X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fmule-charset.c;h=2031052975a38ca6c72c427b3d6154b1568c3ac4;hb=aa982acf01b4e35675a624d78c9e5ee109c1203e;hp=ae25638ba58f32a6e2101a5ec11edc24cdecbe8b;hpb=4d10eacb85aa54c9dc22704e166fac2db29848ea;p=chise%2Fxemacs-chise.git diff --git a/src/mule-charset.c b/src/mule-charset.c index ae25638..2031052 100644 --- a/src/mule-charset.c +++ b/src/mule-charset.c @@ -1,7 +1,7 @@ /* Functions to handle multilingual characters. Copyright (C) 1992, 1995 Free Software Foundation, Inc. Copyright (C) 1995 Sun Microsystems, Inc. - Copyright (C) 1999,2000,2001 MORIOKA Tomohiko + Copyright (C) 1999,2000,2001,2002 MORIOKA Tomohiko This file is part of XEmacs. @@ -66,15 +66,33 @@ Lisp_Object Vcharset_chinese_cns11643_2; #ifdef UTF2000 Lisp_Object Vcharset_ucs; Lisp_Object Vcharset_ucs_bmp; +Lisp_Object Vcharset_ucs_smp; +Lisp_Object Vcharset_ucs_sip; Lisp_Object Vcharset_ucs_cns; Lisp_Object Vcharset_ucs_jis; +Lisp_Object Vcharset_ucs_ks; Lisp_Object Vcharset_ucs_big5; Lisp_Object Vcharset_latin_viscii; Lisp_Object Vcharset_latin_tcvn5712; Lisp_Object Vcharset_latin_viscii_lower; Lisp_Object Vcharset_latin_viscii_upper; +Lisp_Object Vcharset_jis_x0208; Lisp_Object Vcharset_chinese_big5; -Lisp_Object Vcharset_chinese_big5_cdp; +/* Lisp_Object Vcharset_chinese_big5_cdp; */ +Lisp_Object Vcharset_ideograph_hanziku_1; +Lisp_Object Vcharset_ideograph_hanziku_2; +Lisp_Object Vcharset_ideograph_hanziku_3; +Lisp_Object Vcharset_ideograph_hanziku_4; +Lisp_Object Vcharset_ideograph_hanziku_5; +Lisp_Object Vcharset_ideograph_hanziku_6; +Lisp_Object Vcharset_ideograph_hanziku_7; +Lisp_Object Vcharset_ideograph_hanziku_8; +Lisp_Object Vcharset_ideograph_hanziku_9; +Lisp_Object Vcharset_ideograph_hanziku_10; +Lisp_Object Vcharset_ideograph_hanziku_11; +Lisp_Object Vcharset_ideograph_hanziku_12; +Lisp_Object Vcharset_china3_jef; +Lisp_Object Vcharset_ideograph_cbeta; Lisp_Object Vcharset_ideograph_gt; Lisp_Object Vcharset_ideograph_gt_pj_1; Lisp_Object Vcharset_ideograph_gt_pj_2; @@ -87,30 +105,8 @@ Lisp_Object Vcharset_ideograph_gt_pj_8; Lisp_Object Vcharset_ideograph_gt_pj_9; Lisp_Object Vcharset_ideograph_gt_pj_10; Lisp_Object Vcharset_ideograph_gt_pj_11; +Lisp_Object Vcharset_ideograph_daikanwa_2; Lisp_Object Vcharset_ideograph_daikanwa; -Lisp_Object Vcharset_mojikyo; -Lisp_Object Vcharset_mojikyo_2022_1; -Lisp_Object Vcharset_mojikyo_pj_1; -Lisp_Object Vcharset_mojikyo_pj_2; -Lisp_Object Vcharset_mojikyo_pj_3; -Lisp_Object Vcharset_mojikyo_pj_4; -Lisp_Object Vcharset_mojikyo_pj_5; -Lisp_Object Vcharset_mojikyo_pj_6; -Lisp_Object Vcharset_mojikyo_pj_7; -Lisp_Object Vcharset_mojikyo_pj_8; -Lisp_Object Vcharset_mojikyo_pj_9; -Lisp_Object Vcharset_mojikyo_pj_10; -Lisp_Object Vcharset_mojikyo_pj_11; -Lisp_Object Vcharset_mojikyo_pj_12; -Lisp_Object Vcharset_mojikyo_pj_13; -Lisp_Object Vcharset_mojikyo_pj_14; -Lisp_Object Vcharset_mojikyo_pj_15; -Lisp_Object Vcharset_mojikyo_pj_16; -Lisp_Object Vcharset_mojikyo_pj_17; -Lisp_Object Vcharset_mojikyo_pj_18; -Lisp_Object Vcharset_mojikyo_pj_19; -Lisp_Object Vcharset_mojikyo_pj_20; -Lisp_Object Vcharset_mojikyo_pj_21; Lisp_Object Vcharset_ethiopic_ucs; #endif Lisp_Object Vcharset_chinese_big5_1; @@ -181,20 +177,6 @@ const Bytecount rep_bytes_by_first_byte[0xA0] = #ifdef UTF2000 -INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs); -INLINE_HEADER int -CHARSET_BYTE_SIZE (Lisp_Charset* cs) -{ - /* ad-hoc method for `ascii' */ - if ((CHARSET_CHARS (cs) == 94) && - (CHARSET_BYTE_OFFSET (cs) != 33)) - return 128 - CHARSET_BYTE_OFFSET (cs); - else - return CHARSET_CHARS (cs); -} - -#define XCHARSET_BYTE_SIZE(ccs) CHARSET_BYTE_SIZE (XCHARSET (ccs)) - int decoding_table_check_elements (Lisp_Object v, int dim, int ccs_len); int decoding_table_check_elements (Lisp_Object v, int dim, int ccs_len) @@ -223,71 +205,15 @@ decoding_table_check_elements (Lisp_Object v, int dim, int ccs_len) return 0; } -INLINE_HEADER void -decoding_table_remove_char (Lisp_Object v, int dim, int byte_offset, - int code_point); -INLINE_HEADER void -decoding_table_remove_char (Lisp_Object v, int dim, int byte_offset, - int code_point) -{ - int i = -1; - - while (dim > 0) - { - Lisp_Object nv; - - dim--; - i = ((code_point >> (8 * dim)) & 255) - byte_offset; - nv = XVECTOR_DATA(v)[i]; - if (!VECTORP (nv)) - break; - v = nv; - } - if (i >= 0) - XVECTOR_DATA(v)[i] = Qnil; -} - -INLINE_HEADER void -decoding_table_put_char (Lisp_Object v, int dim, int byte_offset, - int code_point, Lisp_Object character); -INLINE_HEADER void -decoding_table_put_char (Lisp_Object v, int dim, int byte_offset, - int code_point, Lisp_Object character) -{ - int i = -1; - Lisp_Object nv; - int ccs_len = XVECTOR_LENGTH (v); - - while (dim > 0) - { - dim--; - i = ((code_point >> (8 * dim)) & 255) - byte_offset; - nv = XVECTOR_DATA(v)[i]; - if (dim > 0) - { - if (!VECTORP (nv)) - nv = (XVECTOR_DATA(v)[i] = make_older_vector (ccs_len, Qnil)); - v = nv; - } - else - break; - } - XVECTOR_DATA(v)[i] = character; -} - Lisp_Object put_char_ccs_code_point (Lisp_Object character, Lisp_Object ccs, Lisp_Object value) { - Lisp_Object encoding_table; - if (!EQ (XCHARSET_NAME (ccs), Qucs) + || !INTP (value) || (XCHAR (character) != XINT (value))) { Lisp_Object v = XCHARSET_DECODING_TABLE (ccs); - int dim = XCHARSET_DIMENSION (ccs); - int ccs_len = XCHARSET_BYTE_SIZE (ccs); - int byte_offset = XCHARSET_BYTE_OFFSET (ccs); int code_point; if (CONSP (value)) @@ -335,26 +261,14 @@ put_char_ccs_code_point (Lisp_Object character, if (VECTORP (v)) { Lisp_Object cpos = Fget_char_attribute (character, ccs, Qnil); - if (!NILP (cpos)) + if (INTP (cpos)) { - decoding_table_remove_char (v, dim, byte_offset, XINT (cpos)); + decoding_table_remove_char (ccs, XINT (cpos)); } } - else - { - XCHARSET_DECODING_TABLE (ccs) - = v = make_older_vector (ccs_len, Qnil); - } - - decoding_table_put_char (v, dim, byte_offset, code_point, character); + decoding_table_put_char (ccs, code_point, character); } - if (NILP (encoding_table = XCHARSET_ENCODING_TABLE (ccs))) - { - XCHARSET_ENCODING_TABLE (ccs) - = encoding_table = make_char_id_table (Qnil); - } - put_char_id_table (XCHAR (character), value, encoding_table); - return Qt; + return value; } Lisp_Object @@ -369,15 +283,12 @@ remove_char_ccs (Lisp_Object character, Lisp_Object ccs) if (!NILP (cpos)) { - decoding_table_remove_char (decoding_table, - XCHARSET_DIMENSION (ccs), - XCHARSET_BYTE_OFFSET (ccs), - XINT (cpos)); + decoding_table_remove_char (ccs, XINT (cpos)); } } - if (CHAR_ID_TABLE_P (encoding_table)) + if (CHAR_TABLEP (encoding_table)) { - put_char_id_table (XCHAR (character), Qnil, encoding_table); + put_char_id_table (XCHAR_TABLE(encoding_table), character, Qunbound); } return Qt; } @@ -396,6 +307,10 @@ Lisp_Object Qdirection; Lisp_Object Qreverse_direction_charset; Lisp_Object Qleading_byte; Lisp_Object Qshort_name, Qlong_name; +#ifdef UTF2000 +Lisp_Object Qmin_code, Qmax_code, Qcode_offset; +Lisp_Object Qmother, Qconversion, Q94x60, Q94x94x60; +#endif Lisp_Object Qascii, Qcontrol_1, @@ -423,8 +338,11 @@ Lisp_Object Qascii, #ifdef UTF2000 Qucs, Qucs_bmp, + Qucs_smp, + Qucs_sip, Qucs_cns, Qucs_jis, + Qucs_ks, Qucs_big5, Qlatin_viscii, Qlatin_tcvn5712, @@ -432,8 +350,24 @@ Lisp_Object Qascii, Qlatin_viscii_upper, Qvietnamese_viscii_lower, Qvietnamese_viscii_upper, + Qjis_x0208, Qchinese_big5, - Qchinese_big5_cdp, + /* Qchinese_big5_cdp, */ + Qideograph_hanziku_1, + Qideograph_hanziku_2, + Qideograph_hanziku_3, + Qideograph_hanziku_4, + Qideograph_hanziku_5, + Qideograph_hanziku_6, + Qideograph_hanziku_7, + Qideograph_hanziku_8, + Qideograph_hanziku_9, + Qideograph_hanziku_10, + Qideograph_hanziku_11, + Qideograph_hanziku_12, + Qchina3_jef, + Qideograph_cbeta, + Qideograph_daikanwa_2, Qideograph_daikanwa, Qideograph_gt, Qideograph_gt_pj_1, @@ -447,29 +381,6 @@ Lisp_Object Qascii, Qideograph_gt_pj_9, Qideograph_gt_pj_10, Qideograph_gt_pj_11, - Qmojikyo, - Qmojikyo_2022_1, - Qmojikyo_pj_1, - Qmojikyo_pj_2, - Qmojikyo_pj_3, - Qmojikyo_pj_4, - Qmojikyo_pj_5, - Qmojikyo_pj_6, - Qmojikyo_pj_7, - Qmojikyo_pj_8, - Qmojikyo_pj_9, - Qmojikyo_pj_10, - Qmojikyo_pj_11, - Qmojikyo_pj_12, - Qmojikyo_pj_13, - Qmojikyo_pj_14, - Qmojikyo_pj_15, - Qmojikyo_pj_16, - Qmojikyo_pj_17, - Qmojikyo_pj_18, - Qmojikyo_pj_19, - Qmojikyo_pj_20, - Qmojikyo_pj_21, Qethiopic_ucs, #endif Qchinese_big5_1, @@ -814,8 +725,8 @@ mark_charset (Lisp_Object obj) mark_object (cs->registry); mark_object (cs->ccl_program); #ifdef UTF2000 - mark_object (cs->encoding_table); - /* mark_object (cs->decoding_table); */ + mark_object (cs->decoding_table); + mark_object (cs->mother); #endif return cs->name; } @@ -862,7 +773,7 @@ static const struct lrecord_description charset_description[] = { { XD_LISP_OBJECT, offsetof (Lisp_Charset, ccl_program) }, #ifdef UTF2000 { XD_LISP_OBJECT, offsetof (Lisp_Charset, decoding_table) }, - { XD_LISP_OBJECT, offsetof (Lisp_Charset, encoding_table) }, + { XD_LISP_OBJECT, offsetof (Lisp_Charset, mother) }, #endif { XD_END } }; @@ -882,8 +793,9 @@ make_charset (Charset_ID id, Lisp_Object name, Lisp_Object long_name, Lisp_Object doc, Lisp_Object reg, Lisp_Object decoding_table, - Emchar ucs_min, Emchar ucs_max, - Emchar code_offset, unsigned char byte_offset) + Emchar min_code, Emchar max_code, + Emchar code_offset, unsigned char byte_offset, + Lisp_Object mother, unsigned char conversion) { Lisp_Object obj; Lisp_Charset *cs = alloc_lcrecord_type (Lisp_Charset, &lrecord_charset); @@ -907,12 +819,13 @@ make_charset (Charset_ID id, Lisp_Object name, 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; + CHARSET_DECODING_TABLE(cs) = Qunbound; + CHARSET_MIN_CODE (cs) = min_code; + CHARSET_MAX_CODE (cs) = max_code; + CHARSET_CODE_OFFSET (cs) = code_offset; + CHARSET_BYTE_OFFSET (cs) = byte_offset; + CHARSET_MOTHER (cs) = mother; + CHARSET_CONVERSION (cs) = conversion; #endif #ifndef UTF2000 @@ -995,37 +908,102 @@ get_unallocated_leading_byte (int dimension) #define BIG5_SAME_ROW (0xFF - 0xA1 + 0x7F - 0x40) Emchar +decode_defined_char (Lisp_Object ccs, int code_point) +{ + int dim = XCHARSET_DIMENSION (ccs); + Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (ccs); + Emchar char_id = -1; + Lisp_Object mother; + + while (dim > 0) + { + dim--; + decoding_table + = get_ccs_octet_table (decoding_table, ccs, + (code_point >> (dim * 8)) & 255); + } + if (CHARP (decoding_table)) + return XCHAR (decoding_table); + if (char_id >= 0) + return char_id; + else if ( CHARSETP (mother = XCHARSET_MOTHER (ccs)) ) + { + if ( XCHARSET_CONVERSION (ccs) == CONVERSION_IDENTICAL ) + { + if ( EQ (mother, Vcharset_ucs) ) + return DECODE_CHAR (mother, code_point); + else + return decode_defined_char (mother, code_point); + } + } + return -1; +} + +Emchar decode_builtin_char (Lisp_Object charset, int code_point) { + Lisp_Object mother = XCHARSET_MOTHER (charset); int final; - if (EQ (charset, Vcharset_chinese_big5)) + if ( CHARSETP (mother) && (XCHARSET_MAX_CODE (charset) > 0) ) { - int c1 = code_point >> 8; - int c2 = code_point & 0xFF; - unsigned int I; - - if ( ( (0xA1 <= c1) && (c1 <= 0xFE) ) - && - ( ((0x40 <= c2) && (c2 <= 0x7E)) || - ((0xA1 <= c2) && (c2 <= 0xFE)) ) ) + int code = code_point; + + if ( XCHARSET_CONVERSION (charset) == CONVERSION_94x60 ) { - I = (c1 - 0xA1) * BIG5_SAME_ROW - + c2 - (c2 < 0x7F ? 0x40 : 0x62); + int row = code_point >> 8; + int cell = code_point & 255; - if (c1 < 0xC9) - { - charset = Vcharset_chinese_big5_1; - } - else - { - charset = Vcharset_chinese_big5_2; - I -= (BIG5_SAME_ROW) * (0xC9 - 0xA1); - } - code_point = ((I / 94 + 33) << 8) | (I % 94 + 33); + if (row < 16 + 32) + return -1; + else if (row < 16 + 32 + 30) + code = (row - (16 + 32)) * 94 + cell - 33; + else if (row < 18 + 32 + 30) + return -1; + else if (row < 18 + 32 + 60) + code = (row - (18 + 32)) * 94 + cell - 33; + } + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_94x94x60 ) + { + int plane = code_point >> 16; + int row = (code_point >> 8) & 255; + int cell = code_point & 255; + + if (row < 16 + 32) + return -1; + else if (row < 16 + 32 + 30) + code + = (plane - 33) * 94 * 60 + + (row - (16 + 32)) * 94 + + cell - 33; + else if (row < 18 + 32 + 30) + return -1; + else if (row < 18 + 32 + 60) + code + = (plane - 33) * 94 * 60 + + (row - (18 + 32)) * 94 + + cell - 33; } + return + decode_builtin_char (mother, code + XCHARSET_CODE_OFFSET(charset)); } - if ((final = XCHARSET_FINAL (charset)) >= '0') + if (XCHARSET_MAX_CODE (charset)) + { + Emchar cid + = (XCHARSET_DIMENSION (charset) == 1 + ? + code_point - XCHARSET_BYTE_OFFSET (charset) + : + ((code_point >> 8) - XCHARSET_BYTE_OFFSET (charset)) + * XCHARSET_CHARS (charset) + + (code_point & 0xFF) - XCHARSET_BYTE_OFFSET (charset)) + + XCHARSET_CODE_OFFSET (charset); + if ((cid < XCHARSET_MIN_CODE (charset)) + || (XCHARSET_MAX_CODE (charset) < cid)) + return -1; + return cid; + } + else if ((final = XCHARSET_FINAL (charset)) >= '0') { if (XCHARSET_DIMENSION (charset) == 1) { @@ -1062,122 +1040,156 @@ decode_builtin_char (Lisp_Object charset, int code_point) } } } - else if (XCHARSET_UCS_MAX (charset)) - { - Emchar cid - = (XCHARSET_DIMENSION (charset) == 1 - ? - code_point - XCHARSET_BYTE_OFFSET (charset) - : - ((code_point >> 8) - XCHARSET_BYTE_OFFSET (charset)) - * XCHARSET_CHARS (charset) - + (code_point & 