Mercurial > hg > xemacs-beta

comparison src/mule-charset.c @ 3439:d1754e7f0cea

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
[xemacs-hg @ 2006-06-03 17:50:39 by aidan] Just-in-time Unicode code point support.
author aidan
date Sat, 03 Jun 2006 17:51:06 +0000
parents facf3239ba30
children 98af8a976fc3
comparison
equal deleted inserted replaced
3438:14fbcab7c67b 3439:d1754e7f0cea
188 static Lisp_Object 188 static Lisp_Object
189 make_charset (int id, Lisp_Object name, int rep_bytes, 189 make_charset (int id, Lisp_Object name, int rep_bytes,
190 int type, int columns, int graphic, 190 int type, int columns, int graphic,
191 Ibyte final, int direction, Lisp_Object short_name, 191 Ibyte final, int direction, Lisp_Object short_name,
192 Lisp_Object long_name, Lisp_Object doc, 192 Lisp_Object long_name, Lisp_Object doc,
193 Lisp_Object reg, int overwrite) 193 Lisp_Object reg, int overwrite, int encode_as_utf_8)
194 { 194 {
195 Lisp_Object obj; 195 Lisp_Object obj;
196 Lisp_Charset *cs; 196 Lisp_Charset *cs;
197 197
198 if (!overwrite) 198 if (!overwrite)
238 CHARSET_COLUMNS (cs) = columns; 238 CHARSET_COLUMNS (cs) = columns;
239 CHARSET_GRAPHIC (cs) = graphic; 239 CHARSET_GRAPHIC (cs) = graphic;
240 CHARSET_FINAL (cs) = final; 240 CHARSET_FINAL (cs) = final;
241 CHARSET_DOC_STRING (cs) = doc; 241 CHARSET_DOC_STRING (cs) = doc;
242 CHARSET_REGISTRY (cs) = reg; 242 CHARSET_REGISTRY (cs) = reg;
243 CHARSET_ENCODE_AS_UTF_8 (cs) = encode_as_utf_8 ? 1 : 0;
243 CHARSET_CCL_PROGRAM (cs) = Qnil; 244 CHARSET_CCL_PROGRAM (cs) = Qnil;
244 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil; 245 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil;
245 246
246 CHARSET_DIMENSION (cs) = (CHARSET_TYPE (cs) == CHARSET_TYPE_94 || 247 CHARSET_DIMENSION (cs) = (CHARSET_TYPE (cs) == CHARSET_TYPE_94 ||
247 CHARSET_TYPE (cs) == CHARSET_TYPE_96) ? 1 : 2; 248 CHARSET_TYPE (cs) == CHARSET_TYPE_96) ? 1 : 2;
452 this charset into an index into the font. This is in 453 this charset into an index into the font. This is in
453 addition to the `graphic' property. The CCL program 454 addition to the `graphic' property. The CCL program
454 is passed the octets of the character, with the high 455 is passed the octets of the character, with the high
455 bit cleared and set depending upon whether the value 456 bit cleared and set depending upon whether the value
456 of the `graphic' property is 0 or 1. 457 of the `graphic' property is 0 or 1.
458 `encode-as-utf-8'
459 If non-nil, the charset will be written out using the UTF-8
460 escape syntax in ISO 2022-oriented coding systems. Used for
461 supporting characters we know are part of Unicode but not of
462 any other known character set in escape-quoted and compound
463 text.
