comparison src/mule-charset.c @ 78:c7528f8e288d r20-0b34

Import from CVS: tag r20-0b34
author cvs
date Mon, 13 Aug 2007 09:05:42 +0200
parents 54cc21c15cbb
children 85ec50267440
comparison
equal deleted inserted replaced
77:6cb4f478e7bc 78:c7528f8e288d
1240 Vcharset_ascii = 1240 Vcharset_ascii =
1241 make_charset (Qascii, LEADING_BYTE_ASCII, 1, 1241 make_charset (Qascii, LEADING_BYTE_ASCII, 1,
1242 CHARSET_TYPE_94, 1, 0, 'B', 1242 CHARSET_TYPE_94, 1, 0, 'B',
1243 CHARSET_LEFT_TO_RIGHT, 1243 CHARSET_LEFT_TO_RIGHT,
1244 build_string ("ASCII"), 1244 build_string ("ASCII"),
1245 build_string ("ISO8859-1")); 1245 build_string ("iso8859-1"));
1246 Vcharset_control_1 = 1246 Vcharset_control_1 =
1247 make_charset (Qcontrol_1, LEADING_BYTE_CONTROL_1, 2, 1247 make_charset (Qcontrol_1, LEADING_BYTE_CONTROL_1, 2,
1248 CHARSET_TYPE_94, 1, 0, 0, 1248 CHARSET_TYPE_94, 1, 0, 0,
1249 CHARSET_LEFT_TO_RIGHT, 1249 CHARSET_LEFT_TO_RIGHT,
1250 build_string ("Control characters"), 1250 build_string ("Control characters"),
1252 Vcharset_latin_iso8859_1 = 1252 Vcharset_latin_iso8859_1 =
1253 make_charset (Qlatin_iso8859_1, LEADING_BYTE_LATIN_ISO8859_1, 2, 1253 make_charset (Qlatin_iso8859_1, LEADING_BYTE_LATIN_ISO8859_1, 2,
1254 CHARSET_TYPE_96, 1, 1, 'A', 1254 CHARSET_TYPE_96, 1, 1, 'A',
1255 CHARSET_LEFT_TO_RIGHT, 1255 CHARSET_LEFT_TO_RIGHT,
1256 build_string ("Latin-1"), 1256 build_string ("Latin-1"),
1257 build_string ("ISO8859-1")); 1257 build_string ("iso8859-1"));
1258 Vcharset_latin_iso8859_2 = 1258 Vcharset_latin_iso8859_2 =
1259 make_charset (Qlatin_iso8859_2, LEADING_BYTE_LATIN_ISO8859_2, 2, 1259 make_charset (Qlatin_iso8859_2, LEADING_BYTE_LATIN_ISO8859_2, 2,
1260 CHARSET_TYPE_96, 1, 1, 'B', 1260 CHARSET_TYPE_96, 1, 1, 'B',
1261 CHARSET_LEFT_TO_RIGHT, 1261 CHARSET_LEFT_TO_RIGHT,
1262 build_string ("Latin-2"), 1262 build_string ("Latin-2"),
1263 build_string ("ISO8859-2")); 1263 build_string ("iso8859-2"));
1264 Vcharset_latin_iso8859_3 = 1264 Vcharset_latin_iso8859_3 =
1265 make_charset (Qlatin_iso8859_3, LEADING_BYTE_LATIN_ISO8859_3, 2, 1265 make_charset (Qlatin_iso8859_3, LEADING_BYTE_LATIN_ISO8859_3, 2,
1266 CHARSET_TYPE_96, 1, 1, 'C', 1266 CHARSET_TYPE_96, 1, 1, 'C',
1267 CHARSET_LEFT_TO_RIGHT, 1267 CHARSET_LEFT_TO_RIGHT,
1268 build_string ("Latin-3"), 1268 build_string ("Latin-3"),
1269 build_string ("ISO8859-3")); 1269 build_string ("iso8859-3"));
1270 Vcharset_latin_iso8859_4 = 1270 Vcharset_latin_iso8859_4 =
1271 make_charset (Qlatin_iso8859_4, LEADING_BYTE_LATIN_ISO8859_4, 2, 1271 make_charset (Qlatin_iso8859_4, LEADING_BYTE_LATIN_ISO8859_4, 2,
1272 CHARSET_TYPE_96, 1, 1, 'D', 1272 CHARSET_TYPE_96, 1, 1, 'D',
1273 CHARSET_LEFT_TO_RIGHT, 1273 CHARSET_LEFT_TO_RIGHT,
1274 build_string ("Latin-4"), 1274 build_string ("Latin-4"),
