#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;
extern Lisp_Object Vcharset_latin_jisx0201;
\f
typedef short Charset_ID;
-#define MIN_LEADING_BYTE -0x100
+#define MIN_LEADING_BYTE -0x200
#define CHARSET_ID_OFFSET 0x00
/* ISO/IEC 10646 */
/* ISO/IEC 10646 BMP */
#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3)
+/* ISO/IEC 10646 SMP */
+#define LEADING_BYTE_UCS_SMP (CHARSET_ID_OFFSET - 4)
+
+/* ISO/IEC 10646 SIP */
+#define LEADING_BYTE_UCS_SIP (CHARSET_ID_OFFSET - 5)
+
/* ISO/IEC 10646 for CNS */
-#define LEADING_BYTE_UCS_CNS (CHARSET_ID_OFFSET - 5)
+#define LEADING_BYTE_UCS_CNS (CHARSET_ID_OFFSET - 6)
/* ISO/IEC 10646 for JIS */
-#define LEADING_BYTE_UCS_JIS (CHARSET_ID_OFFSET - 6)
+#define LEADING_BYTE_UCS_JIS (CHARSET_ID_OFFSET - 7)
+
+/* ISO/IEC 10646 for KS */
+#define LEADING_BYTE_UCS_KS (CHARSET_ID_OFFSET - 8)
/* ISO/IEC 10646 for Big5 */
#define LEADING_BYTE_UCS_BIG5 (CHARSET_ID_OFFSET - 9)
/* 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)
-
/* VISCII 1.1 */
#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 24)
#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_CHINA3_JEF (CHARSET_ID_OFFSET - 72)
-#define LEADING_BYTE_CBETA (CHARSET_ID_OFFSET - 73)
+#define LEADING_BYTE_DAIKANWA_0 (CHARSET_ID_OFFSET - 28)
+#define LEADING_BYTE_DAIKANWA_1 (CHARSET_ID_OFFSET - 29)
+#define LEADING_BYTE_DAIKANWA_2 (CHARSET_ID_OFFSET - 30)
+#define LEADING_BYTE_DAIKANWA_3 (CHARSET_ID_OFFSET - 31)
+
+#define LEADING_BYTE_GT (CHARSET_ID_OFFSET - 40)
+#define LEADING_BYTE_GT_PJ_1 (CHARSET_ID_OFFSET - 41)
+#define LEADING_BYTE_GT_PJ_2 (CHARSET_ID_OFFSET - 42)
+#define LEADING_BYTE_GT_PJ_3 (CHARSET_ID_OFFSET - 43)
+#define LEADING_BYTE_GT_PJ_4 (CHARSET_ID_OFFSET - 44)
+#define LEADING_BYTE_GT_PJ_5 (CHARSET_ID_OFFSET - 45)
+#define LEADING_BYTE_GT_PJ_6 (CHARSET_ID_OFFSET - 46)
+#define LEADING_BYTE_GT_PJ_7 (CHARSET_ID_OFFSET - 47)
+#define LEADING_BYTE_GT_PJ_8 (CHARSET_ID_OFFSET - 48)
+#define LEADING_BYTE_GT_PJ_9 (CHARSET_ID_OFFSET - 49)
+#define LEADING_BYTE_GT_PJ_10 (CHARSET_ID_OFFSET - 50)
+#define LEADING_BYTE_GT_PJ_11 (CHARSET_ID_OFFSET - 51)
+
+#define LEADING_BYTE_CHINA3_JEF (CHARSET_ID_OFFSET - 82)
+#define LEADING_BYTE_CBETA (CHARSET_ID_OFFSET - 83)
+#define LEADING_BYTE_CHINESE_BIG5_CDP (CHARSET_ID_OFFSET - 84)
+#define LEADING_BYTE_HANZIKU_1 (CHARSET_ID_OFFSET - 85)
+#define LEADING_BYTE_HANZIKU_2 (CHARSET_ID_OFFSET - 86)
+#define LEADING_BYTE_HANZIKU_3 (CHARSET_ID_OFFSET - 87)
+#define LEADING_BYTE_HANZIKU_4 (CHARSET_ID_OFFSET - 88)
+#define LEADING_BYTE_HANZIKU_5 (CHARSET_ID_OFFSET - 89)
+#define LEADING_BYTE_HANZIKU_6 (CHARSET_ID_OFFSET - 90)
+#define LEADING_BYTE_HANZIKU_7 (CHARSET_ID_OFFSET - 91)
+#define LEADING_BYTE_HANZIKU_8 (CHARSET_ID_OFFSET - 92)
+#define LEADING_BYTE_HANZIKU_9 (CHARSET_ID_OFFSET - 93)
+#define LEADING_BYTE_HANZIKU_10 (CHARSET_ID_OFFSET - 94)
+#define LEADING_BYTE_HANZIKU_11 (CHARSET_ID_OFFSET - 95)
+#define LEADING_BYTE_HANZIKU_12 (CHARSET_ID_OFFSET - 96)
#define MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE
-#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 74)
+#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 97)
/* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */
/* 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 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 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_94x60 1
+#define CONVERSION_94x94x60 2
#define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
#define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (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
+
#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_CHINA3_JEF 0x00E80000
#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 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)
-{
- 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;
- else
- return 0;
-}
-
extern Lisp_Object Vcharset_chinese_big5;
extern Lisp_Object Vcharset_chinese_big5_1;
extern Lisp_Object Vcharset_chinese_big5_2;
-INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
INLINE_HEADER Emchar
-DECODE_CHAR (Lisp_Object charset, int code_point)
+DECODE_DEFINED_CHAR (Lisp_Object charset, int code_point);
+INLINE_HEADER Emchar
+DECODE_DEFINED_CHAR (Lisp_Object charset, int code_point)
{
int dim = XCHARSET_DIMENSION (charset);
Lisp_Object decoding_table = XCHARSET_DECODING_TABLE (charset);
else
break;
}
- if (XCHARSET_DIMENSION (charset) == 1)
+ return -1;
+}
+
+INLINE_HEADER Emchar DECODE_CHAR (Lisp_Object charset, int code_point);
+INLINE_HEADER Emchar
+DECODE_CHAR (Lisp_Object charset, int code_point)
+{
+ Emchar char_id = DECODE_DEFINED_CHAR (charset, code_point);
+
+ 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 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);
+ int code_point = charset_code_point (*charset, ch);
- if (code_point >= 0)
- return code_point;
- }
+ 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;
}
projects / chise / xemacs-chise.git / blobdiff