457 */ 464 */
458 (name, doc_string, props)) 465 (name, doc_string, props))
459 { 466 {
460 int id, dimension = 1, chars = 94, graphic = 0, columns = -1; 467 int id, dimension = 1, chars = 94, graphic = 0, columns = -1;
461 Ibyte final = 0; 468 Ibyte final = 0;
463 int type; 470 int type;
464 Lisp_Object registry = Qnil; 471 Lisp_Object registry = Qnil;
465 Lisp_Object charset = Qnil; 472 Lisp_Object charset = Qnil;
466 Lisp_Object ccl_program = Qnil; 473 Lisp_Object ccl_program = Qnil;
467 Lisp_Object short_name = Qnil, long_name = Qnil; 474 Lisp_Object short_name = Qnil, long_name = Qnil;
475 int encode_as_utf_8 = 0;
468 Lisp_Object existing_charset; 476 Lisp_Object existing_charset;
469 int temporary = UNBOUNDP (name); 477 int temporary = UNBOUNDP (name);
470 478
471 /* NOTE: name == Qunbound is a directive from the iso2022 code to 479 /* NOTE: name == Qunbound is a directive from the iso2022 code to
472 create a temporary charset for an unknown final. We allow the final 480 create a temporary charset for an unknown final. We allow the final
544 direction = CHARSET_RIGHT_TO_LEFT; 552 direction = CHARSET_RIGHT_TO_LEFT;
545 else 553 else
546 invalid_constant ("Invalid value for `direction'", value); 554 invalid_constant ("Invalid value for `direction'", value);
547 } 555 }
548 556
557 else if (EQ (keyword, Qencode_as_utf_8))
558 {
559 encode_as_utf_8 = NILP (value) ? 0 : 1;
560 }
561
549 else if (EQ (keyword, Qfinal)) 562 else if (EQ (keyword, Qfinal))
550 { 563 {
551 CHECK_CHAR_COERCE_INT (value); 564 CHECK_CHAR_COERCE_INT (value);
552 final = XCHAR (value); 565 final = XCHAR (value);
553 if (final < '0' || final > '~') 566 if (final < '0' || final > '~')
554 invalid_constant ("Invalid value for `final'", value); 567 invalid_constant ("Invalid value for `final'", value);
555 } 568 }
556
557 else if (EQ (keyword, Qccl_program)) 569 else if (EQ (keyword, Qccl_program))
558 { 570 {
559 struct ccl_program test_ccl; 571 struct ccl_program test_ccl;
560 572
561 if (setup_ccl_program (&test_ccl, value) < 0) 573 if (setup_ccl_program (&test_ccl, value) < 0)
610 if (columns == -1) 622 if (columns == -1)
611 columns = dimension; 623 columns = dimension;
612 624
613 charset = make_charset (id, name, dimension + 2, type, columns, graphic, 625 charset = make_charset (id, name, dimension + 2, type, columns, graphic,
614 final, direction, short_name, long_name, 626 final, direction, short_name, long_name,
615 doc_string, registry, !NILP (existing_charset)); 627 doc_string, registry, !NILP (existing_charset),
628 encode_as_utf_8);
616 629
617 XCHARSET (charset)->temporary = temporary; 630 XCHARSET (charset)->temporary = temporary;
618 if (!NILP (ccl_program)) 631 if (!NILP (ccl_program))
619 XCHARSET_CCL_PROGRAM (charset) = ccl_program; 632 XCHARSET_CCL_PROGRAM (charset) = ccl_program;
620 633
639 NEW-NAME is the name of the new charset. Return the new charset. 652 NEW-NAME is the name of the new charset. Return the new charset.
640 */ 653 */
641 (charset, new_name)) 654 (charset, new_name))
642 { 655 {
643 Lisp_Object new_charset = Qnil; 656 Lisp_Object new_charset = Qnil;
644 int id, dimension, columns, graphic; 657 int id, dimension, columns, graphic, encode_as_utf_8;
645 Ibyte final; 658 Ibyte final;
646 int direction, type; 659 int direction, type;
647 Lisp_Object registry, doc_string, short_name, long_name; 660 Lisp_Object registry, doc_string, short_name, long_name;
648 Lisp_Charset *cs; 661 Lisp_Charset *cs;
649 662
670 direction = CHARSET_LEFT_TO_RIGHT; 683 direction = CHARSET_LEFT_TO_RIGHT;
671 doc_string = CHARSET_DOC_STRING (cs); 684 doc_string = CHARSET_DOC_STRING (cs);