1275 build_string ("ISO8859-4")); 1275 build_string ("iso8859-4"));
1276 Vcharset_cyrillic_iso8859_5 = 1276 Vcharset_cyrillic_iso8859_5 =
1277 make_charset (Qcyrillic_iso8859_5, LEADING_BYTE_CYRILLIC_ISO8859_5, 2, 1277 make_charset (Qcyrillic_iso8859_5, LEADING_BYTE_CYRILLIC_ISO8859_5, 2,
1278 CHARSET_TYPE_96, 1, 1, 'L', 1278 CHARSET_TYPE_96, 1, 1, 'L',
1279 CHARSET_LEFT_TO_RIGHT, 1279 CHARSET_LEFT_TO_RIGHT,
1280 build_string ("Cyrillic"), 1280 build_string ("Cyrillic"),
1281 build_string ("ISO8859-5")); 1281 build_string ("iso8859-5"));
1282 Vcharset_arabic_iso8859_6 = 1282 Vcharset_arabic_iso8859_6 =
1283 make_charset (Qarabic_iso8859_6, LEADING_BYTE_ARABIC_ISO8859_6, 2, 1283 make_charset (Qarabic_iso8859_6, LEADING_BYTE_ARABIC_ISO8859_6, 2,
1284 CHARSET_TYPE_96, 1, 1, 'G', 1284 CHARSET_TYPE_96, 1, 1, 'G',
1285 CHARSET_RIGHT_TO_LEFT, 1285 CHARSET_RIGHT_TO_LEFT,
1286 build_string ("Arabic"), 1286 build_string ("Arabic"),
1287 build_string ("ISO8859-6")); 1287 build_string ("iso8859-6"));
1288 Vcharset_greek_iso8859_7 = 1288 Vcharset_greek_iso8859_7 =
1289 make_charset (Qgreek_iso8859_7, LEADING_BYTE_GREEK_ISO8859_7, 2, 1289 make_charset (Qgreek_iso8859_7, LEADING_BYTE_GREEK_ISO8859_7, 2,
1290 CHARSET_TYPE_96, 1, 1, 'F', 1290 CHARSET_TYPE_96, 1, 1, 'F',
1291 CHARSET_LEFT_TO_RIGHT, 1291 CHARSET_LEFT_TO_RIGHT,
1292 build_string ("Greek"), 1292 build_string ("Greek"),
1293 build_string ("ISO8859-7")); 1293 build_string ("iso8859-7"));
1294 Vcharset_hebrew_iso8859_8 = 1294 Vcharset_hebrew_iso8859_8 =
1295 make_charset (Qhebrew_iso8859_8, LEADING_BYTE_HEBREW_ISO8859_8, 2, 1295 make_charset (Qhebrew_iso8859_8, LEADING_BYTE_HEBREW_ISO8859_8, 2,
1296 CHARSET_TYPE_96, 1, 1, 'H', 1296 CHARSET_TYPE_96, 1, 1, 'H',
1297 CHARSET_RIGHT_TO_LEFT, 1297 CHARSET_RIGHT_TO_LEFT,
1298 build_string ("Hebrew"), 1298 build_string ("Hebrew"),
1299 build_string ("ISO8859-8")); 1299 build_string ("iso8859-8"));
1300 Vcharset_latin_iso8859_9 = 1300 Vcharset_latin_iso8859_9 =
1301 make_charset (Qlatin_iso8859_9, LEADING_BYTE_LATIN_ISO8859_9, 2, 1301 make_charset (Qlatin_iso8859_9, LEADING_BYTE_LATIN_ISO8859_9, 2,
1302 CHARSET_TYPE_96, 1, 1, 'M', 1302 CHARSET_TYPE_96, 1, 1, 'M',
1303 CHARSET_LEFT_TO_RIGHT, 1303 CHARSET_LEFT_TO_RIGHT,
1304 build_string ("Latin-5"), 1304 build_string ("Latin-5"),
1305 build_string ("ISO8859-9")); 1305 build_string ("iso8859-9"));
1306 Vcharset_thai_tis620 = 1306 Vcharset_thai_tis620 =
1307 make_charset (Qthai_tis620, LEADING_BYTE_THAI_TIS620, 2, 1307 make_charset (Qthai_tis620, LEADING_BYTE_THAI_TIS620, 2,
1308 CHARSET_TYPE_96, 1, 1, 'T', 1308 CHARSET_TYPE_96, 1, 1, 'T',
1309 CHARSET_LEFT_TO_RIGHT, 1309 CHARSET_LEFT_TO_RIGHT,
1310 build_string ("Thai"), 1310 build_string ("Thai"),
1311 build_string ("TIS620")); 1311 build_string ("tis620"));
1312 1312
