1 |
root |
1.25 |
/*----------------------------------------------------------------------* |
2 |
pcg |
1.16 |
* File: encoding.C |
3 |
|
|
*----------------------------------------------------------------------* |
4 |
|
|
* |
5 |
|
|
* All portions of code are copyright by their respective author/s. |
6 |
root |
1.24 |
* Copyright (c) 2003-2006 Marc Lehmann <pcg@goof.com> |
7 |
pcg |
1.16 |
* |
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 2 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 |
pcg |
1.1 |
#include "../config.h" |
24 |
|
|
|
25 |
|
|
#include "encoding.h" |
26 |
|
|
|
27 |
|
|
#include <cstdlib> |
28 |
|
|
#include <cstring> |
29 |
|
|
|
30 |
|
|
const struct n2cs { |
31 |
|
|
const char *name; |
32 |
|
|
codeset cs; |
33 |
|
|
} n2cs[] = { |
34 |
|
|
/* first one found is the normalized one */ |
35 |
pcg |
1.3 |
{ "ISO88591", CS_ISO8859_1 }, |
36 |
|
|
{ "ISO8859PRIMARY", CS_ISO8859_1 }, // some stupid fonts use this (hi tigert) |
37 |
|
|
{ "ISO88592", CS_ISO8859_2 }, |
38 |
|
|
{ "ISO88593", CS_ISO8859_3 }, |
39 |
|
|
{ "ISO88594", CS_ISO8859_4 }, |
40 |
|
|
{ "ISO88595", CS_ISO8859_5 }, |
41 |
|
|
{ "ISO88596", CS_ISO8859_6 }, |
42 |
|
|
{ "ISO88597", CS_ISO8859_7 }, |
43 |
|
|
{ "ISO88598", CS_ISO8859_8 }, |
44 |
|
|
{ "ISO88599", CS_ISO8859_9 }, |
45 |
|
|
{ "ISO885910", CS_ISO8859_10 }, |
46 |
|
|
{ "ISO885911", CS_ISO8859_11 }, |
47 |
|
|
{ "ISO885913", CS_ISO8859_13 }, |
48 |
|
|
{ "ISO885914", CS_ISO8859_14 }, |
49 |
|
|
{ "ISO885915", CS_ISO8859_15 }, |
50 |
|
|
{ "FCD885915", CS_ISO8859_15 }, |
51 |
|
|
{ "ISO885916", CS_ISO8859_16 }, |
52 |
ayin |
1.26 |
|
53 |
pcg |
1.9 |
{ "TIS620*", CS_ISO8859_11 }, // close enough |
54 |
|
|
|
55 |
pcg |
1.3 |
{ "ISO10646*", CS_UNICODE }, |
56 |
|
|
{ "UNICODE", CS_UNICODE }, |
57 |
|
|
{ "UTF8", CS_UNICODE }, |
58 |
ayin |
1.26 |
|
59 |
pcg |
1.3 |
{ "ASCII", CS_US_ASCII }, |
60 |
|
|
{ "USASCII", CS_US_ASCII }, |
61 |
|
|
{ "ANSIX341968", CS_US_ASCII }, |
62 |
root |
1.28 |
{ "ISO6461991IRV", CS_US_ASCII }, // older versions used the currency sign |
63 |
ayin |
1.26 |
|
64 |
root |
1.22 |
{ "KOI8R*", CS_KOI8_R }, |
65 |
pcg |
1.3 |
{ "GOST1976874*", CS_KOI8_R }, |
66 |
|
|
{ "KOI8RU", CS_KOI8_U }, |
67 |
|
|
{ "KOI8U", CS_KOI8_U }, |
68 |
|
|
|
69 |
|
|
{ "VISCII*", CS_VISCII }, |
70 |
ayin |
1.26 |
|
71 |
pcg |
1.3 |
{ "JISX0201*", CS_JIS0201_1976_0 }, |
72 |
root |
1.17 |
{ "JISC6226*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP) |
73 |
pcg |
1.15 |
{ "JISX0208*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP) |
74 |
pcg |
1.3 |
{ "JISX0212*", CS_JIS0212_1990_0 }, |
75 |
pcg |
1.15 |
{ "JISX021320001", CS_JIS0213_1 }, |
76 |
|
|
{ "JISX021320002", CS_JIS0213_2 }, |
77 |
|
|
