X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fmule-charset.c;h=c3d69deb9f743c12b515ea4d3b8e74af02d53c4d;hb=0680bf5c284a73aaa6e267c4b0f1363d2cb48739;hp=9d5f7d2aa2b56ae417891abf898c52579cb6ae6b;hpb=fffeff219b110f32d1c9e414e0241f89b85fa0d6;p=chise%2Fxemacs-chise.git- diff --git a/src/mule-charset.c b/src/mule-charset.c index 9d5f7d2..c3d69de 100644 --- a/src/mule-charset.c +++ b/src/mule-charset.c @@ -58,12 +58,12 @@ Lisp_Object Vcharset_japanese_jisx0212; Lisp_Object Vcharset_chinese_cns11643_1; Lisp_Object Vcharset_chinese_cns11643_2; #ifdef UTF2000 -Lisp_Object Vcharset_chinese_cns11643_3; -Lisp_Object Vcharset_chinese_cns11643_4; -Lisp_Object Vcharset_chinese_cns11643_5; -Lisp_Object Vcharset_chinese_cns11643_6; -Lisp_Object Vcharset_chinese_cns11643_7; Lisp_Object Vcharset_ucs_bmp; +Lisp_Object Vcharset_latin_viscii; +Lisp_Object Vcharset_latin_viscii_lower; +Lisp_Object Vcharset_latin_viscii_upper; +Lisp_Object Vcharset_hiragana_jisx0208; +Lisp_Object Vcharset_katakana_jisx0208; #endif Lisp_Object Vcharset_chinese_big5_1; Lisp_Object Vcharset_chinese_big5_2; @@ -125,399 +125,189 @@ Bytecount rep_bytes_by_first_byte[0xA0] = #endif #ifdef UTF2000 -Charset_ID latin_a_char_to_charset[128] = { - /* U+0100 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0101 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0102 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0103 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0104 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0105 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0106 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0107 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0108 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0109 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+010A */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+010B */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+010C */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+010D */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+010E */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+010F */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0110 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0111 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0112 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0113 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0114 */ LEADING_BYTE_UCS_BMP, - /* U+0115 */ LEADING_BYTE_UCS_BMP, - /* U+0116 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0117 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0118 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0119 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+011A */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+011B */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+011C */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+011D */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+011E */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+011F */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0120 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0121 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0122 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0123 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0124 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0125 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0126 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0127 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0128 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0129 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+012A */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+012B */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+012C */ LEADING_BYTE_UCS_BMP, - /* U+012D */ LEADING_BYTE_UCS_BMP, - /* U+012E */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+012F */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0130 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0131 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0132 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0133 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0134 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0135 */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+0136 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0137 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0138 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0139 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+013A */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+013B */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+013C */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+013D */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+013E */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+013F */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0140 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0141 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0142 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0143 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0144 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0145 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0146 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0147 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0148 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0149 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+014A */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+014B */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+014C */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+014D */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+014E */ LEADING_BYTE_UCS_BMP, - /* U+014F */ LEADING_BYTE_UCS_BMP, - /* U+0150 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0151 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0152 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0153 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0154 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0155 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0156 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0157 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0158 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0159 