1313 /* Japanese */ 1313 /* Japanese */
1314 Vcharset_katakana_jisx0201 = 1314 Vcharset_katakana_jisx0201 =
1315 make_charset (Qkatakana_jisx0201, 1315 make_charset (Qkatakana_jisx0201,
1316 LEADING_BYTE_KATAKANA_JISX0201, 2, 1316 LEADING_BYTE_KATAKANA_JISX0201, 2,
1317 CHARSET_TYPE_94, 1, 1, 'I', 1317 CHARSET_TYPE_94, 1, 1, 'I',
1318 CHARSET_LEFT_TO_RIGHT, 1318 CHARSET_LEFT_TO_RIGHT,
1319 build_string ("Japanese Katakana"), 1319 build_string ("Japanese Katakana"),
1320 build_string ("JISX0201.1976")); 1320 build_string ("jisx0201.1976"));
1321 Vcharset_latin_jisx0201 = 1321 Vcharset_latin_jisx0201 =
1322 make_charset (Qlatin_jisx0201, 1322 make_charset (Qlatin_jisx0201,
1323 LEADING_BYTE_LATIN_JISX0201, 2, 1323 LEADING_BYTE_LATIN_JISX0201, 2,
1324 CHARSET_TYPE_94, 1, 0, 'J', 1324 CHARSET_TYPE_94, 1, 0, 'J',
1325 CHARSET_LEFT_TO_RIGHT, 1325 CHARSET_LEFT_TO_RIGHT,
1326 build_string ("Japanese Roman"), 1326 build_string ("Japanese Roman"),
1327 build_string ("JISX0201.1976")); 1327 build_string ("jisx0201.1976"));
1328 Vcharset_japanese_jisx0208_1978 = 1328 Vcharset_japanese_jisx0208_1978 =
1329 make_charset (Qjapanese_jisx0208_1978, 1329 make_charset (Qjapanese_jisx0208_1978,
1330 LEADING_BYTE_JAPANESE_JISX0208_1978, 3, 1330 LEADING_BYTE_JAPANESE_JISX0208_1978, 3,
1331 CHARSET_TYPE_94X94, 2, 0, '@', 1331 CHARSET_TYPE_94X94, 2, 0, '@',
1332 CHARSET_LEFT_TO_RIGHT, 1332 CHARSET_LEFT_TO_RIGHT,
1333 build_string ("Japanese Old"), 1333 build_string ("Japanese Old"),
1334 build_string ("\\(JISX0208\\|jisc6226\\).1978")); 1334 build_string ("\\(jisx0208\\|jisc6226\\).19"));
1335 Vcharset_japanese_jisx0208 = 1335 Vcharset_japanese_jisx0208 =
1336 make_charset (Qjapanese_jisx0208, 1336 make_charset (Qjapanese_jisx0208,
1337 LEADING_BYTE_JAPANESE_JISX0208, 3, 1337 LEADING_BYTE_JAPANESE_JISX0208, 3,
1338 CHARSET_TYPE_94X94, 2, 0, 'B', 1338 CHARSET_TYPE_94X94, 2, 0, 'B',
1339 CHARSET_LEFT_TO_RIGHT, 1339 CHARSET_LEFT_TO_RIGHT,
1340 build_string ("Japanese"), 1340 build_string ("Japanese"),
1341 build_string ("JISX0208.\\(1983\\|1990\\)")); 1341 build_string ("jisx0208.19\\(83\\|90\\)"));
1342 Vcharset_japanese_jisx0212 = 1342 Vcharset_japanese_jisx0212 =
1343 make_charset (Qjapanese_jisx0212, 1343 make_charset (Qjapanese_jisx0212,
1344 LEADING_BYTE_JAPANESE_JISX0212, 3, 1344 LEADING_BYTE_JAPANESE_JISX0212, 3,
1345 CHARSET_TYPE_94X94, 2, 0, 'D', 1345 CHARSET_TYPE_94X94, 2, 0, 'D',
1346 CHARSET_LEFT_TO_RIGHT, 1346 CHARSET_LEFT_TO_RIGHT,
1347 build_string ("Japanese Supplement"), 1347 build_string ("Japanese Supplement"),
1348 build_string ("JISX0212")); 1348 build_string ("jisx0212"));
1349 1349
1350 /* Chinese */ 1350 /* Chinese */
1351 Vcharset_chinese_gb2312 = 1351 Vcharset_chinese_gb2312 =