{ "JISX0221*", CS_UNICODE }, // _very_ close |
78 |
ayin |
1.26 |
|
79 |
pcg |
1.3 |
{ "KSC5601*", CS_KSC5601_1987_0 }, |
80 |
|
|
{ "KSX1001*", CS_KSC5601_1987_0 }, |
81 |
|
|
{ "KSC5700*", CS_UNICODE }, // unicode plus extensions |
82 |
ayin |
1.26 |
|
83 |
pcg |
1.3 |
{ "BIG5P*", CS_BIG5_PLUS }, |
84 |
|
|
{ "BIG5ETEN*", CS_BIG5_EXT }, |
85 |
|
|
{ "BIG5*", CS_BIG5 }, |
86 |
|
|
{ "GB2312*", CS_GB2312_1980_0 }, |
87 |
root |
1.21 |
{ "GBK*", CS_GBK_0 }, |
88 |
pcg |
1.3 |
{ "GB6345*", CS_GB2312_1980_0 }, // slightly different to gb2312?? |
89 |
|
|
{ "GB8565*", CS_GB2312_1980_0 }, // a superset of gb2312?? |
90 |
|
|
{ "GB13000*", CS_UNICODE }, |
91 |
|
|
{ "CNS1164319921", CS_CNS11643_1992_1 }, |
92 |
|
|
{ "CNS1164319922", CS_CNS11643_1992_2 }, |
93 |
|
|
{ "CNS1164319923", CS_CNS11643_1992_3 }, |
94 |
|
|
{ "CNS1164319924", CS_CNS11643_1992_4 }, |
95 |
|
|
{ "CNS1164319925", CS_CNS11643_1992_5 }, |
96 |
|
|
{ "CNS1164319926", CS_CNS11643_1992_6 }, |
97 |
|
|
{ "CNS1164319927", CS_CNS11643_1992_7 }, |
98 |
|
|
{ "CNS116431992F", CS_CNS11643_1992_F }, |
99 |
pcg |
1.1 |
|
100 |
|
|
{ 0, CS_UNKNOWN } |
101 |
|
|
}; |
102 |
|
|
|
103 |
|
|
static const char * |
104 |
|
|
normalize_name (const char *name) |
105 |
|
|
{ |
106 |
|
|
static char res[16]; |
107 |
|
|
char *r; |
108 |
|
|
|
109 |
|
|
for (r = res; *name && r < res + 15; name++) |
110 |
|
|
if ((*name >= '0' && *name <= '9') |
111 |
|
|
|| (*name >= 'A' && *name <= 'Z')) |
112 |
|
|
*r++ = *name; |
113 |
|
|
else if (*name >= 'a' && *name <= 'z') |
114 |
|
|
*r++ = *name - ('a' - 'A'); |
115 |
|
|
|
116 |
|
|
*r = 0; |
117 |
|
|
|
118 |
|
|
return res; |
119 |
|
|
} |
120 |
|
|
|
121 |
|
|
codeset |
122 |
|
|
codeset_from_name (const char *name) |
123 |
|
|
{ |
124 |
|
|
if (!name) |
125 |
|
|
return CS_UNKNOWN; |
126 |
|
|
|
127 |
|
|
name = normalize_name (name); |
128 |
|
|
|
129 |
|
|
const struct n2cs *i = n2cs; |
130 |
|
|
|
131 |
|
|
do { |
132 |
pcg |
1.3 |
int len = strlen (i->name); |
133 |
|
|
|
134 |
|
|
if ((i->name[len - 1] == '*' |
135 |
|
|
&& !strncmp (name, i->name, len - 1)) |
136 |
|
|
|| !strcmp (name, i->name)) |
137 |
|
|
return i->cs; |
138 |
|
|
|
139 |
pcg |
1.1 |
} while ((++i)->name); |
140 |
|
|
|
141 |
|
|
return CS_UNKNOWN; |
142 |
|
|
} |
143 |
|
|
|
144 |
root |
1.18 |
static unicode_t cs_unknown_to_unicode (uint32_t enc) { return NOCHAR; } |
145 |
|
|
static uint32_t cs_unknown_from_unicode (unicode_t unicode) { return NOCHAR; } |
146 |
|
|
|
147 |
|
|
static unicode_t cs_unicode_to_unicode (uint32_t enc) { return enc; } |
148 |
|
|
static uint32_t cs_unicode_from_unicode (unicode_t unicode) { return unicode; } |
149 |
|
|
|
150 |
|
|
#define cs_us_ascii_to_unicode cs_unicode_to_unicode |
151 |
|
|
