1 /*----------------------------------------------------------------------*
2 * File: encoding.C
3 *----------------------------------------------------------------------*
4 *
5 * All portions of code are copyright by their respective author/s.
6 * Copyright (c) 2003-2006 Marc Lehmann <schmorp@schmorp.de>
7 *
8 * This program is free software; you can redistribute it and/or modify
9 * it under the terms of the GNU General Public License as published by
10 * the Free Software Foundation; either version 3 of the License, or
11 * (at your option) any later version.
12 *
13 * This program is distributed in the hope that it will be useful,
14 * but WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16 * GNU General Public License for more details.
17 *
18 * You should have received a copy of the GNU General Public License
19 * along with this program; if not, write to the Free Software
20 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
21 *----------------------------------------------------------------------*/
22
23 #include "../config.h"
24
25 #include "encoding.h"
26 #include "rxvtutil.h"
27
28 #include <stdlib.h>
29 #include <string.h>
30
31 static const struct n2cs {
32 const char *name;
33 codeset cs;
34 } n2cs[] = {
35 /* first one found is the normalized one */
36 { "ISO88591", CS_ISO8859_1 },
37 { "ISO8859PRIMARY", CS_ISO8859_1 }, // some stupid fonts use this (hi tigert)
38 { "ISO88592", CS_ISO8859_2 },
39 { "ISO88593", CS_ISO8859_3 },
40 { "ISO88594", CS_ISO8859_4 },
41 { "ISO88595", CS_ISO8859_5 },
42 { "ISO88596", CS_ISO8859_6 },
43 { "ISO88597", CS_ISO8859_7 },
44 { "ISO88598", CS_ISO8859_8 },
45 { "ISO88599", CS_ISO8859_9 },
46 { "ISO885910", CS_ISO8859_10 },
47 { "ISO885911", CS_ISO8859_11 },
48 { "ISO885913", CS_ISO8859_13 },
49 { "ISO885914", CS_ISO8859_14 },
50 { "ISO885915", CS_ISO8859_15 },
51 { "FCD885915", CS_ISO8859_15 },
52 { "ISO885916", CS_ISO8859_16 },
53
54 { "TIS620*", CS_ISO8859_11 }, // close enough
55
56 { "ISO10646*", CS_UNICODE },
57 { "UNICODE", CS_UNICODE },
58 { "UTF8", CS_UNICODE },
59
60 { "ASCII", CS_US_ASCII },
61 { "USASCII", CS_US_ASCII },
62 { "ANSIX341968", CS_US_ASCII },
63 { "ISO6461991IRV", CS_US_ASCII }, // older versions used the currency sign
64
65 { "KOI8R*", CS_KOI8_R },
66 { "GOST1976874*", CS_KOI8_R },
67 { "KOI8RU", CS_KOI8_U },
68 { "KOI8U", CS_KOI8_U },
69
70 { "VISCII*", CS_VISCII },
71
72 { "JISX0201*", CS_JIS0201_1976_0 },
73 { "JISC6226*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
74 { "JISX0208*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
75 { "JISX0212*", CS_JIS0212_1990_0 },
76 { "JISX021320001", CS_JIS0213_1 },
77 { "JISX021320002", CS_JIS0213_2 },
78 { "JISX0221*", CS_UNICODE }, // _very_ close
79
80 { "KSC5601*", CS_KSC5601_1987_0 },
81 { "KSX1001*", CS_KSC5601_1987_0 },
82 { "KSC5700*", CS_UNICODE }, // unicode plus extensions
83
84 { "BIG5P*", CS_BIG5_PLUS },
85 { "BIG5ETEN*", CS_BIG5_EXT },
86 { "BIG5*", CS_BIG5 },
87 { "GB2312*", CS_GB2312_1980_0 },
88 { "GBK*", CS_GBK_0 },
89 { "GB6345*", CS_GB2312_1980_0 }, // slightly different to gb2312??
90 { "GB8565*", CS_GB2312_1980_0 }, // a superset of gb2312??
