X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fchar-ucs.h;h=b27bbd2803235dcecbd21b59da5fbc1a98b23aca;hb=4f29597e4f3696a59bb08ffece07183c1568c4a5;hp=ef96fbf14f2cf6fbe334d10ecb0f218ac0cfd938;hpb=ff0a1120efb56d168c71cc38315ad815339f9fc4;p=chise%2Fxemacs-chise.git- diff --git a/src/char-ucs.h b/src/char-ucs.h index ef96fbf..b27bbd2 100644 --- a/src/char-ucs.h +++ b/src/char-ucs.h @@ -1,6 +1,5 @@ /* Header for UCS-4 character representation. - Copyright (C) 1999 Electrotechnical Laboratory, JAPAN. - Licensed to the Free Software Foundation. + Copyright (C) 1999,2000 MORIOKA Tomohiko This file is part of XEmacs. @@ -19,174 +18,221 @@ along with XEmacs; see the file COPYING. If not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ -/* Rewritten by MORIOKA Tomohiko . */ - -#ifndef _XEMACS_CHAR_UCS_H -#define _XEMACS_CHAR_UCS_H +#ifndef INCLUDED_char_ucs_h_ +#define INCLUDED_char_ucs_h_ #define valid_char_p(ch) 1 #define CHAR_ASCII_P(ch) ((ch) <= 0x7F) -DECLARE_LRECORD (char_byte_table, struct Lisp_Char_Byte_Table); -#define XCHAR_BYTE_TABLE(x) \ - XRECORD (x, char_byte_table, struct Lisp_Char_Byte_Table) -#define XSETCHAR_BYTE_TABLE(x, p) XSETRECORD (x, p, char_byte_table) -#define CHAR_BYTE_TABLE_P(x) RECORDP (x, char_byte_table) -#define GC_CHAR_BYTE_TABLE_P(x) GC_RECORDP (x, char_byte_table) -/* #define CHECK_CHAR_BYTE_TABLE(x) CHECK_RECORD (x, char_byte_table) +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_Byte_Table + +struct Lisp_Char_ID_Table { struct lcrecord_header header; - Lisp_Object property[256]; + 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 */ -Lisp_Object get_char_code_table (Emchar ch, Lisp_Object table); +Lisp_Object get_char_id_table (Emchar ch, Lisp_Object table); -extern Lisp_Object Vcharset_ucs_bmp; + +extern Lisp_Object Vcharset_mojikyo; extern Lisp_Object Vcharset_latin_jisx0201; -extern Lisp_Object Vcharset_latin_iso8859_2; -extern Lisp_Object Vcharset_latin_iso8859_3; -extern Lisp_Object Vcharset_latin_iso8859_4; -extern Lisp_Object Vcharset_latin_iso8859_9; -extern Lisp_Object Vcharset_latin_viscii_lower; -extern Lisp_Object Vcharset_latin_viscii_upper; /************************************************************************/ /* Definition of leading bytes */ /************************************************************************/ -typedef int Charset_ID; +typedef short Charset_ID; -#define MIN_LEADING_BYTE -0x40 +#define MIN_LEADING_BYTE -0x60 #define CHARSET_ID_OFFSET 0x00 +/* ISO/IEC 10646 */ +#define LEADING_BYTE_UCS (CHARSET_ID_OFFSET - 1) + /* represent normal 80-9F */ -#define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 1) +#define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 2) /* ISO/IEC 10646 BMP */ -#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 2) +#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3) /* VISCII 1.1 */ -#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 3) - -#define LEADING_BYTE_HIRAGANA_JISX0208 (CHARSET_ID_OFFSET - 4) -#define LEADING_BYTE_KATAKANA_JISX0208 (CHARSET_ID_OFFSET - 5) +#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 4) + +/* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */ +#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 5) + +/* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */ +#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 6) + +/* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */ +#define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 7) + +/* 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_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 9) + +#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) + +/* 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 - 6) +#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 35) -#define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') +/* #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 + '?') +/* #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 (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 (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 (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) - -#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET_96 + '1') -#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET_96 + '2') +/* #define CHARSET_ID_OFFSET_96 (CHARSET_ID_OFFSET_94 + 80) */ /* Right half of ISO 8859-1 */ -#define LEADING_BYTE_LATIN_ISO8859_1 (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 (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 (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 (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 (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 (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 (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 (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 (CHARSET_ID_OFFSET_96 + 'M') +#define LEADING_BYTE_LATIN_ISO8859_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */ /* TIS620-2533 */ -#define LEADING_BYTE_THAI_TIS620 (CHARSET_ID_OFFSET_96 + 'T') - +#define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */ -#define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) +/* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */ +#define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */ -/* Big5 Level 1 */ -#define LEADING_BYTE_CHINESE_BIG5_1 ('0' + CHARSET_ID_OFFSET_94x94) -/* Big5 Level 2 */ -#define LEADING_BYTE_CHINESE_BIG5_2 ('1' + CHARSET_ID_OFFSET_94x94) +/* #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) +/* #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 */ -#define LEADING_BYTE_JAPANESE_JISX0208_1978 \ - ('@' + CHARSET_ID_OFFSET_94x94) +/* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */ +#define LEADING_BYTE_JAPANESE_JISX0208_1978 42 -/* Chinese Hanzi GB2312-1980 */ -#define LEADING_BYTE_CHINESE_GB2312 ('A' + CHARSET_ID_OFFSET_94x94) +/* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */ +#define LEADING_BYTE_CHINESE_GB2312 58 -/* Japanese JIS X0208-1983 */ -#define LEADING_BYTE_JAPANESE_JISX0208 ('B' + CHARSET_ID_OFFSET_94x94) +/* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */ +#define LEADING_BYTE_JAPANESE_JISX0208 87 -/* Hangul KS C5601-1987 */ -#define LEADING_BYTE_KOREAN_KSC5601 ('C' + CHARSET_ID_OFFSET_94x94) +/* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */ +#define LEADING_BYTE_KOREAN_KSC5601 149 -/* Japanese JIS X0212-1990 */ -#define LEADING_BYTE_JAPANESE_JISX0212 ('D' + CHARSET_ID_OFFSET_94x94) +/* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */ +#define LEADING_BYTE_JAPANESE_JISX0212 159 -/* CCITT Extended GB */ -#define LEADING_BYTE_CHINESE_CCITT_GB ('E' + CHARSET_ID_OFFSET_94x94) +/* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */ +#define LEADING_BYTE_CHINESE_CCITT_GB 165 -/* Chinese CNS11643 Set 1 */ -#define LEADING_BYTE_CHINESE_CNS11643_1 ('G' + CHARSET_ID_OFFSET_94x94) +/* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */ +#define LEADING_BYTE_CHINESE_CNS11643_1 171 -/* Chinese CNS11643 Set 2 */ -#define LEADING_BYTE_CHINESE_CNS11643_2 ('H' + CHARSET_ID_OFFSET_94x94) +/* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */ +#define LEADING_BYTE_CHINESE_CNS11643_2 172 -/* Chinese CNS11643 Set 3 */ -#define LEADING_BYTE_CHINESE_CNS11643_3 ('I' + CHARSET_ID_OFFSET_94x94) +/* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */ +#define