[s];
156 } else if (s >= (84 * 94)) { /* user (85ku - 94ku) */
157 w = s - (84 * 94) + 0xe000;
158 }
159 }
160 if (w <= 0) {
161 w = ((c1 & 0x7f) << 8) | (c & 0x7f);
162 w &= MBFL_WCSPLANE_MASK;
163 w |= MBFL_WCSPLANE_WINCP932;
164 }
165 CK((*filter->output_function)(w, filter->data));
166 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
167 CK((*filter->output_function)(c, filter->data));
168 } else {
169 w = (c1 << 8) | c;
170 w &= MBFL_WCSGROUP_MASK;
171 w |= MBFL_WCSGROUP_THROUGH;
172 CK((*filter->output_function)(w, filter->data));
173 }
174 break;
175
176 case 2: /* got 0x8e, X0201 kana */
177 filter->status = 0;
178 if (c > 0xa0 && c < 0xe0) {
179 w = 0xfec0 + c;
180 CK((*filter->output_function)(w, filter->data));
181 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
182 CK((*filter->output_function)(c, filter->data));
183 } else {
184 w = 0x8e00 | c;
185 w &= MBFL_WCSGROUP_MASK;
186 w |= MBFL_WCSGROUP_THROUGH;
187 CK((*filter->output_function)(w, filter->data));
188 }
189 break;
190
191 case 3: /* got 0x8f, X 0212 first char */
192 if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
193 CK((*filter->output_function)(c, filter->data));
194 filter->status = 0;
195 } else {
196 filter->status++;
197 filter->cache = c;
198 }
199 break;
200 case 4: /* got 0x8f, X 0212 second char */
201 filter->status = 0;
202 c1 = filter->cache;
203 if (c1 > 0xa0 && c1 < 0xff && c > 0xa0 && c < 0xff) {
204 s = (c1 - 0xa1)*94 + c - 0xa1;
205 if (s >= 0 && s < jisx0212_ucs_table_size) {
206 w = jisx0212_ucs_table[s];
207 if (w == 0x007e) {
208 w = 0xff5e; /* FULLWIDTH TILDE */
209 }
210 } else if (s >= (82*94) && s < (84*94)) { /* vender ext3 (83ku - 84ku) <-> CP932 (115ku -120ku) */
211 s = (c1<< 8) | c;
212 w = 0;
213 n = 0;
214 while (n < cp932ext3_eucjp_table_size) {
215 if (s == cp932ext3_eucjp_table[n]) {
216 if (n < (cp932ext3_ucs_table_max - cp932ext3_ucs_table_min)) {
217 w = cp932ext3_ucs_table[n];
218 }
219 break;
220 }
221 n++;
222 }
223 } else if (s >= (84*94)) { /* user (85ku - 94ku) */
224 w = s - (84*94) + (0xe000 + (94*10));
225 } else {
226 w = 0;
227 }
228 if (w == 0x00A6) {
229 w = 0xFFE4; /* FULLWIDTH BROKEN BAR */
230 }
231 if (w <= 0) {
232 w = ((c1 & 0x7f) << 8) | (c & 0x7f);
233 w &= MBFL_WCSPLANE_MASK;
234 w |= MBFL_WCSPLANE_JIS0212;
235 }
236 CK((*filter->output_function)(w, filter->data));
237 } else if ((c >= 0 && c < 0x21) || c == 0x7f) { /* CTLs */
238 CK((*filter->output_function)(c, filter->data));
239 } else {
240 w = (c1 << 8) | c | 0x8f0000;
241 w &= MBFL_WCSGROUP_MASK;
242 w |= MBFL_WCSGROUP_THROUGH;
243 CK((*filter->output_function)(w, filter->data));
244 }
245 break;