91 { "GB13000*", CS_UNICODE },
92 { "CNS1164319921", CS_CNS11643_1992_1 },
93 { "CNS1164319922", CS_CNS11643_1992_2 },
94 { "CNS1164319923", CS_CNS11643_1992_3 },
95 { "CNS1164319924", CS_CNS11643_1992_4 },
96 { "CNS1164319925", CS_CNS11643_1992_5 },
97 { "CNS1164319926", CS_CNS11643_1992_6 },
98 { "CNS1164319927", CS_CNS11643_1992_7 },
99 { "CNS116431992F", CS_CNS11643_1992_F },
100
101 { 0, CS_UNKNOWN }
102 };
103
104 static const char *
normalize_name(const char * name)105 normalize_name (const char *name)
106 {
107 static char res[16];
108 char *r;
109
110 for (r = res; *name && r < res + 15; name++)
111 if ((*name >= '0' && *name <= '9')
112 || (*name >= 'A' && *name <= 'Z'))
113 *r++ = *name;
114 else if (*name >= 'a' && *name <= 'z')
115 *r++ = *name - ('a' - 'A');
116
117 *r = 0;
118
119 return res;
120 }
121
122 codeset
codeset_from_name(const char * name)123 codeset_from_name (const char *name)
124 {
125 if (!name)
126 return CS_UNKNOWN;
127
128 name = normalize_name (name);
129
130 const struct n2cs *i = n2cs;
131
132 do {
133 int len = strlen (i->name);
134
135 if ((i->name[len - 1] == '*'
136 && !strncmp (name, i->name, len - 1))
137 || !strcmp (name, i->name))
138 return i->cs;
139
140 } while ((++i)->name);
141
142 return CS_UNKNOWN;
143 }
144
cs_unknown_to_unicode(uint32_t enc)145 static unicode_t cs_unknown_to_unicode (uint32_t enc) { return NOCHAR; }
cs_unknown_from_unicode(unicode_t unicode)146 static uint32_t cs_unknown_from_unicode (unicode_t unicode) { return NOCHAR; }
147
cs_unicode_to_unicode(uint32_t enc)148 static unicode_t cs_unicode_to_unicode (uint32_t enc) { return enc; }
cs_unicode_from_unicode(unicode_t unicode)149 static uint32_t cs_unicode_from_unicode (unicode_t unicode) { return unicode; }
150
151 #define cs_us_ascii_to_unicode cs_unicode_to_unicode
cs_us_ascii_from_unicode(unicode_t unicode)152 static uint32_t cs_us_ascii_from_unicode (unicode_t unicode) { return unicode <= 127 ? unicode : NOCHAR; }
153
154 #define cs_us_ascii_to_unicode_16 cs_unicode_to_unicode
cs_unicode_16_to_unicode(uint32_t enc)155 static unicode_t cs_unicode_16_to_unicode (uint32_t enc) { return enc <= 65535 ? enc : NOCHAR; }
cs_unicode_16_from_unicode(unicode_t unicode)156 static uint32_t cs_unicode_16_from_unicode (unicode_t unicode) { return unicode <= 65535 ? unicode : NOCHAR; }
157
158 #define ENCODING_DEFAULT
159
160 #include "table/iso8859_1.h"
161 #include "table/iso8859_15.h"
162
163 //#define ENCODING_EU
164
165 #include "table/iso8859_2.h"
166 #include "table/iso8859_3.h"
167 #include "table/iso8859_4.h"
168 #include "table/iso8859_5.h"
169 #include "table/iso8859_6.h"
170 #include "table/iso8859_7.h"
171 #include "table/iso8859_8.h"
172 #include "table/iso8859_9.h"
173 #include "table/iso8859_10.h"
174 #include "table/iso8859_11.h"
175 #include "table/iso8859_13.h"
176 #include "table/iso8859_14.h"
177 #include "table/iso8859_16.h"
178
179 #include "table/koi8_r.h"
180 #include "table/koi8_u.h"
181
182 //#define ENCODING_KR