0xFF) - XCHARSET_BYTE_OFFSET (charset)) - - XCHARSET_CODE_OFFSET (charset) + XCHARSET_UCS_MIN (charset); - if ((cid < XCHARSET_UCS_MIN (charset)) - || (XCHARSET_UCS_MAX (charset) < cid)) - return -1; - return cid; - } else return -1; } int -range_charset_code_point (Lisp_Object charset, Emchar ch) +charset_code_point (Lisp_Object charset, Emchar ch, int defined_only) { - int d; + Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (charset); + Lisp_Object ret; - if ((XCHARSET_UCS_MIN (charset) <= ch) - && (ch <= XCHARSET_UCS_MAX (charset))) - { - d = ch - XCHARSET_UCS_MIN (charset) + XCHARSET_CODE_OFFSET (charset); - - if (XCHARSET_CHARS (charset) == 256) - return d; - else if (XCHARSET_DIMENSION (charset) == 1) - return d + XCHARSET_BYTE_OFFSET (charset); - else if (XCHARSET_DIMENSION (charset) == 2) - return - ((d / XCHARSET_CHARS (charset) - + XCHARSET_BYTE_OFFSET (charset)) << 8) - | (d % XCHARSET_CHARS (charset) + XCHARSET_BYTE_OFFSET (charset)); - else if (XCHARSET_DIMENSION (charset) == 3) - return - ((d / (XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset)) - + XCHARSET_BYTE_OFFSET (charset)) << 16) - | ((d / XCHARSET_CHARS (charset) - % XCHARSET_CHARS (charset) - + XCHARSET_BYTE_OFFSET (charset)) << 8) - | (d % XCHARSET_CHARS (charset) + XCHARSET_BYTE_OFFSET (charset)); - else /* if (XCHARSET_DIMENSION (charset) == 4) */ - return - ((d / (XCHARSET_CHARS (charset) - * XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset)) - + XCHARSET_BYTE_OFFSET (charset)) << 24) - | ((d / (XCHARSET_CHARS (charset) * XCHARSET_CHARS (charset)) - % XCHARSET_CHARS (charset) - + XCHARSET_BYTE_OFFSET (charset)) << 16) - | ((d / XCHARSET_CHARS (charset) % XCHARSET_CHARS (charset) - + XCHARSET_BYTE_OFFSET (charset)) << 8) - | (d % XCHARSET_CHARS (charset) + XCHARSET_BYTE_OFFSET (charset)); - } - else if (XCHARSET_CODE_OFFSET (charset) == 0) + if ( CHAR_TABLEP (encoding_table) + && INTP (ret = get_char_id_table (XCHAR_TABLE(encoding_table), + ch)) ) + return XINT (ret); + else { - if (XCHARSET_DIMENSION (charset) == 1) + Lisp_Object mother = XCHARSET_MOTHER (charset); + int min = XCHARSET_MIN_CODE (charset); + int max = XCHARSET_MAX_CODE (charset); + int code; + + if ( CHARSETP (mother) ) + code = charset_code_point (mother, ch, defined_only); + else if (defined_only) + return -1; + else + code = ch; + if ( ((max == 0) && CHARSETP (mother)) || + ((min <= code) && (code <= max)) ) { - if (XCHARSET_CHARS (charset) == 94) + int d = code - XCHARSET_CODE_OFFSET (charset); + + if ( XCHARSET_CONVERSION (charset) == CONVERSION_IDENTICAL ) + return d; + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_94 ) + return d + 33; + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_96 ) + return d + 32; + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_94x60 ) { - if (((d = ch - (MIN_CHAR_94 - + (XCHARSET_FINAL (charset) - '0') * 94)) >= 0) - && (d < 94)) - return d + 33; + int row = d / 94; + int cell = d % 94 + 33; + + if (row < 30) + row += 16 + 32; + else + row += 18 + 32; + return (row << 8) | cell; } - else if (XCHARSET_CHARS (charset) == 96) + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_94x94 ) + return ((d / 94 + 33) << 8) | (d % 94 + 33); + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_96x96 ) + return ((d / 96 + 32) << 8) | (d % 96 + 32); + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_94x94x60 ) { - if (((d = ch - (MIN_CHAR_96 - + (XCHARSET_FINAL (charset) - '0') * 96)) >= 0) - && (d < 96)) - return d + 32; + int plane = d / (94 * 60) + 33; + int row = (d % (94 * 60)) / 94; + int cell = d % 94 + 33; + + if (row < 30) + row += 16 + 32; + else + row += 18 + 32; + return (plane << 16) | (row << 8) | cell; } + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_94x94x94 ) + return + ( (d / (94 * 94) + 33) << 16) + | ((d / 94 % 94 + 33) << 8) + | (d % 94 + 33); + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_96x96x96 ) + return + ( (d / (96 * 96) + 32) << 16) + | ((d / 96 % 96 + 32) << 8) + | (d % 96 + 32); + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_94x94x94x94 ) + return + ( (d / (94 * 94 * 94) + 33) << 24) + | ((d / (94 * 94) % 94 + 33) << 16) + | ((d / 94 % 94 + 33) << 8) + | (d % 94 + 33); + else if ( XCHARSET_CONVERSION (charset) == CONVERSION_96x96x96x96 ) + return + ( (d / (96 * 96 * 96) + 32) << 24) + | ((d / (96 * 96) % 96 + 32) << 16) + | ((d / 96 % 96 + 32) << 8) + | (d % 96 + 32); else - return -1; + { + printf ("Unknown CCS-conversion %d is specified!", + XCHARSET_CONVERSION (charset)); + exit (-1); + } } - else if (XCHARSET_DIMENSION (charset) == 2) + else if ( ( XCHARSET_FINAL (charset) >= '0' ) && + ( XCHARSET_MIN_CODE (charset) == 0 ) + /* + (XCHARSET_CODE_OFFSET (charset) == 0) || + (XCHARSET_CODE_OFFSET (charset) + == XCHARSET_MIN_CODE (charset)) + */ ) { - if (XCHARSET_CHARS (charset) == 94) + int d; + + if (XCHARSET_DIMENSION (charset) == 1) { - if (((d = ch - (MIN_CHAR_94x94 - + (XCHARSET_FINAL (charset) - '0') * 94 * 94)) - >= 0) - && (d < 94 * 94)) - return (((d / 94) + 33) << 8) | (d % 94 + 33); + 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 -1; } - else if (XCHARSET_CHARS (charset) == 96) + else if (XCHARSET_DIMENSION (charset) == 2) { - if (((d = ch - (MIN_CHAR_96x96 - + (XCHARSET_FINAL (charset) - '0') * 96 * 96)) - >= 0) - && (d < 96 * 96)) - return (((d / 96) + 32) << 8) | (d % 96 + 32); + 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) << 8) | (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) << 8) | (d % 96 + 32); + } + else + return -1; } - else - return -1; } } - if (EQ (charset, Vcharset_mojikyo_2022_1) - && (MIN_CHAR_MOJIKYO < ch) && (ch < MIN_CHAR_MOJIKYO + 94 * 60 * 94)) - { - int m = ch - MIN_CHAR_MOJIKYO - 1; - int byte1 = m / (94 * 60) + 33; - int byte2 = (m % (94 * 60)) / 94; - int byte3 = m % 94 + 33; - - if (byte2 < 30) - byte2 += 16 + 32; - else - byte2 += 18 + 32; - return (byte1 << 16) | (byte2 << 8) | byte3; - } return -1; } @@ -1224,6 +1236,16 @@ encode_builtin_char_1 (Emchar c, Lisp_Object* charset) *charset = Vcharset_ucs_bmp; return c; } + else if (c <= MAX_CHAR_SMP) + { + *charset = Vcharset_ucs_smp; + return c - MIN_CHAR_SMP; + } + else if (c <= MAX_CHAR_SIP) + { + *charset = Vcharset_ucs_sip; + return c - MIN_CHAR_SIP; + } else if (c < MIN_CHAR_DAIKANWA) { *charset = Vcharset_ucs; @@ -1234,11 +1256,6 @@ encode_builtin_char_1 (Emchar c, Lisp_Object* charset) *charset = Vcharset_ideograph_daikanwa; return c - MIN_CHAR_DAIKANWA; } - else if (c <= MAX_CHAR_MOJIKYO_0) - { - *charset = Vcharset_mojikyo; - return c - MIN_CHAR_MOJIKYO_0; - } else if (c < MIN_CHAR_94) { *charset = Vcharset_ucs; @@ -1300,16 +1317,6 @@ encode_builtin_char_1 (Emchar c, Lisp_Object* charset) return c; } } - else if (c < MIN_CHAR_MOJIKYO) - { - *charset = Vcharset_ucs; - return c; - } - else if (c <= MAX_CHAR_MOJIKYO) - { - *charset = Vcharset_mojikyo; - return c - MIN_CHAR_MOJIKYO; - } else { *charset = Vcharset_ucs; @@ -1424,6 +1431,7 @@ character set. Recognized properties are: this character set. 