ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/rxvt-unicode/src/encoding.C
(Generate patch)

Comparing rxvt-unicode/src/encoding.C (file contents):
Revision 1.1 by pcg, Mon Nov 24 17:28:08 2003 UTC vs.
Revision 1.34 by root, Thu May 22 18:54:32 2014 UTC

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
1#include "../config.h" 23#include "../config.h"
2 24
3#include "encoding.h" 25#include "encoding.h"
26#include "rxvtutil.h"
4 27
5#include <cstdlib> 28#include <stdlib.h>
6#include <cstring> 29#include <string.h>
7 30
8const struct n2cs { 31static const struct n2cs {
9 const char *name; 32 const char *name;
10 codeset cs; 33 codeset cs;
11} n2cs[] = { 34} n2cs[] = {
12 /* first one found is the normalized one */ 35 /* first one found is the normalized one */
13 { "ISO88591", CS_ISO8859_1 }, 36 { "ISO88591", CS_ISO8859_1 },
14 { "ISO8859PRIMARY", CS_ISO8859_1 }, // some stupid fonts use this (hi tigert) 37 { "ISO8859PRIMARY", CS_ISO8859_1 }, // some stupid fonts use this (hi tigert)
15 { "ISO88592", CS_ISO8859_2 }, 38 { "ISO88592", CS_ISO8859_2 },
16 { "ISO88593", CS_ISO8859_3 }, 39 { "ISO88593", CS_ISO8859_3 },
17 { "ISO88594", CS_ISO8859_4 }, 40 { "ISO88594", CS_ISO8859_4 },
18 { "ISO88595", CS_ISO8859_5 }, 41 { "ISO88595", CS_ISO8859_5 },
19 { "ISO88596", CS_ISO8859_6 }, 42 { "ISO88596", CS_ISO8859_6 },
20 { "ISO88597", CS_ISO8859_7 }, 43 { "ISO88597", CS_ISO8859_7 },
21 { "ISO88598", CS_ISO8859_8 }, 44 { "ISO88598", CS_ISO8859_8 },
22 { "ISO88599", CS_ISO8859_9 }, 45 { "ISO88599", CS_ISO8859_9 },
23 { "ISO885910", CS_ISO8859_10 }, 46 { "ISO885910", CS_ISO8859_10 },
24 { "ISO885911", CS_ISO8859_11 }, 47 { "ISO885911", CS_ISO8859_11 },
25 { "ISO885913", CS_ISO8859_13 }, 48 { "ISO885913", CS_ISO8859_13 },
26 { "ISO885914", CS_ISO8859_14 }, 49 { "ISO885914", CS_ISO8859_14 },
27 { "ISO885915", CS_ISO8859_15 }, 50 { "ISO885915", CS_ISO8859_15 },
28 { "FCD885915", CS_ISO8859_15 }, 51 { "FCD885915", CS_ISO8859_15 },
29 { "ISO885916", CS_ISO8859_16 }, 52 { "ISO885916", CS_ISO8859_16 },
30 53
54 { "TIS620*", CS_ISO8859_11 }, // close enough
55
31 { "ISO106461", CS_UNICODE }, 56 { "ISO10646*", CS_UNICODE },
32 { "UNICODE", CS_UNICODE }, 57 { "UNICODE", CS_UNICODE },
33 { "UTF8", CS_UNICODE }, 58 { "UTF8", CS_UNICODE },
34 59
35 { "ASCII", CS_US_ASCII }, 60 { "ASCII", CS_US_ASCII },
36 { "USASCII", CS_US_ASCII }, 61 { "USASCII", CS_US_ASCII },
37 { "ANSIX341968", CS_US_ASCII }, 62 { "ANSIX341968", CS_US_ASCII },
63 { "ISO6461991IRV", CS_US_ASCII }, // older versions used the currency sign
38 64
39 { "KOI8R", CS_KOI8_R }, 65 { "KOI8R*", CS_KOI8_R },
40 { "GOST19768741", CS_KOI8_R }, 66 { "GOST1976874*", CS_KOI8_R },
67 { "KOI8RU", CS_KOI8_U },
41 { "KOI8U", CS_KOI8_U }, 68 { "KOI8U", CS_KOI8_U },