246
247 default:
248 filter->status = 0;
249 break;
250 }
251
252 return c;
253 }
254
255 /*
256 * wchar => eucJP-win
257 */
258 int
mbfl_filt_conv_wchar_eucjpwin(int c,mbfl_convert_filter * filter)259 mbfl_filt_conv_wchar_eucjpwin(int c, mbfl_convert_filter *filter)
260 {
261 int c1, c2, s1;
262
263 s1 = 0;
264 if (c >= ucs_a1_jis_table_min && c < ucs_a1_jis_table_max) {
265 s1 = ucs_a1_jis_table[c - ucs_a1_jis_table_min];
266 } else if (c >= ucs_a2_jis_table_min && c < ucs_a2_jis_table_max) {
267 s1 = ucs_a2_jis_table[c - ucs_a2_jis_table_min];
268 } else if (c >= ucs_i_jis_table_min && c < ucs_i_jis_table_max) {
269 s1 = ucs_i_jis_table[c - ucs_i_jis_table_min];
270 } else if (c >= ucs_r_jis_table_min && c < ucs_r_jis_table_max) {
271 s1 = ucs_r_jis_table[c - ucs_r_jis_table_min];
272 } else if (c >= 0xe000 && c < (0xe000 + 10*94)) { /* user (X0208 85ku - 94ku) */
273 s1 = c - 0xe000;
274 c1 = s1/94 + 0x75;
275 c2 = s1%94 + 0x21;
276 s1 = (c1 << 8) | c2;
277 } else if (c >= (0xe000 + 10*94) && c < (0xe000 + 20*94)) { /* user (X0212 85ku - 94ku) */
278 s1 = c - (0xe000 + 10*94);
279 c1 = s1/94 + 0xf5;
280 c2 = s1%94 + 0xa1;
281 s1 = (c1 << 8) | c2;
282 }
283 if (s1 == 0xa2f1) {
284 s1 = 0x2d62; /* NUMERO SIGN */
285 }
286 if (s1 <= 0) {
287 c1 = c & ~MBFL_WCSPLANE_MASK;
288 if (c1 == MBFL_WCSPLANE_WINCP932) {
289 s1 = c & MBFL_WCSPLANE_MASK;
290 if (s1 >= ((85 + 0x20) << 8)) { /* 85ku - 120ku */
291 s1 = -1;
292 }
293 } else if (c1 == MBFL_WCSPLANE_JIS0208) {
294 s1 = c & MBFL_WCSPLANE_MASK;
295 if (s1 >= ((85 + 0x20) << 8)) { /* 85ku - 94ku */
296 s1 = -1;
297 }
298 } else if (c1 == MBFL_WCSPLANE_JIS0212) {
299 s1 = c & MBFL_WCSPLANE_MASK;
300 if (s1 >= ((83 + 0x20) << 8)) { /* 83ku - 94ku */
301 s1 = -1;
302 } else {
303 s1 |= 0x8080;
304 }
305 } else if (c == 0xa5) { /* YEN SIGN */
306 s1 = 0x216f; /* FULLWIDTH YEN SIGN */
307 } else if (c == 0x203e) { /* OVER LINE */
308 s1 = 0x2131; /* FULLWIDTH MACRON */
309 } else if (c == 0xff3c) { /* FULLWIDTH REVERSE SOLIDUS */
310 s1 = 0x2140;
311 } else if (c == 0xff5e) { /* FULLWIDTH TILDE */
312 s1 = 0x2141;
313 } else if (c == 0x2225) { /* PARALLEL TO */
314 s1 = 0x2142;
315 } else if (c == 0xff0d) { /* FULLWIDTH HYPHEN-MINUS */
316 s1 = 0x215d;
317 } else if (c == 0xffe0) { /* FULLWIDTH CENT SIGN */
318 s1 = 0x2171;
319 } else if (c == 0xffe1) { /* FULLWIDTH POUND SIGN */
320 s1 = 0x2172;
321 } else if (c == 0xffe2) { /* FULLWIDTH NOT SIGN */
322 s1 = 0x224c;
323 } else if (c == 0xff5e) { /* FULLWIDTH TILDE */
324 s1 = 0x2141;
325 } else {
326 s1 = -1;
327 c1 = 0;
328 c2 = cp932ext1_ucs_table_max - cp932ext1_ucs_table_min;
329 while (c1 < c2) { /* CP932 vendor ext1 (13ku) */
