X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fchar-ucs.h;h=1e3fbe1e028c3e36599b1626860d48ee305422ee;hb=82da33b61c3e2dd2937db17b75b2838188793053;hp=fe680f6caa8cd852f0cccad96a5a1c666ec90260;hpb=5cc18d83ce16a6766b8151054740d26677d0ae42;p=chise%2Fxemacs-chise.git- diff --git a/src/char-ucs.h b/src/char-ucs.h index fe680f6..1e3fbe1 100644 --- a/src/char-ucs.h +++ b/src/char-ucs.h @@ -29,128 +29,214 @@ Boston, MA 02111-1307, USA. */ #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) + char table entries should never escape to Lisp */ + +struct Lisp_Char_Byte_Table +{ + struct lcrecord_header header; + + Lisp_Object property[256]; +}; + + +DECLARE_LRECORD (char_code_table, struct Lisp_Char_Code_Table); +#define XCHAR_CODE_TABLE(x) \ + XRECORD (x, char_code_table, struct Lisp_Char_Code_Table) +#define XSETCHAR_CODE_TABLE(x, p) XSETRECORD (x, p, char_code_table) +#define CHAR_CODE_TABLE_P(x) RECORDP (x, char_code_table) +#define GC_CHAR_CODE_TABLE_P(x) GC_RECORDP (x, char_code_table) +/* #define CHECK_CHAR_CODE_TABLE(x) CHECK_RECORD (x, char_code_table) + char table entries should never escape to Lisp */ + +struct Lisp_Char_Code_Table +{ + struct lcrecord_header header; + + Lisp_Object table; +}; + +Lisp_Object get_char_code_table (Emchar ch, Lisp_Object table); + + +extern Lisp_Object Vcharset_ucs_bmp; +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; -#define MIN_LEADING_BYTE 0x80 +#define MIN_LEADING_BYTE -0x60 +#define CHARSET_ID_OFFSET 0x00 + +/* represent normal 80-9F */ +#define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 1) + +/* ISO/IEC 10646 BMP */ +#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 2) + +/* VISCII 1.1 */ +#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 3) + +/* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */ +#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 4) + +/* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */ +#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 5) + +/* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */ +#define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 6) + +/* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */ +#define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 7) + +#define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 8) + +#define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 9) -#define LEADING_BYTE_UCS_BMP 0x80 -#define LEADING_BYTE_CONTROL_1 0x81 /* represent normal 80-9F */ +/* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */ +#define LEADING_BYTE_JAPANESE_JISX0208_1990 (CHARSET_ID_OFFSET - 10) +/* Konjaku-Mojikyo font (for pseudo-JIS X 0208 encoding) */ +#define LEADING_BYTE_MOJIKYO_PJ_1 (CHARSET_ID_OFFSET - 11) +#define LEADING_BYTE_MOJIKYO_PJ_2 (CHARSET_ID_OFFSET - 12) +#define LEADING_BYTE_MOJIKYO_PJ_3 (CHARSET_ID_OFFSET - 13) +#define LEADING_BYTE_MOJIKYO_PJ_4 (CHARSET_ID_OFFSET - 14) +#define LEADING_BYTE_MOJIKYO_PJ_5 (CHARSET_ID_OFFSET - 15) +#define LEADING_BYTE_MOJIKYO_PJ_6 (CHARSET_ID_OFFSET - 16) +#define LEADING_BYTE_MOJIKYO_PJ_7 (CHARSET_ID_OFFSET - 17) +#define LEADING_BYTE_MOJIKYO_PJ_8 (CHARSET_ID_OFFSET - 18) +#define LEADING_BYTE_MOJIKYO_PJ_9 (CHARSET_ID_OFFSET - 19) +#define LEADING_BYTE_MOJIKYO_PJ_10 (CHARSET_ID_OFFSET - 20) +#define LEADING_BYTE_MOJIKYO_PJ_11 (CHARSET_ID_OFFSET - 21) +#define LEADING_BYTE_MOJIKYO_PJ_12 (CHARSET_ID_OFFSET - 22) +#define LEADING_BYTE_MOJIKYO_PJ_13 (CHARSET_ID_OFFSET - 23) +#define LEADING_BYTE_MOJIKYO_PJ_14 (CHARSET_ID_OFFSET - 24) +#define LEADING_BYTE_MOJIKYO_PJ_15 (CHARSET_ID_OFFSET - 25) +#define LEADING_BYTE_MOJIKYO_PJ_16 (CHARSET_ID_OFFSET - 26) +#define LEADING_BYTE_MOJIKYO_PJ_17 (CHARSET_ID_OFFSET - 27) +#define LEADING_BYTE_MOJIKYO_PJ_18 (CHARSET_ID_OFFSET - 28) +#define LEADING_BYTE_MOJIKYO_PJ_19 (CHARSET_ID_OFFSET - 29) +#define LEADING_BYTE_MOJIKYO_PJ_20 (CHARSET_ID_OFFSET - 30) +#define LEADING_BYTE_MOJIKYO_PJ_21 (CHARSET_ID_OFFSET - 31) -#define CHARSET_ID_OFFSET_94 0x60 +#define MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE +#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 32) -#define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0') -#define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?') + +/* #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 (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 0x70 +/* #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 MIN_LEADING_BYTE_PRIVATE_1 0xD0 -#define MAX_LEADING_BYTE_PRIVATE_1 0xDF +#define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */ -#define CHARSET_ID_OFFSET_94x94 0xB0 +/* #define CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */ -/* 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 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 2/4 2/{(8),9,10,11} 4/0 (@) */ +#define LEADING_BYTE_JAPANESE_JISX0208_1978 42 -/* Japanese JIS X0208-1978 */ -#define LEADING_BYTE_JAPANESE_JISX0208_1978 \ - ('@' + CHARSET_ID_OFFSET_94x94) +/* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */ +#define LEADING_BYTE_CHINESE_GB2312 58 -/* Chinese Hanzi GB2312-1980 */ -#define LEADING_BYTE_CHINESE_GB2312 ('A' + CHARSET_ID_OFFSET_94x94) +/* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */ +#define LEADING_BYTE_JAPANESE_JISX0208 87 -/* Japanese JIS X0208-1983 */ -#define LEADING_BYTE_JAPANESE_JISX0208 ('B' + CHARSET_ID_OFFSET_94x94) +/* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */ +#define LEADING_BYTE_KOREAN_KSC5601 149 -/* Hangul KS C5601-1987 */ -#define LEADING_BYTE_KOREAN_KSC5601 ('C' + CHARSET_ID_OFFSET_94x94) +/* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */ +#define LEADING_BYTE_JAPANESE_JISX0212 159 -/* Japanese JIS X0212-1990 */ -#define LEADING_BYTE_JAPANESE_JISX0212 ('D' + CHARSET_ID_OFFSET_94x94) +/* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */ +#define LEADING_BYTE_CHINESE_CCITT_GB 165 -/* CCITT Extended GB */ -#define LEADING_BYTE_CHINESE_CCITT_GB ('E' + 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 1 */ -#define LEADING_BYTE_CHINESE_CNS11643_1 ('G' + 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 2 */ -#define LEADING_BYTE_CHINESE_CNS11643_2 ('H' + 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 3 */ -#define LEADING_BYTE_CHINESE_CNS11643_3 ('I' + 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 4 */ -#define LEADING_BYTE_CHINESE_CNS11643_4 ('J' + 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 5 */ -#define LEADING_BYTE_CHINESE_CNS11643_5 ('K' + 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 6 */ -#define LEADING_BYTE_CHINESE_CNS11643_6 ('L' + 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 -/* Chinese CNS11643 Set 7 */ -#define LEADING_BYTE_CHINESE_CNS11643_7 ('M' + 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 -/* DPRK Hangul KPS 9566-1997 */ -#define LEADING_BYTE_KOREAN_KPS9566 ('N' + CHARSET_ID_OFFSET_94x94) -#define MIN_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_JAPANESE_JISX0208_1978 -#define MAX_LEADING_BYTE_OFFICIAL_2 LEADING_BYTE_KOREAN_KPS9566 - -#define NUM_LEADING_BYTES 256 +#define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE) /************************************************************************/ @@ -172,11 +258,6 @@ struct Lisp_Charset /* Final byte of this character set in ISO2022 designating escape sequence */ Bufbyte final; - /* Number of bytes (1 - 4) required in the internal representation - for characters in this character set. This is *not* the - same as the dimension of the character set). */ - unsigned int rep_bytes; - /* Number of columns a character in this charset takes up, on TTY devices. Not used for X devices. */ unsigned int columns; @@ -195,6 +276,18 @@ struct Lisp_Charset /* Which half of font to be used to display this character set */ unsigned int graphic; + + /* Byte->character mapping table */ + Lisp_Object decoding_table; + + /* Range of character code */ + Emchar ucs_min, ucs_max; + + /* Offset for external code */ + Emchar code_offset; + + /* Offset for each byte */ + Emchar byte_offset; }; DECLARE_LRECORD (charset, struct Lisp_Charset); @@ -205,23 +298,24 @@ DECLARE_LRECORD (charset, struct Lisp_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_96 1 /* This charset includes 96 characters. */ -#define CHARSET_TYPE_94X94 2 /* This charset includes 94x94 characters. */ -#define CHARSET_TYPE_96X96 3 /* This charset includes 96x96 characters. */ -#define CHARSET_TYPE_128X128 4 /* This charset includes 128x128 characters. */ -#define CHARSET_TYPE_256X256 5 /* This charset includes 256x256 characters. */ +#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 /* Leading byte and id have been regrouped. -- OG */ #define CHARSET_ID(cs) ((cs)->id) -#define CHARSET_LEADING_BYTE(cs) ((Bufbyte)(CHARSET_ID(cs))) +#define CHARSET_LEADING_BYTE(cs) (CHARSET_ID(cs)) #define CHARSET_NAME(cs) ((cs)->name) #define CHARSET_SHORT_NAME(cs) ((cs)->short_name) #define CHARSET_LONG_NAME(cs) ((cs)->long_name) -#define CHARSET_REP_BYTES(cs) ((cs)->rep_bytes) #define CHARSET_COLUMNS(cs) ((cs)->columns) #define CHARSET_GRAPHIC(cs) ((cs)->graphic) #define CHARSET_TYPE(cs) ((cs)->type) @@ -233,14 +327,17 @@ DECLARE_LRECORD (charset, struct Lisp_Charset); #define CHARSET_DIMENSION(cs) ((cs)->dimension) #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_UCS_MIN(cs) ((cs)->ucs_min) +#define CHARSET_UCS_MAX(cs) ((cs)->ucs_max) +#define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset) +#define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset) #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs)) #define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs)) #define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs)) #define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs)) -#define XCHARSET_REP_BYTES(cs) CHARSET_REP_BYTES (XCHARSET (cs)) -#define XCHARSET_COLUMNS(cs) CHARSET_COLUMNS (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)) @@ -253,12 +350,21 @@ DECLARE_LRECORD (charset, struct Lisp_Charset); #define XCHARSET_CHARS(cs) CHARSET_CHARS (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_UCS_MIN(cs) CHARSET_UCS_MIN(XCHARSET(cs)) +#define XCHARSET_UCS_MAX(cs) CHARSET_UCS_MAX(XCHARSET(cs)) +#define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs)) +#define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs)) + +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 (leading byte - 128). */ -extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES]; - -/* Table of charsets indexed by type/final-byte. */ -extern Lisp_Object charset_by_attributes[4][128]; +extern struct charset_lookup *chlook; #ifdef ERROR_CHECK_TYPECHECK /* int not Bufbyte even though that is the actual type of a leading byte. @@ -270,18 +376,18 @@ 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]) /************************************************************************/ @@ -302,20 +408,34 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb) #define MIN_CHAR_THAI 0x0E00 #define MAX_CHAR_THAI 0x0E5F -#define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60 +/* +#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 MAX_CHAR_BMP 0x00FFFF + +#define MIN_CHAR_DAIKANWA 0xE00000 +#define MAX_CHAR_DAIKANWA 0xE0FFFF + #define MIN_CHAR_94 0xE90940 #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) #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) -extern Lisp_Object Vcharset_ucs_bmp; /* Return a character whose charset is CHARSET and position-codes are C1 and C2. TYPE9N character ignores C2. */ @@ -324,27 +444,41 @@ INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2); INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2) { - if (EQ (charset, Vcharset_ascii)) - return c1; - else if (EQ (charset, Vcharset_control_1)) - return c1 | 0x80; - else if (EQ (charset, Vcharset_ucs_bmp)) - return (c1 << 8) | c2; - else if (EQ (charset, Vcharset_latin_iso8859_1)) - return c1 | 0x80; - else if (EQ (charset, Vcharset_greek_iso8859_7)) - return c1 + MIN_CHAR_GREEK - 0x20; - else if (EQ (charset, Vcharset_cyrillic_iso8859_5)) - return c1 + MIN_CHAR_CYRILLIC - 0x20; - else if (EQ (charset, Vcharset_hebrew_iso8859_8)) - return c1 + MIN_CHAR_HEBREW - 0x20; - else if (EQ (charset, Vcharset_thai_tis620)) - return c1 + MIN_CHAR_THAI - 0x20; - else if (EQ (charset, Vcharset_katakana_jisx0201)) - if (c1 < 0x60) - return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20; - else - return 32; + 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)) + { + if (VECTORP (ch)) + { + if ((0 <= (idx = c2 - XCHARSET_BYTE_OFFSET (charset))) + && (idx < XVECTOR_LENGTH (ch)) + && !EQ (ch = XVECTOR_DATA(ch)[idx], Qnil)) + return XCHAR (ch); + } + else + return XCHAR (ch); + } + 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)) @@ -377,139 +511,65 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2) } } -extern Charset_ID latin_a_char_to_charset[128]; -extern unsigned char latin_a_char_to_byte1[128]; -extern unsigned char latin_a_char_to_byte2[128]; +extern Lisp_Object Vcharacter_attribute_table; + +Lisp_Object split_builtin_char (Emchar c); +Lisp_Object range_charset_code_point (Lisp_Object charset, Emchar ch); +Lisp_Object charset_code_point (Lisp_Object charset, Emchar ch); + +extern Lisp_Object Vdefault_coded_charset_priority_list; +EXFUN (Ffind_charset, 1); + +INLINE Lisp_Object SPLIT_CHAR (Emchar c); +INLINE Lisp_Object +SPLIT_CHAR (Emchar c) +{ + Lisp_Object cdef = get_char_code_table (c, Vcharacter_attribute_table); + + if (!EQ (cdef, Qnil)) + { + Lisp_Object charsets = Vdefault_coded_charset_priority_list; + Lisp_Object field; + + while (!EQ (charsets, Qnil)) + { + Lisp_Object charset = Ffind_charset (Fcar (charsets)); + + if (!EQ (charset, Qnil)) + { + if (!NILP (field = Fassq (charset, cdef))) + return field; + else if (!NILP (field = range_charset_code_point (charset, c))) + return Fcons (charset, field); + } + charsets = Fcdr (charsets); + } + } + + /* otherwise --- maybe for bootstrap */ + return split_builtin_char (c); +} 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) { - if (c <= MAX_CHAR_BASIC_LATIN) - { - *charset = Vcharset_ascii; - *c1 = c; - *c2 = 0; - } - else if (c < 0xA0) - { - *charset = Vcharset_control_1; - *c1 = c & 0x7f; - *c2 = 0; - } - else if (c <= 0xff) - { - *charset = Vcharset_latin_iso8859_1; - *c1 = c & 0x7f; - *c2 = 0; - } - else if (c <= 0x17f) - { - *charset - = CHARSET_BY_LEADING_BYTE (latin_a_char_to_charset[c - 0x100]); - *c1 = latin_a_char_to_byte1[c - 0x100]; - *c2 = latin_a_char_to_byte2[c - 0x100]; - } - else if (c < MIN_CHAR_GREEK) - { - *charset = Vcharset_ucs_bmp; - *c1 = c >> 8; - *c2 = c & 0xff; - } - else if (c <= MAX_CHAR_GREEK) - { - *charset = Vcharset_greek_iso8859_7; - *c1 = c - MIN_CHAR_GREEK + 0x20; - *c2 = 0; - } - else if (c < MIN_CHAR_CYRILLIC) - { - *charset = Vcharset_ucs_bmp; - *c1 = c >> 8; - *c2 = c & 0xff; - } - else if (c <= MAX_CHAR_CYRILLIC) - { - *charset = Vcharset_cyrillic_iso8859_5; - *c1 = c - MIN_CHAR_CYRILLIC + 0x20; - *c2 = 0; - } - else if (c < MIN_CHAR_HEBREW) - { - *charset = Vcharset_ucs_bmp; - *c1 = c >> 8; - *c2 = c & 0xff; - } - else if (c <= MAX_CHAR_HEBREW) - { - *charset = Vcharset_hebrew_iso8859_8; - *c1 = c - MIN_CHAR_HEBREW + 0x20; - *c2 = 0; - } - else if (c < MIN_CHAR_THAI) - { - *charset = Vcharset_ucs_bmp; - *c1 = c >> 8; - *c2 = c & 0xff; - } - else if (c <= MAX_CHAR_THAI) - { - *charset = Vcharset_thai_tis620; - *c1 = c - MIN_CHAR_THAI + 0x20; - *c2 = 0; - } - else if (c < MIN_CHAR_HALFWIDTH_KATAKANA) - { - *charset = Vcharset_ucs_bmp; - *c1 = c >> 8; - *c2 = c & 0xff; - } - else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA) - { - *charset = Vcharset_katakana_jisx0201; - *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20; - *c2 = 0; - } - 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; - } - 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) + Lisp_Object ret = SPLIT_CHAR (c); + + *charset = Fcar (ret); + ret = Fcdr (ret); + if (INTP (Fcar (ret))) { - *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; + *c1 = XINT (Fcar (ret)); + ret = Fcdr (ret); + if (INTP (Fcar (ret))) + *c2 = XINT (Fcar (ret)); + else + *c2 = 0; } else { - printf("u+%x", c); - abort(); + *c1 = *c2 = 0; } } @@ -527,24 +587,14 @@ CHAR_CHARSET (Emchar ch) return charset; } -#define CHAR_LEADING_BYTE(c) (XCHARSET_LEADING_BYTE(CHAR_CHARSET(c))) - - -#ifdef ENABLE_COMPOSITE_CHARS -/************************************************************************/ -/* Composite characters */ -/************************************************************************/ - -Emchar lookup_composite_char (Bufbyte *str, int len); -Lisp_Object composite_char_string (Emchar ch); -#endif /* ENABLE_COMPOSITE_CHARS */ +#define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c))) +#define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c)))) /************************************************************************/ /* Exported functions */ /************************************************************************/ -EXFUN (Ffind_charset, 1); EXFUN (Fget_charset, 1); extern Lisp_Object Vcharset_chinese_big5_1;