'dimension Number of octets used to index a character in this charset. Either 1 or 2. Defaults to 1. + If UTF-2000 feature is enabled, 3 or 4 are also available. 'columns Number of columns used to display a character in this charset. Only used in TTY mode. (Under X, the actual width of a character can be derived from the font used to display the @@ -1432,6 +1440,7 @@ character set. Recognized properties are: 'chars Number of characters in each dimension (94 or 96). Defaults to 94. Note that if the dimension is 2, the character set thus described is 94x94 or 96x96. + If UTF-2000 feature is enabled, 128 or 256 are also available. 'final Final byte of ISO 2022 escape sequence. Must be supplied. Each combination of (DIMENSION, CHARS) defines a separate namespace for final bytes. Note that ISO @@ -1456,6 +1465,13 @@ character set. Recognized properties are: is passed the octets of the character, with the high bit cleared and set depending upon whether the value of the 'graphic property is 0 or 1. +'mother [UTF-2000 only] Base coded-charset. +'code-min [UTF-2000 only] Minimum code-point of a base coded-charset. +'code-max [UTF-2000 only] Maximum code-point of a base coded-charset. +'code-offset [UTF-2000 only] Offset for a code-point of a base + coded-charset. +'conversion [UTF-2000 only] Conversion for a code-point of a base + coded-charset (94x60 or 94x94x60). */ (name, doc_string, props)) { @@ -1465,7 +1481,10 @@ character set. Recognized properties are: Lisp_Object charset; Lisp_Object ccl_program = Qnil; Lisp_Object short_name = Qnil, long_name = Qnil; + Lisp_Object mother = Qnil; + int min_code = 0, max_code = 0, code_offset = 0; int byte_offset = -1; + int conversion = 0; CHECK_SYMBOL (name); if (!NILP (doc_string)) @@ -1494,7 +1513,13 @@ character set. Recognized properties are: { CHECK_INT (value); dimension = XINT (value); - if (dimension < 1 || dimension > 2) + if (dimension < 1 || +#ifdef UTF2000 + dimension > 4 +#else + dimension > 2 +#endif + ) signal_simple_error ("Invalid value for 'dimension", value); } @@ -1502,7 +1527,11 @@ character set. Recognized properties are: { CHECK_INT (value); chars = XINT (value); - if (chars != 94 && chars != 96) + if (chars != 94 && chars != 96 +#ifdef UTF2000 + && chars != 128 && chars != 256 +#endif + ) signal_simple_error ("Invalid value for 'chars", value); } @@ -1518,11 +1547,13 @@ character set. Recognized properties are: { CHECK_INT (value); graphic = XINT (value); + if (graphic < 0 || #ifdef UTF2000 - if (graphic < 0 || graphic > 2) + graphic > 2 #else - if (graphic < 0 || graphic > 1) + graphic > 1 #endif + ) signal_simple_error ("Invalid value for 'graphic", value); } @@ -1550,6 +1581,41 @@ character set. Recognized properties are: signal_simple_error ("Invalid value for 'final", value); } +#ifdef UTF2000 + else if (EQ (keyword, Qmother)) + { + mother = Fget_charset (value); + } + + else if (EQ (keyword, Qmin_code)) + { + CHECK_INT (value); + min_code = XUINT (value); + } + + else if (EQ (keyword, Qmax_code)) + { + CHECK_INT (value); + max_code = XUINT (value); + } + + else if (EQ (keyword, Qcode_offset)) + { + CHECK_INT (value); + code_offset = XUINT (value); + } + + else if (EQ (keyword, Qconversion)) + { + if (EQ (value, Q94x60)) + conversion = CONVERSION_94x60; + else if (EQ (value, Q94x94x60)) + conversion = CONVERSION_94x94x60; + else + signal_simple_error ("Unrecognized conversion", value); + } + +#endif else if (EQ (keyword, Qccl_program)) { struct ccl_program test_ccl; @@ -1564,8 +1630,10 @@ character set. Recognized properties are: } } +#ifndef UTF2000 if (!final) error ("'final must be specified"); +#endif if (dimension == 2 && final > 0x5F) signal_simple_error ("Final must be in the range 0x30 - 0x5F for dimension == 2", @@ -1608,7 +1676,8 @@ character set. Recognized properties are: charset = make_charset (id, name, chars, dimension, columns, graphic, final, direction, short_name, long_name, doc_string, registry, - Qnil, 0, 0, 0, byte_offset); + Qnil, min_code, max_code, code_offset, byte_offset, + mother, conversion); if (!NILP (ccl_program)) XCHARSET_CCL_PROGRAM (charset) = ccl_program; return charset; @@ -1658,12 +1727,14 @@ NEW-NAME is the name of the new charset. Return the new charset. doc_string, registry, #ifdef UTF2000 CHARSET_DECODING_TABLE(cs), - CHARSET_UCS_MIN(cs), - CHARSET_UCS_MAX(cs), + CHARSET_MIN_CODE(cs), + CHARSET_MAX_CODE(cs), CHARSET_CODE_OFFSET(cs), - CHARSET_BYTE_OFFSET(cs) + CHARSET_BYTE_OFFSET(cs), + CHARSET_MOTHER(cs), + CHARSET_CONVERSION (cs) #else - Qnil, 0, 0, 0, 0 + Qnil, 0, 0, 0, 0, Qnil, 0 #endif ); @@ -1801,7 +1872,8 @@ Recognized properties are those listed in `make-charset', as well as if (EQ (prop, Qdimension)) return make_int (CHARSET_DIMENSION (cs)); if (EQ (prop, Qcolumns)) return make_int (CHARSET_COLUMNS (cs)); if (EQ (prop, Qgraphic)) return make_int (CHARSET_GRAPHIC (cs)); - if (EQ (prop, Qfinal)) return make_char (CHARSET_FINAL (cs)); + if (EQ (prop, Qfinal)) return CHARSET_FINAL (cs) == 0 ? + Qnil : make_char (CHARSET_FINAL (cs)); if (EQ (prop, Qchars)) return make_int (CHARSET_CHARS (cs)); if (EQ (prop, Qregistry)) return CHARSET_REGISTRY (cs); if (EQ (prop, Qccl_program)) return CHARSET_CCL_PROGRAM (cs); @@ -1813,6 +1885,14 @@ Recognized properties are those listed in `make-charset', as well as /* #### Is this translation OK? If so, error checking sufficient? */ return CHARSETP (obj) ? XCHARSET_NAME (obj) : obj; } +#ifdef UTF2000 + if (EQ (prop, Qmother)) + return CHARSET_MOTHER (cs); + if (EQ (prop, Qmin_code)) + return make_int (CHARSET_MIN_CODE (cs)); + if (EQ (prop, Qmax_code)) + return make_int (CHARSET_MAX_CODE (cs)); +#endif signal_simple_error ("Unrecognized charset property name", prop); return Qnil; /* not reached */ } @@ -1892,8 +1972,6 @@ Set mapping-table of CHARSET to TABLE. if (NILP (table)) { - if (VECTORP (CHARSET_DECODING_TABLE(cs))) - make_vector_newer (CHARSET_DECODING_TABLE(cs)); CHARSET_DECODING_TABLE(cs) = Qnil; return table; } @@ -1928,8 +2006,8 @@ Set mapping-table of CHARSET to TABLE. Lisp_Object c = XVECTOR_DATA(table)[i]; if (CHARP (c)) - put_char_ccs_code_point (c, charset, - make_int (i + byte_offset)); + Fput_char_attribute (c, XCHARSET_NAME (charset), + make_int (i + byte_offset)); } break; case 2: @@ -1946,16 +2024,16 @@ Set mapping-table