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+015A */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+015B */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+015C */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+015D */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+015E */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+015F */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0160 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0161 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0162 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0163 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0164 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0165 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0166 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0167 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0168 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0169 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+016A */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+016B */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+016C */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+016D */ LEADING_BYTE_LATIN_ISO8859_3, - /* U+016E */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+016F */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0170 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0171 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+0172 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0173 */ LEADING_BYTE_LATIN_ISO8859_4, - /* U+0174 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0175 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0176 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0177 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0178 */ LEADING_BYTE_JAPANESE_JISX0212, - /* U+0179 */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+017A */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+017B */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+017C */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+017D */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+017E */ LEADING_BYTE_LATIN_ISO8859_2, - /* U+017F */ LEADING_BYTE_UCS_BMP -}; +static Lisp_Object +mark_char_byte_table (Lisp_Object obj, void (*markobj) (Lisp_Object)) +{ + struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (obj); + int i; -unsigned char latin_a_char_to_byte1[128] = { - /* U+0100 */ 0xC0 - 0x80, - /* U+0101 */ 0xE0 - 0x80, - /* U+0102 */ 0xC3 - 0x80, - /* U+0103 */ 0xE3 - 0x80, - /* U+0104 */ 0xA1 - 0x80, - /* U+0105 */ 0xB1 - 0x80, - /* U+0106 */ 0xC6 - 0x80, - /* U+0107 */ 0xE6 - 0x80, - /* U+0108 */ 0xC6 - 0x80, - /* U+0109 */ 0xE6 - 0x80, - /* U+010A */ 0xC5 - 0x80, - /* U+010B */ 0xE5 - 0x80, - /* U+010C */ 0xC8 - 0x80, - /* U+010D */ 0xE8 - 0x80, - /* U+010E */ 0xCF - 0x80, - /* U+010F */ 0xEF - 0x80, - /* U+0110 */ 0xD0 - 0x80, - /* U+0111 */ 0xF0 - 0x80, - /* U+0112 */ 0xAA - 0x80, - /* U+0113 */ 0xBA - 0x80, - /* U+0114 */ 0x01, - /* U+0115 */ 0x01, - /* U+0116 */ 0xCC - 0x80, - /* U+0117 */ 0xEC - 0x80, - /* U+0118 */ 0xCA - 0x80, - /* U+0119 */ 0xEA - 0x80, - /* U+011A */ 0xCC - 0x80, - /* U+011B */ 0xEC - 0x80, - /* U+011C */ 0xD8 - 0x80, - /* U+011D */ 0xF8 - 0x80, - /* U+011E */ 0xAB - 0x80, - /* U+011F */ 0xBB - 0x80, - /* U+0120 */ 0xD5 - 0x80, - /* U+0121 */ 0xF5 - 0x80, - /* U+0122 */ 0xAB - 0x80, - /* U+0123 */ 0xBB - 0x80, - /* U+0124 */ 0xA6 - 0x80, - /* U+0125 */ 0xB6 - 0x80, - /* U+0126 */ 0xA1 - 0x80, - /* U+0127 */ 0xB1 - 0x80, - /* U+0128 */ 0xA5 - 0x80, - /* U+0129 */ 0xB5 - 0x80, - /* U+012A */ 0xCF - 0x80, - /* U+012B */ 0xEF - 0x80, - /* U+012C */ 0x01, - /* U+012D */ 0x01, - /* U+012E */ 0xC7 - 0x80, - /* U+012F */ 0xE7 - 0x80, - /* U+0130 */ 0xA9 - 0x80, - /* U+0131 */ 0xB9 - 0x80, - /* U+0132 */ 0x29, - /* U+0133 */ 0x29, - /* U+0134 */ 0xAC - 0x80, - /* U+0135 */ 0xBC - 0x80, - /* U+0136 */ 0xD3 - 0x80, - /* U+0137 */ 0xF3 - 0x80, - /* U+0138 */ 0xA2 - 0x80, - /* U+0139 */ 0xC5 - 0x80, - /* U+013A */ 0xE5 - 0x80, - /* U+013B */ 0xA6 - 0x80, - /* U+013C */ 0xB6 - 0x80, - /* U+013D */ 0xA5 - 0x80, - /* U+013E */ 0xB5 - 0x80, - /* U+013F */ 0x29, - /* U+0140 */ 0x29, - /* U+0141 */ 0xA3 - 0x80, - /* U+0142 */ 0xB3 - 0x80, - /* U+0143 */ 0xD1 - 0x80, - /* U+0144 */ 0xF1 - 0x80, - /* U+0145 */ 0xD1 - 0x80, - /* U+0146 */ 0xF1 - 0x80, - /* U+0147 */ 0xD2 - 0x80, - /* U+0148 */ 0xF2 - 0x80, - /* U+0149 */ 0x29, - /* U+014A */ 0xBD - 0x80, - /* U+014B */ 0xBF - 0x80, - /* U+014C */ 0xD2 - 0x80, - /* U+014D */ 0xF2 - 0x80, - /* U+014E */ 0x01, - /* U+014F */ 0x01, - /* U+0150 */ 0xD5 - 0x80, - /* U+0151 */ 0xF5 - 0x80, - /* U+0152 */ 0x29, - /* U+0153 */ 0x29, - /* U+0154 */ 0xC0 - 0x80, - /* U+0155 */ 0xE0 - 0x80, - /* U+0156 */ 0xA3 - 0x80, - /* U+0157 */ 0xB3 - 0x80, - /* U+0158 */ 0xD8 - 0x80, - /* U+0159 */ 0xF8 - 0x80, - /* U+015A */ 0xA6 - 0x80, - /* U+015B */ 0xB6 - 0x80, - /* U+015C */ 0xDE - 0x80, - /* U+015D */ 0xFE - 0x80, - /* U+015E */ 0xAA - 0x80, - /* U+015F */ 0xBA - 0x80, - /* U+0160 */ 0xA9 - 0x80, - /* U+0161 */ 0xB9 - 0x80, - /* U+0162 */ 0xDE - 0x80, - /* U+0163 */ 0xFE - 0x80, - /* U+0164 */ 0xAB - 0x80, - /* U+0165 */ 0xBB - 0x80, - /* U+0166 */ 0xAC - 0x80, - /* U+0167 */ 0xBC - 0x80, - /* U+0168 */ 0xDD - 0x80, - /* U+0169 */ 0xFD - 0x80, - /* U+016A */ 0xDE - 0x80, - /* U+016B */ 0xFE - 0x80, - /* U+016C */ 0xDD - 0x80, - /* U+016D */ 0xFD - 0x80, - /* U+016E */ 0xD9 - 0x80, - /* U+016F */ 0xF9 - 0x80, - /* U+0170 */ 0xDB - 0x80, - /* U+0171 */ 0xFB - 0x80, - /* U+0172 */ 0xD9 - 0x80, - /* U+0173 */ 0xF9 - 0x80, - /* U+0174 */ 0x2A, - /* U+0175 */ 0x2B, - /* U+0176 */ 0x2A, - /* U+0177 */ 0x2B, - /* U+0178 */ 0x2A, - /* U+0179 */ 0xAC - 0x80, - /* U+017A */ 0xBC - 0x80, - /* U+017B */ 0xAF - 0x80, - /* U+017C */ 0xBF - 0x80, - /* U+017D */ 0xAE - 0x80, - /* U+017E */ 0xBE - 0x80, - /* U+017F */ 0x01 -}; + for (i = 0; i < 256; i++) + { + markobj (cte->property[i]); + } + return Qnil; +} + +static int +char_byte_table_equal (Lisp_Object obj1, Lisp_Object obj2, int depth) +{ + struct Lisp_Char_Byte_Table *cte1 = XCHAR_BYTE_TABLE (obj1); + struct Lisp_Char_Byte_Table *cte2 = XCHAR_BYTE_TABLE (obj2); + int i; + + for (i = 0; i < 256; i++) + if (CHAR_BYTE_TABLE_P (cte1->property[i])) + { + if (CHAR_BYTE_TABLE_P (cte2->property[i])) + { + if (!char_byte_table_equal (cte1->property[i], + cte2->property[i], depth + 1)) + return 0; + } + else + return 0; + } + else + if (!internal_equal (cte1->property[i], cte2->property[i], depth + 1)) + return 0; + return 1; +} -unsigned char latin_a_char_to_byte2[128] = { - /* U+0100 */ 0x00, - /* U+0101 */ 0x00, - /* U+0102 */ 0x00, - /* U+0103 */ 0x00, - /* U+0104 */ 0x00, - /* U+0105 */ 0x00, - /* U+0106 */ 0x00, - /* U+0107 */ 0x00, - /* U+0108 */ 0x00, - /* U+0109 */ 0x00, - /* U+010A */ 0x00, - /* U+010B */ 0x00, - /* U+010C */ 0x00, - /* U+010D */ 0x00, - /* U+010E */ 0x00, - /* U+010F */ 0x00, - /* U+0110 */ 0x00, - /* U+0111 */ 0x00, - /* U+0112 */ 0x00, - /* U+0113 */ 0x00, - /* U+0114 */ 0x14, - /* U+0115 */ 0x15, - /* U+0116 */ 0x00, - /* U+0117 */ 0x00, - /* U+0118 */ 0x00, - /* U+0119 */ 0x00, - /* U+011A */ 0x00, - /* U+011B */ 0x00, - /* U+011C */ 0x00, - /* U+011D */ 0x00, - /* U+011E */ 0x00, - /* U+011F */ 0x00, - /* U+0120 */ 0x00, - /* U+0121 */ 0x00, - /* U+0122 */ 0x00, - /* U+0123 */ 0x00, - /* U+0124 */ 0x00, - /* U+0125 */ 0x00, - /* U+0126 */ 0x00, - /* U+0127 */ 0x00, - /* U+0128 */ 0x00, - /* U+0129 */ 0x00, - /* U+012A */ 0x00, - /* U+012B */ 0x00, - /* U+012C */ 0x2C, - /* U+012D */ 0x2D, - /* U+012E */ 0x00, - /* U+012F */ 0x00, - /* U+0130 */ 0x00, - /* U+0131 */ 0x00, - /* U+0132 */ 0x26, - /* U+0133 */ 0x46, - /* U+0134 */ 0x00, - /* U+0135 */ 0x00, - /* U+0136 */ 0x00, - /* U+0137 */ 0x00, - /* U+0138 */ 0x00, - /* U+0139 */ 0x00, - /* U+013A */ 0x00, - /* U+013B */ 0x00, - /* U+013C */ 0x00, - /* U+013D */ 0x00, - /* U+013E */ 0x00, - /* U+013F */ 0x29, - /* U+0140 */ 0x49, - /* U+0141 */ 0x00, - /* U+0142 */ 0x00, - /* U+0143 */ 0x00, - /* U+0144 */ 0x00, - /* U+0145 */ 0x00, - /* U+0146 */ 0x00, - /* U+0147 */ 0x00, - /* U+0148 */ 0x00, - /* U+0149 */ 0x4A, - /* U+014A */ 0x00, - /* U+014B */ 0x00, - /* U+014C */ 0x00, - /* U+014D */ 0x00, - /* U+014E */ 0x4E, - /* U+014F */ 0x4F, - /* U+0150 */ 0x00, - /* U+0151 */ 0x00, - /* U+0152 */ 0x2D, - /* U+0153 */ 0x4D, - /* U+0154 */ 0x00, - /* U+0155 */ 0x00, - /* U+0156 */ 0x00, - /* U+0157 */ 0x00, - /* U+0158 */ 0x00, - /* U+0159 */ 0x00, - /* U+015A */ 0x00, - /* U+015B */ 0x00, - /* U+015C */ 0x00, - /* U+015D */ 0x00, - /* U+015E */ 0x00, - /* U+015F */ 0x00, - /* U+0160 */ 0x00, - /* U+0161 */ 0x00, - /* U+0162 */ 0x00, - /* U+0163 */ 0x00, - /* U+0164 */ 0x00, - /* U+0165 */ 0x00, - /* U+0166 */ 0x00, - /* U+0167 */ 0x00, - /* U+0168 */ 0x00, - /* U+0169 */ 0x00, - /* U+016A */ 0x00, - /* U+016B */ 0x00, - /* U+016C */ 0x00, - /* U+016D */ 0x00, - /* U+016E */ 0x00, - /* U+016F */ 0x00, - /* U+0170 */ 0x00, - /* U+0171 */ 0x00, - /* U+0172 */ 0x00, - /* U+0173 */ 0x00, - /* U+0174 */ 0x71, - /* U+0175 */ 0x71, - /* U+0176 */ 0x74, - /* U+0177 */ 0x74, - /* U+0178 */ 0x73, - /* U+0179 */ 0x00, - /* U+017A */ 0x00, - /* U+017B */ 0x00, - /* U+017C */ 0x00, - /* U+017D */ 0x00, - /* U+017E */ 0x00, - /* U+017F */ 0x7F +static unsigned long +char_byte_table_hash (Lisp_Object obj, int depth) +{ + struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (obj); + + return internal_array_hash (cte->property, 256, depth); +} + +static const struct lrecord_description char_byte_table_description[] = { + { XD_LISP_OBJECT, offsetof(struct Lisp_Char_Byte_Table, property), 256 }, + { XD_END } }; +DEFINE_LRECORD_IMPLEMENTATION ("char-code-table", char_byte_table, + mark_char_byte_table, + internal_object_printer, + 0, char_byte_table_equal, + char_byte_table_hash, + char_byte_table_description, + struct Lisp_Char_Byte_Table); + + +static Lisp_Object +make_char_byte_table (Lisp_Object initval) +{ + Lisp_Object obj; + int i; + struct Lisp_Char_Byte_Table *cte = + alloc_lcrecord_type (struct Lisp_Char_Byte_Table, + &lrecord_char_byte_table); + + for (i = 0; i < 256; i++) + cte->property[i] = initval; + + XSETCHAR_BYTE_TABLE (obj, cte); + return obj; +} + +static Lisp_Object +copy_char_byte_table (Lisp_Object entry) +{ + struct Lisp_Char_Byte_Table *cte = XCHAR_BYTE_TABLE (entry); + Lisp_Object obj; + int i; + struct Lisp_Char_Byte_Table *ctenew = + alloc_lcrecord_type (struct Lisp_Char_Byte_Table, + &lrecord_char_byte_table); + + for (i = 0; i < 256; i++) + { + Lisp_Object new = cte->property[i]; + if (CHAR_BYTE_TABLE_P (new)) + ctenew->property[i] = copy_char_byte_table (new); + else + ctenew->property[i] = new; + } + + XSETCHAR_BYTE_TABLE (obj, ctenew); + return obj; +} + +#define make_char_code_table(initval) make_char_byte_table(initval) + +Lisp_Object +get_char_code_table (Emchar ch, Lisp_Object table) +{ + struct Lisp_Char_Byte_Table* cpt = XCHAR_BYTE_TABLE (table); + Lisp_Object ret = cpt->property [ch >> 24]; + + if (CHAR_BYTE_TABLE_P (ret)) + cpt = XCHAR_BYTE_TABLE (ret); + else + return ret; + + ret = cpt->property [(unsigned char) (ch >> 16)]; + if (CHAR_BYTE_TABLE_P (ret)) + cpt = XCHAR_BYTE_TABLE (ret); + else + return ret; + + ret = cpt->property [(unsigned char) (ch >> 8)]; + if (CHAR_BYTE_TABLE_P (ret)) + cpt = XCHAR_BYTE_TABLE (ret); + else + return ret; + + return cpt->property [(unsigned char) ch]; +} + +void +put_char_code_table (Emchar ch, Lisp_Object value, Lisp_Object table) +{ + struct Lisp_Char_Byte_Table* cpt1 = XCHAR_BYTE_TABLE (table); + Lisp_Object ret = cpt1->property[ch >> 24]; + + if (CHAR_BYTE_TABLE_P (ret)) + { + struct Lisp_Char_Byte_Table* cpt2 = XCHAR_BYTE_TABLE (ret); + + ret = cpt2->property[(unsigned char)(ch >> 16)]; + if (CHAR_BYTE_TABLE_P (ret)) + { + struct Lisp_Char_Byte_Table* cpt3 = XCHAR_BYTE_TABLE (ret); + + ret = cpt3->property[(unsigned char)(ch >> 8)]; + if (CHAR_BYTE_TABLE_P (ret)) + { + struct Lisp_Char_Byte_Table* cpt4 + = XCHAR_BYTE_TABLE (ret); + + cpt4->property[(unsigned char)ch] = value; + } + else if (!EQ (ret, value)) + { + Lisp_Object cpt4 = make_char_byte_table (ret); + + XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)ch] = value; + cpt3->property[(unsigned char)(ch >> 8)] = cpt4; + } + } + else if (!EQ (ret, value)) + { + Lisp_Object cpt3 = make_char_byte_table (ret); + Lisp_Object cpt4 = make_char_byte_table (ret); + + XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)ch] = value; + XCHAR_BYTE_TABLE(cpt3)->property[(unsigned char)(ch >> 8)] + = cpt4; + cpt2->property[(unsigned char)(ch >> 16)] = cpt3; + } + } + else if (!EQ (ret, value)) + { + Lisp_Object cpt2 = make_char_byte_table (ret); + Lisp_Object cpt3 = make_char_byte_table (ret); + Lisp_Object cpt4 = make_char_byte_table (ret); + + XCHAR_BYTE_TABLE(cpt4)->property[(unsigned char)ch] = value; + XCHAR_BYTE_TABLE(cpt3)->property[(unsigned char)(ch >> 8)] = cpt4; + XCHAR_BYTE_TABLE(cpt2)->property[(unsigned char)(ch >> 16)] = cpt3; + cpt1->property[(unsigned char)(ch >> 24)] = cpt2; + } +} + + Lisp_Object Vutf_2000_version; #endif @@ -556,12 +346,14 @@ Lisp_Object Qascii, Qchinese_cns11643_1, Qchinese_cns11643_2, #ifdef UTF2000 - Qchinese_cns11643_3, - Qchinese_cns11643_4, - Qchinese_cns11643_5, - Qchinese_cns11643_6, - Qchinese_cns11643_7, Qucs_bmp, + Qlatin_viscii, + Qlatin_viscii_lower, + Qlatin_viscii_upper, + Qvietnamese_viscii_lower, + Qvietnamese_viscii_upper, + Qhiragana_jisx0208, + Qkatakana_jisx0208, #endif Qchinese_big5_1, Qchinese_big5_2, @@ -571,8 +363,12 @@ Lisp_Object Ql2r, Qr2l; Lisp_Object Vcharset_hash_table; +#ifdef UTF2000 +static Charset_ID next_allocated_leading_byte; +#else static Charset_ID next_allocated_1_byte_leading_byte; static Charset_ID next_allocated_2_byte_leading_byte; +#endif /* Composite characters are characters constructed by overstriking two or more regular characters. @@ -934,6 +730,10 @@ mark_charset (Lisp_Object obj, void (*markobj) (Lisp_Object)) markobj (cs->doc_string); markobj (cs->registry); markobj (cs->ccl_program); +#ifdef UTF2000 + markobj (cs->decoding_table); + markobj (cs->encoding_table); +#endif return cs->name; } @@ -973,20 +773,28 @@ print_charset (Lisp_Object obj, Lisp_Object printcharfun, int escapeflag) static const struct lrecord_description charset_description[] = { { XD_LISP_OBJECT, offsetof(struct Lisp_Charset, name), 7 }, +#ifdef UTF2000 + { XD_LISP_OBJECT, offsetof(struct Lisp_Charset, decoding_table), 2 }, +#endif { XD_END } }; DEFINE_LRECORD_IMPLEMENTATION ("charset", charset, - mark_charset, print_charset, 0, 0, 0, charset_description, + mark_charset, print_charset, 0, 0, 0, + charset_description, struct Lisp_Charset); + /* Make a new charset. */ static Lisp_Object -make_charset (Charset_ID id, Lisp_Object name, unsigned char rep_bytes, +make_charset (Charset_ID id, Lisp_Object name, unsigned char type, unsigned char columns, unsigned char graphic, - Bufbyte final, unsigned char direction, Lisp_Object short_name, + Bufbyte final, unsigned char direction, Lisp_Object short_name, Lisp_Object long_name, Lisp_Object doc, - Lisp_Object reg) + Lisp_Object reg, + Lisp_Object decoding_table, + Emchar ucs_min, Emchar ucs_max, + Emchar code_offset, unsigned char byte_offset) { Lisp_Object obj; struct Lisp_Charset *cs = @@ -997,7 +805,6 @@ make_charset (Charset_ID id, Lisp_Object name, unsigned char rep_bytes, CHARSET_NAME (cs) = name; CHARSET_SHORT_NAME (cs) = short_name; CHARSET_LONG_NAME (cs) = long_name; - CHARSET_REP_BYTES (cs) = rep_bytes; CHARSET_DIRECTION (cs) = direction; CHARSET_TYPE (cs) = type; CHARSET_COLUMNS (cs) = columns; @@ -1007,8 +814,16 @@ make_charset (Charset_ID id, Lisp_Object name, unsigned char rep_bytes, CHARSET_REGISTRY (cs) = reg; CHARSET_CCL_PROGRAM (cs) = Qnil; CHARSET_REVERSE_DIRECTION_CHARSET (cs) = Qnil; +#ifdef UTF2000 + CHARSET_DECODING_TABLE(cs) = Qnil; + CHARSET_ENCODING_TABLE(cs) = Qnil; + CHARSET_UCS_MIN(cs) = ucs_min; + CHARSET_UCS_MAX(cs) = ucs_max; + CHARSET_CODE_OFFSET(cs) = code_offset; + CHARSET_BYTE_OFFSET(cs) = byte_offset; +#endif - switch ( CHARSET_TYPE (cs) ) + switch (CHARSET_TYPE (cs)) { case CHARSET_TYPE_94: CHARSET_DIMENSION (cs) = 1; @@ -1027,10 +842,18 @@ make_charset (Charset_ID id, Lisp_Object name, unsigned char rep_bytes, CHARSET_CHARS (cs) = 96; break; #ifdef UTF2000 + case CHARSET_TYPE_128: + CHARSET_DIMENSION (cs) = 1; + CHARSET_CHARS (cs) = 128; + break; case CHARSET_TYPE_128X128: CHARSET_DIMENSION (cs) = 2; CHARSET_CHARS (cs) = 128; break; + case CHARSET_TYPE_256: + CHARSET_DIMENSION (cs) = 1; + CHARSET_CHARS (cs) = 256; + break; case CHARSET_TYPE_256X256: CHARSET_DIMENSION (cs) = 2; CHARSET_CHARS (cs) = 256; @@ -1038,14 +861,26 @@ make_charset (Charset_ID id, Lisp_Object name, unsigned char rep_bytes, #endif } +#ifndef UTF2000 + if (id == LEADING_BYTE_ASCII) + CHARSET_REP_BYTES (cs) = 1; + else if (id < 0xA0) + CHARSET_REP_BYTES (cs) = CHARSET_DIMENSION (cs) + 1; + else + CHARSET_REP_BYTES (cs) = CHARSET_DIMENSION (cs) + 2; +#endif + if (final) { /* some charsets do not have final characters. This includes ASCII, Control-1, Composite, and the two faux private charsets. */ #if UTF2000 - assert (NILP (charset_by_attributes[type][final])); - charset_by_attributes[type][final] = obj; + if (code_offset == 0) + { + assert (NILP (charset_by_attributes[type][final])); + charset_by_attributes[type][final] = obj; + } #else assert (NILP (charset_by_attributes[type][final][direction])); charset_by_attributes[type][final][direction] = obj; @@ -1057,7 +892,7 @@ make_charset (Charset_ID id, Lisp_Object name, unsigned char rep_bytes, #ifndef UTF2000 if (id < 0xA0) /* official leading byte */ - rep_bytes_by_first_byte[id] = rep_bytes; + rep_bytes_by_first_byte[id] = CHARSET_REP_BYTES (cs); #endif /* Some charsets are "faux" and don't have names or really exist at @@ -1072,6 +907,12 @@ get_unallocated_leading_byte (int dimension) { Charset_ID lb; +#ifdef UTF2000 + if (next_allocated_leading_byte > MAX_LEADING_BYTE_PRIVATE) + lb = 0; + else + lb = next_allocated_leading_byte++; +#else if (dimension == 1) { if (next_allocated_1_byte_leading_byte > MAX_LEADING_BYTE_PRIVATE_1) @@ -1086,6 +927,7 @@ get_unallocated_leading_byte (int dimension) else lb = next_allocated_2_byte_leading_byte++; } +#endif if (!lb) signal_simple_error @@ -1095,6 +937,147 @@ get_unallocated_leading_byte (int dimension) return lb; } +#ifdef UTF2000 +unsigned char +charset_get_byte1 (Lisp_Object charset, Emchar ch) +{ + Lisp_Object table; + int d; + + if (!EQ (table = XCHARSET_ENCODING_TABLE (charset), Qnil)) + { + Lisp_Object value = get_char_code_table (ch, table); + + if (INTP (value)) + { + Emchar code = XINT (value); + + if (code < (1 << 8)) + return code; + else if (code < (1 << 16)) + return code >> 8; + else if (code < (1 << 24)) + return code >> 16; + else + return code >> 24; + } + } + if ((XCHARSET_UCS_MIN (charset) <= ch) + && (ch <= XCHARSET_UCS_MAX (charset))) + return (ch - XCHARSET_UCS_MIN (charset) + + XCHARSET_CODE_OFFSET (charset)) + / (XCHARSET_DIMENSION (charset) == 1 ? + 1 + : + XCHARSET_DIMENSION (charset) == 2 ? + XCHARSET_CHARS (charset) + : + XCHARSET_DIMENSION (charset) == 3 ? + XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset) + : + XCHARSET_CHARS (charset) + * XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset)) + + XCHARSET_BYTE_OFFSET (charset); + else if (XCHARSET_CODE_OFFSET (charset) == 0) + { + if (XCHARSET_DIMENSION (charset) == 1) + { + if (XCHARSET_CHARS (charset) == 94) + { + if (((d = ch - (MIN_CHAR_94 + + (XCHARSET_FINAL (charset) - '0') * 94)) >= 0) + && (d < 94)) + return d + 33; + } + else if (XCHARSET_CHARS (charset) == 96) + { + if (((d = ch - (MIN_CHAR_96 + + (XCHARSET_FINAL (charset) - '0') * 96)) >= 0) + && (d < 96)) + return d + 32; + } + else + return 0; + } + else if (XCHARSET_DIMENSION (charset) == 2) + { + if (XCHARSET_CHARS (charset) == 94) + { + if (((d = ch - (MIN_CHAR_94x94 + + (XCHARSET_FINAL (charset) - '0') * 94 * 94)) + >= 0) + && (d < 94 * 94)) + return (d / 94) + 33; + } + else if (XCHARSET_CHARS (charset) == 96) + { + if (((d = ch - (MIN_CHAR_96x96 + + (XCHARSET_FINAL (charset) - '0') * 96 * 96)) + >= 0) + && (d < 96 * 96)) + return (d / 96) + 32; + } + } + } + return 0; +} + +unsigned char +charset_get_byte2 (Lisp_Object charset, Emchar ch) +{ + if (XCHARSET_DIMENSION (charset) == 1) + return 0; + else + { + Lisp_Object table; + + if (!EQ (table = XCHARSET_ENCODING_TABLE (charset), Qnil)) + { + Lisp_Object value = get_char_code_table (ch, table); + + if (INTP (value)) + { + Emchar code = XINT (value); + + if (code < (1 << 16)) + return (unsigned char)code; + else if (code < (1 << 24)) + return (unsigned char)(code >> 16); + else + return (unsigned char)(code >> 24); + } + } + if ((XCHARSET_UCS_MIN (charset) <= ch) + && (ch <= XCHARSET_UCS_MAX (charset))) + return ((ch - XCHARSET_UCS_MIN (charset) + + XCHARSET_CODE_OFFSET (charset)) + / (XCHARSET_DIMENSION (charset) == 2 ? + 1 + : + XCHARSET_DIMENSION (charset) == 3 ? + XCHARSET_CHARS (charset) + : + XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset))) + % XCHARSET_CHARS (charset) + + XCHARSET_BYTE_OFFSET (charset); + else if (XCHARSET_CHARS (charset) == 94) + return (MIN_CHAR_94x94 + + (XCHARSET_FINAL (charset) - '0') * 94 * 94 <= ch) + && (ch < MIN_CHAR_94x94 + + (XCHARSET_FINAL (charset) - '0' + 1) * 94 * 94) ? + ((ch - MIN_CHAR_94x94) % 94) + 33 : 0; + else /* if (XCHARSET_CHARS (charset) == 96) */ + return (MIN_CHAR_96x96 + + (XCHARSET_FINAL (charset) - '0') * 96 * 96 <= ch) + && (ch < MIN_CHAR_96x96 + + (XCHARSET_FINAL (charset) - '0' + 1) * 96 * 96) ? + ((ch - MIN_CHAR_96x96) % 96) + 32 : 0; + } +} + +Lisp_Object Vdefault_coded_charset_priority_list; +#endif + /************************************************************************/ /* Basic charset Lisp functions */ @@ -1241,6 +1224,10 @@ character set. Recognized properties are: Lisp_Object rest, keyword, value; Lisp_Object ccl_program = Qnil; Lisp_Object short_name = Qnil, long_name = Qnil; +#ifdef UTF2000 + Emchar code_offset = 0; + unsigned char byte_offset = 0; +#endif CHECK_SYMBOL (name); if (!NILP (doc_string)) @@ -1292,7 +1279,11 @@ character set. Recognized properties are: { CHECK_INT (value); graphic = XINT (value); +#ifdef UTF2000 + if (graphic < 0 || graphic > 2) +#else if (graphic < 0 || graphic > 1) +#endif signal_simple_error ("Invalid value for 'graphic", value); } @@ -1352,12 +1343,17 @@ character set. Recognized properties are: { if (chars == 94) { - /* id = CHARSET_ID_OFFSET_94 + final; */ - id = get_unallocated_leading_byte (dimension); + if (code_offset == 0) + id = CHARSET_ID_OFFSET_94 + final; + else + id = get_unallocated_leading_byte (dimension); } else if (chars == 96) { - id = get_unallocated_leading_byte (dimension); + if (code_offset == 0) + id = CHARSET_ID_OFFSET_96 + final; + else + id = get_unallocated_leading_byte (dimension); } else { @@ -1368,7 +1364,10 @@ character set. Recognized properties are: { if (chars == 94) { - id = get_unallocated_leading_byte (dimension); + if (code_offset == 0) + id = CHARSET_ID_OFFSET_94x94 + final; + else + id = get_unallocated_leading_byte (dimension); } else if (chars == 96) { @@ -1383,6 +1382,13 @@ character set. Recognized properties are: { abort (); } + if (final) + { + if (chars == 94) + byte_offset = 33; + else if (chars == 96) + byte_offset = 32; + } #else id = get_unallocated_leading_byte (dimension); #endif @@ -1401,8 +1407,10 @@ character set. Recognized properties are: if (columns == -1) columns = dimension; - charset = make_charset (id, name, dimension + 2, type, columns, graphic, - final, direction, short_name, long_name, doc_string, registry); + charset = make_charset (id, name, type, columns, graphic, + final, direction, short_name, long_name, + doc_string, registry, + Qnil, 0, 0, 0, byte_offset); if (!NILP (ccl_program)) XCHARSET_CCL_PROGRAM (charset) = ccl_program; return charset; @@ -1447,9 +1455,19 @@ NEW-NAME is the name of the new charset. Return the new charset. long_name = CHARSET_LONG_NAME (cs); registry = CHARSET_REGISTRY (cs); - new_charset = make_charset (id, new_name, dimension + 2, type, columns, + new_charset = make_charset (id, new_name, type, columns, graphic, final, direction, short_name, long_name, - doc_string, registry); + doc_string, registry, +#ifdef UTF2000 + CHARSET_DECODING_TABLE(cs), + CHARSET_UCS_MIN(cs), + CHARSET_UCS_MAX(cs), + CHARSET_CODE_OFFSET(cs), + CHARSET_BYTE_OFFSET(cs) +#else + Qnil, 0, 0, 0, 0 +#endif +); CHARSET_REVERSE_DIRECTION_CHARSET (cs) = new_charset; XCHARSET_REVERSE_DIRECTION_CHARSET (new_charset) = charset; @@ -1457,6 +1475,16 @@ NEW-NAME is the name of the new charset. Return the new charset. return new_charset; } +DEFUN ("define-charset-alias", Fdefine_charset_alias, 2, 2, 0, /* +Define symbol ALIAS as an alias for CHARSET. +*/ + (alias, charset)) +{ + CHECK_SYMBOL (alias); + charset = Fget_charset (charset); + return Fputhash (alias, charset, Vcharset_hash_table); +} + /* #### Reverse direction charsets not yet implemented. */ #if 0 DEFUN ("charset-reverse-direction-charset", Fcharset_reverse_direction_charset, @@ -1635,7 +1663,6 @@ invalidate_charset_font_caches (Lisp_Object charset) } } -/* Japanese folks may want to (set-charset-registry 'ascii "jisx0201") */ DEFUN ("set-charset-registry", Fset_charset_registry, 2, 2, 0, /* Set the 'registry property of CHARSET to REGISTRY. */ @@ -1649,6 +1676,98 @@ Set the 'registry property of CHARSET to