X-Git-Url: http://git.chise.org/gitweb/?a=blobdiff_plain;ds=sidebyside;f=src%2Fchar-ucs.h;h=1e3fbe1e028c3e36599b1626860d48ee305422ee;hb=82da33b61c3e2dd2937db17b75b2838188793053;hp=2637fa7a79874633b7c44001cf8e997803073cfe;hpb=68deb7c85bfa4b72cd9f23f53deb675f1e9f74b6;p=chise%2Fxemacs-chise.git- diff --git a/src/char-ucs.h b/src/char-ucs.h index 2637fa7..1e3fbe1 100644 --- a/src/char-ucs.h +++ b/src/char-ucs.h @@ -45,6 +45,23 @@ struct Lisp_Char_Byte_Table 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); @@ -64,7 +81,7 @@ extern Lisp_Object Vcharset_latin_viscii_upper; typedef int Charset_ID; -#define MIN_LEADING_BYTE -0x40 +#define MIN_LEADING_BYTE -0x60 #define CHARSET_ID_OFFSET 0x00 /* represent normal 80-9F */ @@ -88,11 +105,38 @@ typedef int Charset_ID; /* 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_HIRAGANA_JISX0208 (CHARSET_ID_OFFSET - 8) -#define LEADING_BYTE_KATAKANA_JISX0208 (CHARSET_ID_OFFSET - 9) +#define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 8) + +#define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 9) + +/* 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 MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE -#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 10) +#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 32) /* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */ @@ -236,9 +280,6 @@ struct Lisp_Charset /* Byte->character mapping table */ Lisp_Object decoding_table; - /* Character->byte mapping table */ - Lisp_Object encoding_table; - /* Range of character code */ Emchar ucs_min, ucs_max; @@ -287,7 +328,6 @@ 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_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) @@ -311,17 +351,20 @@ 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_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]; +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]; +extern struct charset_lookup *chlook; #ifdef ERROR_CHECK_TYPECHECK /* int not Bufbyte even though that is the actual type of a leading byte. @@ -333,18 +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]) /************************************************************************/ @@ -365,17 +408,21 @@ 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_DAIKANWA 0xE00000 +#define MAX_CHAR_DAIKANWA 0xE0FFFF #define MIN_CHAR_94 0xE90940 #define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1) @@ -383,7 +430,9 @@ 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) @@ -414,13 +463,7 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2) 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)) + if (XCHARSET_UCS_MAX (charset)) { Emchar code = (XCHARSET_DIMENSION (charset) == 1 @@ -470,10 +513,9 @@ MAKE_CHAR (Lisp_Object charset, int c1, int c2) extern Lisp_Object Vcharacter_attribute_table; +Lisp_Object split_builtin_char (Emchar c); Lisp_Object range_charset_code_point (Lisp_Object charset, Emchar ch); - -unsigned char charset_get_byte1 (Lisp_Object charset, Emchar ch); -unsigned char charset_get_byte2 (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); @@ -495,8 +537,9 @@ SPLIT_CHAR (Emchar c) if (!EQ (charset, Qnil)) { - if (!EQ (field = Fcdr (Fassq (charset, cdef)), Qnil) || - !EQ (field = range_charset_code_point (charset, c), 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); @@ -504,97 +547,7 @@ SPLIT_CHAR (Emchar c) } /* otherwise --- maybe for bootstrap */ - if (c < MIN_CHAR_OBS_94x94) - { - if (c <= MAX_CHAR_BASIC_LATIN) - { - return list2 (Vcharset_ascii, make_int (c)); - } - else if (c < 0xA0) - { - return list2 (Vcharset_control_1, make_int (c & 0x7F)); - } - else if (c <= 0xff) - { - return list2 (Vcharset_latin_iso8859_1, make_int (c & 0x7F)); - } - else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK)) - { - return list2 (Vcharset_greek_iso8859_7, - make_int (c - MIN_CHAR_GREEK + 0x20)); - } - else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC)) - { - return list2 (Vcharset_cyrillic_iso8859_5, - make_int (c - MIN_CHAR_CYRILLIC + 0x20)); - } - else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW)) - { - return list2 (Vcharset_hebrew_iso8859_8, - make_int (c - MIN_CHAR_HEBREW + 0x20)); - } - else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI)) - { - return list2 (Vcharset_thai_tis620, - make_int (c - MIN_CHAR_THAI + 0x20)); - } - else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c) - && (c <= MAX_CHAR_HALFWIDTH_KATAKANA)) - { - return list2 (Vcharset_katakana_jisx0201, - make_int (c - MIN_CHAR_HALFWIDTH_KATAKANA + 33)); - } - else - { - return list3 (Vcharset_ucs_bmp, - make_int (c >> 8), make_int (c & 0xff)); - } - } - else if (c <= MAX_CHAR_OBS_94x94) - { - return list3 (CHARSET_BY_ATTRIBUTES - (CHARSET_TYPE_94X94, - ((c - MIN_CHAR_OBS_94x94) / (94 * 94)) + '@', - CHARSET_LEFT_TO_RIGHT), - make_int ((((c - MIN_CHAR_OBS_94x94) / 94) % 94) + 33), - make_int (((c - MIN_CHAR_OBS_94x94) % 94) + 33)); - } - else if (c <= MAX_CHAR_94) - { - return list2 (CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94, - ((c - MIN_CHAR_94) / 94) + '0', - CHARSET_LEFT_TO_RIGHT), - make_int (((c - MIN_CHAR_94) % 94) + 33)); - } - else if (c <= MAX_CHAR_96) - { - return list2 (CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96, - ((c - MIN_CHAR_96) / 96) + '0', - CHARSET_LEFT_TO_RIGHT), - make_int (((c - MIN_CHAR_96) % 96) + 32)); - } - else if (c <= MAX_CHAR_94x94) - { - return list3 (CHARSET_BY_ATTRIBUTES - (CHARSET_TYPE_94X94, - ((c - MIN_CHAR_94x94) / (94 * 94)) + '0', - CHARSET_LEFT_TO_RIGHT), - make_int ((((c - MIN_CHAR_94x94) / 94) % 94) + 33), - make_int (((c - MIN_CHAR_94x94) % 94) + 33)); - } - else if (c <= MAX_CHAR_96x96) - { - return list3 (CHARSET_BY_ATTRIBUTES - (CHARSET_TYPE_96X96, - ((c - MIN_CHAR_96x96) / (96 * 96)) + '0', - CHARSET_LEFT_TO_RIGHT), - make_int ((((c - MIN_CHAR_96x96) / 96) % 96) + 32), - make_int (((c - MIN_CHAR_96x96) % 96) + 32)); - } - else - { - return Qnil; - } + return split_builtin_char (c); } INLINE void breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);