/* Header for UCS-4 character representation.
- Copyright (C) 1999 Electrotechnical Laboratory, JAPAN.
- Licensed to the Free Software Foundation.
+ Copyright (C) 1999,2000 MORIOKA Tomohiko
This file is part of XEmacs.
the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
-/* Rewritten by MORIOKA Tomohiko <tomo@m17n.org>. */
-
-#ifndef _XEMACS_CHAR_UCS_H
-#define _XEMACS_CHAR_UCS_H
+#ifndef INCLUDED_char_ucs_h_
+#define INCLUDED_char_ucs_h_
#define valid_char_p(ch) 1
#define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
\f
-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)
+struct Lisp_Uint8_Byte_Table
+{
+ struct lcrecord_header header;
+
+ unsigned char property[256];
+};
+typedef struct Lisp_Uint8_Byte_Table Lisp_Uint8_Byte_Table;
+
+DECLARE_LRECORD (uint8_byte_table, Lisp_Uint8_Byte_Table);
+#define XUINT8_BYTE_TABLE(x) \
+ XRECORD (x, uint8_byte_table, Lisp_Uint8_Byte_Table)
+#define XSETUINT8_BYTE_TABLE(x, p) XSETRECORD (x, p, uint8_byte_table)
+#define UINT8_BYTE_TABLE_P(x) RECORDP (x, uint8_byte_table)
+#define GC_UINT8_BYTE_TABLE_P(x) GC_RECORDP (x, uint8_byte_table)
+/* #define CHECK_UINT8_BYTE_TABLE(x) CHECK_RECORD (x, uint8_byte_table)
+ char table entries should never escape to Lisp */
+
+
+struct Lisp_Uint16_Byte_Table
+{
+ struct lcrecord_header header;
+
+ unsigned short property[256];
+};
+typedef struct Lisp_Uint16_Byte_Table Lisp_Uint16_Byte_Table;
+
+DECLARE_LRECORD (uint16_byte_table, Lisp_Uint16_Byte_Table);
+#define XUINT16_BYTE_TABLE(x) \
+ XRECORD (x, uint16_byte_table, Lisp_Uint16_Byte_Table)
+#define XSETUINT16_BYTE_TABLE(x, p) XSETRECORD (x, p, uint16_byte_table)
+#define UINT16_BYTE_TABLE_P(x) RECORDP (x, uint16_byte_table)
+#define GC_UINT16_BYTE_TABLE_P(x) GC_RECORDP (x, uint16_byte_table)
+/* #define CHECK_UINT16_BYTE_TABLE(x) CHECK_RECORD (x, uint16_byte_table)
char table entries should never escape to Lisp */
-struct Lisp_Char_Byte_Table
+
+struct Lisp_Byte_Table
{
struct lcrecord_header header;
Lisp_Object property[256];
};
+typedef struct Lisp_Byte_Table Lisp_Byte_Table;
+
+DECLARE_LRECORD (byte_table, Lisp_Byte_Table);
+#define XBYTE_TABLE(x) XRECORD (x, byte_table, Lisp_Byte_Table)
+#define XSETBYTE_TABLE(x, p) XSETRECORD (x, p, byte_table)
+#define BYTE_TABLE_P(x) RECORDP (x, byte_table)
+#define GC_BYTE_TABLE_P(x) GC_RECORDP (x, byte_table)
+/* #define CHECK_BYTE_TABLE(x) CHECK_RECORD (x, byte_table)
+ char table entries should never escape to Lisp */
+
+
+struct Lisp_Char_ID_Table
+{
+ struct lcrecord_header header;
+
+ Lisp_Object table;
+};
+typedef struct Lisp_Char_ID_Table Lisp_Char_ID_Table;
+
+DECLARE_LRECORD (char_id_table, Lisp_Char_ID_Table);
+#define XCHAR_ID_TABLE(x) XRECORD (x, char_id_table, Lisp_Char_ID_Table)
+#define XSETCHAR_ID_TABLE(x, p) XSETRECORD (x, p, char_id_table)
+#define CHAR_ID_TABLE_P(x) RECORDP (x, char_id_table)
+#define GC_CHAR_ID_TABLE_P(x) GC_RECORDP (x, char_id_table)
+/* #define CHECK_CHAR_ID_TABLE(x) CHECK_RECORD (x, char_id_table)
+ char table entries should never escape to Lisp */
+
-Lisp_Object get_char_code_table (Emchar ch, Lisp_Object table);
+Lisp_Object get_char_id_table (Emchar ch, Lisp_Object table);
-extern Lisp_Object Vcharset_ucs_bmp;
+extern Lisp_Object Vcharset_mojikyo;
