/* Header for UCS-4 character representation.
- Copyright (C) 1999,2000,2001 MORIOKA Tomohiko
+ Copyright (C) 1999,2000,2001,2002,2003 MORIOKA Tomohiko
This file is part of XEmacs.
#define INCLUDED_char_ucs_h_
#include "chartab.h"
+#include "elhash.h"
+
+extern Lisp_Object Vchar_attribute_hash_table;
#define valid_char_p(ch) 1
#define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
-extern Lisp_Object Vcharset_mojikyo;
-extern Lisp_Object Vcharset_mojikyo_2022_1;
+\f
+/************************************************************************/
+/* Exported functions */
+/************************************************************************/
+
+extern Lisp_Object Vcharset_ucs;
extern Lisp_Object Vcharset_latin_jisx0201;
+extern Lisp_Object Vcharset_chinese_big5;
+extern Lisp_Object Vcharset_chinese_big5_1;
+extern Lisp_Object Vcharset_chinese_big5_2;
+extern Lisp_Object Vcharset_japanese_jisx0208;
+extern Lisp_Object Vcharset_japanese_jisx0208_1990;
+extern Lisp_Object Vcharset_japanese_jisx0212;
+
+EXFUN (Fget_charset, 1);
+
+extern Lisp_Object Qmap_ucs, Qucs;
+
+Lisp_Object put_char_ccs_code_point (Lisp_Object character,
+ Lisp_Object ccs, Lisp_Object value);
+Lisp_Object remove_char_ccs (Lisp_Object character, Lisp_Object ccs);
\f
/************************************************************************/
typedef short Charset_ID;
-#define MIN_LEADING_BYTE -0x100
-#define CHARSET_ID_OFFSET 0x00
-
/* ISO/IEC 10646 */
-#define LEADING_BYTE_UCS (CHARSET_ID_OFFSET - 1)
+#define LEADING_BYTE_UCS -177
/* represent normal 80-9F */
-#define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 2)
+#define LEADING_BYTE_CONTROL_1 -77
/* ISO/IEC 10646 BMP */
-#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3)
+#define LEADING_BYTE_UCS_BMP -176
-/* ISO/IEC 10646 for CNS */
-#define LEADING_BYTE_UCS_CNS (CHARSET_ID_OFFSET - 5)
+/* ISO/IEC 10646 SMP */
+#define LEADING_BYTE_UCS_SMP 1
-/* ISO/IEC 10646 for JIS */
-#define LEADING_BYTE_UCS_JIS (CHARSET_ID_OFFSET - 6)
+/* ISO/IEC 10646 SIP */
+#define LEADING_BYTE_UCS_SIP 2
-/* ISO/IEC 10646 for Big5 */
-#define LEADING_BYTE_UCS_BIG5 (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)
+/* Japanese JIS X0208 Common 2/4 2/{(8),9,10,11} 4/2 (B) */
+#define LEADING_BYTE_JIS_X0208 3
/* Chinese GB 12345-1990 */
-#define LEADING_BYTE_CHINESE_GB12345 (CHARSET_ID_OFFSET - 11)
+#define LEADING_BYTE_CHINESE_GB12345 4
-#define LEADING_BYTE_CHINESE_BIG5 (CHARSET_ID_OFFSET - 20)
+#define LEADING_BYTE_CHINESE_BIG5 5
/* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
-#define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 21)
+#define LEADING_BYTE_CHINESE_BIG5_1 6
/* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
-#define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 22)
-
-#define LEADING_BYTE_CHINESE_BIG5_CDP (CHARSET_ID_OFFSET - 23)
+#define LEADING_BYTE_CHINESE_BIG5_2 7
/* VISCII 1.1 */
-#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 24)
+#define LEADING_BYTE_LATIN_VISCII 8
/* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
-#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 25)
+#define LEADING_BYTE_LATIN_VISCII_LOWER 9
/* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
-#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 26)