672 short_name = CHARSET_SHORT_NAME (cs); 685 short_name = CHARSET_SHORT_NAME (cs);
673 long_name = CHARSET_LONG_NAME (cs); 686 long_name = CHARSET_LONG_NAME (cs);
674 registry = CHARSET_REGISTRY (cs); 687 registry = CHARSET_REGISTRY (cs);
688 encode_as_utf_8 = CHARSET_ENCODE_AS_UTF_8 (cs);
675 689
676 new_charset = make_charset (id, new_name, dimension + 2, type, columns, 690 new_charset = make_charset (id, new_name, dimension + 2, type, columns,
677 graphic, final, direction, short_name, long_name, 691 graphic, final, direction, short_name, long_name,
678 doc_string, registry, 0); 692 doc_string, registry, 0, encode_as_utf_8);
679 693
680 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset; 694 CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset;
681 XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset; 695 XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset;
682 696
683 return new_charset; 697 return new_charset;
805 if (EQ (prop, Qcolumns)) return make_int (CHARSET_COLUMNS (cs)); 819 if (EQ (prop, Qcolumns)) return make_int (CHARSET_COLUMNS (cs));
806 if (EQ (prop, Qgraphic)) return make_int (CHARSET_GRAPHIC (cs)); 820 if (EQ (prop, Qgraphic)) return make_int (CHARSET_GRAPHIC (cs));
807 if (EQ (prop, Qfinal)) return make_char (CHARSET_FINAL (cs)); 821 if (EQ (prop, Qfinal)) return make_char (CHARSET_FINAL (cs));
808 if (EQ (prop, Qchars)) return make_int (CHARSET_CHARS (cs)); 822 if (EQ (prop, Qchars)) return make_int (CHARSET_CHARS (cs));
809 if (EQ (prop, Qregistry)) return CHARSET_REGISTRY (cs); 823 if (EQ (prop, Qregistry)) return CHARSET_REGISTRY (cs);
824 if (EQ (prop, Qencode_as_utf_8))
825 return CHARSET_ENCODE_AS_UTF_8 (cs) ? Qt : Qnil;
810 if (EQ (prop, Qccl_program)) return CHARSET_CCL_PROGRAM (cs); 826 if (EQ (prop, Qccl_program)) return CHARSET_CCL_PROGRAM (cs);
811 if (EQ (prop, Qdirection)) 827 if (EQ (prop, Qdirection))
812 return CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? Ql2r : Qr2l; 828 return CHARSET_DIRECTION (cs) == CHARSET_LEFT_TO_RIGHT ? Ql2r : Qr2l;
813 if (EQ (prop, Qreverse_direction_charset)) 829 if (EQ (prop, Qreverse_direction_charset))
814 { 830 {
1038 CHARSET_TYPE_94, 1, 0, 'B', 1054 CHARSET_TYPE_94, 1, 0, 'B',
1039 CHARSET_LEFT_TO_RIGHT, 1055 CHARSET_LEFT_TO_RIGHT,
1040 build_string ("ASCII"), 1056 build_string ("ASCII"),
1041 build_msg_string ("ASCII"), 1057 build_msg_string ("ASCII"),
1042 build_msg_string ("ASCII (ISO646 IRV)"), 1058 build_msg_string ("ASCII (ISO646 IRV)"),
1043 build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"), 0); 1059 build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"), 0, 0);
1044 staticpro (&Vcharset_control_1); 1060 staticpro (&Vcharset_control_1);
1045 Vcharset_control_1 = 1061 Vcharset_control_1 =
1046 make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 2, 1062 make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 2,
1047 CHARSET_TYPE_94, 1, 1, 0, 1063 CHARSET_TYPE_94, 1, 1, 0,
1048 CHARSET_LEFT_TO_RIGHT, 1064 CHARSET_LEFT_TO_RIGHT,
1049 build_string ("C1"), 1065 build_string ("C1"),
1050 build_msg_string ("Control characters"), 1066 build_msg_string ("Control characters"),
1051 build_msg_string ("Control characters 128-191"), 1067 build_msg_string ("Control characters 128-191"),
1052 build_string (""), 0); 1068 build_string (""), 0, 0);
1053 staticpro (&Vcharset_latin_iso8859_1); 1069 staticpro (&Vcharset_latin_iso8859_1);
1054 Vcharset_latin_iso8859_1 = 1070 Vcharset_latin_iso8859_1 =
1055 make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 2, 1071 make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 2,
1056 CHARSET_TYPE_96, 1, 1, 'A', 1072 CHARSET_TYPE_96, 1, 1, 'A',
1057 CHARSET_LEFT_TO_RIGHT, 1073 CHARSET_LEFT_TO_RIGHT,