42 69
43 { "KSC560119870", CS_KSC5601_1987_0 },
44 { "KSX100119970", CS_KSC5601_1987_0 },
45 { "KSX100119980", CS_KSC5601_1987_0 }, // adds johab
46
47 { "GB231219800", CS_GB2312_1980_0 },
48
49 { "VISCII", CS_VISCII }, 70 { "VISCII*", CS_VISCII },
50 { "VISCII111", CS_VISCII },
51 { "TIS62025291", CS_VISCII }, /* close enough */
52 71
53 { "JISX020119760", CS_JIS0201_1976_0 }, 72 { "JISX0201*", CS_JIS0201_1976_0 },
54 { "JISX020819830", CS_JIS0208_1983_0 }, 73 { "JISC6226*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
55 { "JISX020819900", CS_JIS0208_1983_0 }, /* ehrm. */ 74 { "JISX0208*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
56 { "JISX021219900", CS_JIS0212_1990_0 }, 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 },
57 100
58 { 0, CS_UNKNOWN } 101 { 0, CS_UNKNOWN }
59}; 102};
60 103
61static const char * 104static const char *
… …
85 name = normalize_name (name); 128 name = normalize_name (name);
86 129
87 const struct n2cs *i = n2cs; 130 const struct n2cs *i = n2cs;
88 131
89 do { 132 do {
133 int len = strlen (i->name);
134
135 if ((i->name[len - 1] == '*'
136 && !strncmp (name, i->name, len - 1))
90 if (!strcmp (name, i->name)) 137 || !strcmp (name, i->name))
91 return i->cs; 138 return i->cs;
139
92 } while ((++i)->name); 140 } while ((++i)->name);
93 141
94 return CS_UNKNOWN; 142 return CS_UNKNOWN;
95} 143}
96 144
97struct rxvt_codeset_conv_unknown : rxvt_codeset_conv { 145static unicode_t cs_unknown_to_unicode (uint32_t enc) { return NOCHAR; }
98 uint32_t to_unicode (uint32_t enc) const { return NOCHAR; }
99 uint32_t from_unicode (uint32_t unicode) const { return NOCHAR; } 146static uint32_t cs_unknown_from_unicode (unicode_t unicode) { return NOCHAR; }
100} rxvt_codeset_conv_unknown;
101 147
102struct rxvt_codeset_conv_us_ascii : rxvt_codeset_conv { 148static unicode_t cs_unicode_to_unicode (uint32_t enc) { return enc; }
149static uint32_t cs_unicode_from_unicode (unicode_t unicode) { return unicode; }
150
151#define cs_us_ascii_to_unicode cs_unicode_to_unicode
103 uint32_t from_unicode (uint32_t unicode) const { return unicode <= 127 ? unicode : NOCHAR; } 152static uint32_t cs_us_ascii_from_unicode (unicode_t unicode) { return unicode <= 127 ? unicode : NOCHAR; }
104} rxvt_codeset_conv_us_ascii;
105 153
106struct rxvt_codeset_conv_unicode : rxvt_codeset_conv { 154#define cs_us_ascii_to_unicode_16 cs_unicode_to_unicode
107 /* transparent */
108} rxvt_codeset_conv_unicode;
109
110struct rxvt_codeset_conv_unicode_16 : rxvt_codeset_conv {
111 uint32_t to_unicode (uint32_t enc) const { return enc; }
112 uint32_t from_unicode (uint32_t unicode) const { return unicode <= 65535 ? unicode : NOCHAR; } 155static uint32_t cs_unicode_16_from_unicode (unicode_t unicode) { return unicode <= 65535 ? unicode : NOCHAR; }