-
-#define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 27)
-
-#define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 28)
-#define LEADING_BYTE_DAIKANWA_EKANJI (CHARSET_ID_OFFSET - 29)
-
-#define LEADING_BYTE_GT (CHARSET_ID_OFFSET - 30)
-#define LEADING_BYTE_GT_PJ_1 (CHARSET_ID_OFFSET - 31)
-#define LEADING_BYTE_GT_PJ_2 (CHARSET_ID_OFFSET - 32)
-#define LEADING_BYTE_GT_PJ_3 (CHARSET_ID_OFFSET - 33)
-#define LEADING_BYTE_GT_PJ_4 (CHARSET_ID_OFFSET - 34)
-#define LEADING_BYTE_GT_PJ_5 (CHARSET_ID_OFFSET - 35)
-#define LEADING_BYTE_GT_PJ_6 (CHARSET_ID_OFFSET - 36)
-#define LEADING_BYTE_GT_PJ_7 (CHARSET_ID_OFFSET - 37)
-#define LEADING_BYTE_GT_PJ_8 (CHARSET_ID_OFFSET - 38)
-#define LEADING_BYTE_GT_PJ_9 (CHARSET_ID_OFFSET - 39)
-#define LEADING_BYTE_GT_PJ_10 (CHARSET_ID_OFFSET - 40)
-#define LEADING_BYTE_GT_PJ_11 (CHARSET_ID_OFFSET - 41)
-
-#define LEADING_BYTE_MOJIKYO (CHARSET_ID_OFFSET - 48)
-#define LEADING_BYTE_MOJIKYO_2022_1 (CHARSET_ID_OFFSET - 49)
-#define LEADING_BYTE_MOJIKYO_2022_2 (CHARSET_ID_OFFSET - 50)
-
-/* Konjaku-Mojikyo font (for pseudo-JIS X 0208 encoding) */
-#define LEADING_BYTE_MOJIKYO_PJ_1 (CHARSET_ID_OFFSET - 51)
-#define LEADING_BYTE_MOJIKYO_PJ_2 (CHARSET_ID_OFFSET - 52)
-#define LEADING_BYTE_MOJIKYO_PJ_3 (CHARSET_ID_OFFSET - 53)
-#define LEADING_BYTE_MOJIKYO_PJ_4 (CHARSET_ID_OFFSET - 54)
-#define LEADING_BYTE_MOJIKYO_PJ_5 (CHARSET_ID_OFFSET - 55)
-#define LEADING_BYTE_MOJIKYO_PJ_6 (CHARSET_ID_OFFSET - 56)
-#define LEADING_BYTE_MOJIKYO_PJ_7 (CHARSET_ID_OFFSET - 57)
-#define LEADING_BYTE_MOJIKYO_PJ_8 (CHARSET_ID_OFFSET - 58)
-#define LEADING_BYTE_MOJIKYO_PJ_9 (CHARSET_ID_OFFSET - 59)
-#define LEADING_BYTE_MOJIKYO_PJ_10 (CHARSET_ID_OFFSET - 60)
-#define LEADING_BYTE_MOJIKYO_PJ_11 (CHARSET_ID_OFFSET - 61)
-#define LEADING_BYTE_MOJIKYO_PJ_12 (CHARSET_ID_OFFSET - 62)
-#define LEADING_BYTE_MOJIKYO_PJ_13 (CHARSET_ID_OFFSET - 63)
-#define LEADING_BYTE_MOJIKYO_PJ_14 (CHARSET_ID_OFFSET - 64)
-#define LEADING_BYTE_MOJIKYO_PJ_15 (CHARSET_ID_OFFSET - 65)
-#define LEADING_BYTE_MOJIKYO_PJ_16 (CHARSET_ID_OFFSET - 66)
-#define LEADING_BYTE_MOJIKYO_PJ_17 (CHARSET_ID_OFFSET - 67)
-#define LEADING_BYTE_MOJIKYO_PJ_18 (CHARSET_ID_OFFSET - 68)
-#define LEADING_BYTE_MOJIKYO_PJ_19 (CHARSET_ID_OFFSET - 69)
-#define LEADING_BYTE_MOJIKYO_PJ_20 (CHARSET_ID_OFFSET - 70)
-#define LEADING_BYTE_MOJIKYO_PJ_21 (CHARSET_ID_OFFSET - 71)
-
-#define LEADING_BYTE_JEF_CHINA3 (CHARSET_ID_OFFSET - 72)
-#define LEADING_BYTE_CBETA (CHARSET_ID_OFFSET - 73)
-
-#define MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE
-#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 74)
-
-
-/* #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 LEADING_BYTE_LATIN_VISCII_UPPER 10
+
+#define LEADING_BYTE_ETHIOPIC_UCS 11
+
+#define MIN_LEADING_BYTE_PRIVATE 12
+#define MAX_LEADING_BYTE_PRIVATE 512
+
/* ISO 646 IRV */
-#define LEADING_BYTE_ASCII 6 /* (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 13 /* (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 14 /* (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) */
-
/* Right half of ISO 8859-1 */