1058 build_string ("Latin-1"), 1074 build_string ("Latin-1"),
1059 build_msg_string ("ISO8859-1 (Latin-1)"), 1075 build_msg_string ("ISO8859-1 (Latin-1)"),
1060 build_msg_string ("ISO8859-1 (Latin-1)"), 1076 build_msg_string ("ISO8859-1 (Latin-1)"),
1061 build_string ("iso8859-1"), 0); 1077 build_string ("iso8859-1"), 0, 0);
1062 staticpro (&Vcharset_latin_iso8859_2); 1078 staticpro (&Vcharset_latin_iso8859_2);
1063 Vcharset_latin_iso8859_2 = 1079 Vcharset_latin_iso8859_2 =
1064 make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 2, 1080 make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 2,
1065 CHARSET_TYPE_96, 1, 1, 'B', 1081 CHARSET_TYPE_96, 1, 1, 'B',
1066 CHARSET_LEFT_TO_RIGHT, 1082 CHARSET_LEFT_TO_RIGHT,
1067 build_string ("Latin-2"), 1083 build_string ("Latin-2"),
1068 build_msg_string ("ISO8859-2 (Latin-2)"), 1084 build_msg_string ("ISO8859-2 (Latin-2)"),
1069 build_msg_string ("ISO8859-2 (Latin-2)"), 1085 build_msg_string ("ISO8859-2 (Latin-2)"),
1070 build_string ("iso8859-2"), 0); 1086 build_string ("iso8859-2"), 0, 0);
1071 staticpro (&Vcharset_latin_iso8859_3); 1087 staticpro (&Vcharset_latin_iso8859_3);
1072 Vcharset_latin_iso8859_3 = 1088 Vcharset_latin_iso8859_3 =
1073 make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 2, 1089 make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 2,
1074 CHARSET_TYPE_96, 1, 1, 'C', 1090 CHARSET_TYPE_96, 1, 1, 'C',
1075 CHARSET_LEFT_TO_RIGHT, 1091 CHARSET_LEFT_TO_RIGHT,
1076 build_string ("Latin-3"), 1092 build_string ("Latin-3"),
1077 build_msg_string ("ISO8859-3 (Latin-3)"), 1093 build_msg_string ("ISO8859-3 (Latin-3)"),
1078 build_msg_string ("ISO8859-3 (Latin-3)"), 1094 build_msg_string ("ISO8859-3 (Latin-3)"),
1079 build_string ("iso8859-3"), 0); 1095 build_string ("iso8859-3"), 0, 0);
1080 staticpro (&Vcharset_latin_iso8859_4); 1096 staticpro (&Vcharset_latin_iso8859_4);
1081 Vcharset_latin_iso8859_4 = 1097 Vcharset_latin_iso8859_4 =
1082 make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 2, 1098 make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 2,
1083 CHARSET_TYPE_96, 1, 1, 'D', 1099 CHARSET_TYPE_96, 1, 1, 'D',
1084 CHARSET_LEFT_TO_RIGHT, 1100 CHARSET_LEFT_TO_RIGHT,
1085 build_string ("Latin-4"), 1101 build_string ("Latin-4"),
1086 build_msg_string ("ISO8859-4 (Latin-4)"), 1102 build_msg_string ("ISO8859-4 (Latin-4)"),
1087 build_msg_string ("ISO8859-4 (Latin-4)"), 1103 build_msg_string ("ISO8859-4 (Latin-4)"),
1088 build_string ("iso8859-4"), 0); 1104 build_string ("iso8859-4"), 0, 0);
1089 staticpro (&Vcharset_thai_tis620); 1105 staticpro (&Vcharset_thai_tis620);
1090 Vcharset_thai_tis620 = 1106 Vcharset_thai_tis620 =
1091 make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 2, 1107 make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 2,
1092 CHARSET_TYPE_96, 1, 1, 'T', 1108 CHARSET_TYPE_96, 1, 1, 'T',
1093 CHARSET_LEFT_TO_RIGHT, 1109 CHARSET_LEFT_TO_RIGHT,
1094 build_string ("TIS620"), 1110 build_string ("TIS620"),
1095 build_msg_string ("TIS620 (Thai)"), 1111 build_msg_string ("TIS620 (Thai)"),
1096 build_msg_string ("TIS620.2529 (Thai)"), 1112 build_msg_string ("TIS620.2529 (Thai)"),
1097 build_string ("tis620"),0); 1113 build_string ("tis620"), 0, 0);
1098 staticpro (&Vcharset_greek_iso8859_7); 1114 staticpro (&Vcharset_greek_iso8859_7);
1099 Vcharset_greek_iso8859_7 = 1115 Vcharset_greek_iso8859_7 =
1100 make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 2, 1116 make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 2,
1101 CHARSET_TYPE_96, 1, 1, 'F', 1117 CHARSET_TYPE_96, 1, 1, 'F',
1102 CHARSET_LEFT_TO_RIGHT, 1118 CHARSET_LEFT_TO_RIGHT,
