| 1 |
/*--------------------------------*-C-*---------------------------------* |
| 2 |
* File: encoding.C |
| 3 |
*----------------------------------------------------------------------* |
| 4 |
* |
| 5 |
* All portions of code are copyright by their respective author/s. |
| 6 |
* Copyright (c) 2003-2004 Marc Lehmann <pcg@goof.com> |
| 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 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 |
#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 |
{ "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 |
|
| 53 |
{ "TIS620*", CS_ISO8859_11 }, // close enough |
| 54 |
|
| 55 |
{ "ISO10646*", CS_UNICODE }, |
| 56 |
{ "UNICODE", CS_UNICODE }, |
| 57 |
{ "UTF8", CS_UNICODE }, |
| 58 |
|
| 59 |
{ "ASCII", CS_US_ASCII }, |
| 60 |
{ "USASCII", CS_US_ASCII }, |
| 61 |
{ "ANSIX341968", CS_US_ASCII }, |
| 62 |
|
| 63 |
{ "KOI8R", CS_KOI8_R }, |
| 64 |
{ "GOST1976874*", CS_KOI8_R }, |
| 65 |
{ "KOI8RU", CS_KOI8_U }, |
| 66 |
{ "KOI8U", CS_KOI8_U }, |
| 67 |
|
| 68 |
{ "VISCII*", CS_VISCII }, |
| 69 |
|
| 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 |
| 77 |
|
| 78 |
{ "KSC5601*", CS_KSC5601_1987_0 }, |
| 79 |
{ "KSX1001*", CS_KSC5601_1987_0 }, |
| 80 |
{ "KSC5700*", CS_UNICODE }, // unicode plus extensions |
| 81 |
|
| 82 |
{ "BIG5P*", CS_BIG5_PLUS }, |
| 83 |
{ "BIG5ETEN*", CS_BIG5_EXT }, |
| 84 |
{ "BIG5*", CS_BIG5 }, |
| 85 |
{ "GB2312*", CS_GB2312_1980_0 }, |
| 86 |
{ "GB6345*", CS_GB2312_1980_0 }, // slightly different to gb2312?? |
| 87 |
{ "GB8565*", CS_GB2312_1980_0 }, // a superset of gb2312?? |
| 88 |
{ "GB13000*", CS_UNICODE }, |
| 89 |
{ "CNS1164319921", CS_CNS11643_1992_1 }, |
| 90 |
{ "CNS1164319922", CS_CNS11643_1992_2 }, |
| 91 |
{ "CNS1164319923", CS_CNS11643_1992_3 }, |
| 92 |
{ "CNS1164319924", CS_CNS11643_1992_4 }, |
| 93 |
{ "CNS1164319925", CS_CNS11643_1992_5 }, |
| 94 |
{ "CNS1164319926", CS_CNS11643_1992_6 }, |
| 95 |
{ "CNS1164319927", CS_CNS11643_1992_7 }, |
| 96 |
{ "CNS116431992F", CS_CNS11643_1992_F }, |
| 97 |
|
| 98 |
{ 0, CS_UNKNOWN } |
| 99 |
}; |
| 100 |
|
| 101 |
static const char * |
| 102 |
normalize_name (const char *name) |
| 103 |
{ |
| 104 |
static char res[16]; |
| 105 |
char *r; |
| 106 |
|
| 107 |
for (r = res; *name && r < res + 15; name++) |
| 108 |
if ((*name >= '0' && *name <= '9') |
| 109 |
|| (*name >= 'A' && *name <= 'Z')) |
| 110 |
*r++ = *name; |
| 111 |
else if (*name >= 'a' && *name <= 'z') |
| 112 |
*r++ = *name - ('a' - 'A'); |
| 113 |
|
| 114 |
*r = 0; |
| 115 |
|
| 116 |
return res; |
| 117 |
} |
| 118 |
|
| 119 |
codeset |
| 120 |
codeset_from_name (const char *name) |
| 121 |
{ |
| 122 |
if (!name) |
| 123 |
return CS_UNKNOWN; |
| 124 |
|
| 125 |
name = normalize_name (name); |
| 126 |
|
| 127 |
const struct n2cs *i = n2cs; |
| 128 |
|
| 129 |
do { |
| 130 |
int len = strlen (i->name); |
| 131 |
|
| 132 |
if ((i->name[len - 1] == '*' |
| 133 |