-#define LEADING_BYTE_LATIN_ISO8859_1 100 /* (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_2 101 /* (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_3 109 /* (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_4 110 /* (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_7 126 /* (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_6 127 /* (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_8 138 /* (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_5 144 /* (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_9 148 /* (CHARSET_ID_OFFSET_96 + 'M') */
+#define LEADING_BYTE_LATIN_ISO8859_9 -148 /* (CHARSET_ID_OFFSET_96 + 'M') */
/* TIS620-2533 */
-#define LEADING_BYTE_THAI_TIS620 166 /* (CHARSET_ID_OFFSET_96 + 'T') */
+#define LEADING_BYTE_THAI_TIS620 -166 /* (CHARSET_ID_OFFSET_96 + 'T') */
/* Right-hand Part of the VSCII-2 (TCVN 5712:1983) */
-#define LEADING_BYTE_LATIN_TCVN5712 180 /* F = 5/10 0x5A `Z' */
-
+#define LEADING_BYTE_LATIN_TCVN5712 -180 /* F = 5/10 0x5A `Z' */
-/* #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) */
/* Japanese JIS X0208-1978 2/4 2/{(8),9,10,11} 4/0 (@) */
-#define LEADING_BYTE_JAPANESE_JISX0208_1978 42
+#define LEADING_BYTE_JAPANESE_JISX0208_1978 -42
/* Chinese Hanzi GB2312-1980 2/4 2/{(8),9,10,11} 4/1 (A) */
-#define LEADING_BYTE_CHINESE_GB2312 58
+#define LEADING_BYTE_CHINESE_GB2312 -58
/* Japanese JIS X0208-1983 2/4 2/{(8),9,10,11} 4/2 (B) */
-#define LEADING_BYTE_JAPANESE_JISX0208 87
+#define LEADING_BYTE_JAPANESE_JISX0208 -87
+
+/* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
+#define LEADING_BYTE_JAPANESE_JISX0208_1990 -168
/* Hangul KS C5601-1987 2/4 2/{8,9,10,11} 4/3 (C) */
-#define LEADING_BYTE_KOREAN_KSC5601 149
+#define LEADING_BYTE_KOREAN_KSC5601 -149
/* Japanese JIS X0212-1990 2/4 2/{8,9,10,11} 4/4 (D) */
-#define LEADING_BYTE_JAPANESE_JISX0212 159
+#define LEADING_BYTE_JAPANESE_JISX0212 -159
/* CCITT Extended GB 2/4 2/{8,9,10,11} 4/5 (E) */
-#define LEADING_BYTE_CHINESE_CCITT_GB 165
+#define LEADING_BYTE_CHINESE_CCITT_GB -165
/* Chinese CNS11643 Set 1 2/4 2/{8,9,10,11} 4/7 (G) */
-#define LEADING_BYTE_CHINESE_CNS11643_1 171
+#define LEADING_BYTE_CHINESE_CNS11643_1 -171
/* Chinese CNS11643 Set 2 2/4 2/{8,9,10,11} 4/8 (H) */
-#define LEADING_BYTE_CHINESE_CNS11643_2 172
+#define LEADING_BYTE_CHINESE_CNS11643_2 -172
/* Chinese CNS11643 Set 3 2/4 2/{8,9,10,11} 4/9 (I) */
-#define LEADING_BYTE_CHINESE_CNS11643_3 183
+#define LEADING_BYTE_CHINESE_CNS11643_3 -183
/* Chinese CNS11643 Set 4 2/4 2/{8,9,10,11} 4/10 (J) */
-#define LEADING_BYTE_CHINESE_CNS11643_4 184
+#define LEADING_BYTE_CHINESE_CNS11643_4 -184
/* Chinese CNS11643 Set 5 2/4 2/{8,9,10,11} 4/11 (K) */
-#define LEADING_BYTE_CHINESE_CNS11643_5 185
+#define LEADING_BYTE_CHINESE_CNS11643_5 -185
/* Chinese CNS11643 Set 6 2/4 2/{8,9,10,11} 4/12 (L) */
-#define LEADING_BYTE_CHINESE_CNS11643_6 186
+#define LEADING_BYTE_CHINESE_CNS11643_6 -186
/* Chinese CNS11643 Set 7 2/4 2/{8,9,10,11} 4/13 (M) */
-#define LEADING_BYTE_CHINESE_CNS11643_7 187
+#define LEADING_BYTE_CHINESE_CNS11643_7 -187
/* DPRK Hangul KPS 9566-1997 2/4 2/{8,9,10,11} 4/14 (N) */
-#define LEADING_BYTE_KOREAN_KPS9566 202
+#define LEADING_BYTE_KOREAN_KPS9566 -202
+
+#define MIN_LEADING_BYTE (- 80 * 3)
-#define NUM_LEADING_BYTES (80 * 3 - MIN_LEADING_BYTE)
+#define NUM_LEADING_BYTES (MAX_LEADING_BYTE_PRIVATE - MIN_LEADING_BYTE)