1103 build_string ("ISO8859-7"), 1119 build_string ("ISO8859-7"),
1104 build_msg_string ("ISO8859-7 (Greek)"), 1120 build_msg_string ("ISO8859-7 (Greek)"),
1105 build_msg_string ("ISO8859-7 (Greek)"), 1121 build_msg_string ("ISO8859-7 (Greek)"),
1106 build_string ("iso8859-7"), 0); 1122 build_string ("iso8859-7"), 0, 0);
1107 staticpro (&Vcharset_arabic_iso8859_6); 1123 staticpro (&Vcharset_arabic_iso8859_6);
1108 Vcharset_arabic_iso8859_6 = 1124 Vcharset_arabic_iso8859_6 =
1109 make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 2, 1125 make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 2,
1110 CHARSET_TYPE_96, 1, 1, 'G', 1126 CHARSET_TYPE_96, 1, 1, 'G',
1111 CHARSET_RIGHT_TO_LEFT, 1127 CHARSET_RIGHT_TO_LEFT,
1112 build_string ("ISO8859-6"), 1128 build_string ("ISO8859-6"),
1113 build_msg_string ("ISO8859-6 (Arabic)"), 1129 build_msg_string ("ISO8859-6 (Arabic)"),
1114 build_msg_string ("ISO8859-6 (Arabic)"), 1130 build_msg_string ("ISO8859-6 (Arabic)"),
1115 build_string ("iso8859-6"), 0); 1131 build_string ("iso8859-6"), 0, 0);
1116 staticpro (&Vcharset_hebrew_iso8859_8); 1132 staticpro (&Vcharset_hebrew_iso8859_8);
1117 Vcharset_hebrew_iso8859_8 = 1133 Vcharset_hebrew_iso8859_8 =
1118 make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 2, 1134 make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 2,
1119 CHARSET_TYPE_96, 1, 1, 'H', 1135 CHARSET_TYPE_96, 1, 1, 'H',
1120 CHARSET_RIGHT_TO_LEFT, 1136 CHARSET_RIGHT_TO_LEFT,
1121 build_string ("ISO8859-8"), 1137 build_string ("ISO8859-8"),
1122 build_msg_string ("ISO8859-8 (Hebrew)"), 1138 build_msg_string ("ISO8859-8 (Hebrew)"),
1123 build_msg_string ("ISO8859-8 (Hebrew)"), 1139 build_msg_string ("ISO8859-8 (Hebrew)"),
1124 build_string ("iso8859-8"), 0); 1140 build_string ("iso8859-8"), 0, 0);
1125 staticpro (&Vcharset_katakana_jisx0201); 1141 staticpro (&Vcharset_katakana_jisx0201);
1126 Vcharset_katakana_jisx0201 = 1142 Vcharset_katakana_jisx0201 =
1127 make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 2, 1143 make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 2,
1128 CHARSET_TYPE_94, 1, 1, 'I', 1144 CHARSET_TYPE_94, 1, 1, 'I',
1129 CHARSET_LEFT_TO_RIGHT, 1145 CHARSET_LEFT_TO_RIGHT,
1130 build_string ("JISX0201 Kana"), 1146 build_string ("JISX0201 Kana"),
1131 build_msg_string ("JISX0201.1976 (Japanese Kana)"), 1147 build_msg_string ("JISX0201.1976 (Japanese Kana)"),
1132 build_msg_string ("JISX0201.1976 Japanese Kana"), 1148 build_msg_string ("JISX0201.1976 Japanese Kana"),
1133 build_string ("jisx0201.1976"), 0); 1149 build_string ("jisx0201.1976"), 0, 0);
1134 staticpro (&Vcharset_latin_jisx0201); 1150 staticpro (&Vcharset_latin_jisx0201);
1135 Vcharset_latin_jisx0201 = 1151 Vcharset_latin_jisx0201 =
1136 make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 2, 1152 make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 2,
1137 CHARSET_TYPE_94, 1, 0, 'J', 1153 CHARSET_TYPE_94, 1, 0, 'J',
1138 CHARSET_LEFT_TO_RIGHT, 1154 CHARSET_LEFT_TO_RIGHT,
1139 build_string ("JISX0201 Roman"), 1155 build_string ("JISX0201 Roman"),
1140 build_msg_string ("JISX0201.1976 (Japanese Roman)"), 1156 build_msg_string ("JISX0201.1976 (Japanese Roman)"),
1141 build_msg_string ("JISX0201.1976 Japanese Roman"), 1157 build_msg_string ("JISX0201.1976 Japanese Roman"),
1142 build_string ("jisx0201.1976"), 0); 1158 build_string ("jisx0201.1976"), 0, 0);
1143 staticpro (&Vcharset_cyrillic_iso8859_5); 1159 staticpro (&Vcharset_cyrillic_iso8859_5);
1144 Vcharset_cyrillic_iso8859_5 = 1160 Vcharset_cyrillic_iso8859_5 =
1145 make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 2, 1161 make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 2,