of CHARSET to TABLE. Lisp_Object c = XVECTOR_DATA(v)[j]; if (CHARP (c)) - put_char_ccs_code_point - (c, charset, + Fput_char_attribute + (c, XCHARSET_NAME (charset), make_int ( ( (i + byte_offset) << 8 ) | (j + byte_offset) ) ); } } else if (CHARP (v)) - put_char_ccs_code_point (v, charset, - make_int (i + byte_offset)); + Fput_char_attribute (v, XCHARSET_NAME (charset), + make_int (i + byte_offset)); } break; } @@ -1969,10 +2047,12 @@ Set mapping-table of CHARSET to TABLE. /************************************************************************/ #ifdef UTF2000 -DEFUN ("decode-char", Fdecode_char, 2, 2, 0, /* +DEFUN ("decode-char", Fdecode_char, 2, 3, 0, /* Make a character from CHARSET and code-point CODE. +If DEFINED_ONLY is non-nil, builtin character is not returned. +If corresponding character is not found, nil is returned. */ - (charset, code)) + (charset, code, defined_only)) { int c; @@ -1981,7 +2061,10 @@ Make a character from CHARSET and code-point CODE. c = XINT (code); if (XCHARSET_GRAPHIC (charset) == 1) c &= 0x7F7F7F7F; - c = DECODE_CHAR (charset, c); + if (NILP (defined_only)) + c = DECODE_CHAR (charset, c); + else + c = decode_defined_char (charset, c); return c >= 0 ? make_char (c) : Qnil; } @@ -1996,7 +2079,7 @@ Make a builtin character from CHARSET and code-point CODE. CHECK_INT (code); if (EQ (charset, Vcharset_latin_viscii)) { - Lisp_Object chr = Fdecode_char (charset, code); + Lisp_Object chr = Fdecode_char (charset, code, Qnil); Lisp_Object ret; if (!NILP (chr)) @@ -2025,7 +2108,7 @@ Make a builtin character from CHARSET and code-point CODE. c &= 0x7F7F7F7F; #endif c = decode_builtin_char (charset, c); - return c >= 0 ? make_char (c) : Fdecode_char (charset, code); + return c >= 0 ? make_char (c) : Fdecode_char (charset, code, Qnil); } #endif @@ -2120,6 +2203,25 @@ N defaults to 0 if omitted. signal_simple_error ("Octet number must be 0 or 1", n); } +#ifdef UTF2000 +DEFUN ("encode-char", Fencode_char, 2, 3, 0, /* +Return code-point of CHARACTER in specified CHARSET. +*/ + (character, charset, defined_only)) +{ + int code_point; + + CHECK_CHAR_COERCE_INT (character); + charset = Fget_charset (charset); + code_point = charset_code_point (charset, XCHAR (character), + !NILP (defined_only)); + if (code_point >= 0) + return make_int (code_point); + else + return Qnil; +} +#endif + DEFUN ("split-char", Fsplit_char, 1, 1, 0, /* Return list of charset and one or two position-codes of CHARACTER. */ @@ -2276,6 +2378,7 @@ syms_of_mule_charset (void) #ifdef UTF2000 DEFSUBR (Fdecode_char); DEFSUBR (Fdecode_builtin_char); + DEFSUBR (Fencode_char); #endif DEFSUBR (Fmake_char); DEFSUBR (Fchar_charset); @@ -2295,6 +2398,15 @@ syms_of_mule_charset (void) defsymbol (&Qreverse_direction_charset, "reverse-direction-charset"); defsymbol (&Qshort_name, "short-name"); defsymbol (&Qlong_name, "long-name"); +#ifdef UTF2000 + defsymbol (&Qmother, "mother"); + defsymbol (&Qmin_code, "min-code"); + defsymbol (&Qmax_code, "max-code"); + defsymbol (&Qcode_offset, "code-offset"); + defsymbol (&Qconversion, "conversion"); + defsymbol (&Q94x60, "94x60"); + defsymbol (&Q94x94x60, "94x94x60"); +#endif defsymbol (&Ql2r, "l2r"); defsymbol (&Qr2l, "r2l"); @@ -2327,8 +2439,11 @@ syms_of_mule_charset (void) #ifdef UTF2000 defsymbol (&Qucs, "ucs"); defsymbol (&Qucs_bmp, "ucs-bmp"); + defsymbol (&Qucs_smp, "ucs-smp"); + defsymbol (&Qucs_sip, "ucs-sip"); defsymbol (&Qucs_cns, "ucs-cns"); defsymbol (&Qucs_jis, "ucs-jis"); + defsymbol (&Qucs_ks, "ucs-ks"); defsymbol (&Qucs_big5, "ucs-big5"); defsymbol (&Qlatin_viscii, "latin-viscii"); defsymbol (&Qlatin_tcvn5712, "latin-tcvn5712"); @@ -2336,6 +2451,7 @@ syms_of_mule_charset (void) defsymbol (&Qlatin_viscii_upper, "latin-viscii-upper"); defsymbol (&Qvietnamese_viscii_lower, "vietnamese-viscii-lower"); defsymbol (&Qvietnamese_viscii_upper, "vietnamese-viscii-upper"); + defsymbol (&Qjis_x0208, "=jis-x0208"); defsymbol (&Qideograph_gt, "ideograph-gt"); defsymbol (&Qideograph_gt_pj_1, "ideograph-gt-pj-1"); defsymbol (&Qideograph_gt_pj_2, "ideograph-gt-pj-2"); @@ -2348,32 +2464,24 @@ syms_of_mule_charset (void) defsymbol (&Qideograph_gt_pj_9, "ideograph-gt-pj-9"); defsymbol (&Qideograph_gt_pj_10, "ideograph-gt-pj-10"); defsymbol (&Qideograph_gt_pj_11, "ideograph-gt-pj-11"); + defsymbol (&Qideograph_daikanwa_2, "ideograph-daikanwa-2"); defsymbol (&Qideograph_daikanwa, "ideograph-daikanwa"); defsymbol (&Qchinese_big5, "chinese-big5"); - defsymbol (&Qchinese_big5_cdp, "chinese-big5-cdp"); - defsymbol (&Qmojikyo, "mojikyo"); - defsymbol (&Qmojikyo_2022_1, "mojikyo-2022-1"); - defsymbol (&Qmojikyo_pj_1, "mojikyo-pj-1"); - defsymbol (&Qmojikyo_pj_2, "mojikyo-pj-2"); - defsymbol (&Qmojikyo_pj_3, "mojikyo-pj-3"); - defsymbol (&Qmojikyo_pj_4, "mojikyo-pj-4"); - defsymbol (&Qmojikyo_pj_5, "mojikyo-pj-5"); - defsymbol (&Qmojikyo_pj_6, "mojikyo-pj-6"); - defsymbol (&Qmojikyo_pj_7, "mojikyo-pj-7"); - defsymbol (&Qmojikyo_pj_8, "mojikyo-pj-8"); - defsymbol (&Qmojikyo_pj_9, "mojikyo-pj-9"); - defsymbol (&Qmojikyo_pj_10, "mojikyo-pj-10"); - defsymbol (&Qmojikyo_pj_11, "mojikyo-pj-11"); - defsymbol (&Qmojikyo_pj_12, "mojikyo-pj-12"); - defsymbol (&Qmojikyo_pj_13, "mojikyo-pj-13"); - defsymbol (&Qmojikyo_pj_14, "mojikyo-pj-14"); - defsymbol (&Qmojikyo_pj_15, "mojikyo-pj-15"); - defsymbol (&Qmojikyo_pj_16, "mojikyo-pj-16"); - defsymbol (&Qmojikyo_pj_17, "mojikyo-pj-17"); - defsymbol (&Qmojikyo_pj_18, "mojikyo-pj-18"); - defsymbol (&Qmojikyo_pj_19, "mojikyo-pj-19"); - defsymbol (&Qmojikyo_pj_20, "mojikyo-pj-20"); - defsymbol (&Qmojikyo_pj_21, "mojikyo-pj-21"); + /* defsymbol (&Qchinese_big5_cdp, "chinese-big5-cdp"); */ + defsymbol (&Qideograph_hanziku_1, "ideograph-hanziku-1"); + defsymbol (&Qideograph_hanziku_2, "ideograph-hanziku-2"); + defsymbol (&Qideograph_hanziku_3, "ideograph-hanziku-3"); + defsymbol (&Qideograph_hanziku_4, "ideograph-hanziku-4"); + defsymbol (&Qideograph_hanziku_5, "ideograph-hanziku-5"); + defsymbol (&Qideograph_hanziku_6, "ideograph-hanziku-6"); + defsymbol (&Qideograph_hanziku_7, "ideograph-hanziku-7"); + defsymbol (&Qideograph_hanziku_8, "ideograph-hanziku-8"); + defsymbol (&Qideograph_hanziku_9, "ideograph-hanziku-9"); + defsymbol (&Qideograph_hanziku_10, "ideograph-hanziku-10"); + defsymbol (&Qideograph_hanziku_11, "ideograph-hanziku-11"); + defsymbol (&Qideograph_hanziku_12, "ideograph-hanziku-12"); + defsymbol (&Qchina3_jef, "china3-jef"); + defsymbol (&Qideograph_cbeta, "ideograph-cbeta"); defsymbol (&Qethiopic_ucs, "ethiopic-ucs"); #endif defsymbol (&Qchinese_big5_1, "chinese-big5-1"); @@ -2453,43 +2561,74 @@ complex_vars_of_mule_charset (void) build_string ("UCS"), build_string ("ISO/IEC 10646"), build_string (""), - Qnil, 0, 0xFFFFFFF, 0, 0); + Qnil, 0, 0x7FFFFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_ucs_bmp); Vcharset_ucs_bmp = make_charset (LEADING_BYTE_UCS_BMP, Qucs_bmp, 256, 2, 1, 2, 0, CHARSET_LEFT_TO_RIGHT, build_string ("BMP"), - build_string ("BMP"), + build_string ("UCS-BMP"), build_string ("ISO/IEC 10646 Group 0 Plane 0 (BMP)"), - build_string ("\\(ISO10646.