1352 make_charset (Qchinese_gb2312, LEADING_BYTE_CHINESE_GB2312, 3, 1352 make_charset (Qchinese_gb2312, LEADING_BYTE_CHINESE_GB2312, 3,
1353 CHARSET_TYPE_94X94, 2, 0, 'A', 1353 CHARSET_TYPE_94X94, 2, 0, 'A',
1354 CHARSET_LEFT_TO_RIGHT, 1354 CHARSET_LEFT_TO_RIGHT,
1355 build_string ("Chinese GB2312"), 1355 build_string ("Chinese GB2312"),
1356 build_string ("GB2312")); 1356 build_string ("gb2312"));
1357 #define CHINESE_CNS_PLANE_RE(n) "CNS11643[.-]\\(.*[.-]\\)?" n "$" 1357 #define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$"
1358 Vcharset_chinese_cns11643_1 = 1358 Vcharset_chinese_cns11643_1 =
1359 make_charset (Qchinese_cns11643_1, 1359 make_charset (Qchinese_cns11643_1,
1360 LEADING_BYTE_CHINESE_CNS11643_1, 3, 1360 LEADING_BYTE_CHINESE_CNS11643_1, 3,
1361 CHARSET_TYPE_94X94, 2, 0, 'G', 1361 CHARSET_TYPE_94X94, 2, 0, 'G',
1362 CHARSET_LEFT_TO_RIGHT, 1362 CHARSET_LEFT_TO_RIGHT,
1372 Vcharset_chinese_big5_1 = 1372 Vcharset_chinese_big5_1 =
1373 make_charset (Qchinese_big5_1, LEADING_BYTE_CHINESE_BIG5_1, 3, 1373 make_charset (Qchinese_big5_1, LEADING_BYTE_CHINESE_BIG5_1, 3,
1374 CHARSET_TYPE_94X94, 2, 0, '0', 1374 CHARSET_TYPE_94X94, 2, 0, '0',
1375 CHARSET_LEFT_TO_RIGHT, 1375 CHARSET_LEFT_TO_RIGHT,
1376 build_string ("Chinese Big5 Level 1"), 1376 build_string ("Chinese Big5 Level 1"),
1377 build_string ("Big5")); 1377 build_string ("big5"));
1378 Vcharset_chinese_big5_2 = 1378 Vcharset_chinese_big5_2 =
1379 make_charset (Qchinese_big5_2, LEADING_BYTE_CHINESE_BIG5_2, 3, 1379 make_charset (Qchinese_big5_2, LEADING_BYTE_CHINESE_BIG5_2, 3,
1380 CHARSET_TYPE_94X94, 2, 0, '1', 1380 CHARSET_TYPE_94X94, 2, 0, '1',
1381 CHARSET_LEFT_TO_RIGHT, 1381 CHARSET_LEFT_TO_RIGHT,
1382 build_string ("Chinese Big5 Level 2"), 1382 build_string ("Chinese Big5 Level 2"),
1383 build_string ("Big5")); 1383 build_string ("big5"));
1384 1384
1385 Vcharset_korean_ksc5601 = 1385 Vcharset_korean_ksc5601 =
1386 make_charset (Qkorean_ksc5601, LEADING_BYTE_KOREAN_KSC5601, 3, 1386 make_charset (Qkorean_ksc5601, LEADING_BYTE_KOREAN_KSC5601, 3,
1387 CHARSET_TYPE_94X94, 2, 0, 'C', 1387 CHARSET_TYPE_94X94, 2, 0, 'C',
1388 CHARSET_LEFT_TO_RIGHT, 1388 CHARSET_LEFT_TO_RIGHT,
1389 build_string ("Korean"), 1389 build_string ("Korean"),
1390 build_string ("KSC5601")); 1390 build_string ("ksc5601"));
1391 /* #### For simplicity, we put composite chars into a 96x96 charset. 1391 /* #### For simplicity, we put composite chars into a 96x96 charset.
1392 This is going to lead to problems because you can run out of 1392 This is going to lead to problems because you can run out of
1393 room, esp. as we don't yet recycle numbers. */ 1393 room, esp. as we don't yet recycle numbers. */
1394 Vcharset_composite = 1394 Vcharset_composite =
1395 make_charset (Qcomposite, LEADING_BYTE_COMPOSITE, 3, 1395 make_charset (Qcomposite, LEADING_BYTE_COMPOSITE, 3,