X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fchar-ucs.h;h=c8d9ea504ce21fdcfd9758607cd72bbd6e7e9d10;hb=4515c44d0462e7905a8013b6ceb52792a9c31462;hp=b27bbd2803235dcecbd21b59da5fbc1a98b23aca;hpb=0ad17a1fa11632d97cb655dbbdf9cde7b69ab69a;p=chise%2Fxemacs-chise.git diff --git a/src/char-ucs.h b/src/char-ucs.h index b27bbd2..c8d9ea5 100644 --- a/src/char-ucs.h +++ b/src/char-ucs.h @@ -1,5 +1,5 @@ /* Header for UCS-4 character representation. - Copyright (C) 1999,2000 MORIOKA Tomohiko + Copyright (C) 1999,2000,2001,2002,2003 MORIOKA Tomohiko This file is part of XEmacs. @@ -21,50 +21,36 @@ Boston, MA 02111-1307, USA. */ #ifndef INCLUDED_char_ucs_h_ #define INCLUDED_char_ucs_h_ +#include "chartab.h" +#include "elhash.h" + +extern Lisp_Object Vchar_attribute_hash_table; + #define valid_char_p(ch) 1 #define CHAR_ASCII_P(ch) ((ch) <= 0x7F) -struct Lisp_Byte_Table -{ - struct lcrecord_header header; - - Lisp_Object property[256]; -}; -typedef struct Lisp_Byte_Table Lisp_Byte_Table; - -DECLARE_LRECORD (byte_table, Lisp_Byte_Table); -#define XBYTE_TABLE(x) XRECORD (x, byte_table, Lisp_Byte_Table) -#define XSETBYTE_TABLE(x, p) XSETRECORD (x, p, byte_table) -#define BYTE_TABLE_P(x) RECORDP (x, byte_table) -#define GC_BYTE_TABLE_P(x) GC_RECORDP (x, byte_table) -/* #define CHECK_BYTE_TABLE(x) CHECK_RECORD (x, byte_table) - char table entries should never escape to Lisp */ - - -struct Lisp_Char_ID_Table -{ - struct lcrecord_header header; - - Lisp_Object table; -}; -typedef struct Lisp_Char_ID_Table Lisp_Char_ID_Table; - -DECLARE_LRECORD (char_id_table, Lisp_Char_ID_Table); -#define XCHAR_ID_TABLE(x) XRECORD (x, char_id_table, Lisp_Char_ID_Table) -#define XSETCHAR_ID_TABLE(x, p) XSETRECORD (x, p, char_id_table) -#define CHAR_ID_TABLE_P(x) RECORDP (x, char_id_table) -#define GC_CHAR_ID_TABLE_P(x) GC_RECORDP (x, char_id_table) -/* #define CHECK_CHAR_ID_TABLE(x) CHECK_RECORD (x, char_id_table) - char table entries should never escape to Lisp */ +/************************************************************************/ +/* Exported functions */ +/************************************************************************/ +extern Lisp_Object Vcharset_ucs; +extern Lisp_Object Vcharset_latin_jisx0201; +extern Lisp_Object Vcharset_chinese_big5; +extern Lisp_Object Vcharset_chinese_big5_1; +extern Lisp_Object Vcharset_chinese_big5_2; +extern Lisp_Object Vcharset_japanese_jisx0208; +extern Lisp_Object Vcharset_japanese_jisx0208_1990; +extern Lisp_Object Vcharset_japanese_jisx0212; -Lisp_Object get_char_id_table (Emchar ch, Lisp_Object table); +EXFUN (Fget_charset, 1); +extern Lisp_Object Qmap_ucs, Qucs; -extern Lisp_Object Vcharset_mojikyo; -extern Lisp_Object Vcharset_latin_jisx0201; +Lisp_Object put_char_ccs_code_point (Lisp_Object character, + Lisp_Object ccs, Lisp_Object value); +Lisp_Object remove_char_ccs (Lisp_Object character, Lisp_Object ccs); /************************************************************************/ @@ -73,169 +59,143 @@ extern Lisp_Object Vcharset_latin_jisx0201; typedef short Charset_ID; -#define MIN_LEADING_BYTE -0x60 -#define CHARSET_ID_OFFSET 0x00 - /* ISO/IEC 10646 */ -#define LEADING_BYTE_UCS (CHARSET_ID_OFFSET - 1) +#define LEADING_BYTE_UCS -177 /* represent normal 80-9F */ -#define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 2) +#define LEADING_BYTE_CONTROL_1 -77 /* ISO/IEC 10646 BMP */ -#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3) +#define LEADING_BYTE_UCS_BMP -176 -/* VISCII 1.1 */ -#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 4) +/* ISO/IEC 10646 SMP */ +#define LEADING_BYTE_UCS_SMP 1 -/* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */ -#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 5) +/* ISO/IEC 10646 SIP */ +#define LEADING_BYTE_UCS_SIP 2 -/* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */ -#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 6) +/* Japanese JIS X0208 Common 2/4 2/{(8),9,10,11} 4/2 (B) */ +#define LEADING_BYTE_JIS_X0208 3 + +/* Chinese GB 12345-1990 */ +#define LEADING_BYTE_CHINESE_GB12345 4 + +#define LEADING_BYTE_CHINESE_BIG5 5 /* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */ -#define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 7) +#define LEADING_BYTE_CHINESE_BIG5_1 6 /* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */ -#define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 8) +#define LEADING_BYTE_CHINESE_BIG5_2 7 -#define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 9) +/* VISCII 1.1 */ +#define LEADING_BYTE_LATIN_VISCII 8 -#define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 10) -#define LEADING_BYTE_DAIKANWA_EKANJI (CHARSET_ID_OFFSET - 11) -#define LEADING_BYTE_MOJIKYO (CHARSET_ID_OFFSET - 12) +/* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */ +#define LEADING_BYTE_LATIN_VISCII_LOWER 9 + +/* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */ +#define LEADING_BYTE_LATIN_VISCII_UPPER 10 + +#define LEADING_BYTE_ETHIOPIC_UCS 11 + +#define MIN_LEADING_BYTE_PRIVATE 12 +#define MAX_LEADING_BYTE_PRIVATE 512 -/* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */ -#define LEADING_BYTE_JAPANESE_JISX0208_1990 (CHARSET_ID_OFFSET - 13) - -/* Konjaku-Mojikyo font (for pseudo-JIS X 0208 encoding) */ -#define LEADING_BYTE_MOJIKYO_PJ_1 (CHARSET_ID_OFFSET - 14) -#define LEADING_BYTE_MOJIKYO_PJ_2 (CHARSET_ID_OFFSET - 15) -#define LEADING_BYTE_MOJIKYO_PJ_3 (CHARSET_ID_OFFSET - 16) -#define LEADING_BYTE_MOJIKYO_PJ_4 (CHARSET_ID_OFFSET - 17) -#define LEADING_BYTE_MOJIKYO_PJ_5 (CHARSET_ID_OFFSET - 18) -#define LEADING_BYTE_MOJIKYO_PJ_6 (CHARSET_ID_OFFSET - 19) -#define LEADING_BYTE_MOJIKYO_PJ_7 (CHARSET_ID_OFFSET - 20) -#define LEADING_BYTE_MOJIKYO_PJ_8 (CHARSET_ID_OFFSET - 21) -#define LEADING_BYTE_MOJIKYO_PJ_9 (CHARSET_ID_OFFSET - 22) -#define LEADING_BYTE_MOJIKYO_PJ_10 (CHARSET_ID_OFFSET - 23) -#define LEADING_BYTE_MOJIKYO_PJ_11 (CHARSET_ID_OFFSET - 24) -#define LEADING_BYTE_MOJIKYO_PJ_12 (CHARSET_ID_OFFSET - 25) -#define LEADING_BYTE_MOJIKYO_PJ_13 (CHARSET_ID_OFFSET - 26) -#define LEADING_BYTE_MOJIKYO_PJ_14 (CHARSET_ID_OFFSET - 27) -#define LEADING_BYTE_MOJIKYO_PJ_15 (CHARSET_ID_OFFSET - 28) -#define LEADING_BYTE_MOJIKYO_PJ_16 (CHARSET_ID_OFFSET - 29) -#define LEADING_BYTE_MOJIKYO_PJ_17 (CHARSET_ID_OFFSET - 30) -#define LEADING_BYTE_MOJIKYO_PJ_18 (CHARSET_ID_OFFSET - 31) -#define LEADING_BYTE_MOJIKYO_PJ_19 (CHARSET_ID_OFFSET - 32) -#define LEADING_BYTE_MOJIKYO_PJ_20 (CHARSET_ID_OFFSET - 33) -#define LEADING_BYTE_MOJIKYO_PJ_21 (CHARSET_ID_OFFSET - 34) - -#define MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE -#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 35) - - -/* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */ - -/* #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0') */ -/* #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?') */ /* ISO 646 IRV */ -#define LEADING_BYTE_ASCII 6 /* (CHARSET_ID_OFFSET_94 + 'B') */ +#define LEADING_BYTE_ASCII -6 /* (CHARSET_ID_OFFSET_94 + 'B') */ /* Right half of JIS X0201-1976 */ -#define LEADING_BYTE_KATAKANA_JISX0201 13 /* (CHARSET_ID_OFFSET_94 + 'I') */ +#define LEADING_BYTE_KATAKANA_JISX0201 -13 /* (CHARSET_ID_OFFSET_94 + 'I') */ /* Left half of JIS X0201-1976 */ -#define LEADING_BYTE_LATIN_JISX0201 14 /* (CHARSET_ID_OFFSET_94 + 'J') */ - +#define LEADING_BYTE_LATIN_JISX0201 -14 /* (CHARSET_ID_OFFSET_94 + 'J') */ -/* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */ /* Right half of ISO 8859-1 */ -#define LEADING_BYTE_LATIN_ISO8859_1 100 /* (CHARSET_ID_OFFSET_96 + 'A') */ +#define LEADING_BYTE_LATIN_ISO8859_1 -100 /* (CHARSET_ID_OFFSET_96 + 'A') */ /* Right half of ISO 8859-2 */ -#define LEADING_BYTE_LATIN_ISO8859_2 101 /* (CHARSET_ID_OFFSET_96 + 'B') */ +#define LEADING_BYTE_LATIN_ISO8859_2 -101 /* (CHARSET_ID_OFFSET_96 + 'B') */ /* Right half of ISO 8859-3 */ -#define LEADING_BYTE_LATIN_ISO8859_3 109 /* (CHARSET_ID_OFFSET_96 + 'C') */ +#define LEADING_BYTE_LATIN_ISO8859_3 -109 /* (CHARSET_ID_OFFSET_96 + 'C') */ /* Right half of ISO 8859-4 */ -#define LEADING_BYTE_LATIN_ISO8859_4 110 /* (CHARSET_ID_OFFSET_96 + 'D') */ +#define LEADING_BYTE_LATIN_ISO8859_4 -110 /* (CHARSET_ID_OFFSET_96 + 'D') */ /* Right half of ISO 8859-7 */ -#define LEADING_BYTE_GREEK_ISO8859_7 126 /* (CHARSET_ID_OFFSET_96 + 'F') */ +#define LEADING_BYTE_GREEK_ISO8859_7 -126 /* (CHARSET_ID_OFFSET_96 + 'F') */ /* Right half of ISO 8859-6 */ -#define LEADING_BYTE_ARABIC_ISO8859_6 127 /* (CHARSET_ID_OFFSET_96 + 'G') */ +#define LEADING_BYTE_ARABIC_ISO8859_6 -127 /* (CHARSET_ID_OFFSET_96 + 'G') */ /* Right half of ISO 8859-8 */ -#define LEADING_BYTE_HEBREW_ISO8859_8 138 /* (CHARSET_ID_OFFSET_96 + 'H') */ +#define LEADING_BYTE_HEBREW_ISO8859_8 -138 /* (CHARSET_ID_OFFSET_96 + 'H') */ /* Right half of ISO 8859-5 */ -#define LEADING_BYTE_CYRILLIC_ISO8859_5 144 /* (CHARSET_ID_OFFSET_96 + 'L') */ +#define LEADING_BYTE_CYRILLIC_ISO8859_5 -144 /* (CHARSET_ID_OFFSET_96 + 'L') */ /* Right half of ISO 8859-9 */ -#define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */ +#define LEADING_BYTE_LATIN_ISO8859_9 -148 /* (CHARSET_ID_OFFSET_96 + 'M') */ /* TIS620-2533 */ -#define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */ +#define LEADING_BYTE_THAI_TIS620 -166 /* (CHARSET_ID_OFFSET_96 + 'T') */ /* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */ -#define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */ +#define LEADING_BYTE_LATIN_TCVN5712 -180 /* F = 5/10 0x5A `Z' */ -/* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */ - -/* #define MIN_LEADING_BYTE_PRIVATE_2 ('0' + CHARSET_ID_OFFSET_94x94) */ -/* #define MAX_LEADING_BYTE_PRIVATE_2 ('?' + CHARSET_ID_OFFSET_94x94) */ - /* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */ -#define LEADING_BYTE_JAPANESE_JISX0208_1978 42 +#define LEADING_BYTE_JAPANESE_JISX0208_1978 -42 /* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */ -#define LEADING_BYTE_CHINESE_GB2312 58 +#define LEADING_BYTE_CHINESE_GB2312 -58 /* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */ -#define LEADING_BYTE_JAPANESE_JISX0208 87 +#define LEADING_BYTE_JAPANESE_JISX0208 -87 + +/* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */ +#define LEADING_BYTE_JAPANESE_JISX0208_1990 -168 /* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */ -#define LEADING_BYTE_KOREAN_KSC5601 149 +#define LEADING_BYTE_KOREAN_KSC5601 -149 /* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */ -#define LEADING_BYTE_JAPANESE_JISX0212 159 +#define LEADING_BYTE_JAPANESE_JISX0212 -159 /* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */ -#define LEADING_BYTE_CHINESE_CCITT_GB 165 +#define LEADING_BYTE_CHINESE_CCITT_GB -165 /* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */ -#define LEADING_BYTE_CHINESE_CNS11643_1 171 +#define LEADING_BYTE_CHINESE_CNS11643_1 -171 /* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */ -#define LEADING_BYTE_CHINESE_CNS11643_2 172 +#define LEADING_BYTE_CHINESE_CNS11643_2 -172 /* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */ -#define LEADING_BYTE_CHINESE_CNS11643_3 183 +#define LEADING_BYTE_CHINESE_CNS11643_3 -183 /* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */ -#define LEADING_BYTE_CHINESE_CNS11643_4 184 +#define LEADING_BYTE_CHINESE_CNS11643_4 -184 /* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */ -#define LEADING_BYTE_CHINESE_CNS11643_5 185 +#define LEADING_BYTE_CHINESE_CNS11643_5 -185 /* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */ -#define LEADING_BYTE_CHINESE_CNS11643_6 186 +#define LEADING_BYTE_CHINESE_CNS11643_6 -186 /* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */ -#define LEADING_BYTE_CHINESE_CNS11643_7 187 +#define LEADING_BYTE_CHINESE_CNS11643_7 -187 /* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */ -#define LEADING_BYTE_KOREAN_KPS9566 202 +#define LEADING_BYTE_KOREAN_KPS9566 -202 + +#define MIN_LEADING_BYTE (- 80 * 3) -#define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE) +#define NUM_LEADING_BYTES (MAX_LEADING_BYTE_PRIVATE - MIN_LEADING_BYTE) /************************************************************************/ @@ -279,17 +239,20 @@ struct Lisp_Charset /* Code-point->character mapping table */ Lisp_Object decoding_table; - /* Character->code-point mapping table */ - Lisp_Object encoding_table; + /* Base CCS */ + Lisp_Object mother; /* Range of character code */ - Emchar ucs_min, ucs_max; + int min_code, max_code; /* Offset for external code */ - Emchar code_offset; + int code_offset; + + /* Type of conversion from mother CCS */ + unsigned char conversion; /* Offset for each byte */ - Emchar byte_offset; + int byte_offset; }; typedef struct Lisp_Charset Lisp_Charset; @@ -297,19 +260,9 @@ DECLARE_LRECORD (charset, Lisp_Charset); #define XCHARSET(x) XRECORD (x, charset, Lisp_Charset) #define XSETCHARSET(x, p) XSETRECORD (x, p, charset) #define CHARSETP(x) RECORDP (x, charset) -#define GC_CHARSETP(x) GC_RECORDP (x, charset) #define CHECK_CHARSET(x) CHECK_RECORD (x, charset) #define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, charset) -#define CHARSET_TYPE_94 0 /* This charset includes 94 characters. */ -#define CHARSET_TYPE_94X94 1 /* This charset includes 94x94 characters. */ -#define CHARSET_TYPE_96 2 /* This charset includes 96 characters. */ -#define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */ -#define CHARSET_TYPE_128 4 /* This charset includes 128 characters. */ -#define CHARSET_TYPE_128X128 5 /* This charset includes 128x128 characters. */ -#define CHARSET_TYPE_256 6 /* This charset includes 256 characters. */ -#define CHARSET_TYPE_256X256 7 /* This charset includes 256x256 characters. */ - #define CHARSET_LEFT_TO_RIGHT 0 #define CHARSET_RIGHT_TO_LEFT 1 @@ -330,12 +283,46 @@ DECLARE_LRECORD (charset, Lisp_Charset); #define CHARSET_CHARS(cs) ((cs)->chars) #define CHARSET_REVERSE_DIRECTION_CHARSET(cs) ((cs)->reverse_direction_charset) #define CHARSET_DECODING_TABLE(cs) ((cs)->decoding_table) -#define CHARSET_ENCODING_TABLE(cs) ((cs)->encoding_table) -#define CHARSET_UCS_MIN(cs) ((cs)->ucs_min) -#define CHARSET_UCS_MAX(cs) ((cs)->ucs_max) +#define CHARSET_MIN_CODE(cs) ((cs)->min_code) +#define CHARSET_MAX_CODE(cs) ((cs)->max_code) #define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset) #define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset) +#define CHARSET_MOTHER(cs) ((cs)->mother) +#define CHARSET_CONVERSION(cs) ((cs)->conversion) +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); +} + +INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs); +INLINE_HEADER Lisp_Object +CHARSET_ENCODING_TABLE (Lisp_Charset* cs) +{ + return Fgethash (CHARSET_NAME(cs), + Vchar_attribute_hash_table, + Qnil); +} + +#define