/* Header for UCS-4 character representation.
- Copyright (C) 1999,2000 MORIOKA Tomohiko
+ Copyright (C) 1999,2000,2001 MORIOKA Tomohiko
This file is part of XEmacs.
#define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
\f
+/************************************************************************/
+/* Char-ID Tables */
+/************************************************************************/
+
struct Lisp_Uint8_Byte_Table
{
struct lcrecord_header header;
char table entries should never escape to Lisp */
-Lisp_Object get_char_id_table (Emchar ch, Lisp_Object table);
+Lisp_Object get_char_id_table (Lisp_Char_ID_Table* cit, Emchar ch);
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 -0x60
+#define MIN_LEADING_BYTE -0x70
#define CHARSET_ID_OFFSET 0x00
/* ISO/IEC 10646 */
/* ISO/IEC 10646 BMP */
#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3)
-/* VISCII 1.1 */
-#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 4)
+/* ISO/IEC 10646 for CNS */
+#define LEADING_BYTE_UCS_CNS (CHARSET_ID_OFFSET - 5)
-/* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
-#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 5)
+/* ISO/IEC 10646 for JIS */
+#define LEADING_BYTE_UCS_JIS (CHARSET_ID_OFFSET - 6)
-/* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
-#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 6)
+/* 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)
+
+/* Chinese GB 12345-1990 */
+#define LEADING_BYTE_CHINESE_GB12345 (CHARSET_ID_OFFSET - 11)
+
+#define LEADING_BYTE_CHINESE_BIG5 (CHARSET_ID_OFFSET - 20)
/* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
-#define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 7)
+#define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 21)
/* Big5 Level 2 2/4 2/{(8),9,10,11} 4/0 '1' */
-#define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 8)
+#define LEADING_BYTE_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 22)
-#define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 9)
+#define LEADING_BYTE_CHINESE_BIG5_CDP (CHARSET_ID_OFFSET - 23)
-#define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 10)
-#define LEADING_BYTE_DAIKANWA_EKANJI (CHARSET_ID_OFFSET - 11)
-#define LEADING_BYTE_MOJIKYO (CHARSET_ID_OFFSET - 12)
+/* VISCII 1.1 */
+#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 24)
-/* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
-#define LEADING_BYTE_JAPANESE_JISX0208_1990 (CHARSET_ID_OFFSET - 13)
+/* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
+#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 25)
+
+/* 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 - 14)
-#define LEADING_BYTE_MOJIKYO_PJ_2 (CHARSET_ID_OFFSET - 15)
-#define LEADING_BYTE_MOJIKYO_PJ_3 (CHARSET_ID_OFFSET - 16)
-#define LEADING_BYTE_MOJIKYO_PJ_4 (CHARSET_ID_OFFSET - 17)
-#define LEADING_BYTE_MOJIKYO_PJ_5 (CHARSET_ID_OFFSET - 18)
-#define LEADING_BYTE_MOJIKYO_PJ_6 (CHARSET_ID_OFFSET - 19)
-#define LEADING_BYTE_MOJIKYO_PJ_7 (CHARSET_ID_OFFSET - 20)
-#define LEADING_BYTE_MOJIKYO_PJ_8 (CHARSET_ID_OFFSET - 21)
-#define LEADING_BYTE_MOJIKYO_PJ_9 (CHARSET_ID_OFFSET - 22)
-#define LEADING_BYTE_MOJIKYO_PJ_10 (CHARSET_ID_OFFSET - 23)
-#define LEADING_BYTE_MOJIKYO_PJ_11 (CHARSET_ID_OFFSET - 24)
-#define LEADING_BYTE_MOJIKYO_PJ_12 (CHARSET_ID_OFFSET - 25)
-#define LEADING_BYTE_MOJIKYO_PJ_13 (CHARSET_ID_OFFSET - 26)
-#define LEADING_BYTE_MOJIKYO_PJ_14 (CHARSET_ID_OFFSET - 27)
-#define LEADING_BYTE_MOJIKYO_PJ_15 (CHARSET_ID_OFFSET - 28)
-#define LEADING_BYTE_MOJIKYO_PJ_16 (CHARSET_ID_OFFSET - 29)
-#define LEADING_BYTE_MOJIKYO_PJ_17 (CHARSET_ID_OFFSET - 30)
-#define LEADING_BYTE_MOJIKYO_PJ_18 (CHARSET_ID_OFFSET - 31)
-#define LEADING_BYTE_MOJIKYO_PJ_19 (CHARSET_ID_OFFSET - 32)
-#define LEADING_BYTE_MOJIKYO_PJ_20 (CHARSET_ID_OFFSET - 33)
-#define LEADING_BYTE_MOJIKYO_PJ_21 (CHARSET_ID_OFFSET - 34)
+#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 MIN_LEADING_BYTE_PRIVATE MIN_LEADING_BYTE
