X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;f=src%2Fchar-ucs.h;h=a47ea808fc503afca1d736808b851c6e393fe0a5;hb=d4fd14df47400ce4a63d921ec1a4c9de649622dc;hp=42d98ef5e639a48092e49b1fe0d3311bd175fbf8;hpb=83672a528db7fe9cace421905b7efd06c11b7c98;p=chise%2Fxemacs-chise.git diff --git a/src/char-ucs.h b/src/char-ucs.h index 42d98ef..a47ea80 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; @@ -62,7 +70,7 @@ typedef int Charset_ID; #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 CHARSET_ID_OFFSET_94 0x55 @@ -221,8 +229,7 @@ struct Lisp_Charset 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; @@ -242,12 +249,14 @@ 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 @@ -270,8 +279,7 @@ 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) @@ -295,8 +303,7 @@ 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)) @@ -359,6 +366,9 @@ CHARSET_BY_LEADING_BYTE (Charset_ID lb) #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) @@ -382,11 +392,21 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2) Lisp_Object ch; if (!EQ (decoding_table, Qnil) - && (0 <= (idx = c1 - (XCHARSET_CHARS (charset) == 94 ? 33 : 32))) + && (0 <= (idx = c1 - XCHARSET_BYTE_OFFSET (charset))) && (idx < XVECTOR_LENGTH (decoding_table)) && !EQ (ch = XVECTOR_DATA(decoding_table)[idx], Qnil)) - return XCHAR (ch); - else if (EQ (charset, Vcharset_katakana_jisx0201)) + { + 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 @@ -450,7 +470,7 @@ 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)) @@ -521,6 +541,15 @@ 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