\f
/************************************************************************/
/* Code-point->character mapping table */
Lisp_Object decoding_table;
- /* Character->code-point mapping table */
- Lisp_Object encoding_table;
+ /* Base CCS */
+ Lisp_Object mother;
/* Range of character code */
- Emchar ucs_min, ucs_max;
+ int min_code, max_code;
/* Offset for external code */
- Emchar code_offset;
+ int code_offset;
+
+ /* Type of conversion from mother CCS */
+ unsigned char conversion;
/* Offset for each byte */
- Emchar byte_offset;
+ int byte_offset;
};
typedef struct Lisp_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)
#define CHECK_CHARSET(x) CHECK_RECORD (x, charset)
#define CONCHECK_CHARSET(x) CONCHECK_RECORD (x, 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_MIN_CODE(cs) ((cs)->min_code)
+#define CHARSET_MAX_CODE(cs) ((cs)->max_code)
#define CHARSET_CODE_OFFSET(cs) ((cs)->code_offset)
#define CHARSET_BYTE_OFFSET(cs) ((cs)->byte_offset)
+#define CHARSET_MOTHER(cs) ((cs)->mother)
+#define CHARSET_CONVERSION(cs) ((cs)->conversion)
+
+INLINE_HEADER int CHARSET_BYTE_SIZE (Lisp_Charset* cs);
+INLINE_HEADER int
+CHARSET_BYTE_SIZE (Lisp_Charset* cs)
+{
+ /* ad-hoc method for `ascii' */
+ if ((CHARSET_CHARS (cs) == 94) &&
+ (CHARSET_BYTE_OFFSET (cs) != 33))
+ return 128 - CHARSET_BYTE_OFFSET (cs);
+ else
+ return CHARSET_CHARS (cs);
+}
+INLINE_HEADER Lisp_Object CHARSET_ENCODING_TABLE (Lisp_Charset* cs);
+INLINE_HEADER Lisp_Object
+CHARSET_ENCODING_TABLE (Lisp_Charset* cs)
+{
+ return Fgethash (CHARSET_NAME(cs),
+ Vchar_attribute_hash_table,
+ Qnil);
+}
+
+#define CONVERSION_IDENTICAL 0
+#define CONVERSION_94 1
+#define CONVERSION_96 2
+#define CONVERSION_94x60 3
+#define CONVERSION_94x94 4
+#define CONVERSION_96x96 5
+#define CONVERSION_94x94x60 6
+#define CONVERSION_94x94x94 7
+#define CONVERSION_96x96x96 8
+#define CONVERSION_94x94x94x60 9
+#define CONVERSION_94x94x94x94 10
+#define CONVERSION_96x96x96x96 11
#define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
#define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
#define XCHARSET_CCL_PROGRAM(cs) CHARSET_CCL_PROGRAM (XCHARSET (cs))
#define XCHARSET_DIMENSION(cs) CHARSET_DIMENSION (XCHARSET (cs))
#define XCHARSET_CHARS(cs) CHARSET_CHARS (XCHARSET (cs))
+#define XCHARSET_BYTE_SIZE(cs) CHARSET_BYTE_SIZE (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_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_MIN_CODE(cs) CHARSET_MIN_CODE(XCHARSET(cs))
+#define XCHARSET_MAX_CODE(cs) CHARSET_MAX_CODE(XCHARSET(cs))
#define XCHARSET_CODE_OFFSET(cs) CHARSET_CODE_OFFSET(XCHARSET(cs))
#define XCHARSET_BYTE_OFFSET(cs) CHARSET_BYTE_OFFSET(XCHARSET(cs))
+#define XCHARSET_MOTHER(cs) CHARSET_MOTHER(XCHARSET(cs))
+#define XCHARSET_CONVERSION(cs) CHARSET_CONVERSION(XCHARSET(cs))
struct charset_lookup {
/* Table of charsets indexed by (leading byte - 128). */
#define MAX_CHAR_BMP 0x00FFFF
+#define MIN_CHAR_SMP 0x010000
+#define MAX_CHAR_SMP 0x01FFFF
+
+#define MIN_CHAR_SIP 0x020000
+#define MAX_CHAR_SIP 0x02FFFF
+
+#if 0
#define MIN_CHAR_DAIKANWA 0x00E00000
#define MAX_CHAR_DAIKANWA (MIN_CHAR_DAIKANWA + 50100) /* 0xE0FFFF */
-/*
-#define MIN_CHAR_MOJIKYO_0 MIN_CHAR_DAIKANWA
-#define MAX_CHAR_MOJIKYO_0 (MIN_CHAR_MOJIKYO_0 + 94 * 60 * 22)