static uint32_t cs_us_ascii_from_unicode (unicode_t unicode) { return unicode <= 127 ? unicode : NOCHAR; } |
152 |
|
|
|
153 |
|
|
#define cs_us_ascii_to_unicode_16 cs_unicode_to_unicode |
154 |
|
|
static uint32_t cs_unicode_16_from_unicode (unicode_t unicode) { return unicode <= 65535 ? unicode : NOCHAR; } |
155 |
pcg |
1.1 |
|
156 |
|
|
#define ENCODING_DEFAULT |
157 |
|
|
|
158 |
|
|
#include "table/iso8859_1.h" |
159 |
|
|
#include "table/iso8859_15.h" |
160 |
|
|
|
161 |
|
|
//#define ENCODING_EU |
162 |
|
|
|
163 |
|
|
#include "table/iso8859_2.h" |
164 |
|
|
#include "table/iso8859_3.h" |
165 |
|
|
#include "table/iso8859_4.h" |
166 |
|
|
#include "table/iso8859_5.h" |
167 |
|
|
#include "table/iso8859_6.h" |
168 |
|
|
#include "table/iso8859_7.h" |
169 |
|
|
#include "table/iso8859_8.h" |
170 |
|
|
#include "table/iso8859_9.h" |
171 |
|
|
#include "table/iso8859_10.h" |
172 |
|
|
#include "table/iso8859_11.h" |
173 |
|
|
#include "table/iso8859_13.h" |
174 |
|
|
#include "table/iso8859_14.h" |
175 |
|
|
#include "table/iso8859_16.h" |
176 |
|
|
|
177 |
|
|
#include "table/koi8_r.h" |
178 |
|
|
#include "table/koi8_u.h" |
179 |
|
|
|
180 |
|
|
//#define ENCODING_KR |
181 |
|
|
|
182 |
|
|
#include "table/ksc5601_1987_0.h" |
183 |
|
|
|
184 |
root |
1.20 |
//#define ENCODING_ZH |
185 |
pcg |
1.1 |
|
186 |
root |
1.21 |
#include "table/big5.h" |
187 |
|
|
#include "table/gbk_0.h" |
188 |
pcg |
1.1 |
#include "table/gb2312_1980_0.h" |
189 |
|
|
|
190 |
root |
1.20 |
//#define ENCODING_ZH_EXT |
191 |
pcg |
1.1 |
|
192 |
|
|
#include "table/cns11643_1992_1.h" |
193 |
|
|
#include "table/cns11643_1992_2.h" |
194 |
|
|
#include "table/cns11643_1992_3.h" |
195 |
|
|
#include "table/cns11643_1992_4.h" |
196 |
|
|
#include "table/cns11643_1992_5.h" |
197 |
|
|
#include "table/cns11643_1992_6.h" |
198 |
|
|
#include "table/cns11643_1992_7.h" |
199 |
|
|
#include "table/cns11643_1992_f.h" |
200 |
|
|
#include "table/big5_ext.h" |
201 |
|
|
#include "table/big5_plus.h" |
202 |
|
|
|
203 |
|
|
//#define ENCODING_VN |
204 |
|
|
|
205 |
|
|
#include "table/viscii.h" |
206 |
|
|
|
207 |
|
|
//#define ENCODING_JP |
208 |
|
|
|
209 |
|
|
#include "table/jis0201_1976_0.h" |
210 |
pcg |
1.15 |
#include "table/jis0208_1990_0.h" |
211 |
pcg |
1.1 |
#include "table/jis0212_1990_0.h" |
212 |
|
|
|
213 |
|
|
//#define ENCODING_JP_EXT |
214 |
|
|
|
215 |
|
|
#include "table/jis0213_1.h" |
216 |
|
|
#include "table/jis0213_2.h" |
217 |
|
|
|
218 |
root |
1.18 |
#if ENCODING_TO_UNICODE |
219 |
|
|
# define ENC(base) { cs_ ## base ## _from_unicode, cs_ ## base ## _to_unicode } |
220 |
|
|
#else |
221 |
|
|
# define ENC(base) { cs_ ## base ## _from_unicode } |
222 |
|
|
#endif |
223 |
ayin |
1.26 |
|
224 |
root |
1.18 |
|
225 |
pcg |