LEADING_BYTE_CHINESE_CNS11643_3 183 -/* Chinese CNS11643 Set 4 */ -#define LEADING_BYTE_CHINESE_CNS11643_4 ('J' + CHARSET_ID_OFFSET_94x94) +/* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */ +#define LEADING_BYTE_CHINESE_CNS11643_4 184 -/* Chinese CNS11643 Set 5 */ -#define LEADING_BYTE_CHINESE_CNS11643_5 ('K' + CHARSET_ID_OFFSET_94x94) +/* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */ +#define LEADING_BYTE_CHINESE_CNS11643_5 185 -/* Chinese CNS11643 Set 6 */ -#define LEADING_BYTE_CHINESE_CNS11643_6 ('L' + CHARSET_ID_OFFSET_94x94) +/* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */ +#define LEADING_BYTE_CHINESE_CNS11643_6 186 -/* Chinese CNS11643 Set 7 */ -#define LEADING_BYTE_CHINESE_CNS11643_7 ('M' + CHARSET_ID_OFFSET_94x94) +/* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */ +#define LEADING_BYTE_CHINESE_CNS11643_7 187 -/* DPRK Hangul KPS 9566-1997 */ -#define LEADING_BYTE_KOREAN_KPS9566 ('N' + CHARSET_ID_OFFSET_94x94) +/* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */ +#define LEADING_BYTE_KOREAN_KPS9566 202 #define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE) @@ -202,7 +248,10 @@ struct Lisp_Charset int id; Lisp_Object name; - Lisp_Object doc_string, registry, short_name, long_name; + Lisp_Object doc_string; + Lisp_Object registry; + Lisp_Object short_name; + Lisp_Object long_name; Lisp_Object reverse_direction_charset; @@ -218,22 +267,19 @@ struct Lisp_Charset /* Direction of this character set */ unsigned int direction; - /* Type of this character set (94, 96, 94x94, 96x96) */ - unsigned int type; - - /* Number of bytes used in encoding of this character set (1 or 2) */ - unsigned int dimension; + /* Number of bytes used in encoding of this character set (1 .. 4) */ + unsigned short dimension; - /* Number of chars in each dimension (usually 94 or 96) */ - unsigned int chars; + /* Number of chars in each dimension (94, 96, 128, 256) */ + unsigned short chars; /* Which half of font to be used to display this character set */ unsigned int graphic; - /* Byte->character mapping table */ + /* Code-point->character mapping table */ Lisp_Object decoding_table; - /* Character->byte mapping table */ + /* Character->code-point mapping table */ Lisp_Object encoding_table; /* Range of character code */ @@ -245,9 +291,10 @@ struct Lisp_Charset /* Offset for each byte */ Emchar byte_offset; }; +typedef struct Lisp_Charset Lisp_Charset; -DECLARE_LRECORD (charset, struct Lisp_Charset); -#define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset) +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) @@ -274,7 +321,6 @@ DECLARE_LRECORD (charset, struct Lisp_Charset); #define CHARSET_LONG_NAME(cs) ((cs)->long_name) #define CHARSET_COLUMNS(cs) ((cs)->columns) #define CHARSET_GRAPHIC(cs) ((cs)->graphic) -#define CHARSET_TYPE(cs) ((cs)->type) #define CHARSET_DIRECTION(cs) ((cs)->direction) #define CHARSET_FINAL(cs) ((cs)->final) #define CHARSET_DOC_STRING(cs) ((cs)->doc_string) @@ -296,7 +342,6 @@ DECLARE_LRECORD (charset, struct Lisp_Charset); #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs)) #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs)) #define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs)) -#define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs)) #define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs)) #define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs)) #define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (XCHARSET (cs)) @@ -314,34 +359,40 @@ DECLARE_LRECORD (charset, struct Lisp_Charset); #define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs)) #define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs)) -/* Table