REGISTRY. return Qnil; } +#ifdef UTF2000 +DEFUN ("charset-mapping-table", Fcharset_mapping_table, 1, 1, 0, /* +Return mapping-table of CHARSET. +*/ + (charset)) +{ + return XCHARSET_DECODING_TABLE (Fget_charset (charset)); +} + +DEFUN ("set-charset-mapping-table", Fset_charset_mapping_table, 2, 2, 0, /* +Set mapping-table of CHARSET to TABLE. +*/ + (charset, table)) +{ + struct Lisp_Charset *cs; + Lisp_Object old_table; + size_t i; + + charset = Fget_charset (charset); + cs = XCHARSET (charset); + + if (EQ (table, Qnil)) + { + CHARSET_DECODING_TABLE(cs) = table; + CHARSET_ENCODING_TABLE(cs) = Qnil; + return table; + } + else if (VECTORP (table)) + { + if (XVECTOR_LENGTH (table) > CHARSET_CHARS (cs)) + args_out_of_range (table, make_int (CHARSET_CHARS (cs))); + old_table = CHARSET_ENCODING_TABLE(cs); + CHARSET_DECODING_TABLE(cs) = table; + } + else + signal_error (Qwrong_type_argument, + list2 (build_translated_string ("vector-or-nil-p"), + table)); + /* signal_simple_error ("Wrong type argument: vector-or-nil-p", table); */ + + switch (CHARSET_DIMENSION (cs)) + { + case 1: + CHARSET_ENCODING_TABLE(cs) = make_char_code_table (Qnil); + for (i = 0; i < XVECTOR_LENGTH (table); i++) + { + Lisp_Object c = XVECTOR_DATA(table)[i]; + + if (CHARP (c)) + put_char_code_table (XCHAR (c), + make_int (i + CHARSET_BYTE_OFFSET (cs)), + CHARSET_ENCODING_TABLE(cs)); + } + break; + case 2: + CHARSET_ENCODING_TABLE(cs) = make_char_code_table (Qnil); + for (i = 0; i < XVECTOR_LENGTH (table); i++) + { + Lisp_Object v = XVECTOR_DATA(table)[i]; + + if (VECTORP (v)) + { + size_t j; + + if (XVECTOR_LENGTH (v) > CHARSET_CHARS (cs)) + { + CHARSET_DECODING_TABLE(cs) = old_table; + args_out_of_range (v, make_int (CHARSET_CHARS (cs))); + } + for (j = 0; j < XVECTOR_LENGTH (v); j++) + { + Lisp_Object c = XVECTOR_DATA(v)[j]; + + if (CHARP (c)) + put_char_code_table + (XCHAR (c), + make_int (( (i + CHARSET_BYTE_OFFSET (cs)) << 8) + | (j + CHARSET_BYTE_OFFSET (cs))), + CHARSET_ENCODING_TABLE(cs)); + } + } + else if (CHARP (v)) + put_char_code_table (XCHAR (v), + make_int (i + CHARSET_BYTE_OFFSET (cs)), + CHARSET_ENCODING_TABLE(cs)); + } + break; + } + return table; +} +#endif + /************************************************************************/ /* Lisp primitives for working with characters */ @@ -1843,6 +1962,7 @@ syms_of_mule_charset (void) DEFSUBR (Fmake_charset); DEFSUBR (Fmake_reverse_direction_charset); /* DEFSUBR (Freverse_direction_charset); */ + DEFSUBR (Fdefine_charset_alias); DEFSUBR (Fcharset_from_attributes); DEFSUBR (Fcharset_short_name); DEFSUBR (Fcharset_long_name); @@ -1852,6 +1972,10 @@ syms_of_mule_charset (void) DEFSUBR (Fcharset_id); DEFSUBR (Fset_charset_ccl_program); DEFSUBR (Fset_charset_registry); +#ifdef UTF2000 + DEFSUBR (Fcharset_mapping_table); + DEFSUBR (Fset_charset_mapping_table); +#endif DEFSUBR (Fmake_char); DEFSUBR (Fchar_charset); @@ -1898,12 +2022,14 @@ syms_of_mule_charset (void) defsymbol (&Qchinese_cns11643_1, "chinese-cns11643-1"); defsymbol (&Qchinese_cns11643_2, "chinese-cns11643-2"); #ifdef UTF2000 - defsymbol (&Qchinese_cns11643_3, "chinese-cns11643-3"); - defsymbol (&Qchinese_cns11643_4, "chinese-cns11643-4"); - defsymbol (&Qchinese_cns11643_5, "chinese-cns11643-5"); - defsymbol (&Qchinese_cns11643_6, "chinese-cns11643-6"); - defsymbol (&Qchinese_cns11643_7, "chinese-cns11643-7"); defsymbol (&Qucs_bmp, "ucs-bmp"); + defsymbol (&Qlatin_viscii, "latin-viscii"); + defsymbol (&Qlatin_viscii_lower, "latin-viscii-lower"); + defsymbol (&Qlatin_viscii_upper, "latin-viscii-upper"); + defsymbol (&Qvietnamese_viscii_lower, "vietnamese-viscii-lower"); + defsymbol (&Qvietnamese_viscii_upper, "vietnamese-viscii-upper"); + defsymbol (&Qhiragana_jisx0208, "hiragana-jisx0208"); + defsymbol (&Qkatakana_jisx0208, "katakana-jisx0208"); #endif defsymbol (&Qchinese_big5_1, "chinese-big5-1"); defsymbol (&Qchinese_big5_2, "chinese-big5-2"); @@ -1936,10 +2062,10 @@ vars_of_mule_charset (void) charset_by_attributes[i][j][k] = Qnil; #endif - next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1; #ifdef UTF2000 - next_allocated_2_byte_leading_byte = LEADING_BYTE_CHINESE_BIG5_2 + 1; + next_allocated_leading_byte = MIN_LEADING_BYTE_PRIVATE; #else + next_allocated_1_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_1; next_allocated_2_byte_leading_byte = MIN_LEADING_BYTE_PRIVATE_2; #endif @@ -1952,10 +2078,16 @@ Leading-code of private TYPE9N charset of column-width 1. #endif #ifdef UTF2000 - Vutf_2000_version = build_string("0.6 (Tōbushijō-mae)"); + Vutf_2000_version = build_string("0.9 (Kyūhōji)"); DEFVAR_LISP ("utf-2000-version", &Vutf_2000_version /* Version number of UTF-2000. */ ); + + Vdefault_coded_charset_priority_list = Qnil; + DEFVAR_LISP ("default-coded-charset-priority-list", + &Vdefault_coded_charset_priority_list /* +Default order of preferred coded-character-sets. +*/ ); #endif } @@ -1971,260 +2103,298 @@ complex_vars_of_mule_charset (void) #ifdef UTF2000 Vcharset_ucs_bmp = - make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp, 1, - CHARSET_TYPE_256X256, 1, 0, 0, + make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp, + CHARSET_TYPE_256X256, 1, 2, 0, CHARSET_LEFT_TO_RIGHT, build_string ("BMP"), build_string ("BMP"), - build_string ("BMP"), - build_string ("")); + build_string ("ISO/IEC 10646 Group 0 Plane 0 (BMP)"), + build_string ("\\(ISO10646.*-1\\|UNICODE[23]?-0\\)"), + Qnil, 0, 0xFFFF, 0, 0); +#else +# define MIN_CHAR_THAI 0 +# define MAX_CHAR_THAI 0 +# define MIN_CHAR_GREEK 0 +# define MAX_CHAR_GREEK 0 +# define MIN_CHAR_HEBREW 0 +# define MAX_CHAR_HEBREW 0 +# define MIN_CHAR_HALFWIDTH_KATAKANA 0 +# define MAX_CHAR_HALFWIDTH_KATAKANA 0 +# define MIN_CHAR_CYRILLIC 0 +# define MAX_CHAR_CYRILLIC 0 #endif Vcharset_ascii = - make_charset (LEADING_BYTE_ASCII, Qascii, 1, + make_charset (LEADING_BYTE_ASCII, Qascii, CHARSET_TYPE_94, 1, 0, 'B', CHARSET_LEFT_TO_RIGHT, build_string ("ASCII"), build_string ("ASCII)"), build_string ("ASCII (ISO646 IRV)"), - build_string ("\\(iso8859-[0-9]*\\|-ascii\\)")); + build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"), + Qnil, 0, 0x7F, 0, 0); Vcharset_control_1 = - make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 2, + make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, CHARSET_TYPE_94, 1, 1, 0, CHARSET_LEFT_TO_RIGHT, build_string ("C1"), build_string ("Control