X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fchar-ucs.h;h=4c7697bb3d3fb414e3f3ba327928acf3f847117d;hb=63e55d9007ffeb3803b57bb6b7d82b7e8ab96335;hp=c6837708bdee0cc50b0f45aba80c9f7791887563;hpb=173eb2c59c4f1eefabbd6c9a22b71258d20316cb;p=chise%2Fxemacs-chise.git diff --git a/src/char-ucs.h b/src/char-ucs.h index c683770..4c7697b 100644 --- a/src/char-ucs.h +++ b/src/char-ucs.h @@ -29,15 +29,23 @@ Boston, MA 02111-1307, USA. */ #define CHAR_ASCII_P(ch) ((ch) <= 0x7F) -typedef struct +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 { - unsigned char *base; - size_t offset; - size_t size; -} Emchar_to_byte_table; + struct lcrecord_header header; + + Lisp_Object property[256]; +}; -unsigned char -get_byte_from_character_table (Emchar ch, Emchar_to_byte_table* table); +Lisp_Object get_char_code_table (Emchar ch, Lisp_Object table); extern Lisp_Object Vcharset_ucs_bmp; @@ -60,9 +68,15 @@ typedef int Charset_ID; #define LEADING_BYTE_UCS_BMP 0x80 #define LEADING_BYTE_CONTROL_1 0x81 /* represent normal 80-9F */ +#define LEADING_BYTE_HIRAGANA_JISX0208 0x82 +#define LEADING_BYTE_KATAKANA_JISX0208 0x83 +#define LEADING_BYTE_LATIN_VISCII 0x84 +#define MIN_LEADING_BYTE_PRIVATE 0x85 +#define MAX_LEADING_BYTE_PRIVATE 0x94 -#define CHARSET_ID_OFFSET_94 0x55 + +#define CHARSET_ID_OFFSET_94 (0x95 - '0') #define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0') #define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?') @@ -77,7 +91,7 @@ typedef int Charset_ID; #define LEADING_BYTE_LATIN_JISX0201 (CHARSET_ID_OFFSET_94 + 'J') -#define CHARSET_ID_OFFSET_96 0x70 +#define CHARSET_ID_OFFSET_96 (0xB0 - '0') #define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET_96 + '1') #define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET_96 + '2') @@ -113,11 +127,7 @@ typedef int Charset_ID; #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 CHARSET_ID_OFFSET_94x94 0xB0 +#define CHARSET_ID_OFFSET_94x94 (0xE0 - '0') /* Big5 Level 1 */ #define LEADING_BYTE_CHINESE_BIG5_1 ('0' + CHARSET_ID_OFFSET_94x94) @@ -171,8 +181,6 @@ typedef int Charset_ID; /* 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 @@ -216,17 +224,19 @@ struct Lisp_Charset unsigned int graphic; /* Byte->character mapping table */ - Emchar* decoding_table; + Lisp_Object decoding_table; /* Character->byte mapping table */ - Emchar_to_byte_table* to_byte1_table; - Emchar_to_byte_table* to_byte2_table; + Lisp_Object encoding_table; /* Range of character code */ Emchar ucs_min, ucs_max; - /* Offset for external representation */ + /* Offset for external code */ Emchar code_offset; + + /* Offset for each byte */ + Emchar byte_offset; }; DECLARE_LRECORD (charset, struct Lisp_Charset); @@ -237,12 +247,14 @@ 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 @@ -265,11 +277,11 @@ DECLARE_LRECORD (charset, struct 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_TO_BYTE1_TABLE(cs) ((cs)->to_byte1_table) -#define CHARSET_TO_BYTE2_TABLE(cs) ((cs)->to_byte2_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_CODE_OFFSET(cs) ((cs)->code_offset) +#define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset) #define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs)) @@ -289,8 +301,11 @@ DECLARE_LRECORD (charset, struct Lisp_Charset); #define XCHARSET_REVERSE_DIRECTION_CHARSET(cs) \ CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs)) #define XCHARSET_DECODING_TABLE(cs) CHARSET_DECODING_TABLE(XCHARSET(cs)) -#define XCHARSET_TO_BYTE1_TABLE(cs) CHARSET_TO_BYTE1_TABLE(XCHARSET(cs)) -#define XCHARSET_TO_BYTE2_TABLE(cs) CHARSET_TO_BYTE2_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_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]; @@ -340,9 +355,18 @@ 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 MIN_CHAR_94 0xE90940 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1) #define MIN_CHAR_96 (MIN_CHAR_94 + 94 * 80) @@ -361,25 +385,47 @@ INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2); INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2) { - Emchar* decoding_table; - - if ((decoding_table = XCHARSET_DECODING_TABLE (charset)) != NULL) - return decoding_table[c1 - (XCHARSET_CHARS (charset) == 94 ? 33 : 32)]; - else if (EQ (charset, Vcharset_katakana_jisx0201)) + 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 (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 (CHARSET_UCS_MAX (XCHARSET (charset))) - return (XCHARSET_DIMENSION (charset) == 1 - ? - c1 - CHARSET_CODE_OFFSET (XCHARSET (charset)) - : - (c1 - CHARSET_CODE_OFFSET (XCHARSET (charset))) - * XCHARSET_CHARS (charset) - + c2 - CHARSET_CODE_OFFSET (XCHARSET (charset))) - + CHARSET_UCS_MIN (XCHARSET (charset)); + 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)) @@ -422,7 +468,7 @@ 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 < MIN_CHAR_94) + if (c < MIN_CHAR_OBS_94x94) { Lisp_Object charsets = Vdefault_coded_charset_priority_list; while (!EQ (charsets, Qnil)) @@ -493,6 +539,15 @@ breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2) *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