-*/
+
#define MIN_CHAR_CBETA 0x00E20000
#define MAX_CHAR_CBETA 0x00E2FFFF
-#define MIN_CHAR_JEF_CHINA3 0x00E80000
-#define MAX_CHAR_JEF_CHINA3 0x00E8FFFF
+
+#define MIN_CHAR_CHINA3_JEF 0x00E80000
+#define MAX_CHAR_CHINA3_JEF 0x00E8FFFF
+#endif
#define MIN_CHAR_94 0x00E90940
#define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
#define MIN_CHAR_96x96 0xF4C000
#define MAX_CHAR_96x96 (MIN_CHAR_96x96 + 96 * 96 * 80 - 1)
-#define MIN_CHAR_MOJIKYO 0x60000000
-#define MAX_CHAR_MOJIKYO (MIN_CHAR_MOJIKYO + 94 * 60 * 22)
+/*
#define MIN_CHAR_GT 0x61000000
-#define MAX_CHAR_GT (MIN_CHAR_GT + 66773)
+#define MAX_CHAR_GT (MIN_CHAR_GT + 67547)
+*/
+#define MIN_CHAR_BIG5_CDP 0x62000000
+#define MAX_CHAR_BIG5_CDP 0x6200FFFF
+/*
+#define MIN_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1)
+#define MAX_CHAR_HANZIKU_1 (0x62000000 + 65536 * 1 + 65535)
+#define MIN_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2)
+#define MAX_CHAR_HANZIKU_2 (0x62000000 + 65536 * 2 + 65535)
+#define MIN_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3)
+#define MAX_CHAR_HANZIKU_3 (0x62000000 + 65536 * 3 + 65535)
+#define MIN_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4)
+#define MAX_CHAR_HANZIKU_4 (0x62000000 + 65536 * 4 + 65535)
+#define MIN_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5)
+#define MAX_CHAR_HANZIKU_5 (0x62000000 + 65536 * 5 + 65535)
+#define MIN_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6)
+#define MAX_CHAR_HANZIKU_6 (0x62000000 + 65536 * 6 + 65535)
+#define MIN_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7)
+#define MAX_CHAR_HANZIKU_7 (0x62000000 + 65536 * 7 + 65535)
+#define MIN_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8)
+#define MAX_CHAR_HANZIKU_8 (0x62000000 + 65536 * 8 + 65535)
+#define MIN_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9)
+#define MAX_CHAR_HANZIKU_9 (0x62000000 + 65536 * 9 + 65535)
+#define MIN_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10)
+#define MAX_CHAR_HANZIKU_10 (0x62000000 + 65536 * 10 + 65535)
+#define MIN_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11)
+#define MAX_CHAR_HANZIKU_11 (0x62000000 + 65536 * 11 + 65535)
+#define MIN_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12)
+#define MAX_CHAR_HANZIKU_12 (0x62000000 + 65536 * 12 + 65535)
+*/
Emchar decode_builtin_char (Lisp_Object charset, int code_point);
-INLINE_HEADER int
-DECODE_MOJIKYO_2022 (unsigned char b1, unsigned char b2, unsigned char b3);
-INLINE_HEADER int
-DECODE_MOJIKYO_2022 (unsigned char b1, unsigned char b2, unsigned char b3)
+INLINE_HEADER Lisp_Object
+get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code);
+INLINE_HEADER Lisp_Object
+get_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code)
{
- if (b2 < 16 + 32)
- return 0;
- else if (b2 < 16 + 32 + 30)
- return
- (b1 - 33) * (94 * 60)
- + (b2 - (16 + 32)) * 94
- + (b3 - 33)
- + 1;
- else if (b2 < 18 + 32 + 30)
- return 0;
- else if (b2 < 18 + 32 + 60)
- return
- (b1 - 33) * (94 * 60)
- + (b2 - (18 + 32)) * 94
- + (b3 - 33)
- + 1;
+ int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
+
+ if (VECTORP (table))
+ {
+ int idx = code - byte_offset;
+
+ if (idx < XVECTOR_LENGTH(table))
+ return XVECTOR_DATA(table)[idx];
+ else
+ return Qunbound;
+ }
else
- return 0;
+ return table;
}
-extern Lisp_Object Vcharset_chinese_big5;
-extern Lisp_Object Vcharset_chinese_big5_1;
-extern Lisp_Object Vcharset_chinese_big5_2;
+INLINE_HEADER Lisp_Object
+put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
+ Lisp_Object value);
+INLINE_HEADER Lisp_Object
+put_ccs_octet_table (Lisp_Object table, Lisp_Object ccs, int code,
+ Lisp_Object value)
+{
+ int byte_offset = XCHARSET_BYTE_OFFSET (ccs);
+ int ccs_len = XCHARSET_BYTE_SIZE (ccs);
+
+ if (VECTORP (table))
+ {
+ XVECTOR_DATA(table)[code - byte_offset] = value;
+ return table;
+ }
+ else if (EQ (table, value))
+ return table;
+ else
+ {
+ table = make_vector (ccs_len, table);
+ XVECTOR_DATA(table)[code - byte_offset] = value;
+ return table;
+ }
+}
+
+INLINE_HEADER void
+decoding_table_put_char (Lisp_Object ccs,
+ int code_point, Lisp_Object character);
+INLINE_HEADER void
+decoding_table_put_char (Lisp_Object ccs,
+ int code_point, Lisp_Object character)
+{
+ Lisp_Object table1 = XCHARSET_DECODING_TABLE (ccs);
+ int dim = XCHARSET_DIMENSION (ccs);
+
+ if (dim == 1)
+ XCHARSET_DECODING_TABLE (ccs)
+ = put_ccs_octet_table (table1, ccs, code_point, character);
+ else if (dim == 2)
+ {
+ Lisp_Object table2
+ = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 8));
+
+ table2 = put_ccs_octet_table (table2, ccs,
+ (unsigned char)code_point, character);
+ XCHARSET_DECODING_TABLE (ccs)
+ = put_ccs_octet_table (table1, ccs,
+ (unsigned char)(code_point >> 8), table2);
+ }
+ else if (dim == 3)
+ {
+ Lisp_Object table2
+ = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 16));
+ Lisp_Object table3
+ = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 8));
+
+ table3 = put_ccs_octet_table (table3, ccs,
+ (unsigned char)code_point, character);
+ table2 = put_ccs_octet_table (table2, ccs,
+ (unsigned char)(code_point >> 8), table3);
+ XCHARSET_DECODING_TABLE (ccs)
+ = put_ccs_octet_table (table1, ccs,
+ (unsigned char)(code_point >> 16), table2);
+ }
+ else /* if (dim == 4) */
+ {
+ Lisp_Object table2
+ = get_ccs_octet_table (table1, ccs, (unsigned char)(code_point >> 24));
+ Lisp_Object table3
+ = get_ccs_octet_table (table2, ccs, (unsigned char)(code_point >> 16));
+ Lisp_Object table4
+ = get_ccs_octet_table (table3, ccs, (unsigned char)(code_point >> 8));
+
+ table4 = put_ccs_octet_table (table4, ccs,
+ (unsigned char)code_point, character);
+ table3 = put_ccs_octet_table (table3, ccs,
+ (unsigned char)(code_point >> 8), table4);
+ table2 = put_ccs_octet_table (table2, ccs,
+ (unsigned char)(code_point >> 16), table3);
+ XCHARSET_DECODING_TABLE (ccs)
+ = put_ccs_octet_table (table1, ccs,
+ (unsigned char)(code_point >> 24), table2);
+ }
+}
+
+INLINE_HEADER void
+decoding_table_remove_char (Lisp_Object ccs, int code_point);
+INLINE_HEADER void
+decoding_table_remove_char (Lisp_Object ccs, int code_point)
+{
+ decoding_table_put_char (ccs, code_point, Qunbound);
+}
+
+Emchar decode_defined_char (Lisp_Object charset, int code_point);
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;
+ Emchar char_id = decode_defined_char (charset, code_point);
- while (dim > 0)
- {
- 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 (CHARP (ch))
- return XCHAR (ch);
- else
- decoding_table = ch;