characters"), build_string ("Control characters 128-191"), - build_string ("")); + build_string (""), + Qnil, 0x80, 0x9F, 0, 0); Vcharset_latin_iso8859_1 = - make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, CHARSET_TYPE_96, 1, 1, 'A', CHARSET_LEFT_TO_RIGHT, build_string ("Latin-1"), build_string ("ISO8859-1 (Latin-1)"), build_string ("ISO8859-1 (Latin-1)"), - build_string ("iso8859-1")); + build_string ("iso8859-1"), + Qnil, 0xA0, 0xFF, 0, 32); Vcharset_latin_iso8859_2 = - make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, CHARSET_TYPE_96, 1, 1, 'B', CHARSET_LEFT_TO_RIGHT, build_string ("Latin-2"), build_string ("ISO8859-2 (Latin-2)"), build_string ("ISO8859-2 (Latin-2)"), - build_string ("iso8859-2")); + build_string ("iso8859-2"), + Qnil, 0, 0, 0, 32); Vcharset_latin_iso8859_3 = - make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, CHARSET_TYPE_96, 1, 1, 'C', CHARSET_LEFT_TO_RIGHT, build_string ("Latin-3"), build_string ("ISO8859-3 (Latin-3)"), build_string ("ISO8859-3 (Latin-3)"), - build_string ("iso8859-3")); + build_string ("iso8859-3"), + Qnil, 0, 0, 0, 32); Vcharset_latin_iso8859_4 = - make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, CHARSET_TYPE_96, 1, 1, 'D', CHARSET_LEFT_TO_RIGHT, build_string ("Latin-4"), build_string ("ISO8859-4 (Latin-4)"), build_string ("ISO8859-4 (Latin-4)"), - build_string ("iso8859-4")); + build_string ("iso8859-4"), + Qnil, 0, 0, 0, 32); Vcharset_thai_tis620 = - make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 2, + make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, CHARSET_TYPE_96, 1, 1, 'T', CHARSET_LEFT_TO_RIGHT, build_string ("TIS620"), build_string ("TIS620 (Thai)"), build_string ("TIS620.2529 (Thai)"), - build_string ("tis620")); + build_string ("tis620"), + Qnil, MIN_CHAR_THAI, MAX_CHAR_THAI, 0, 32); Vcharset_greek_iso8859_7 = - make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 2, + make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, CHARSET_TYPE_96, 1, 1, 'F', CHARSET_LEFT_TO_RIGHT, build_string ("ISO8859-7"), build_string ("ISO8859-7 (Greek)"), build_string ("ISO8859-7 (Greek)"), - build_string ("iso8859-7")); + build_string ("iso8859-7"), + Qnil, MIN_CHAR_GREEK, MAX_CHAR_GREEK, 0, 32); Vcharset_arabic_iso8859_6 = - make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 2, + make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, CHARSET_TYPE_96, 1, 1, 'G', CHARSET_RIGHT_TO_LEFT, build_string ("ISO8859-6"), build_string ("ISO8859-6 (Arabic)"), build_string ("ISO8859-6 (Arabic)"), - build_string ("iso8859-6")); + build_string ("iso8859-6"), + Qnil, 0, 0, 0, 32); Vcharset_hebrew_iso8859_8 = - make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 2, + make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, CHARSET_TYPE_96, 1, 1, 'H', CHARSET_RIGHT_TO_LEFT, build_string ("ISO8859-8"), build_string ("ISO8859-8 (Hebrew)"), build_string ("ISO8859-8 (Hebrew)"), - build_string ("iso8859-8")); + build_string ("iso8859-8"), + Qnil, MIN_CHAR_HEBREW, MAX_CHAR_HEBREW, 0, 32); Vcharset_katakana_jisx0201 = - make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 2, + make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, CHARSET_TYPE_94, 1, 1, 'I', CHARSET_LEFT_TO_RIGHT, build_string ("JISX0201 Kana"), build_string ("JISX0201.1976 (Japanese Kana)"), build_string ("JISX0201.1976 Japanese Kana"), - build_string ("jisx0201.1976")); + build_string ("jisx0201\\.1976"), + Qnil, + MIN_CHAR_HALFWIDTH_KATAKANA, + MAX_CHAR_HALFWIDTH_KATAKANA, 0, 33); Vcharset_latin_jisx0201 = - make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 2, + make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, CHARSET_TYPE_94, 1, 0, 'J', CHARSET_LEFT_TO_RIGHT, build_string ("JISX0201 Roman"), build_string ("JISX0201.1976 (Japanese Roman)"), build_string ("JISX0201.1976 Japanese Roman"), - build_string ("jisx0201.1976")); + build_string ("jisx0201\\.1976"), + Qnil, 0, 0, 0, 33); Vcharset_cyrillic_iso8859_5 = - make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 2, + make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, CHARSET_TYPE_96, 1, 1, 'L', CHARSET_LEFT_TO_RIGHT, build_string ("ISO8859-5"), build_string ("ISO8859-5 (Cyrillic)"), build_string ("ISO8859-5 (Cyrillic)"), - build_string ("iso8859-5")); + build_string ("iso8859-5"), + Qnil, MIN_CHAR_CYRILLIC, MAX_CHAR_CYRILLIC, 0, 32); Vcharset_latin_iso8859_9 = - make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 2, + make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, CHARSET_TYPE_96, 1, 1, 'M', CHARSET_LEFT_TO_RIGHT, build_string ("Latin-5"), build_string ("ISO8859-9 (Latin-5)"), build_string ("ISO8859-9 (Latin-5)"), - build_string ("iso8859-9")); + build_string ("iso8859-9"), + Qnil, 0, 0, 0, 32); Vcharset_japanese_jisx0208_1978 = - make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, 3, + make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, Qjapanese_jisx0208_1978, CHARSET_TYPE_94X94, 2, 0, '@', CHARSET_LEFT_TO_RIGHT, - build_string ("JISX0208.1978"), - build_string ("JISX0208.1978 (Japanese)"), + build_string ("JIS X0208:1978"), + build_string ("JIS X0208:1978 (Japanese)"), build_string - ("JISX0208.1978 Japanese Kanji (so called \"old JIS\")"), - build_string ("\\(jisx0208\\|jisc6226\\)\\.1978")); + ("JIS X0208:1978 Japanese Kanji (so called \"old JIS\")"), + build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"), + Qnil, 0, 0, 0, 33); Vcharset_chinese_gb2312 = - make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 3, + make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, CHARSET_TYPE_94X94, 2, 0, 'A', CHARSET_LEFT_TO_RIGHT, build_string ("GB2312"), build_string ("GB2312)"), build_string ("GB2312 Chinese simplified"), - build_string ("gb2312")); + build_string ("gb2312"), + Qnil, 0, 0, 0, 33); Vcharset_japanese_jisx0208 = - make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 3, + make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, CHARSET_TYPE_94X94, 2, 0, 'B', CHARSET_LEFT_TO_RIGHT, build_string ("JISX0208"), - build_string ("JISX0208.1983/1990 (Japanese)"), - build_string ("JISX0208.1983/1990 Japanese Kanji"), - build_string ("jisx0208.19\\(83\\|90\\)")); + build_string ("JIS X0208:1983 (Japanese)"), + build_string ("JIS X0208:1983 Japanese Kanji"), + build_string ("jisx0208\\.1983"), + Qnil, 0, 0, 0, 33); Vcharset_korean_ksc5601 = - make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, 3, + make_charset (LEADING_BYTE_KOREAN_KSC5601, Qkorean_ksc5601, CHARSET_TYPE_94X94, 2, 0, 'C', CHARSET_LEFT_TO_RIGHT, build_string ("KSC5601"), build_string ("KSC5601 (Korean"), build_string ("KSC5601 Korean Hangul and Hanja"), - build_string ("ksc5601")); + build_string ("ksc5601"), + Qnil, 0, 0, 0, 33); Vcharset_japanese_jisx0212 = - make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 3, + make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, CHARSET_TYPE_94X94, 2, 0, 'D', CHARSET_LEFT_TO_RIGHT, build_string ("JISX0212"), build_string ("JISX0212 (Japanese)"), build_string ("JISX0212 Japanese Supplement"), - build_string ("jisx0212")); + build_string ("jisx0212"), + Qnil, 0, 0, 0, 33); #define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$" Vcharset_chinese_cns11643_1 = - make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, 3, + make_charset (LEADING_BYTE_CHINESE_CNS11643_1, Qchinese_cns11643_1, CHARSET_TYPE_94X94, 2, 0, 'G', CHARSET_LEFT_TO_RIGHT, build_string ("CNS11643-1"), build_string ("CNS11643-1 (Chinese traditional)"), build_string ("CNS 11643 Plane 1 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("1"))); + build_string (CHINESE_CNS_PLANE_RE("1")), + Qnil, 0, 0, 0, 33); Vcharset_chinese_cns11643_2 = - make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 3, + make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, CHARSET_TYPE_94X94, 2, 0, 'H', CHARSET_LEFT_TO_RIGHT, build_string ("CNS11643-2"), build_string ("CNS11643-2 (Chinese traditional)"), build_string ("CNS 11643 Plane 2 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("2"))); + build_string (CHINESE_CNS_PLANE_RE("2")), + Qnil, 0, 0, 0, 33); #ifdef UTF2000 - Vcharset_chinese_cns11643_3 = - make_charset (LEADING_BYTE_CHINESE_CNS11643_3, Qchinese_cns11643_3, 3, - CHARSET_TYPE_94X94, 2, 0, 'I', + Vcharset_latin_viscii_lower = + make_charset (LEADING_BYTE_LATIN_VISCII_LOWER, Qlatin_viscii_lower, + CHARSET_TYPE_96, 1, 1, '1', CHARSET_LEFT_TO_RIGHT, - build_string ("CNS11643-3"), - build_string ("CNS11643-3 (Chinese traditional)"), - build_string - ("CNS 11643 Plane 3 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("3"))); - Vcharset_chinese_cns11643_4 = - make_charset (LEADING_BYTE_CHINESE_CNS11643_4, Qchinese_cns11643_4, 3, - CHARSET_TYPE_94X94, 2, 0, 'J', + build_string ("VISCII lower"), + build_string ("VISCII lower (Vietnamese)"), + build_string ("VISCII lower (Vietnamese)"), + build_string ("MULEVISCII-LOWER"), + Qnil, 0, 0, 0, 32); + Vcharset_latin_viscii_upper = + make_charset (LEADING_BYTE_LATIN_VISCII_UPPER, Qlatin_viscii_upper, + CHARSET_TYPE_96, 1, 1, '2', CHARSET_LEFT_TO_RIGHT, - build_string ("CNS11643-4"), - build_string ("CNS11643-4 (Chinese traditional)"), - build_string - ("CNS 11643 Plane 4 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("4"))); - Vcharset_chinese_cns11643_5 = - make_charset (LEADING_BYTE_CHINESE_CNS11643_5, Qchinese_cns11643_5, 3, - CHARSET_TYPE_94X94, 2, 0, 'K', + build_string ("VISCII upper"), + build_string ("VISCII upper (Vietnamese)"), + build_string ("VISCII upper (Vietnamese)"), + build_string ("MULEVISCII-UPPER"), + Qnil, 0, 0, 0, 32); + Vcharset_latin_viscii = + make_charset (LEADING_BYTE_LATIN_VISCII, Qlatin_viscii, + CHARSET_TYPE_256, 1, 2, 0, CHARSET_LEFT_TO_RIGHT, - build_string ("CNS11643-5"), - build_string ("CNS11643-5 (Chinese traditional)"), - build_string - ("CNS 11643 Plane 5 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("5"))); - Vcharset_chinese_cns11643_6 = - make_charset (LEADING_BYTE_CHINESE_CNS11643_6, Qchinese_cns11643_6, 3, - CHARSET_TYPE_94X94, 2, 0, 'L', + build_string ("VISCII"), + build_string ("VISCII 1.1 (Vietnamese)"), + build_string ("VISCII 1.1 (Vietnamese)"), + build_string ("VISCII1\\.1"), + Qnil, 0, 0, 0, 0); + Vcharset_hiragana_jisx0208 = + make_charset (LEADING_BYTE_HIRAGANA_JISX0208, Qhiragana_jisx0208, + CHARSET_TYPE_94X94, 2, 0, 'B', CHARSET_LEFT_TO_RIGHT, - build_string ("CNS11643-6"), - build_string ("CNS11643-6 (Chinese traditional)"), - build_string - ("CNS 11643 Plane 6 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("6"))); - Vcharset_chinese_cns11643_7 = - make_charset (LEADING_BYTE_CHINESE_CNS11643_7, Qchinese_cns11643_7, 3, - CHARSET_TYPE_94X94, 2, 0, 'M', + build_string ("Hiragana"), + build_string ("Hiragana of JIS X0208"), + build_string ("Japanese Hiragana of JIS X0208"), + build_string ("jisx0208\\.19\\(78\\|83\\|90\\)"), + Qnil, MIN_CHAR_HIRAGANA, MAX_CHAR_HIRAGANA, + (0x24 - 33) * 94 + (0x21 - 33), 33); + Vcharset_katakana_jisx0208 = + make_charset (LEADING_BYTE_KATAKANA_JISX0208, Qkatakana_jisx0208, + CHARSET_TYPE_94X94, 2, 0, 'B', CHARSET_LEFT_TO_RIGHT, - build_string ("CNS11643-7"), - build_string ("CNS11643-7 (Chinese traditional)"), - build_string - ("CNS 11643 Plane 7 Chinese traditional"), - build_string (CHINESE_CNS_PLANE_RE("7"))); + build_string ("Katakana"), + build_string ("Katakana of JIS X0208"), + build_string ("Japanese Katakana of JIS X0208"), + build_string ("jisx0208\\.19\\(78\\|83\\|90\\)"), + Qnil, MIN_CHAR_KATAKANA, MAX_CHAR_KATAKANA, + (0x25 - 33) * 94 + (0x21 - 33), 33); #endif Vcharset_chinese_big5_1 = - make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, 3, + make_charset (LEADING_BYTE_CHINESE_BIG5_1, Qchinese_big5_1, CHARSET_TYPE_94X94, 2, 0, '0', CHARSET_LEFT_TO_RIGHT, build_string ("Big5"), build_string ("Big5 (Level-1)"), build_string ("Big5 Level-1 Chinese traditional"), - build_string ("big5")); + build_string ("big5"), + Qnil, 0, 0, 0, 33); Vcharset_chinese_big5_2 = - make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 3, + make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, CHARSET_TYPE_94X94, 2, 0, '1', CHARSET_LEFT_TO_RIGHT, build_string ("Big5"), build_string ("Big5 (Level-2)"), build_string ("Big5 Level-2 Chinese traditional"), - build_string ("big5")); - + build_string ("big5"), + Qnil, 0, 0, 0, 33); #ifdef ENABLE_COMPOSITE_CHARS /* #### For simplicity, we put composite chars into a 96x96 charset. This is going to lead to problems because you can run out of room, esp. as we don't yet recycle numbers. */ Vcharset_composite = - make_charset (LEADING_BYTE_COMPOSITE, Qcomposite, 3, + make_charset (LEADING_BYTE_COMPOSITE, Qcomposite, CHARSET_TYPE_96X96, 2, 0, 0, CHARSET_LEFT_TO_RIGHT, build_string ("Composite"),