-#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 35)
+#define MAX_LEADING_BYTE_PRIVATE (CHARSET_ID_OFFSET - 72)
/* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */
#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_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
#endif
-#define CHARSET_BY_ATTRIBUTES(type, final, dir) \
- (chlook->charset_by_attributes[type][final])
+INLINE_HEADER Lisp_Object
+CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir);
+INLINE_HEADER Lisp_Object
+CHARSET_BY_ATTRIBUTES (int chars, int dimension, int final, int dir)
+{
+ int type;
+
+ if (chars == 94)
+ type = 0;
+ else if (chars == 96)
+ type = 1;
+ else
+ return Qnil;
+ type += dimension == 1 ? 0 : 2;
+ return chlook->charset_by_attributes[type][final];
+}
\f
/************************************************************************/
#define MAX_CHAR_BASIC_LATIN 0x007F
/*
-#define MIN_CHAR_GREEK 0x0370
-#define MAX_CHAR_GREEK 0x03CF
-
-#define MIN_CHAR_CYRILLIC 0x0400
-#define MAX_CHAR_CYRILLIC 0x045F
-*/
-
#define MIN_CHAR_HEBREW 0x0590
#define MAX_CHAR_HEBREW 0x05EF
+*/
#define MIN_CHAR_THAI 0x0E00
#define MAX_CHAR_THAI 0x0E5F
#define MAX_CHAR_BMP 0x00FFFF
-#define MIN_CHAR_MOJIKYO 0xE00000
-#define MIN_CHAR_DAIKANWA MIN_CHAR_MOJIKYO
-#define MAX_CHAR_DAIKANWA (MIN_CHAR_MOJIKYO + 50100) /* 0xE0FFFF */
-/* #define MAX_CHAR_MOJIKYO 0xE9093F */
-#define MAX_CHAR_MOJIKYO (MIN_CHAR_MOJIKYO + 94 * 60 * 22)
+#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_94 0xE90940
#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)
-Emchar make_builtin_char (Lisp_Object charset, int c1, int c2);
+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
break;
}
if (XCHARSET_DIMENSION (charset) == 1)
- return make_builtin_char (charset, code_point, 0);
+ return decode_builtin_char (charset, code_point);
+ else if (EQ (charset, Vcharset_chinese_big5_1))
+ {
+ unsigned int I
+ = ((code_point >> 8) - 33) * (0xFF - 0xA1)
+ + ((code_point & 0xFF) - 33);
+ unsigned char b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
+ unsigned char b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
+
+ b2 += b2 < 0x3F ? 0x40 : 0x62;
+ return DECODE_CHAR (Vcharset_chinese_big5, (b1 << 8) | b2);
+ }
+ else if (EQ (charset, Vcharset_chinese_big5_2))
+ {
+ unsigned int I
+ = ((code_point >> 8) - 33) * (0xFF - 0xA1)
+ + ((code_point & 0xFF) - 33);
+ unsigned char b1, b2;
+
+ I += (0xFF - 0xA1 + 0x7F - 0x40) * (0xC9 - 0xA1);
+ b1 = I / (0xFF - 0xA1 + 0x7F - 0x40) + 0xA1;
+ b2 = I % (0xFF - 0xA1 + 0x7F - 0x40);
+ 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 c1 = code_point >> 8;
- int c2 = code_point & 255;
-
- if (c1 < 16 + 32)
- return ' ';
- else if (c1 < 16 + 32 + 30)
- return DECODE_CHAR (Vcharset_mojikyo,
- plane * (94 * 60)
- + (c1 - (16 + 32)) * 94
- + (c2 - 33)
- + 1);
- else if (c1 < 18 + 32 + 30)
- return ' ';
- else if (c1 < 18 + 32 + 60)
- return DECODE_CHAR (Vcharset_mojikyo,
- plane * (94 * 60)
- + (c1 - (18 + 32)) * 94
- + (c2 - 33)
- + 1);
+ 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 make_builtin_char (charset, code_point >> 8, code_point & 255);
+ return decode_builtin_char (charset, code_point);
}
}
Lisp_Object ret;
if ( CHAR_ID_TABLE_P (encoding_table)
- && INTP (ret = get_char_id_table (ch, encoding_table)) )
+ && INTP (ret = get_char_id_table (XCHAR_ID_TABLE(encoding_table),
+ ch)) )
return XINT (ret);
else
return range_charset_code_point (charset, ch);
Lisp_Object ret;
if ( CHAR_ID_TABLE_P (encoding_table)
- && INTP (ret = get_char_id_table (ch, encoding_table)) )
+ && INTP (ret
+ = get_char_id_table (XCHAR_ID_TABLE(encoding_table),
+ ch)) )
return XINT (ret);
else
{
- int code_point;
+ int code_point = range_charset_code_point (*charset, ch);
- if ((code_point
- = range_charset_code_point (*charset, ch)) >= 0)
+ if (code_point >= 0)
return code_point;
}
}
EXFUN (Fget_charset, 1);
-extern Lisp_Object Vcharset_chinese_big5_1;
-extern Lisp_Object Vcharset_chinese_big5_2;
+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