CONVERSION_IDENTICAL 0 +#define CONVERSION_94 1 +#define CONVERSION_96 2 +#define CONVERSION_94x60 3 +#define CONVERSION_94x94 4 +#define CONVERSION_96x96 5 +#define CONVERSION_94x94x60 6 +#define CONVERSION_94x94x94 7 +#define CONVERSION_96x96x96 8 +#define CONVERSION_94x94x94x60 9 +#define CONVERSION_94x94x94x94 10 +#define CONVERSION_96x96x96x96 11 #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs)) #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs)) @@ -350,14 +337,17 @@ DECLARE_LRECORD (charset, Lisp_Charset); #define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs)) #define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs)) #define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs)) +#define XCHARSET_BYTE_SIZE(cs) CHARSET_BYTE_SIZE (XCHARSET (cs)) #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \ CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs)) #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs)) #define XCHARSET_ENCODING_TABLE(cs) CHARSET_ENCODING_TABLE(XCHARSET(cs)) -#define XCHARSET_UCS_MIN(cs) CHARSET_UCS_MIN(XCHARSET(cs)) -#define XCHARSET_UCS_MAX(cs) CHARSET_UCS_MAX(XCHARSET(cs)) +#define XCHARSET_MIN_CODE(cs) CHARSET_MIN_CODE(XCHARSET(cs)) +#define XCHARSET_MAX_CODE(cs) CHARSET_MAX_CODE(XCHARSET(cs)) #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs)) #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs)) +#define XCHARSET_MOTHER(cs) CHARSET_MOTHER(XCHARSET(cs)) +#define XCHARSET_CONVERSION(cs) CHARSET_CONVERSION(XCHARSET(cs)) struct charset_lookup { /* Table of charsets indexed by (leading byte - 128). */ @@ -391,8 +381,22 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb) #endif -#define CHARSET_BY_ATTRIBUTES(type, final, dir) \ - (chlook->charset_by_attributes[type][final]) +INLINE_HEADER Lisp_Object +CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir); +INLINE_HEADER Lisp_Object +CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir) +{ + int type; + + if (chars == 94) + type = 0; + else if (chars == 96) + type = 1; + else + return Qnil; + type += dimension == 1 ? 0 : 2; + return chlook->charset_by_attributes[type][final]; +} /************************************************************************/ @@ -402,15 +406,9 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb) #define MAX_CHAR_BASIC_LATIN 0x007F /* -#define MIN_CHAR_GREEK 0x0370 -#define MAX_CHAR_GREEK 0x03CF - -#define MIN_CHAR_CYRILLIC 0x0400 -#define MAX_CHAR_CYRILLIC 0x045F -*/ - #define MIN_CHAR_HEBREW 0x0590 #define MAX_CHAR_HEBREW 0x05EF +*/ #define MIN_CHAR_THAI 0x0E00 #define MAX_CHAR_THAI 0x0E5F @@ -428,13 +426,24 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb) #define MAX_CHAR_BMP 0x00FFFF -#define MIN_CHAR_MOJIKYO 0xE00000 -#define MIN_CHAR_DAIKANWA MIN_CHAR_MOJIKYO -#define MAX_CHAR_DAIKANWA 0xE0FFFF -/* #define MAX_CHAR_MOJIKYO 0xE9093F */ -#define MAX_CHAR_MOJIKYO (MIN_CHAR_MOJIKYO + 94 * 60 * 22) +#define MIN_CHAR_SMP 0x010000 +#define MAX_CHAR_SMP 0x01FFFF + +#define MIN_CHAR_SIP 0x020000 +#define MAX_CHAR_SIP 0x02FFFF + +#if 0 +#define MIN_CHAR_DAIKANWA 0x00E00000 +#define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */ + +#define MIN_CHAR_CBETA 0x00E20000 +#define MAX_CHAR_CBETA 0x00E2FFFF -#define MIN_CHAR_94 0xE90940 +#define MIN_CHAR_CHINA3_JEF 0x00E80000 +#define MAX_CHAR_CHINA3_JEF 0x00E8FFFF +#endif + +#define MIN_CHAR_94 0x00E90940 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1) #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80) #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1) @@ -446,70 +455,193 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb) #define MIN_CHAR_96x96 