183
184 #include "table/ksc5601_1987_0.h"
185
186 //#define ENCODING_ZH
187
188 #include "table/big5.h"
189 #include "table/gbk_0.h"
190 #include "table/gb2312_1980_0.h"
191
192 //#define ENCODING_ZH_EXT
193
194 #include "table/cns11643_1992_1.h"
195 #include "table/cns11643_1992_2.h"
196 #include "table/cns11643_1992_3.h"
197 #include "table/cns11643_1992_4.h"
198 #include "table/cns11643_1992_5.h"
199 #include "table/cns11643_1992_6.h"
200 #include "table/cns11643_1992_7.h"
201 #include "table/cns11643_1992_f.h"
202 #include "table/big5_ext.h"
203 #include "table/big5_plus.h"
204
205 //#define ENCODING_VN
206
207 #include "table/viscii.h"
208
209 //#define ENCODING_JP
210
211 #include "table/jis0201_1976_0.h"
212 #include "table/jis0208_1990_0.h"
213 #include "table/jis0212_1990_0.h"
214
215 //#define ENCODING_JP_EXT
216
217 #include "table/jis0213_1.h"
218 #include "table/jis0213_2.h"
219
220 #if ENCODING_TO_UNICODE
221 # define ENC(base) { cs_ ## base ## _from_unicode, cs_ ## base ## _to_unicode }
222 #else
223 # define ENC(base) { cs_ ## base ## _from_unicode }
224 #endif
225
226
227 // order must match table in encoding.h(!)
228 const rxvt_codeset_conv rxvt_codeset[NUM_CODESETS] = {
229 ENC (unknown),
230
231 ENC (us_ascii),
232
233 ENC (iso8859_1),
234 ENC (iso8859_2),
235 ENC (iso8859_3),
236 ENC (iso8859_4),
237 ENC (iso8859_5),
238 ENC (iso8859_6),
239 ENC (iso8859_7),
240 ENC (iso8859_8),
241 ENC (iso8859_9),
242 ENC (iso8859_10),
243 ENC (iso8859_11),
244 ENC (iso8859_13),
245 ENC (iso8859_14),
246 ENC (iso8859_15),
247 ENC (iso8859_16),
248
249 ENC (koi8_r),
250 ENC (koi8_u),
251
252 ENC (jis0201_1976_0),
253 ENC (jis0208_1990_0),
254 ENC (jis0212_1990_0),
255
256 ENC (jis0213_1),
257 ENC (jis0213_2),
258
259 ENC (ksc5601_1987_0),
260
261 ENC (gb2312_1980_0),
262 ENC (gbk_0),
263
264 ENC (cns11643_1992_1),
265 ENC (cns11643_1992_2),
266 ENC (cns11643_1992_3),
267 ENC (cns11643_1992_4),
268 ENC (cns11643_1992_5),
269 ENC (cns11643_1992_6),
270 ENC (cns11643_1992_7),
271 ENC (cns11643_1992_f),
272 ENC (big5),
273 ENC (big5_ext),
274 ENC (big5_plus),
275
276 ENC (viscii),
277
278 ENC (unicode_16),
279 ENC (unicode),
280 };
281
282 #if ENABLE_COMBINING
283 # define ENCODING_COMPOSE
284 #endif
285
286 #include "table/compose.h"
287
288 unicode_t
rxvt_compose(unicode_t c1,unicode_t c2)289 rxvt_compose (unicode_t c1, unicode_t c2)
290 {
291 int l = 0;
292 int r = ecb_array_length (rxvt_compose_table) - 1;
293 int m;
294
295 while (r >= l)
296 {
297 m = (l + r) / 2;
298 rxvt_compose_entry &c = rxvt_compose_table[m];
299
300 if (c.c1 < c1 || (c.c1 == c1 && c.c2 < c2))
301 l = m + 1;
302 else if (c.c1 > c1 || (c.c1 == c1 && c.c2 > c2))
303 r = m - 1;
304 else
305 return c.r;
306 }
307
308 return NOCHAR;
309 }
310
311 #include "table/category.h"
312
is_space(unicode_t c)313 bool unicode::is_space (unicode_t c)
314 {
315 return IS_SPACE (c)
316 || c == 0x09; // exclude tabs, too, as we store them in the buffer
317 }
318