113} rxvt_codeset_conv_unicode_16;
114
115/* block character set, must conform to the dec special pseudofont in defaultfont.C */
116struct rxvt_codeset_conv_special : rxvt_codeset_conv {
117 uint32_t to_unicode (uint32_t enc) const {
118 return enc;
119 }
120
121 uint32_t from_unicode (uint32_t unicode) const {
122 return unicode;
123 }
124} rxvt_codeset_conv_special;
125 156
126#define ENCODING_DEFAULT 157#define ENCODING_DEFAULT
127 158
128#include "table/iso8859_1.h" 159#include "table/iso8859_1.h"
129#include "table/iso8859_15.h" 160#include "table/iso8859_15.h"
… …
149 180
150//#define ENCODING_KR 181//#define ENCODING_KR
151 182
152#include "table/ksc5601_1987_0.h" 183#include "table/ksc5601_1987_0.h"
153 184
154//#define ENCODING_CN 185//#define ENCODING_ZH
155 186
187#include "table/big5.h"
188#include "table/gbk_0.h"
156#include "table/gb2312_1980_0.h" 189#include "table/gb2312_1980_0.h"
157 190
158//#define ENCODING_CN_EXT 191//#define ENCODING_ZH_EXT
159 192
160#include "table/cns11643_1992_1.h" 193#include "table/cns11643_1992_1.h"
161#include "table/cns11643_1992_2.h" 194#include "table/cns11643_1992_2.h"
162#include "table/cns11643_1992_3.h" 195#include "table/cns11643_1992_3.h"
163#include "table/cns11643_1992_4.h" 196#include "table/cns11643_1992_4.h"
… …
173#include "table/viscii.h" 206#include "table/viscii.h"
174 207
175//#define ENCODING_JP 208//#define ENCODING_JP
176 209
177#include "table/jis0201_1976_0.h" 210#include "table/jis0201_1976_0.h"
178#include "table/jis0208_1983_0.h" 211#include "table/jis0208_1990_0.h"
179#include "table/jis0212_1990_0.h" 212#include "table/jis0212_1990_0.h"
180 213
181//#define ENCODING_JP_EXT 214//#define ENCODING_JP_EXT
182 215
183#include "table/jis0213_1.h" 216#include "table/jis0213_1.h"
184#include "table/jis0213_2.h" 217#include "table/jis0213_2.h"
185 218
219#if ENCODING_TO_UNICODE
220# define ENC(base) { cs_ ## base ## _from_unicode, cs_ ## base ## _to_unicode }
221#else
222# define ENC(base) { cs_ ## base ## _from_unicode }
223#endif
224
225
226// order must match table in encoding.h(!)
186const rxvt_codeset_conv *rxvt_codeset[NUM_CODESETS] = { 227const rxvt_codeset_conv rxvt_codeset[NUM_CODESETS] = {
187 &rxvt_codeset_conv_unknown, 228 ENC (unknown),
188 &rxvt_codeset_conv_special,
189 229
190 &rxvt_codeset_conv_us_ascii, 230 ENC (us_ascii),
191 231
192 &rxvt_codeset_conv_iso8859_1, 232 ENC (iso8859_1),
193 &rxvt_codeset_conv_iso8859_2, 233 ENC (iso8859_2),
194 &rxvt_codeset_conv_iso8859_3, 234 ENC (iso8859_3),
195 &rxvt_codeset_conv_iso8859_4, 235 ENC (iso8859_4),
196 &rxvt_codeset_conv_iso8859_5, 236 ENC (iso8859_5),
197 &rxvt_codeset_conv_iso8859_6, 237 ENC (iso8859_6),