330 const int oh = cp932ext1_ucs_table_min / 94;
331
332 if (c == cp932ext1_ucs_table[c1]) {
333 s1 = ((c1 / 94 + oh + 0x21) << 8) + (c1 % 94 + 0x21);
334 break;
335 }
336 c1++;
337 }
338 if (s1 < 0) {
339 c1 = 0;
340 c2 = cp932ext3_ucs_table_max - cp932ext3_ucs_table_min;
341 while (c1 < c2) { /* CP932 vendor ext3 (115ku - 119ku) */
342 if (c == cp932ext3_ucs_table[c1]) {
343 if (c1 < cp932ext3_eucjp_table_size) {
344 s1 = cp932ext3_eucjp_table[c1];
345 }
346 break;
347 }
348 c1++;
349 }
350 }
351 }
352 if (c == 0) {
353 s1 = 0;
354 } else if (s1 <= 0) {
355 s1 = -1;
356 }
357 }
358
359 if (s1 >= 0) {
360 if (s1 < 0x80) { /* latin */
361 CK((*filter->output_function)(s1, filter->data));
362 } else if (s1 < 0x100) { /* kana */
363 CK((*filter->output_function)(0x8e, filter->data));
364 CK((*filter->output_function)(s1, filter->data));
365 } else if (s1 < 0x8080) { /* X 0208 */
366 CK((*filter->output_function)(((s1 >> 8) & 0xff) | 0x80, filter->data));
367 CK((*filter->output_function)((s1 & 0xff) | 0x80, filter->data));
368 } else { /* X 0212 */
369 CK((*filter->output_function)(0x8f, filter->data));
370 CK((*filter->output_function)(((s1 >> 8) & 0xff) | 0x80, filter->data));
371 CK((*filter->output_function)((s1 & 0xff) | 0x80, filter->data));
372 }
373 } else {
374 if (filter->illegal_mode != MBFL_OUTPUTFILTER_ILLEGAL_MODE_NONE) {
375 CK(mbfl_filt_conv_illegal_output(c, filter));
376 }
377 }
378
379 return c;
380 }
381
mbfl_filt_ident_eucjp_win(int c,mbfl_identify_filter * filter)382 static int mbfl_filt_ident_eucjp_win(int c, mbfl_identify_filter *filter)
383 {
384 switch (filter->status) {
385 case 0: /* latin */
386 if (c >= 0 && c < 0x80) { /* ok */
387 ;
388 } else if (c > 0xa0 && c < 0xff) { /* kanji first char */
389 filter->status = 1;
390 } else if (c == 0x8e) { /* kana first char */
391 filter->status = 2;
392 } else if (c == 0x8f) { /* X 0212 first char */
393 filter->status = 3;
394 } else { /* bad */
395 filter->flag = 1;
396 }
397 break;
398
399 case 1: /* got first half */
400 if (c < 0xa1 || c > 0xfe) { /* bad */
401 filter->flag = 1;
402 }
403 filter->status = 0;
404 break;
405
406 case 2: /* got 0x8e */
407 if (c < 0xa1 || c > 0xdf) { /* bad */
408 filter->flag = 1;
409 }
410 filter->status = 0;
411 break;
412
413 case 3: /* got 0x8f */
414 if (c < 0xa1 || c > 0xfe) { /* bad */
415 filter->flag = 1;
416 }
417 filter->status++;
418 break;
419 case 4: /* got 0x8f */
420 if (c < 0xa1 || c > 0xfe) { /* bad */
421 filter->flag = 1;
422 }
423 filter->status = 0;
424 break;
425
426 default:
427 filter->status = 0;
428 break;
429 }
430
431 return c;
432 }
433
434
435