*-1\\|UNICODE[23]?-0\\)"), - Qnil, 0, 0xFFFF, 0, 0); + build_string + ("\\(ISO10646.*-[01]\\|UCS00-0\\|UNICODE[23]?-0\\)"), + Qnil, 0, 0xFFFF, 0, 0, Qnil, CONVERSION_IDENTICAL); + staticpro (&Vcharset_ucs_smp); + Vcharset_ucs_smp = + make_charset (LEADING_BYTE_UCS_SMP, Qucs_smp, 256, 2, + 1, 2, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("SMP"), + build_string ("UCS-SMP"), + build_string ("ISO/IEC 10646 Group 0 Plane 1 (SMP)"), + build_string ("UCS00-1"), + Qnil, MIN_CHAR_SMP, MAX_CHAR_SMP, + MIN_CHAR_SMP, 0, Qnil, CONVERSION_IDENTICAL); + staticpro (&Vcharset_ucs_sip); + Vcharset_ucs_sip = + make_charset (LEADING_BYTE_UCS_SIP, Qucs_sip, 256, 2, + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("SIP"), + build_string ("UCS-SIP"), + build_string ("ISO/IEC 10646 Group 0 Plane 2 (SIP)"), + build_string ("\\(ISO10646.*-2\\|UCS00-2\\)"), + Qnil, MIN_CHAR_SIP, MAX_CHAR_SIP, + MIN_CHAR_SIP, 0, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_ucs_cns); Vcharset_ucs_cns = make_charset (LEADING_BYTE_UCS_CNS, Qucs_cns, 256, 3, - 1, 2, 0, CHARSET_LEFT_TO_RIGHT, + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, build_string ("UCS for CNS"), build_string ("UCS for CNS 11643"), build_string ("ISO/IEC 10646 for CNS 11643"), build_string (""), - Qnil, 0, 0, 0, 0); + Qnil, 0, 0, 0, 0, Vcharset_ucs, CONVERSION_IDENTICAL); staticpro (&Vcharset_ucs_jis); Vcharset_ucs_jis = make_charset (LEADING_BYTE_UCS_JIS, Qucs_jis, 256, 3, - 1, 2, 0, CHARSET_LEFT_TO_RIGHT, + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, build_string ("UCS for JIS"), build_string ("UCS for JIS X 0208, 0212 and 0213"), - build_string ("ISO/IEC 10646 for JIS X 0208, 0212 and 0213"), + build_string + ("ISO/IEC 10646 for JIS X 0208, 0212 and 0213"), build_string (""), - Qnil, 0, 0, 0, 0); + Qnil, 0, 0, 0, 0, Vcharset_ucs, CONVERSION_IDENTICAL); + staticpro (&Vcharset_ucs_ks); + Vcharset_ucs_ks = + make_charset (LEADING_BYTE_UCS_KS, Qucs_ks, 256, 3, + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("UCS for KS"), + build_string ("UCS for CCS defined by KS"), + build_string ("ISO/IEC 10646 for Korean Standards"), + build_string (""), + Qnil, 0, 0, 0, 0, Vcharset_ucs, CONVERSION_IDENTICAL); staticpro (&Vcharset_ucs_big5); Vcharset_ucs_big5 = make_charset (LEADING_BYTE_UCS_BIG5, Qucs_big5, 256, 3, - 1, 2, 0, CHARSET_LEFT_TO_RIGHT, + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, build_string ("UCS for Big5"), build_string ("UCS for Big5"), build_string ("ISO/IEC 10646 for Big5"), build_string (""), - Qnil, 0, 0, 0, 0); + Qnil, 0, 0, 0, 0, Vcharset_ucs, CONVERSION_IDENTICAL); #else # define MIN_CHAR_THAI 0 # define MAX_CHAR_THAI 0 @@ -2506,7 +2645,7 @@ complex_vars_of_mule_charset (void) build_string ("ASCII)"), build_string ("ASCII (ISO646 IRV)"), build_string ("\\(iso8859-[0-9]*\\|-ascii\\)"), - Qnil, 0, 0x7F, 0, 0); + Qnil, 0, 0x7F, 0, 0, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_control_1); Vcharset_control_1 = make_charset (LEADING_BYTE_CONTROL_1, Qcontrol_1, 94, 1, @@ -2515,7 +2654,7 @@ complex_vars_of_mule_charset (void) build_string ("Control characters"), build_string ("Control characters 128-191"), build_string (""), - Qnil, 0x80, 0x9F, 0, 0); + Qnil, 0x80, 0x9F, 0x80, 0, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_iso8859_1); Vcharset_latin_iso8859_1 = make_charset (LEADING_BYTE_LATIN_ISO8859_1, Qlatin_iso8859_1, 96, 1, @@ -2524,7 +2663,7 @@ complex_vars_of_mule_charset (void) build_string ("ISO8859-1 (Latin-1)"), build_string ("ISO8859-1 (Latin-1)"), build_string ("iso8859-1"), - Qnil, 0xA0, 0xFF, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_iso8859_2); Vcharset_latin_iso8859_2 = make_charset (LEADING_BYTE_LATIN_ISO8859_2, Qlatin_iso8859_2, 96, 1, @@ -2533,7 +2672,7 @@ complex_vars_of_mule_charset (void) build_string ("ISO8859-2 (Latin-2)"), build_string ("ISO8859-2 (Latin-2)"), build_string ("iso8859-2"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_iso8859_3); Vcharset_latin_iso8859_3 = make_charset (LEADING_BYTE_LATIN_ISO8859_3, Qlatin_iso8859_3, 96, 1, @@ -2542,7 +2681,7 @@ complex_vars_of_mule_charset (void) build_string ("ISO8859-3 (Latin-3)"), build_string ("ISO8859-3 (Latin-3)"), build_string ("iso8859-3"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_iso8859_4); Vcharset_latin_iso8859_4 = make_charset (LEADING_BYTE_LATIN_ISO8859_4, Qlatin_iso8859_4, 96, 1, @@ -2551,7 +2690,7 @@ complex_vars_of_mule_charset (void) build_string ("ISO8859-4 (Latin-4)"), build_string ("ISO8859-4 (Latin-4)"), build_string ("iso8859-4"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_thai_tis620); Vcharset_thai_tis620 = make_charset (LEADING_BYTE_THAI_TIS620, Qthai_tis620, 96, 1, @@ -2560,7 +2699,7 @@ complex_vars_of_mule_charset (void) build_string ("TIS620 (Thai)"), build_string ("TIS620.2529 (Thai)"), build_string ("tis620"), - Qnil, MIN_CHAR_THAI, MAX_CHAR_THAI, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_greek_iso8859_7); Vcharset_greek_iso8859_7 = make_charset (LEADING_BYTE_GREEK_ISO8859_7, Qgreek_iso8859_7, 96, 1, @@ -2569,7 +2708,7 @@ complex_vars_of_mule_charset (void) build_string ("ISO8859-7 (Greek)"), build_string ("ISO8859-7 (Greek)"), build_string ("iso8859-7"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_arabic_iso8859_6); Vcharset_arabic_iso8859_6 = make_charset (LEADING_BYTE_ARABIC_ISO8859_6, Qarabic_iso8859_6, 96, 1, @@ -2578,7 +2717,7 @@ complex_vars_of_mule_charset (void) build_string ("ISO8859-6 (Arabic)"), build_string ("ISO8859-6 (Arabic)"), build_string ("iso8859-6"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_hebrew_iso8859_8); Vcharset_hebrew_iso8859_8 = make_charset (LEADING_BYTE_HEBREW_ISO8859_8, Qhebrew_iso8859_8, 96, 1, @@ -2589,7 +2728,8 @@ complex_vars_of_mule_charset (void) build_string ("iso8859-8"), Qnil, 0 /* MIN_CHAR_HEBREW */, - 0 /* MAX_CHAR_HEBREW */, 0, 32); + 0 /* MAX_CHAR_HEBREW */, 0, 32, + Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_katakana_jisx0201); Vcharset_katakana_jisx0201 = make_charset (LEADING_BYTE_KATAKANA_JISX0201, Qkatakana_jisx0201, 94, 1, @@ -2598,7 +2738,7 @@ complex_vars_of_mule_charset (void) build_string ("JISX0201.1976 (Japanese Kana)"), build_string ("JISX0201.1976 Japanese Kana"), build_string ("jisx0201\\.1976"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_jisx0201); Vcharset_latin_jisx0201 = make_charset (LEADING_BYTE_LATIN_JISX0201, Qlatin_jisx0201, 94, 1, @@ -2607,7 +2747,7 @@ complex_vars_of_mule_charset (void) build_string ("JISX0201.1976 (Japanese Roman)"), build_string ("JISX0201.1976 Japanese Roman"), build_string ("jisx0201\\.1976"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_cyrillic_iso8859_5); Vcharset_cyrillic_iso8859_5 = make_charset (LEADING_BYTE_CYRILLIC_ISO8859_5, Qcyrillic_iso8859_5, 96, 1, @@ -2616,7 +2756,7 @@ complex_vars_of_mule_charset (void) build_string ("ISO8859-5 (Cyrillic)"), build_string ("ISO8859-5 (Cyrillic)"), build_string ("iso8859-5"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_iso8859_9); Vcharset_latin_iso8859_9 = make_charset (LEADING_BYTE_LATIN_ISO8859_9, Qlatin_iso8859_9, 96, 1, @@ -2625,7 +2765,22 @@ complex_vars_of_mule_charset (void) build_string ("ISO8859-9 (Latin-5)"), build_string ("ISO8859-9 (Latin-5)"), build_string ("iso8859-9"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); +#ifdef UTF2000 + staticpro (&Vcharset_jis_x0208); + Vcharset_jis_x0208 = + make_charset (LEADING_BYTE_JIS_X0208, + Qjis_x0208, 94, 2, + 2, 0, 'B', CHARSET_LEFT_TO_RIGHT, + build_string ("JIS X0208"), + build_string ("JIS X0208 Common"), + build_string ("JIS X0208 Common part"), + build_string ("jisx0208\\.1990"), + Qnil, + MIN_CHAR_JIS_X0208_1990, + MAX_CHAR_JIS_X0208_1990, MIN_CHAR_JIS_X0208_1990, 33, + Qnil, CONVERSION_94x94); +#endif staticpro (&Vcharset_japanese_jisx0208_1978); Vcharset_japanese_jisx0208_1978 = make_charset (LEADING_BYTE_JAPANESE_JISX0208_1978, @@ -2636,7 +2791,13 @@ complex_vars_of_mule_charset (void) build_string ("JIS X0208:1978 Japanese Kanji (so called \"old JIS\")"), build_string ("\\(jisx0208\\|jisc6226\\)\\.1978"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, +#ifdef UTF2000 + Vcharset_jis_x0208, +#else + Qnil, +#endif + CONVERSION_IDENTICAL); staticpro (&Vcharset_chinese_gb2312); Vcharset_chinese_gb2312 = make_charset (LEADING_BYTE_CHINESE_GB2312, Qchinese_gb2312, 94, 2, @@ -2645,7 +2806,7 @@ complex_vars_of_mule_charset (void) build_string ("GB2312)"), build_string ("GB2312 Chinese simplified"), build_string ("gb2312"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_chinese_gb12345); Vcharset_chinese_gb12345 = make_charset (LEADING_BYTE_CHINESE_GB12345, Qchinese_gb12345, 94, 2, @@ -2654,7 +2815,7 @@ complex_vars_of_mule_charset (void) build_string ("GB 12345)"), build_string ("GB 12345-1990"), build_string ("GB12345\\(\\.1990\\)?-0"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_japanese_jisx0208); Vcharset_japanese_jisx0208 = make_charset (LEADING_BYTE_JAPANESE_JISX0208, Qjapanese_jisx0208, 94, 2, @@ -2663,7 +2824,13 @@ complex_vars_of_mule_charset (void) build_string ("JIS X0208:1983 (Japanese)"), build_string ("JIS X0208:1983 Japanese Kanji"), build_string ("jisx0208\\.1983"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, +#ifdef UTF2000 + Vcharset_jis_x0208, +#else + Qnil, +#endif + CONVERSION_IDENTICAL); #ifdef UTF2000 staticpro (&Vcharset_japanese_jisx0208_1990); Vcharset_japanese_jisx0208_1990 = @@ -2675,8 +2842,11 @@ complex_vars_of_mule_charset (void) build_string ("JIS X0208:1990 Japanese Kanji"), build_string ("jisx0208\\.1990"), Qnil, - MIN_CHAR_JIS_X0208_1990, - MAX_CHAR_JIS_X0208_1990, 0, 33); + 0x2121 /* MIN_CHAR_JIS_X0208_1990 */, + 0x7426 /* MAX_CHAR_JIS_X0208_1990 */, + 0 /* MIN_CHAR_JIS_X0208_1990 */, 33, + Vcharset_jis_x0208 /* Qnil */, + CONVERSION_IDENTICAL /* CONVERSION_94x94 */); #endif staticpro (&Vcharset_korean_ksc5601); Vcharset_korean_ksc5601 = @@ -2686,7 +2856,7 @@ complex_vars_of_mule_charset (void) build_string ("KSC5601 (Korean"), build_string ("KSC5601 Korean Hangul and Hanja"), build_string ("ksc5601"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_japanese_jisx0212); Vcharset_japanese_jisx0212 = make_charset (LEADING_BYTE_JAPANESE_JISX0212, Qjapanese_jisx0212, 94, 2, @@ -2695,7 +2865,7 @@ complex_vars_of_mule_charset (void) build_string ("JISX0212 (Japanese)"), build_string ("JISX0212 Japanese Supplement"), build_string ("jisx0212"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); #define CHINESE_CNS_PLANE_RE(n) "cns11643[.-]\\(.*[.-]\\)?" n "$" staticpro (&Vcharset_chinese_cns11643_1); @@ -2707,7 +2877,7 @@ complex_vars_of_mule_charset (void) build_string ("CNS 11643 Plane 1 Chinese traditional"), build_string (CHINESE_CNS_PLANE_RE("1")), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_chinese_cns11643_2); Vcharset_chinese_cns11643_2 = make_charset (LEADING_BYTE_CHINESE_CNS11643_2, Qchinese_cns11643_2, 94, 2, @@ -2717,7 +2887,7 @@ complex_vars_of_mule_charset (void) build_string ("CNS 11643 Plane 2 Chinese traditional"), build_string (CHINESE_CNS_PLANE_RE("2")), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); #ifdef UTF2000 staticpro (&Vcharset_latin_tcvn5712); Vcharset_latin_tcvn5712 = @@ -2727,7 +2897,7 @@ complex_vars_of_mule_charset (void) build_string ("TCVN 5712 (VSCII-2)"), build_string ("Vietnamese TCVN 5712:1983 (VSCII-2)"), build_string ("tcvn5712\\(\\.1993\\)?-1"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_viscii_lower); Vcharset_latin_viscii_lower = make_charset (LEADING_BYTE_LATIN_VISCII_LOWER, Qlatin_viscii_lower, 96, 1, @@ -2736,7 +2906,7 @@ complex_vars_of_mule_charset (void) build_string ("VISCII lower (Vietnamese)"), build_string ("VISCII lower (Vietnamese)"), build_string ("MULEVISCII-LOWER"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_viscii_upper); Vcharset_latin_viscii_upper = make_charset (LEADING_BYTE_LATIN_VISCII_UPPER, Qlatin_viscii_upper, 96, 1, @@ -2745,7 +2915,7 @@ complex_vars_of_mule_charset (void) build_string ("VISCII upper (Vietnamese)"), build_string ("VISCII upper (Vietnamese)"), build_string ("MULEVISCII-UPPER"), - Qnil, 0, 0, 0, 32); + Qnil, 0, 0, 0, 32, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_latin_viscii); Vcharset_latin_viscii = make_charset (LEADING_BYTE_LATIN_VISCII, Qlatin_viscii, 256, 1, @@ -2754,7 +2924,7 @@ complex_vars_of_mule_charset (void) build_string ("VISCII 1.1 (Vietnamese)"), build_string ("VISCII 1.1 (Vietnamese)"), build_string ("VISCII1\\.1"), - Qnil, 0, 0, 0, 0); + Qnil, 0, 0, 0, 0, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_chinese_big5); Vcharset_chinese_big5 = make_charset (LEADING_BYTE_CHINESE_BIG5, Qchinese_big5, 256, 2, @@ -2762,8 +2932,11 @@ complex_vars_of_mule_charset (void) build_string ("Big5"), build_string ("Big5"), build_string ("Big5 Chinese traditional"), - build_string ("big5"), - Qnil, 0, 0, 0, 0); + build_string ("big5-0"), + Qnil, + MIN_CHAR_BIG5_CDP, MAX_CHAR_BIG5_CDP, + MIN_CHAR_BIG5_CDP, 