1146 CHARSET_TYPE_96, 1, 1, 'L', 1162 CHARSET_TYPE_96, 1, 1, 'L',
1147 CHARSET_LEFT_TO_RIGHT, 1163 CHARSET_LEFT_TO_RIGHT,
1148 build_string ("ISO8859-5"), 1164 build_string ("ISO8859-5"),
1149 build_msg_string ("ISO8859-5 (Cyrillic)"), 1165 build_msg_string ("ISO8859-5 (Cyrillic)"),
1150 build_msg_string ("ISO8859-5 (Cyrillic)"), 1166 build_msg_string ("ISO8859-5 (Cyrillic)"),
1151 build_string ("iso8859-5"), 0); 1167 build_string ("iso8859-5"), 0, 0);
1152 staticpro (&Vcharset_latin_iso8859_9); 1168 staticpro (&Vcharset_latin_iso8859_9);
1153 Vcharset_latin_iso8859_9 = 1169 Vcharset_latin_iso8859_9 =
1154 make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 2, 1170 make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 2,
1155 CHARSET_TYPE_96, 1, 1, 'M', 1171 CHARSET_TYPE_96, 1, 1, 'M',
1156 CHARSET_LEFT_TO_RIGHT, 1172 CHARSET_LEFT_TO_RIGHT,
1157 build_string ("Latin-5"), 1173 build_string ("Latin-5"),
1158 build_msg_string ("ISO8859-9 (Latin-5)"), 1174 build_msg_string ("ISO8859-9 (Latin-5)"),
1159 build_msg_string ("ISO8859-9 (Latin-5)"), 1175 build_msg_string ("ISO8859-9 (Latin-5)"),
1160 build_string ("iso8859-9"), 0); 1176 build_string ("iso8859-9"), 0, 0);
1161 staticpro (&Vcharset_latin_iso8859_15); 1177 staticpro (&Vcharset_latin_iso8859_15);
1162 Vcharset_latin_iso8859_15 = 1178 Vcharset_latin_iso8859_15 =
1163 make_charset (LEADING_BYTE_LATIN_ISO8859_15, Qlatin_iso8859_15, 2, 1179 make_charset (LEADING_BYTE_LATIN_ISO8859_15, Qlatin_iso8859_15, 2,
1164 CHARSET_TYPE_96, 1, 1, 'b', 1180 CHARSET_TYPE_96, 1, 1, 'b',
1165 CHARSET_LEFT_TO_RIGHT, 1181 CHARSET_LEFT_TO_RIGHT,
1166 build_string ("Latin-9"), 1182 build_string ("Latin-9"),
1167 build_msg_string ("ISO8859-15 (Latin-9)"), 1183 build_msg_string ("ISO8859-15 (Latin-9)"),
1168 build_msg_string ("ISO8859-15 (Latin-9)"), 1184 build_msg_string ("ISO8859-15 (Latin-9)"),
1169 build_string ("iso8859-15"), 0); 1185 build_string ("iso8859-15"), 0, 0);
1170 staticpro (&Vcharset_japanese_jisx0208_1978); 1186 staticpro (&Vcharset_japanese_jisx0208_1978);
1171 Vcharset_japanese_jisx0208_1978 = 1187 Vcharset_japanese_jisx0208_1978 =
1172 make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, 3, 1188 make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, 3,
1173 CHARSET_TYPE_94X94, 2, 0, '@', 1189 CHARSET_TYPE_94X94, 2, 0, '@',
1174 CHARSET_LEFT_TO_RIGHT, 1190 CHARSET_LEFT_TO_RIGHT,
1175 build_string ("JISX0208.1978"), 1191 build_string ("JISX0208.1978"),
1176 build_msg_string ("JISX0208.1978 (Japanese)"), 1192 build_msg_string ("JISX0208.1978 (Japanese)"),
1177 build_msg_string 1193 build_msg_string
1178 ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"), 1194 ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"),
1179 build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"), 0); 1195 build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"), 0, 0);
1180 staticpro (&Vcharset_chinese_gb2312); 1196 staticpro (&Vcharset_chinese_gb2312);
1181 Vcharset_chinese_gb2312 = 1197 Vcharset_chinese_gb2312 =
1182 make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 3, 1198 make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 3,
1183 CHARSET_TYPE_94X94, 2, 0, 'A', 1199 CHARSET_TYPE_94X94, 2, 0, 'A',
1184 CHARSET_LEFT_TO_RIGHT, 1200 CHARSET_LEFT_TO_RIGHT,
1185 build_string ("GB2312"), 1201 build_string ("GB2312"),
1186 build_msg_string ("GB2312)"), 1202 build_msg_string ("GB2312)"),
1187 build_msg_string ("GB2312 Chinese simplified"), 1203 build_msg_string ("GB2312 Chinese simplified"),
1188 build_string ("gb2312"), 0); 1204 build_string ("gb2312"), 0, 0);
1189 staticpro (&Vcharset_japanese_jisx0208); 1205 staticpro (&Vcharset_japanese_jisx0208);