0xF4C000 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1) +/* +#define MIN_CHAR_GT 0x61000000 +#define MAX_CHAR_GT (MIN_CHAR_GT + 67547) +*/ +#define MIN_CHAR_BIG5_CDP 0x62000000 +#define MAX_CHAR_BIG5_CDP 0x6200FFFF +/* +#define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1) +#define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535) +#define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2) +#define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535) +#define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3) +#define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535) +#define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4) +#define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535) +#define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5) +#define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535) +#define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6) +#define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535) +#define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7) +#define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535) +#define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8) +#define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535) +#define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9) +#define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535) +#define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10) +#define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535) +#define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11) +#define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535) +#define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12) +#define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535) +*/ -Emchar make_builtin_char (Lisp_Object charset, int c1, int c2); +Emchar decode_builtin_char (Lisp_Object charset, int code_point); -INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point); -INLINE_HEADER Emchar -DECODE_CHAR (Lisp_Object charset, int code_point) +INLINE_HEADER Lisp_Object +get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code); +INLINE_HEADER Lisp_Object +get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code) { - int dim = XCHARSET_DIMENSION (charset); - Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (charset); - int idx; - Lisp_Object ch; + int byte_offset = XCHARSET_BYTE_OFFSET (ccs); - while (dim > 0) + if (VECTORP (table)) { - dim--; - if ( VECTORP (decoding_table) - && ( 0 <= (idx = ((code_point >> (dim * 8)) - & 255) - XCHARSET_BYTE_OFFSET (charset)) ) - && ( idx < XVECTOR_LENGTH (decoding_table) ) - && !NILP (ch = XVECTOR_DATA(decoding_table)[idx]) ) - { - if (CHARP (ch)) - return XCHAR (ch); - else - decoding_table = ch; - } + int idx = code - byte_offset; + + if (idx < XVECTOR_LENGTH(table)) + return XVECTOR_DATA(table)[idx]; else - break; + return Qunbound; } - if (XCHARSET_DIMENSION (charset) == 1) - return make_builtin_char (charset, code_point, 0); + else + return table; +} + +INLINE_HEADER Lisp_Object +put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code, + Lisp_Object value); +INLINE_HEADER Lisp_Object +put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code, + Lisp_Object value) +{ + int byte_offset = XCHARSET_BYTE_OFFSET (ccs); + int ccs_len = XCHARSET_BYTE_SIZE (ccs); + + if (VECTORP (table)) + { + XVECTOR_DATA(table)[code - byte_offset] = value; + return table; + } + else if (EQ (table, value)) + return table; else { - int plane = LEADING_BYTE_MOJIKYO_PJ_1 - XCHARSET_ID (charset); + table = make_vector (ccs_len, table); + XVECTOR_DATA(table)[code - byte_offset] = value; + return table; + } +} - if ( (0 <= plane) && (plane <= 21) ) - { - int c1 = code_point >> 8; - int c2 = code_point & 255; - - if (c1 < 16 + 32) - return ' '; - else if (c1 < 16 + 32 + 30) - return DECODE_CHAR (Vcharset_mojikyo, - plane * (94 * 60) - + (c1 - (16 + 32)) * 94 - + (c2 - 33) - + 1); - else if (c1 < 18 + 32 + 30) - return ' '; - else if (c1 < 18 + 32 + 60) - return DECODE_CHAR (Vcharset_mojikyo, - plane * (94 * 60) - + (c1 - (18 + 32)) * 94 - + (c2 - 33) - + 1); - else - return ' '; - } - else - return make_builtin_char (charset, code_point >> 8, code_point & 255); +INLINE_HEADER void +decoding_table_put_char (Lisp_Object ccs, + int code_point, Lisp_Object character); +INLINE_HEADER void +decoding_table_put_char (Lisp_Object ccs, + int code_point, Lisp_Object character) +{ + Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs); + int dim = XCHARSET_DIMENSION (ccs); + + if (dim == 1) + XCHARSET_DECODING_TABLE (ccs) + = put_ccs_octet_table (table1, ccs, code_point, character); + else if (dim == 2) + { + Lisp_Object table2 + = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8)); + + table2 = put_ccs_octet_table (table2, ccs, + (unsigned char)code_point, character); + XCHARSET_DECODING_TABLE (ccs) + = put_ccs_octet_table (table1, ccs, + (unsigned char)(code_point >> 8), table2); + } + else if (dim == 3) + { + Lisp_Object table2 + = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16)); + Lisp_Object table3 + = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8)); + + table3 = put_ccs_octet_table (table3, ccs, + (unsigned char)code_point, character); + table2 = put_ccs_octet_table (table2, ccs, + (unsigned char)(code_point >> 8), table3); + XCHARSET_DECODING_TABLE (ccs) + = put_ccs_octet_table (table1, ccs, + (unsigned char)(code_point >> 16), table2); + } + else /* if (dim == 4) */ + { + Lisp_Object table2 + = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24)); + Lisp_Object table3 + = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16)); + Lisp_Object table4 + = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8)); + + table4 = put_ccs_octet_table (table4, ccs, + (unsigned char)code_point, character); + table3 = put_ccs_octet_table (table3, ccs, + (unsigned char)(code_point >> 8), table4); + table2 = put_ccs_octet_table (table2, ccs, + (unsigned char)(code_point >> 16), table3); + XCHARSET_DECODING_TABLE (ccs) + = put_ccs_octet_table (table1, ccs, + (unsigned char)(code_point >> 24), table2); } } +INLINE_HEADER void +decoding_table_remove_char (Lisp_Object ccs, int code_point); +INLINE_HEADER void +decoding_table_remove_char (Lisp_Object ccs, int code_point) +{ + decoding_table_put_char (ccs, code_point, Qunbound); +} + +Emchar decode_defined_char (Lisp_Object charset, int code_point); + +INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point); +INLINE_HEADER Emchar +DECODE_CHAR (Lisp_Object charset, int code_point) +{ + Emchar char_id = decode_defined_char (charset, code_point); + + if (char_id >= 0) + return char_id; + else if (XCHARSET_DIMENSION (charset) == 1) + return decode_builtin_char (charset, code_point); + else if (EQ (charset, Vcharset_chinese_big5_1)) + { + unsigned int I + = ((code_point >> 8) - 33) * (0xFF - 0xA1) + + ((code_point & 0xFF) - 33); + unsigned char b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1; + unsigned char b2 = I % (0xFF - 0xA1 + 0x7F - 0x40); + + b2 += b2 < 0x3F ? 0x40 : 0x62; + return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2); + } + else if (EQ (charset, Vcharset_chinese_big5_2)) + { + unsigned int I + = ((code_point >> 8) - 33) * (0xFF - 0xA1) + + ((code_point & 0xFF) - 33); + unsigned char b1, b2; + + I += (0xFF - 0xA1 + 0x7F - 0x40) * (0xC9 - 0xA1); + b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1; + b2 = I % (0xFF - 0xA1 + 0x7F - 0x40); + b2 += b2 < 0x3F ? 