of charsets indexed by (leading byte - 128). */ -extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES]; +struct charset_lookup { + /* Table of charsets indexed by (leading byte - 128). */ + Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES]; + + /* Table of charsets indexed by type/final-byte/direction. */ + Lisp_Object charset_by_attributes[4][128]; -/* Table of charsets indexed by type/final-byte. */ -extern Lisp_Object charset_by_attributes[4][128]; + Charset_ID next_allocated_leading_byte; +}; + +extern struct charset_lookup *chlook; #ifdef ERROR_CHECK_TYPECHECK /* int not Bufbyte even though that is the actual type of a leading byte. This way, out-ot-range values will get caught rather than automatically truncated. */ -INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb); -INLINE Lisp_Object +INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb); +INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb) { assert (lb >= MIN_LEADING_BYTE && lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES)); - return charset_by_leading_byte[lb - MIN_LEADING_BYTE]; + return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE]; } #else #define CHARSET_BY_LEADING_BYTE(lb) \ - (charset_by_leading_byte[(lb) - MIN_LEADING_BYTE]) + (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE]) #endif #define CHARSET_BY_ATTRIBUTES(type, final, dir) \ - (charset_by_attributes[type][final]) + (chlook->charset_by_attributes[type][final]) /************************************************************************/ @@ -350,11 +401,13 @@ 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 @@ -362,17 +415,24 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb) #define MIN_CHAR_THAI 0x0E00 #define MAX_CHAR_THAI 0x0E5F +/* #define MIN_CHAR_HIRAGANA 0x3041 #define MAX_CHAR_HIRAGANA 0x3093 #define MIN_CHAR_KATAKANA 0x30A1 #define MAX_CHAR_KATAKANA 0x30F6 +*/ #define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61 #define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F -#define MIN_CHAR_OBS_94x94 0xE00000 -#define MAX_CHAR_OBS_94x94 (0xE00000 + 94 * 94 * 14 - 1) +#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_94 0xE90940 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1) @@ -380,241 +440,222 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb) #define MAX_CHAR_96 (MIN_CHAR_96 + 96 * 80 - 1) #define MIN_CHAR_94x94 0xE9F6C0 +#define MIN_CHAR_JIS_X0208_1990 (MIN_CHAR_94x94 + 94 * 94 * 79) #define MAX_CHAR_94x94 (MIN_CHAR_94x94 + 94 * 94 * 80 - 1) +#define MAX_CHAR_JIS_X0208_1990 MAX_CHAR_94x94 #define MIN_CHAR_96x96 0xF4C000 #define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1) -/* Return a character whose charset is CHARSET and position-codes - are C1 and C2. TYPE9N character ignores C2. */ +Emchar make_builtin_char (Lisp_Object charset, int c1, int c2); -INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2); -INLINE Emchar -MAKE_CHAR (Lisp_Object charset, int c1, int c2) +INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point); +INLINE_HEADER Emchar +DECODE_CHAR (Lisp_Object charset, int code_point) { + int dim = XCHARSET_DIMENSION (charset); Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (charset); int idx; Lisp_Object ch; - if (!EQ (decoding_table, Qnil) - && (0 <= (idx = c1 - XCHARSET_BYTE_OFFSET (charset))) - && (idx < XVECTOR_LENGTH (decoding_table)) - && !EQ (ch = XVECTOR_DATA(decoding_table)[idx], Qnil)) + while (dim > 0) { - if (VECTORP (ch)) + 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 ((0 <= (idx = c2 - XCHARSET_BYTE_OFFSET (charset))) - && (idx < XVECTOR_LENGTH (ch)) - && !EQ (ch = XVECTOR_DATA(ch)[idx], Qnil)) + if (CHARP (ch)) return XCHAR (ch); + else + decoding_table = ch; } else - return XCHAR (ch); - } - if (EQ (charset, Vcharset_katakana_jisx0201)) - if (c1 < 0x60) - return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 33; - else - /* return MIN_CHAR_94 + ('I' - '0') * 94 + (c1 - 33); */ - return ' '; - else if (XCHARSET_UCS_MAX (charset)) - { - Emchar code - = (XCHARSET_DIMENSION (charset) == 1 - ? - c1 - XCHARSET_BYTE_OFFSET (charset) - : - (c1 - XCHARSET_BYTE_OFFSET (charset)) * XCHARSET_CHARS (charset) - + c2 - XCHARSET_BYTE_OFFSET (charset)) - - XCHARSET_CODE_OFFSET (charset) + XCHARSET_UCS_MIN (charset); - if ((code < XCHARSET_UCS_MIN (charset)) - || (XCHARSET_UCS_MAX (charset) < code)) - signal_simple_error ("Arguments makes invalid character", - make_char (code)); - return code; - } - else if (XCHARSET_DIMENSION (charset) == 1) - { - switch (XCHARSET_CHARS (charset)) - { - case 94: - return MIN_CHAR_94 - + (XCHARSET_FINAL (charset) - '0') * 94 + (c1 - 33); - case 96: - return MIN_CHAR_96 - + (XCHARSET_FINAL (charset) - '0') * 96 + (c1 - 32); - default: - abort (); - } + break; } + if (XCHARSET_DIMENSION (charset) == 1) + return make_builtin_char (charset, code_point, 0); else { - switch (XCHARSET_CHARS (charset)) + int plane = LEADING_BYTE_MOJIKYO_PJ_1 - XCHARSET_ID (charset); + + if ( (0 <= plane) && (plane <= 21) ) { - case 94: - return MIN_CHAR_94x94 - + (XCHARSET_FINAL (charset) - '0') * 94 * 94 - + (c1 - 33) * 94 + (c2 - 33); - case 96: - return MIN_CHAR_96x96 - + (XCHARSET_FINAL (charset) - '0') * 96 * 96 - + (c1 - 32) * 96 + (c2 - 32); - default: - abort (); + 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); } } -unsigned char charset_get_byte1 (Lisp_Object charset, Emchar ch); -unsigned char charset_get_byte2 (Lisp_Object charset, Emchar ch); +/* Return a character whose charset is CHARSET and position-codes + are C1 and C2. TYPE9N character ignores C2. */ + +INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2); +INLINE_HEADER Emchar +MAKE_CHAR (Lisp_Object charset, int c1, int c2) +{ + if (XCHARSET_DIMENSION (charset) == 1) + return DECODE_CHAR (charset, c1); + else + return DECODE_CHAR (charset, (c1 << 8) | c2); +} + +extern Lisp_Object Vcharacter_attribute_table; + +int encode_builtin_char_1 (Emchar c, Lisp_Object* charset); +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); -INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2); -INLINE void -breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2) +INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset); +INLINE_HEADER int +encode_char_1 (Emchar ch, Lisp_Object* charset) { - if (c < MIN_CHAR_OBS_94x94) + Lisp_Object charsets = Vdefault_coded_charset_priority_list; + + while (!NILP (charsets)) { - Lisp_Object charsets = Vdefault_coded_charset_priority_list; - while (!EQ (charsets, Qnil)) + *charset = Ffind_charset (Fcar (charsets)); + if (!NILP (*charset)) { - *charset = Ffind_charset (Fcar (charsets)); - if (!EQ (*charset, Qnil) - && (*c1 = charset_get_byte1 (*charset, c)) ) + 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 { - *c2 = charset_get_byte2 (*charset, c); - return; + int code_point; + + if ((code_point + = range_charset_code_point (*charset, ch)) >= 0) + return code_point; } - charsets = Fcdr (charsets); } - /* otherwise --- maybe for bootstrap */ - if (c <= MAX_CHAR_BASIC_LATIN) - { - *charset = Vcharset_ascii; - *c1 = charset_get_byte1 (*charset, c); - *c2 = charset_get_byte2 (*charset, c); - } - else if (c < 0xA0) - { - *charset = Vcharset_control_1; - *c1 = charset_get_byte1 (*charset, c); - *c2 = charset_get_byte2 (*charset, c); - } - else if (c <= 0xff) - { - *charset = Vcharset_latin_iso8859_1; - *c1 = charset_get_byte1 (*charset, c); - *c2 = charset_get_byte2 (*charset, c); - } - else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK)) - { - *charset = Vcharset_greek_iso8859_7; - *c1 = c - MIN_CHAR_GREEK + 0x20; - *c2 = 0; - } - else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC)) - { - *charset = Vcharset_cyrillic_iso8859_5; - *c1 = c - MIN_CHAR_CYRILLIC + 0x20; - *c2 = 0; - } - else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW)) - { - *charset = Vcharset_hebrew_iso8859_8; - *c1 = c - MIN_CHAR_HEBREW + 0x20; - *c2 = 0; - } - else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI)) - { - *charset = Vcharset_thai_tis620; - *c1 = c - MIN_CHAR_THAI + 0x20; - *c2 = 0; - } - else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c) - && (c <= MAX_CHAR_HALFWIDTH_KATAKANA)) - { - *charset = Vcharset_katakana_jisx0201; - *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 33; - *c2 = 0; - } - else - { - *charset = Vcharset_ucs_bmp; - *c1 = c >> 8; - *c2 = c & 0xff; - } - } - else if (c <= MAX_CHAR_OBS_94x94) - { - *charset - = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94X94, - ((c - MIN_CHAR_OBS_94x94) / (94 * 94)) + '@', - CHARSET_LEFT_TO_RIGHT); - *c1 = (((c - MIN_CHAR_OBS_94x94) / 94) % 94) + 33; - *c2 = ((c - MIN_CHAR_OBS_94x94) % 94) + 33; - } - else if (c <= MAX_CHAR_94) - { - *charset - = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94, - ((c - MIN_CHAR_94) / 94) + '0', - CHARSET_LEFT_TO_RIGHT); - *c1 = ((c - MIN_CHAR_94) % 94) + 33; - *c2 = 0; + charsets = Fcdr (charsets); } - else if (c <= MAX_CHAR_96) - { - *charset - = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96, - ((c - MIN_CHAR_96) / 96) + '0', - CHARSET_LEFT_TO_RIGHT); - *c1 = ((c - MIN_CHAR_96) % 96) + 32; - *c2 = 0; - } - else if (c <= MAX_CHAR_94x94) - { - *charset - = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94X94, - ((c - MIN_CHAR_94x94) / (94 * 94)) + '0', - CHARSET_LEFT_TO_RIGHT); - *c1 = (((c - MIN_CHAR_94x94) / 94) % 94) + 33; - *c2 = ((c - MIN_CHAR_94x94) % 94) + 33; - } - else if (c <= MAX_CHAR_96x96) + + /* otherwise --- maybe for bootstrap */ + 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_ATTRIBUTES (CHARSET_TYPE_96X96, - ((c - MIN_CHAR_96x96) / (96 * 96)) + '0', - CHARSET_LEFT_TO_RIGHT); - *c1 = (((c - MIN_CHAR_96x96) / 96) % 96) + 32; - *c2 = ((c - MIN_CHAR_96x96) % 96) + 32; + = 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)) + +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); + + if (code_point >= 0) { - printf("u+%x", c); - abort(); + int dim = XCHARSET_DIMENSION (*charset); + + if (dim == 1) + { + *c1 = code_point; + *c2 = 0; + } + else /* if (dim == 2) */ + { + *c1 = code_point >> 8; + *c2 = code_point & 255; + } } + else{ + *c1 = *c2 = 0; + } } #define BREAKUP_CHAR(ch, charset, b1, b2) \ breakup_char_1 (ch, &(charset), &(b1), &(b2)) -INLINE Lisp_Object CHAR_CHARSET (Emchar ch); -INLINE Lisp_Object +INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch); +INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch) { Lisp_Object charset; - int b1, b2; - - BREAKUP_CHAR(ch, charset, b1, b2); + + ENCODE_CHAR (ch, charset); return charset; } #define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c))) #define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c)))) + +typedef struct Charc +{ + Lisp_Object charset; + int code_point; +} Charc; + /************************************************************************/ /* Exported functions */ @@ -627,4 +668,4 @@ extern Lisp_Object Vcharset_chinese_big5_2; extern Lisp_Object Vcharset_japanese_jisx0208; extern Lisp_Object Vcharset_japanese_jisx0212; -#endif /* _XEMACS_CHAR_UCS_H */ +#endif /* INCLUDED_char_ucs_h_ */