&& !strncmp (name, i->name, len - 1)) |
| 134 |
|| !strcmp (name, i->name)) |
| 135 |
return i->cs; |
| 136 |
|
| 137 |
} while ((++i)->name); |
| 138 |
|
| 139 |
return CS_UNKNOWN; |
| 140 |
} |
| 141 |
|
| 142 |
struct rxvt_codeset_conv_unknown : rxvt_codeset_conv { |
| 143 |
unicode_t to_unicode (uint32_t enc) const { return NOCHAR; } |
| 144 |
uint32_t from_unicode (unicode_t unicode) const { return NOCHAR; } |
| 145 |
} rxvt_codeset_conv_unknown; |
| 146 |
|
| 147 |
struct rxvt_codeset_conv_us_ascii : rxvt_codeset_conv { |
| 148 |
uint32_t from_unicode (unicode_t unicode) const { return unicode <= 127 ? unicode : NOCHAR; } |
| 149 |
} rxvt_codeset_conv_us_ascii; |
| 150 |
|
| 151 |
struct rxvt_codeset_conv_unicode : rxvt_codeset_conv { |
| 152 |
/* transparent */ |
| 153 |
} rxvt_codeset_conv_unicode; |
| 154 |
|
| 155 |
struct rxvt_codeset_conv_unicode_16 : rxvt_codeset_conv { |
| 156 |
unicode_t to_unicode (uint32_t enc) const { return enc; } |
| 157 |
uint32_t from_unicode (unicode_t unicode) const { return unicode <= 65535 ? unicode : NOCHAR; } |
| 158 |
} rxvt_codeset_conv_unicode_16; |
| 159 |
|
| 160 |
#define ENCODING_DEFAULT |
| 161 |
|
| 162 |
#include "table/iso8859_1.h" |
| 163 |
#include "table/iso8859_15.h" |
| 164 |
|
| 165 |
//#define ENCODING_EU |
| 166 |
|
| 167 |
#include "table/iso8859_2.h" |
| 168 |
#include "table/iso8859_3.h" |
| 169 |
#include "table/iso8859_4.h" |
| 170 |
#include "table/iso8859_5.h" |
| 171 |
#include "table/iso8859_6.h" |
| 172 |
#include "table/iso8859_7.h" |
| 173 |
#include "table/iso8859_8.h" |
| 174 |
#include "table/iso8859_9.h" |
| 175 |
#include "table/iso8859_10.h" |
| 176 |
#include "table/iso8859_11.h" |
| 177 |
#include "table/iso8859_13.h" |
| 178 |
#include "table/iso8859_14.h" |
| 179 |
#include "table/iso8859_16.h" |
| 180 |
|
| 181 |
#include "table/koi8_r.h" |
| 182 |
#include "table/koi8_u.h" |
| 183 |
|
| 184 |
//#define ENCODING_KR |
| 185 |
|
| 186 |
#include "table/ksc5601_1987_0.h" |
| 187 |
|
| 188 |
//#define ENCODING_CN |
| 189 |
|
| 190 |
#include "table/gb2312_1980_0.h" |
| 191 |
#include "table/big5.h" |
| 192 |
|
| 193 |
//#define ENCODING_CN_EXT |
| 194 |
|
| 195 |
#include "table/cns11643_1992_1.h" |
| 196 |
#include "table/cns11643_1992_2.h" |
| 197 |
#include "table/cns11643_1992_3.h" |
| 198 |
#include "table/cns11643_1992_4.h" |
| 199 |
#include "table/cns11643_1992_5.h" |
| 200 |
#include "table/cns11643_1992_6.h" |
| 201 |
#include "table/cns11643_1992_7.h" |
| 202 |
#include "table/cns11643_1992_f.h" |
| 203 |
#include "table/big5_ext.h" |
| 204 |
#include "table/big5_plus.h" |
| 205 |
|
| 206 |
//#define ENCODING_VN |
| 207 |
|
| 208 |
#include "table/viscii.h" |
| 209 |
|
| 210 |
//#define ENCODING_JP |
| 211 |
|
| 212 |
#include "table/jis0201_1976_0.h" |
| 213 |
#include "table/jis0208_1990_0.h" |
| 214 |
#include "table/jis0212_1990_0.h" |
| 215 |
|
| 216 |
