1 /*--------------------------------*-C-*---------------------------------*
3 *----------------------------------------------------------------------*
5 * All portions of code are copyright by their respective author/s.
6 * Copyright (c) 2003-2004 Marc Lehmann <pcg@goof.com>
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.
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.
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 *----------------------------------------------------------------------*/
23 #include "../config.h"
34 /* first one found is the normalized one */
35 { "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 },
53 { "TIS620*", CS_ISO8859_11 }, // close enough
55 { "ISO10646*", CS_UNICODE },
56 { "UNICODE", CS_UNICODE },
57 { "UTF8", CS_UNICODE },
59 { "ASCII", CS_US_ASCII },
60 { "USASCII", CS_US_ASCII },
61 { "ANSIX341968", CS_US_ASCII },
63 { "KOI8R", CS_KOI8_R },
64 { "GOST1976874*", CS_KOI8_R },
65 { "KOI8RU", CS_KOI8_U },
66 { "KOI8U", CS_KOI8_U },
68 { "VISCII*", CS_VISCII },
70 { "JISX0201*", CS_JIS0201_1976_0 },
71 { "JISC6226*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
72 { "JISX0208*", CS_JIS0208_1990_0 }, // also wrongly matches -1987-0? (check Encode::JP)
73 { "JISX0212*", CS_JIS0212_1990_0 },
74 { "JISX021320001", CS_JIS0213_1 },
75 { "JISX021320002", CS_JIS0213_2 },
76 { "JISX0221*", CS_UNICODE }, // _very_ close
78 { "KSC5601*", CS_KSC5601_1987_0 },
79 { "KSX1001*", CS_KSC5601_1987_0 },
80 { "KSC5700*", CS_UNICODE }, // unicode plus extensions
82 { "BIG5P*", CS_BIG5_PLUS },
83 { "BIG5ETEN*", CS_BIG5_EXT },
85 { "GB2312*", CS_GB2312_1980_0 },
87 { "GB6345*", CS_GB2312_1980_0 }, // slightly different to gb2312??
88 { "GB8565*", CS_GB2312_1980_0 }, // a superset of gb2312??
89 { "GB13000*", CS_UNICODE },
90 { "CNS1164319921", CS_CNS11643_1992_1 },
91 { "CNS1164319922", CS_CNS11643_1992_2 },
92 { "CNS1164319923", CS_CNS11643_1992_3 },
93 { "CNS1164319924", CS_CNS11643_1992_4 },
94 { "CNS1164319925", CS_CNS11643_1992_5 },
95 { "CNS1164319926", CS_CNS11643_1992_6 },
96 { "CNS1164319927", CS_CNS11643_1992_7 },
97 { "CNS116431992F", CS_CNS11643_1992_F },
103 normalize_name (const char *name)
108 for (r = res; *name && r < res + 15; name++)
109 if ((*name >= '0' && *name <= '9')
110 || (*name >= 'A' && *name <= 'Z'))
112 else if (*name >= 'a' && *name <= 'z')
113 *r++ = *name - ('a' - 'A');
121 codeset_from_name (const char *name)
126 name = normalize_name (name);
128 const struct n2cs *i = n2cs;
131 int len = strlen (i->name);
133 if ((i->name[len - 1] == '*'
134 && !strncmp (name, i->name, len - 1))
135 || !strcmp (name, i->name))
138 } while ((++i)->name);
143 static unicode_t cs_unknown_to_unicode (uint32_t enc) { return NOCHAR; }
144 static uint32_t cs_unknown_from_unicode (unicode_t unicode) { return NOCHAR; }
146 static unicode_t cs_unicode_to_unicode (uint32_t enc) { return enc; }
147 static uint32_t cs_unicode_from_unicode (unicode_t unicode) { return unicode; }
149 #define cs_us_ascii_to_unicode cs_unicode_to_unicode
150 static uint32_t cs_us_ascii_from_unicode (unicode_t unicode) { return unicode <= 127 ? unicode : NOCHAR; }
152 #define cs_us_ascii_to_unicode_16 cs_unicode_to_unicode
153 static uint32_t cs_unicode_16_from_unicode (unicode_t unicode) { return unicode <= 65535 ? unicode : NOCHAR; }
155 #define ENCODING_DEFAULT
157 #include "table/iso8859_1.h"
158 #include "table/iso8859_15.h"
160 //#define ENCODING_EU
162 #include "table/iso8859_2.h"
163 #include "table/iso8859_3.h"
164 #include "table/iso8859_4.h"
165 #include "table/iso8859_5.h"
166 #include "table/iso8859_6.h"
167 #include "table/iso8859_7.h"
168 #include "table/iso8859_8.h"
169 #include "table/iso8859_9.h"
170 #include "table/iso8859_10.h"
171 #include "table/iso8859_11.h"
172 #include "table/iso8859_13.h"
173 #include "table/iso8859_14.h"
174 #include "table/iso8859_16.h"
176 #include "table/koi8_r.h"
177 #include "table/koi8_u.h"
179 //#define ENCODING_KR
181 #include "table/ksc5601_1987_0.h"
183 //#define ENCODING_ZH
185 #include "table/big5.h"
186 #include "table/gbk_0.h"
187 #include "table/gb2312_1980_0.h"
189 //#define ENCODING_ZH_EXT
191 #include "table/cns11643_1992_1.h"
192 #include "table/cns11643_1992_2.h"
193 #include "table/cns11643_1992_3.h"
194 #include "table/cns11643_1992_4.h"
195 #include "table/cns11643_1992_5.h"
196 #include "table/cns11643_1992_6.h"
197 #include "table/cns11643_1992_7.h"
198 #include "table/cns11643_1992_f.h"
199 #include "table/big5_ext.h"
200 #include "table/big5_plus.h"
202 //#define ENCODING_VN
204 #include "table/viscii.h"
206 //#define ENCODING_JP
208 #include "table/jis0201_1976_0.h"
209 #include "table/jis0208_1990_0.h"
210 #include "table/jis0212_1990_0.h"
212 //#define ENCODING_JP_EXT
214 #include "table/jis0213_1.h"
215 #include "table/jis0213_2.h"
217 #if ENCODING_TO_UNICODE
218 # define ENC(base) { cs_ ## base ## _from_unicode, cs_ ## base ## _to_unicode }
220 # define ENC(base) { cs_ ## base ## _from_unicode }
224 // order must match table in encoding.h(!)
225 const rxvt_codeset_conv rxvt_codeset[NUM_CODESETS] = {
249 ENC (jis0201_1976_0),
250 ENC (jis0208_1990_0),
251 ENC (jis0212_1990_0),
256 ENC (ksc5601_1987_0),
261 ENC (cns11643_1992_1),
262 ENC (cns11643_1992_2),
263 ENC (cns11643_1992_3),
264 ENC (cns11643_1992_4),
265 ENC (cns11643_1992_5),
266 ENC (cns11643_1992_6),
267 ENC (cns11643_1992_7),
268 ENC (cns11643_1992_f),
280 # define ENCODING_COMPOSE
283 #include "table/compose.h"
286 rxvt_compose (unicode_t c1, unicode_t c2)
289 int r = sizeof (rxvt_compose_table) / sizeof (rxvt_compose_entry) - 1;
295 rxvt_compose_entry &c = rxvt_compose_table[m];
297 if (c.c1 < c1 || (c.c1 == c1 && c.c2 < c2))
299 else if (c.c1 > c1 || (c.c1 == c1 && c.c2 > c2))
308 #include "table/category.h"
310 bool unicode::is_space (unicode_t c)
313 || c == 0x09; // exclude tabs, too, as we store them in the buffer