1.3 |
// order must match table in encoding.h(!) |
226 |
root |
1.18 |
const rxvt_codeset_conv rxvt_codeset[NUM_CODESETS] = { |
227 |
|
|
ENC (unknown), |
228 |
pcg |
1.1 |
|
229 |
root |
1.18 |
ENC (us_ascii), |
230 |
pcg |
1.1 |
|
231 |
root |
1.18 |
ENC (iso8859_1), |
232 |
|
|
ENC (iso8859_2), |
233 |
|
|
ENC (iso8859_3), |
234 |
|
|
ENC (iso8859_4), |
235 |
|
|
ENC (iso8859_5), |
236 |
|
|
ENC (iso8859_6), |
237 |
|
|
ENC (iso8859_7), |
238 |
|
|
ENC (iso8859_8), |
239 |
|
|
ENC (iso8859_9), |
240 |
|
|
ENC (iso8859_10), |
241 |
|
|
ENC (iso8859_11), |
242 |
|
|
ENC (iso8859_13), |
243 |
|
|
ENC (iso8859_14), |
244 |
|
|
ENC (iso8859_15), |
245 |
|
|
ENC (iso8859_16), |
246 |
|
|
|
247 |
|
|
ENC (koi8_r), |
248 |
|
|
ENC (koi8_u), |
249 |
|
|
|
250 |
|
|
ENC (jis0201_1976_0), |
251 |
|
|
ENC (jis0208_1990_0), |
252 |
|
|
ENC (jis0212_1990_0), |
253 |
|
|
|
254 |
|
|
ENC (jis0213_1), |
255 |
|
|
ENC (jis0213_2), |
256 |
|
|
|
257 |
|
|
ENC (ksc5601_1987_0), |
258 |
|
|
|
259 |
|
|
ENC (gb2312_1980_0), |
260 |
root |
1.21 |
ENC (gbk_0), |
261 |
root |
1.18 |
|
262 |
|
|
ENC (cns11643_1992_1), |
263 |
|
|
ENC (cns11643_1992_2), |
264 |
|
|
ENC (cns11643_1992_3), |
265 |
|
|
ENC (cns11643_1992_4), |
266 |
|
|
ENC (cns11643_1992_5), |
267 |
|
|
ENC (cns11643_1992_6), |
268 |
|
|
ENC (cns11643_1992_7), |
269 |
|
|
ENC (cns11643_1992_f), |
270 |
|
|
ENC (big5), |
271 |
|
|
ENC (big5_ext), |
272 |
|
|
ENC (big5_plus), |
273 |
pcg |
1.1 |
|
274 |
root |
1.18 |
ENC (viscii), |
275 |
pcg |
1.1 |
|
276 |
root |
1.18 |
ENC (unicode_16), |
277 |
|
|
ENC (unicode), |
278 |
pcg |
1.1 |
}; |
279 |
|
|
|
280 |
pcg |
1.10 |
#if ENABLE_COMBINING |
281 |
|
|
# define ENCODING_COMPOSE |
282 |
|
|
#endif |
283 |
pcg |
1.9 |
|
284 |
|
|
#include "table/compose.h" |
285 |
|
|
|
286 |
pcg |
1.15 |
unicode_t |
287 |
|
|
rxvt_compose (unicode_t c1, unicode_t c2) |
288 |
pcg |
1.9 |
{ |
289 |
|
|
int l = 0; |
290 |
|
|
int r = sizeof (rxvt_compose_table) / sizeof (rxvt_compose_entry) - 1; |
291 |
|
|
int m; |
292 |
|
|
|
293 |
root |
1.27 |
while (r >= l) |
294 |
pcg |
1.9 |
{ |
295 |
|
|
m = (l + r) / 2; |
296 |
|
|
rxvt_compose_entry &c = rxvt_compose_table[m]; |
297 |
|
|
|
298 |
|
|
if (c.c1 < c1 || (c.c1 == c1 && c.c2 < c2)) |
299 |
|
|
l = m + 1; |
300 |
|
|
else if (c.c1 > c1 || (c.c1 == c1 && c.c2 > c2)) |
301 |
|
|
r = m - 1; |
302 |
|
|
else |
303 |
|
|
return c.r; |
304 |
|
|
} |
305 |
|
|
|
306 |
|
|
return NOCHAR; |
307 |
|
|
} |
308 |
pcg |
1.15 |
|
309 |
|
|
#include "table/category.h" |
310 |
|
|
|
311 |
|
|
bool unicode::is_space (unicode_t c) |
312 |
|
|
{ |
313 |
root |
1.19 |
return IS_SPACE (c) |
314 |
|
|
|| c == 0x09; // exclude tabs, too, as we store them in the buffer |
315 |
pcg |
1.15 |
} |