198 &rxvt_codeset_conv_iso8859_7, 238 ENC (iso8859_7),
199 &rxvt_codeset_conv_iso8859_8, 239 ENC (iso8859_8),
200 &rxvt_codeset_conv_iso8859_9, 240 ENC (iso8859_9),
201 &rxvt_codeset_conv_iso8859_10, 241 ENC (iso8859_10),
202 &rxvt_codeset_conv_iso8859_11, 242 ENC (iso8859_11),
203 &rxvt_codeset_conv_iso8859_13, 243 ENC (iso8859_13),
204 &rxvt_codeset_conv_iso8859_14, 244 ENC (iso8859_14),
205 &rxvt_codeset_conv_iso8859_15, 245 ENC (iso8859_15),
206 &rxvt_codeset_conv_iso8859_16, 246 ENC (iso8859_16),
207 247
208 &rxvt_codeset_conv_koi8_r, 248 ENC (koi8_r),
209 &rxvt_codeset_conv_koi8_u, 249 ENC (koi8_u),
210 250
211 &rxvt_codeset_conv_jis0201_1976_0, 251 ENC (jis0201_1976_0),
212 &rxvt_codeset_conv_jis0208_1983_0, 252 ENC (jis0208_1990_0),
213 &rxvt_codeset_conv_jis0212_1990_0, 253 ENC (jis0212_1990_0),
214 254
215 &rxvt_codeset_conv_jis0213_1, 255 ENC (jis0213_1),
216 &rxvt_codeset_conv_jis0213_2, 256 ENC (jis0213_2),
217 257
218 &rxvt_codeset_conv_ksc5601_1987_0, 258 ENC (ksc5601_1987_0),
219 259
220 &rxvt_codeset_conv_gb2312_1980_0, 260 ENC (gb2312_1980_0),
261 ENC (gbk_0),
221 262
222 &rxvt_codeset_conv_cns11643_1992_1, 263 ENC (cns11643_1992_1),
223 &rxvt_codeset_conv_cns11643_1992_2, 264 ENC (cns11643_1992_2),
224 &rxvt_codeset_conv_cns11643_1992_3, 265 ENC (cns11643_1992_3),
225 &rxvt_codeset_conv_cns11643_1992_4, 266 ENC (cns11643_1992_4),
226 &rxvt_codeset_conv_cns11643_1992_5, 267 ENC (cns11643_1992_5),
227 &rxvt_codeset_conv_cns11643_1992_6, 268 ENC (cns11643_1992_6),
228 &rxvt_codeset_conv_cns11643_1992_7, 269 ENC (cns11643_1992_7),
229 &rxvt_codeset_conv_cns11643_1992_f, 270 ENC (cns11643_1992_f),
230 &rxvt_codeset_conv_big5_ext, 271 ENC (big5),
231 &rxvt_codeset_conv_big5_plus, 272 ENC (big5_ext),
273 ENC (big5_plus),
232 274
233 &rxvt_codeset_conv_viscii, 275 ENC (viscii),
234 276
235 &rxvt_codeset_conv_unicode_16, 277 ENC (unicode_16),
236 &rxvt_codeset_conv_unicode 278 ENC (unicode),
237}; 279};
238 280
281#if ENABLE_COMBINING
282# define ENCODING_COMPOSE
283#endif
284
285#include "table/compose.h"
286
287unicode_t
288rxvt_compose (unicode_t c1, unicode_t c2)
289{
290 int l = 0;
291 int r = ecb_array_length (rxvt_compose_table) - 1;
292 int m;
293
294 while (r >= l)
295 {
296 m = (l + r) / 2;
297 rxvt_compose_entry &c = rxvt_compose_table[m];
298
299 if (c.c1 < c1 || (c.c1 == c1 && c.c2 < c2))
300 l = m + 1;
301 else if (c.c1 > c1 || (c.c1 == c1 && c.c2 > c2))
302 r = m - 1;
303 else
304 return c.r;
305 }
306
307 return NOCHAR;
308}
309
310#include "table/category.h"
311
312bool unicode::is_space (unicode_t c)
313{
314 return IS_SPACE (c)
315 || c == 0x09; // exclude tabs, too, as we store them in the buffer
316}

Diff Legend

– Removed lines
+ Added lines
< Changed lines
> Changed lines