1190 Vcharset_japanese_jisx0208 = 1206 Vcharset_japanese_jisx0208 =
1191 make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 3, 1207 make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 3,
1192 CHARSET_TYPE_94X94, 2, 0, 'B', 1208 CHARSET_TYPE_94X94, 2, 0, 'B',
1193 CHARSET_LEFT_TO_RIGHT, 1209 CHARSET_LEFT_TO_RIGHT,
1194 build_string ("JISX0208"), 1210 build_string ("JISX0208"),
1195 build_msg_string ("JISX0208.1983/1990 (Japanese)"), 1211 build_msg_string ("JISX0208.1983/1990 (Japanese)"),
1196 build_msg_string ("JISX0208.1983/1990 Japanese Kanji"), 1212 build_msg_string ("JISX0208.1983/1990 Japanese Kanji"),
1197 build_string ("jisx0208.19\\(83\\|90\\)"), 0); 1213 build_string ("jisx0208.19\\(83\\|90\\)"), 0, 0);
1198 staticpro (&Vcharset_korean_ksc5601); 1214 staticpro (&Vcharset_korean_ksc5601);
1199 Vcharset_korean_ksc5601 = 1215 Vcharset_korean_ksc5601 =
1200 make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 3, 1216 make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 3,
1201 CHARSET_TYPE_94X94, 2, 0, 'C', 1217 CHARSET_TYPE_94X94, 2, 0, 'C',
1202 CHARSET_LEFT_TO_RIGHT, 1218 CHARSET_LEFT_TO_RIGHT,
1203 build_string ("KSC5601"), 1219 build_string ("KSC5601"),
1204 build_msg_string ("KSC5601 (Korean"), 1220 build_msg_string ("KSC5601 (Korean"),
1205 build_msg_string ("KSC5601 Korean Hangul and Hanja"), 1221 build_msg_string ("KSC5601 Korean Hangul and Hanja"),
1206 build_string ("ksc5601"), 0); 1222 build_string ("ksc5601"), 0, 0);
1207 staticpro (&Vcharset_japanese_jisx0212); 1223 staticpro (&Vcharset_japanese_jisx0212);
1208 Vcharset_japanese_jisx0212 = 1224 Vcharset_japanese_jisx0212 =
1209 make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 3, 1225 make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 3,
1210 CHARSET_TYPE_94X94, 2, 0, 'D', 1226 CHARSET_TYPE_94X94, 2, 0, 'D',
1211 CHARSET_LEFT_TO_RIGHT, 1227 CHARSET_LEFT_TO_RIGHT,
1212 build_string ("JISX0212"), 1228 build_string ("JISX0212"),
1213 build_msg_string ("JISX0212 (Japanese)"), 1229 build_msg_string ("JISX0212 (Japanese)"),
1214 build_msg_string ("JISX0212 Japanese Supplement"), 1230 build_msg_string ("JISX0212 Japanese Supplement"),
1215 build_string ("jisx0212"), 0); 1231 build_string ("jisx0212"), 0, 0);
1216 1232
1217 #define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$" 1233 #define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$"
1218 staticpro (&Vcharset_chinese_cns11643_1); 1234 staticpro (&Vcharset_chinese_cns11643_1);
1219 Vcharset_chinese_cns11643_1 = 1235 Vcharset_chinese_cns11643_1 =
1220 make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, 3, 1236 make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, 3,
1222 CHARSET_LEFT_TO_RIGHT, 1238 CHARSET_LEFT_TO_RIGHT,
1223 build_string ("CNS11643-1"), 1239 build_string ("CNS11643-1"),
1224 build_msg_string ("CNS11643-1 (Chinese traditional)"), 1240 build_msg_string ("CNS11643-1 (Chinese traditional)"),
1225 build_msg_string 1241 build_msg_string
1226 ("CNS 11643 Plane 1 Chinese traditional"), 1242 ("CNS 11643 Plane 1 Chinese traditional"),
1227 build_string (CHINESE_CNS_PLANE_RE("1")), 0); 1243 build_string (CHINESE_CNS_PLANE_RE("1")), 0, 0);
1228 staticpro (&Vcharset_chinese_cns11643_2); 1244 staticpro (&Vcharset_chinese_cns11643_2);
1229 Vcharset_chinese_cns11643_2 = 1245 Vcharset_chinese_cns11643_2 =
1230 make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 3, 1246 make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 3,
1231 CHARSET_TYPE_94X94, 2, 0, 'H', 1247 CHARSET_TYPE_94X94, 2, 0, 'H',
1232 CHARSET_LEFT_TO_RIGHT, 1248 CHARSET_LEFT_TO_RIGHT,
1233 build_string ("CNS11643-2"), 1249 build_string ("CNS11643-2"),