0, Qnil, CONVERSION_IDENTICAL); +#if 0 staticpro (&Vcharset_chinese_big5_cdp); Vcharset_chinese_big5_cdp = make_charset (LEADING_BYTE_CHINESE_BIG5_CDP, Qchinese_big5_cdp, 256, 2, @@ -2772,7 +2945,53 @@ complex_vars_of_mule_charset (void) build_string ("Big5 + CDP extension"), build_string ("Big5 with CDP extension"), build_string ("big5\\.cdp-0"), - Qnil, 0, 0, 0, 0); + Qnil, MIN_CHAR_BIG5_CDP, MAX_CHAR_BIG5_CDP, + MIN_CHAR_BIG5_CDP, 0, Qnil, CONVERSION_IDENTICAL); +#endif +#define DEF_HANZIKU(n) \ + staticpro (&Vcharset_ideograph_hanziku_##n); \ + Vcharset_ideograph_hanziku_##n = \ + make_charset (LEADING_BYTE_HANZIKU_##n, Qideograph_hanziku_##n, 256, 2, \ + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, \ + build_string ("HZK-"#n), \ + build_string ("HANZIKU-"#n), \ + build_string ("HANZIKU (pseudo BIG5 encoding) part "#n), \ + build_string \ + ("hanziku-"#n"$"), \ + Qnil, MIN_CHAR_HANZIKU_##n, MAX_CHAR_HANZIKU_##n, \ + MIN_CHAR_HANZIKU_##n, 0, Qnil, CONVERSION_IDENTICAL); + DEF_HANZIKU (1); + DEF_HANZIKU (2); + DEF_HANZIKU (3); + DEF_HANZIKU (4); + DEF_HANZIKU (5); + DEF_HANZIKU (6); + DEF_HANZIKU (7); + DEF_HANZIKU (8); + DEF_HANZIKU (9); + DEF_HANZIKU (10); + DEF_HANZIKU (11); + DEF_HANZIKU (12); + staticpro (&Vcharset_china3_jef); + Vcharset_china3_jef = + make_charset (LEADING_BYTE_CHINA3_JEF, Qchina3_jef, 256, 2, + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("JC3"), + build_string ("JEF + CHINA3"), + build_string ("JEF + CHINA3 private characters"), + build_string ("china3jef-0"), + Qnil, MIN_CHAR_CHINA3_JEF, MAX_CHAR_CHINA3_JEF, + MIN_CHAR_CHINA3_JEF, 0, Qnil, CONVERSION_IDENTICAL); + staticpro (&Vcharset_ideograph_cbeta); + Vcharset_ideograph_cbeta = + make_charset (LEADING_BYTE_CBETA, Qideograph_cbeta, 256, 2, + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("CB"), + build_string ("CBETA"), + build_string ("CBETA private characters"), + build_string ("cbeta-0"), + Qnil, MIN_CHAR_CBETA, MAX_CHAR_CBETA, + MIN_CHAR_CBETA, 0, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_ideograph_gt); Vcharset_ideograph_gt = make_charset (LEADING_BYTE_GT, Qideograph_gt, 256, 3, @@ -2781,7 +3000,8 @@ complex_vars_of_mule_charset (void) build_string ("GT"), build_string ("GT"), build_string (""), - Qnil, MIN_CHAR_GT, MAX_CHAR_GT, 0, 0); + Qnil, MIN_CHAR_GT, MAX_CHAR_GT, + MIN_CHAR_GT, 0, Qnil, CONVERSION_IDENTICAL); #define DEF_GT_PJ(n) \ staticpro (&Vcharset_ideograph_gt_pj_##n); \ Vcharset_ideograph_gt_pj_##n = \ @@ -2792,7 +3012,7 @@ complex_vars_of_mule_charset (void) build_string ("GT 2000 (pseudo JIS encoding) part "#n), \ build_string \ ("\\(GTpj-"#n "\\|jisx0208\\.GT-"#n "\\)$"), \ - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); DEF_GT_PJ (1); DEF_GT_PJ (2); DEF_GT_PJ (3); @@ -2805,68 +3025,27 @@ complex_vars_of_mule_charset (void) DEF_GT_PJ (10); DEF_GT_PJ (11); + staticpro (&Vcharset_ideograph_daikanwa_2); + Vcharset_ideograph_daikanwa_2 = + make_charset (LEADING_BYTE_DAIKANWA_2, Qideograph_daikanwa_2, 256, 2, + 2, 2, 0, CHARSET_LEFT_TO_RIGHT, + build_string ("Daikanwa Rev."), + build_string ("Morohashi's Daikanwa Rev."), + build_string + ("Daikanwa dictionary (revised version)"), + build_string ("Daikanwa\\(\\.[0-9]+\\)?-2"), + Qnil, 0, 0, 0, 0, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_ideograph_daikanwa); Vcharset_ideograph_daikanwa = - make_charset (LEADING_BYTE_DAIKANWA, Qideograph_daikanwa, 256, 2, + make_charset (LEADING_BYTE_DAIKANWA_3, Qideograph_daikanwa, 256, 2, 2, 2, 0, CHARSET_LEFT_TO_RIGHT, build_string ("Daikanwa"), - build_string ("Morohashi's Daikanwa"), - build_string ("Daikanwa dictionary by MOROHASHI Tetsuji"), - build_string ("Daikanwa"), - Qnil, MIN_CHAR_DAIKANWA, MAX_CHAR_DAIKANWA, 0, 0); - staticpro (&Vcharset_mojikyo); - Vcharset_mojikyo = - make_charset (LEADING_BYTE_MOJIKYO, Qmojikyo, 256, 3, - 2, 2, 0, CHARSET_LEFT_TO_RIGHT, - build_string ("Mojikyo"), - build_string ("Mojikyo"), - build_string ("Konjaku-Mojikyo"), - build_string (""), - Qnil, MIN_CHAR_MOJIKYO, MAX_CHAR_MOJIKYO, 0, 0); - staticpro (&Vcharset_mojikyo_2022_1); - Vcharset_mojikyo_2022_1 = - make_charset (LEADING_BYTE_MOJIKYO_2022_1, Qmojikyo_2022_1, 94, 3, - 2, 2, ':', CHARSET_LEFT_TO_RIGHT, - build_string ("Mojikyo-2022-1"), - build_string ("Mojikyo ISO-2022 Part 1"), - build_string ("Konjaku-Mojikyo for ISO/IEC 2022 Part 1"), - build_string (""), - Qnil, 0, 0, 0, 33); - -#define DEF_MOJIKYO_PJ(n) \ - staticpro (&Vcharset_mojikyo_pj_##n); \ - Vcharset_mojikyo_pj_##n = \ - make_charset (LEADING_BYTE_MOJIKYO_PJ_##n, Qmojikyo_pj_##n, 94, 2, \ - 2, 0, 0, CHARSET_LEFT_TO_RIGHT, \ - build_string ("Mojikyo-PJ-"#n), \ - build_string ("Mojikyo (pseudo JIS encoding) part "#n), \ - build_string \ - ("Konjaku-Mojikyo (pseudo JIS encoding) part "#n), \ - build_string \ - ("\\(MojikyoPJ-"#n "\\|jisx0208\\.Mojikyo-"#n "\\)$"), \ - Qnil, 0, 0, 0, 33); - - DEF_MOJIKYO_PJ (1); - DEF_MOJIKYO_PJ (2); - DEF_MOJIKYO_PJ (3); - DEF_MOJIKYO_PJ (4); - DEF_MOJIKYO_PJ (5); - DEF_MOJIKYO_PJ (6); - DEF_MOJIKYO_PJ (7); - DEF_MOJIKYO_PJ (8); - DEF_MOJIKYO_PJ (9); - DEF_MOJIKYO_PJ (10); - DEF_MOJIKYO_PJ (11); - DEF_MOJIKYO_PJ (12); - DEF_MOJIKYO_PJ (13); - DEF_MOJIKYO_PJ (14); - DEF_MOJIKYO_PJ (15); - DEF_MOJIKYO_PJ (16); - DEF_MOJIKYO_PJ (17); - DEF_MOJIKYO_PJ (18); - DEF_MOJIKYO_PJ (19); - DEF_MOJIKYO_PJ (20); - DEF_MOJIKYO_PJ (21); + build_string ("Morohashi's Daikanwa Rev.2"), + build_string + ("Daikanwa dictionary (second revised version)"), + build_string ("Daikanwa\\(\\.[0-9]+\\)?-3"), + Qnil, MIN_CHAR_DAIKANWA, MAX_CHAR_DAIKANWA, + MIN_CHAR_DAIKANWA, 0, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_ethiopic_ucs); Vcharset_ethiopic_ucs = @@ -2876,7 +3055,8 @@ complex_vars_of_mule_charset (void) build_string ("Ethiopic (UCS)"), build_string ("Ethiopic of UCS"), build_string ("Ethiopic-Unicode"), - Qnil, 0x1200, 0x137F, 0x1200, 0); + Qnil, 0x1200, 0x137F, 0, 0, + Qnil, CONVERSION_IDENTICAL); #endif staticpro (&Vcharset_chinese_big5_1); Vcharset_chinese_big5_1 = @@ -2887,7 +3067,7 @@ complex_vars_of_mule_charset (void) build_string ("Big5 Level-1 Chinese traditional"), build_string ("big5"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); staticpro (&Vcharset_chinese_big5_2); Vcharset_chinese_big5_2 = make_charset (LEADING_BYTE_CHINESE_BIG5_2, Qchinese_big5_2, 94, 2, @@ -2897,7 +3077,7 @@ complex_vars_of_mule_charset (void) build_string ("Big5 Level-2 Chinese traditional"), build_string ("big5"), - Qnil, 0, 0, 0, 33); + Qnil, 0, 0, 0, 33, Qnil, CONVERSION_IDENTICAL); #ifdef ENABLE_COMPOSITE_CHARS /* #### For simplicity, we put composite chars into a 96x96 charset.