0x40 : 0x62; + return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2); + } + return decode_builtin_char (charset, code_point); +} + /* Return a character whose charset is CHARSET and position-codes are C1 and C2. TYPE9N character ignores C2. */ @@ -526,22 +658,9 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2) extern Lisp_Object Vcharacter_attribute_table; int encode_builtin_char_1 (Emchar c, Lisp_Object* charset); +int charset_code_point (Lisp_Object charset, Emchar ch, int defined_only); int range_charset_code_point (Lisp_Object charset, Emchar ch); -INLINE_HEADER int charset_code_point (Lisp_Object charset, Emchar ch); -INLINE_HEADER int -charset_code_point (Lisp_Object charset, Emchar ch) -{ - Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (charset); - Lisp_Object ret; - - if ( CHAR_ID_TABLE_P (encoding_table) - && INTP (ret = get_char_id_table (ch, encoding_table)) ) - return XINT (ret); - else - return range_charset_code_point (charset, ch); -} - extern Lisp_Object Vdefault_coded_charset_priority_list; EXFUN (Ffind_charset, 1); @@ -556,20 +675,10 @@ encode_char_1 (Emchar ch, Lisp_Object* charset) *charset = Ffind_charset (Fcar (charsets)); if (!NILP (*charset)) { - Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (*charset); - Lisp_Object ret; - - if ( CHAR_ID_TABLE_P (encoding_table) - && INTP (ret = get_char_id_table (ch, encoding_table)) ) - return XINT (ret); - else - { - int code_point; - - if ((code_point - = range_charset_code_point (*charset, ch)) >= 0) - return code_point; - } + int code_point = charset_code_point (*charset, ch, 0); + + if (code_point >= 0) + return code_point; } charsets = Fcdr (charsets); } @@ -578,40 +687,14 @@ encode_char_1 (Emchar ch, Lisp_Object* charset) return encode_builtin_char_1 (ch, charset); } -INLINE_HEADER int encode_char_2 (Emchar ch, Lisp_Object* charset); -INLINE_HEADER int -encode_char_2 (Emchar ch, Lisp_Object* charset) -{ - int code_point = encode_char_1 (ch, charset); - - if (EQ (*charset, Vcharset_mojikyo)) - { - int plane, byte1, byte2; - - code_point--; - plane = code_point / (94 * 60); - byte1 = (code_point % (94 * 60)) / 94; - if (byte1 < 30) - byte1 += 16 + 32; - else - byte1 += 18 + 32; - byte2 = code_point % 94 + 33; - *charset - = CHARSET_BY_LEADING_BYTE (LEADING_BYTE_MOJIKYO_PJ_1 - plane); - return (byte1 << 8) | byte2; - } - else - return code_point; -} - -#define ENCODE_CHAR(ch, charset) encode_char_2 (ch, &(charset)) +#define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset)) INLINE_HEADER void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2); INLINE_HEADER void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2) { - int code_point = encode_char_2 (c, charset); + int code_point = encode_char_1 (c, charset); if (code_point >= 0) { @@ -656,16 +739,14 @@ typedef struct Charc int code_point; } Charc; - -/************************************************************************/ -/* Exported functions */ -/************************************************************************/ - -EXFUN (Fget_charset, 1); +INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch); +INLINE_HEADER Charc +CHAR_TO_CHARC (Emchar ch) +{ + Charc cc; -extern Lisp_Object Vcharset_chinese_big5_1; -extern Lisp_Object Vcharset_chinese_big5_2; -extern Lisp_Object Vcharset_japanese_jisx0208; -extern Lisp_Object Vcharset_japanese_jisx0212; + cc.code_point = encode_char_1 (ch, &cc.charset); + return cc; +} #endif /* INCLUDED_char_ucs_h_ */