- }
- else
- break;
- }
- if (XCHARSET_DIMENSION (charset) == 1)
+ if (char_id >= 0)
+ return char_id;
+ else if (XCHARSET_DIMENSION (charset) == 1)
return decode_builtin_char (charset, code_point);
else if (EQ (charset, Vcharset_chinese_big5_1))
{
b2 += b2 < 0x3F ? 0x40 : 0x62;
return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
}
- else if (EQ (charset, Vcharset_mojikyo_2022_1))
- {
- int m =
- DECODE_MOJIKYO_2022
- ((unsigned char)(code_point >> 16),
- (unsigned char)(code_point >> 8),
- (unsigned char) code_point);
-
- if (m > 0)
- return DECODE_CHAR (Vcharset_mojikyo, m);
- else
- return ' ';
- }
- else
- {
- int plane = LEADING_BYTE_MOJIKYO_PJ_1 - XCHARSET_ID (charset);
-
- if ( (0 <= plane) && (plane < 21) )
- {
- int m = DECODE_MOJIKYO_2022 (plane + 33,
- code_point >> 8,
- (unsigned char)code_point);
- if (m > 0)
- return DECODE_CHAR (Vcharset_mojikyo, m);
- else
- return ' ';
- }
- else
- return decode_builtin_char (charset, code_point);
- }
+ return decode_builtin_char (charset, code_point);
}
/* Return a character whose charset is CHARSET and position-codes
extern Lisp_Object Vcharacter_attribute_table;
int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
+int charset_code_point (Lisp_Object charset, Emchar ch, int defined_only);
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_TABLEP (encoding_table)
- && INTP (ret = get_char_id_table (XCHAR_TABLE(encoding_table),
- ch)) )
- return XINT (ret);
- else
- return range_charset_code_point (charset, ch);
-}
-
extern Lisp_Object Vdefault_coded_charset_priority_list;
EXFUN (Ffind_charset, 1);
*charset = Ffind_charset (Fcar (charsets));
if (!NILP (*charset))
{
- Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (*charset);
- Lisp_Object ret;
-
- if ( CHAR_TABLEP (encoding_table)
- && INTP (ret
- = get_char_id_table (XCHAR_TABLE(encoding_table),
- ch)) )
- return XINT (ret);
- else
- {
- int code_point = range_charset_code_point (*charset, ch);
-
- if (code_point >= 0)
- return code_point;
- }
+ int code_point = charset_code_point (*charset, ch, 0);
+
+ if (code_point >= 0)
+ return code_point;
}
charsets = Fcdr (charsets);
}
Charc cc;
cc.code_point = encode_char_1 (ch, &cc.charset);
- if (EQ (cc.charset, Vcharset_mojikyo))
- {
- int plane, byte1, byte2;
-
- cc.code_point--;
- plane = cc.code_point / (94 * 60);
- byte1 = (cc.code_point % (94 * 60)) / 94;
- if (byte1 < 30)
- byte1 += 16 + 32;
- else
- byte1 += 18 + 32;
- byte2 = cc.code_point % 94 + 33;
- cc.charset
- = CHARSET_BY_LEADING_BYTE (LEADING_BYTE_MOJIKYO_PJ_1 - plane);
- cc.code_point = (byte1 << 8) | byte2;
- }
return cc;
}
-\f
-/************************************************************************/
-/* Exported functions */
-/************************************************************************/
-
-EXFUN (Fget_charset, 1);
-
-extern Lisp_Object Qucs;
-
-extern Lisp_Object Vcharset_japanese_jisx0208;
-extern Lisp_Object Vcharset_japanese_jisx0208_1990;
-extern Lisp_Object Vcharset_japanese_jisx0212;
-
-Lisp_Object put_char_ccs_code_point (Lisp_Object character,
- Lisp_Object ccs, Lisp_Object value);
-Lisp_Object remove_char_ccs (Lisp_Object character, Lisp_Object ccs);
-
#endif /* INCLUDED_char_ucs_h_ */
projects / chise / xemacs-chise.git / blobdiff