//#define ENCODING_JP_EXT |
| 217 |
|
| 218 |
#include "table/jis0213_1.h" |
| 219 |
#include "table/jis0213_2.h" |
| 220 |
|
| 221 |
// order must match table in encoding.h(!) |
| 222 |
const rxvt_codeset_conv *rxvt_codeset[NUM_CODESETS] = { |
| 223 |
&rxvt_codeset_conv_unknown, |
| 224 |
|
| 225 |
&rxvt_codeset_conv_us_ascii, |
| 226 |
|
| 227 |
&rxvt_codeset_conv_iso8859_1, |
| 228 |
&rxvt_codeset_conv_iso8859_2, |
| 229 |
&rxvt_codeset_conv_iso8859_3, |
| 230 |
&rxvt_codeset_conv_iso8859_4, |
| 231 |
&rxvt_codeset_conv_iso8859_5, |
| 232 |
&rxvt_codeset_conv_iso8859_6, |
| 233 |
&rxvt_codeset_conv_iso8859_7, |
| 234 |
&rxvt_codeset_conv_iso8859_8, |
| 235 |
&rxvt_codeset_conv_iso8859_9, |
| 236 |
&rxvt_codeset_conv_iso8859_10, |
| 237 |
&rxvt_codeset_conv_iso8859_11, |
| 238 |
&rxvt_codeset_conv_iso8859_13, |
| 239 |
&rxvt_codeset_conv_iso8859_14, |
| 240 |
&rxvt_codeset_conv_iso8859_15, |
| 241 |
&rxvt_codeset_conv_iso8859_16, |
| 242 |
|
| 243 |
&rxvt_codeset_conv_koi8_r, |
| 244 |
&rxvt_codeset_conv_koi8_u, |
| 245 |
|
| 246 |
&rxvt_codeset_conv_jis0201_1976_0, |
| 247 |
&rxvt_codeset_conv_jis0208_1990_0, |
| 248 |
&rxvt_codeset_conv_jis0212_1990_0, |
| 249 |
|
| 250 |
&rxvt_codeset_conv_jis0213_1, |
| 251 |
&rxvt_codeset_conv_jis0213_2, |
| 252 |
|
| 253 |
&rxvt_codeset_conv_ksc5601_1987_0, |
| 254 |
|
| 255 |
&rxvt_codeset_conv_gb2312_1980_0, |
| 256 |
|
| 257 |
&rxvt_codeset_conv_cns11643_1992_1, |
| 258 |
&rxvt_codeset_conv_cns11643_1992_2, |
| 259 |
&rxvt_codeset_conv_cns11643_1992_3, |
| 260 |
&rxvt_codeset_conv_cns11643_1992_4, |
| 261 |
&rxvt_codeset_conv_cns11643_1992_5, |
| 262 |
&rxvt_codeset_conv_cns11643_1992_6, |
| 263 |
&rxvt_codeset_conv_cns11643_1992_7, |
| 264 |
&rxvt_codeset_conv_cns11643_1992_f, |
| 265 |
&rxvt_codeset_conv_big5, |
| 266 |
&rxvt_codeset_conv_big5_ext, |
| 267 |
&rxvt_codeset_conv_big5_plus, |
| 268 |
|
| 269 |
&rxvt_codeset_conv_viscii, |
| 270 |
|
| 271 |
&rxvt_codeset_conv_unicode_16, |
| 272 |
&rxvt_codeset_conv_unicode |
| 273 |
}; |
| 274 |
|
| 275 |
#if ENABLE_COMBINING |
| 276 |
# define ENCODING_COMPOSE |
| 277 |
#endif |
| 278 |
|
| 279 |
#include "table/compose.h" |
| 280 |
|
| 281 |
unicode_t |
| 282 |
rxvt_compose (unicode_t c1, unicode_t c2) |
| 283 |
{ |
| 284 |
int l = 0; |
| 285 |
int r = sizeof (rxvt_compose_table) / sizeof (rxvt_compose_entry) - 1; |
| 286 |
int m; |
| 287 |
|
| 288 |
while (r > l) |
| 289 |
{ |
| 290 |
m = (l + r) / 2; |
| 291 |
rxvt_compose_entry &c = rxvt_compose_table[m]; |
| 292 |
|
| 293 |
if (c.c1 < c1 || (c.c1 == c1 && c.c2 < c2)) |
| 294 |
l = m + 1; |
| 295 |
else if (c.c1 > c1 || (c.c1 == c1 && c.c2 > c2)) |
| 296 |
r = m - 1; |
| 297 |
else |
| 298 |
return c.r; |
| 299 |
} |
| 300 |
|
| 301 |
return NOCHAR; |
| 302 |
} |
| 303 |
|
| 304 |
#include "table/category.h" |
| 305 |
|
| 306 |
bool unicode::is_space (unicode_t c) |
| 307 |
{ |
| 308 |
return IS_SPACE (c); |
| 309 |
} |