1234 build_msg_string ("CNS11643-2 (Chinese traditional)"), 1250 build_msg_string ("CNS11643-2 (Chinese traditional)"),
1235 build_msg_string 1251 build_msg_string
1236 ("CNS 11643 Plane 2 Chinese traditional"), 1252 ("CNS 11643 Plane 2 Chinese traditional"),
1237 build_string (CHINESE_CNS_PLANE_RE("2")), 0); 1253 build_string (CHINESE_CNS_PLANE_RE("2")), 0, 0);
1238 staticpro (&Vcharset_chinese_big5_1); 1254 staticpro (&Vcharset_chinese_big5_1);
1239 Vcharset_chinese_big5_1 = 1255 Vcharset_chinese_big5_1 =
1240 make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 3, 1256 make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 3,
1241 CHARSET_TYPE_94X94, 2, 0, '0', 1257 CHARSET_TYPE_94X94, 2, 0, '0',
1242 CHARSET_LEFT_TO_RIGHT, 1258 CHARSET_LEFT_TO_RIGHT,
1243 build_string ("Big5"), 1259 build_string ("Big5"),
1244 build_msg_string ("Big5 (Level-1)"), 1260 build_msg_string ("Big5 (Level-1)"),
1245 build_msg_string 1261 build_msg_string
1246 ("Big5 Level-1 Chinese traditional"), 1262 ("Big5 Level-1 Chinese traditional"),
1247 build_string ("big5"), 0); 1263 build_string ("big5"), 0, 0);
1248 staticpro (&Vcharset_chinese_big5_2); 1264 staticpro (&Vcharset_chinese_big5_2);
1249 Vcharset_chinese_big5_2 = 1265 Vcharset_chinese_big5_2 =
1250 make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 3, 1266 make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 3,
1251 CHARSET_TYPE_94X94, 2, 0, '1', 1267 CHARSET_TYPE_94X94, 2, 0, '1',
1252 CHARSET_LEFT_TO_RIGHT, 1268 CHARSET_LEFT_TO_RIGHT,
1253 build_string ("Big5"), 1269 build_string ("Big5"),
1254 build_msg_string ("Big5 (Level-2)"), 1270 build_msg_string ("Big5 (Level-2)"),
1255 build_msg_string 1271 build_msg_string
1256 ("Big5 Level-2 Chinese traditional"), 1272 ("Big5 Level-2 Chinese traditional"),
1257 build_string ("big5"), 0); 1273 build_string ("big5"), 0, 0);
1258 1274
1259 1275
1260 #ifdef ENABLE_COMPOSITE_CHARS 1276 #ifdef ENABLE_COMPOSITE_CHARS
1261 /* #### For simplicity, we put composite chars into a 96x96 charset. 1277 /* #### For simplicity, we put composite chars into a 96x96 charset.
1262 This is going to lead to problems because you can run out of 1278 This is going to lead to problems because you can run out of
1267 CHARSET_TYPE_96X96, 2, 0, 0, 1283 CHARSET_TYPE_96X96, 2, 0, 0,
1268 CHARSET_LEFT_TO_RIGHT, 1284 CHARSET_LEFT_TO_RIGHT,
1269 build_string ("Composite"), 1285 build_string ("Composite"),
1270 build_msg_string ("Composite characters"), 1286 build_msg_string ("Composite characters"),
1271 build_msg_string ("Composite characters"), 1287 build_msg_string ("Composite characters"),
1272 build_string (""), 0); 1288 build_string (""), 0, 0);
1273 #else 1289 #else
1274 /* We create a hack so that we have a way of storing ESC 0 and ESC 1 1290 /* We create a hack so that we have a way of storing ESC 0 and ESC 1
1275 sequences as "characters", so that they will be output correctly. */ 1291 sequences as "characters", so that they will be output correctly. */
1276 staticpro (&Vcharset_composite); 1292 staticpro (&Vcharset_composite);
1277 Vcharset_composite = 1293 Vcharset_composite =
1279 CHARSET_TYPE_96, 1, 1, '|', 1295 CHARSET_TYPE_96, 1, 1, '|',
1280 CHARSET_LEFT_TO_RIGHT, 1296 CHARSET_LEFT_TO_RIGHT,
1281 build_string ("Composite hack"), 1297 build_string ("Composite hack"),
1282 build_msg_string ("Composite characters hack"), 1298 build_msg_string ("Composite characters hack"),
1283 build_msg_string ("Composite characters hack"), 1299 build_msg_string ("Composite characters hack"),
1284 build_string (""), 0); 1300 build_string (""), 0, 0);
1285 #endif /* ENABLE_COMPOSITE_CHARS */ 1301 #endif /* ENABLE_COMPOSITE_CHARS */
1286 } 1302 }