+extern Lisp_Object Vcharset_mojikyo_2022_1;
extern Lisp_Object Vcharset_latin_jisx0201;
-extern Lisp_Object Vcharset_latin_iso8859_2;
-extern Lisp_Object Vcharset_latin_iso8859_3;
-extern Lisp_Object Vcharset_latin_iso8859_4;
-extern Lisp_Object Vcharset_latin_iso8859_9;
-extern Lisp_Object Vcharset_latin_viscii_lower;
-extern Lisp_Object Vcharset_latin_viscii_upper;
\f
/************************************************************************/
/* Definition of leading bytes */
/************************************************************************/
-typedef int Charset_ID;
+typedef short Charset_ID;
-#define MIN_LEADING_BYTE -0x40
+#define MIN_LEADING_BYTE -0x60
#define CHARSET_ID_OFFSET 0x00
+/* ISO/IEC 10646 */
+#define LEADING_BYTE_UCS (CHARSET_ID_OFFSET - 1)
+
/* represent normal 80-9F */
-#define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 1)
+#define LEADING_BYTE_CONTROL_1 (CHARSET_ID_OFFSET - 2)
/* ISO/IEC 10646 BMP */
-#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 2)
+#define LEADING_BYTE_UCS_BMP (CHARSET_ID_OFFSET - 3)
+
+/* ISO/IEC 10646 for CNS */
+#define LEADING_BYTE_UCS_CNS (CHARSET_ID_OFFSET - 5)
+
+/* Japanese JIS X0208-1990 2/4 2/{(8),9,10,11} 4/2 (B) */
+#define LEADING_BYTE_JAPANESE_JISX0208_1990 (CHARSET_ID_OFFSET - 6)
/* VISCII 1.1 */
-#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 3)
+#define LEADING_BYTE_LATIN_VISCII (CHARSET_ID_OFFSET - 7)
/* MULE VISCII-LOWER (CHARSET_ID_OFFSET_96 + '1') */
-#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 4)
+#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET - 8)
/* MULE VISCII-UPPER (CHARSET_ID_OFFSET_96 + '2') */
-#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 5)
+#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET - 9)
+
+#define LEADING_BYTE_CHINESE_BIG5 (CHARSET_ID_OFFSET - 10)
/* Big5 Level 1 2/4 2/{(8),9,10,11} 4/0 '0' */
-#define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 6)
+#define LEADING_BYTE_CHINESE_BIG5_1 (CHARSET_ID_OFFSET - 11)
/* 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_CHINESE_BIG5_2 (CHARSET_ID_OFFSET - 12)
+
+#define LEADING_BYTE_ETHIOPIC_UCS (CHARSET_ID_OFFSET - 13)
+
+#define LEADING_BYTE_DAIKANWA (CHARSET_ID_OFFSET - 14)
+#define LEADING_BYTE_DAIKANWA_EKANJI (CHARSET_ID_OFFSET - 15)
+#define LEADING_BYTE_MOJIKYO (CHARSET_ID_OFFSET - 16)
+#define LEADING_BYTE_MOJIKYO_2022_1 (CHARSET_ID_OFFSET - 17)
+#define LEADING_BYTE_MOJIKYO_2022_2 (CHARSET_ID_OFFSET - 18)
+
+/* Konjaku-Mojikyo font (for pseudo-JIS X 0208 encoding) */
+#define LEADING_BYTE_MOJIKYO_PJ_1 (CHARSET_ID_OFFSET - 19)
+#define LEADING_BYTE_MOJIKYO_PJ_2 (CHARSET_ID_OFFSET - 20)
+#define LEADING_BYTE_MOJIKYO_PJ_3 (CHARSET_ID_OFFSET - 21)
+#define LEADING_BYTE_MOJIKYO_PJ_4 (CHARSET_ID_OFFSET - 22)
+#define LEADING_BYTE_MOJIKYO_PJ_5 (CHARSET_ID_OFFSET - 23)
+#define LEADING_BYTE_MOJIKYO_PJ_6 (CHARSET_ID_OFFSET - 24)
+#define LEADING_BYTE_MOJIKYO_PJ_7 (CHARSET_ID_OFFSET - 25)
+#define LEADING_BYTE_MOJIKYO_PJ_8 (CHARSET_ID_OFFSET - 26)
+#define LEADING_BYTE_MOJIKYO_PJ_9 (CHARSET_ID_OFFSET - 27)
+#define LEADING_BYTE_MOJIKYO_PJ_10 (CHARSET_ID_OFFSET - 28)
+#define LEADING_BYTE_MOJIKYO_PJ_11 (CHARSET_ID_OFFSET - 29)
+#define LEADING_BYTE_MOJIKYO_PJ_12 (CHARSET_ID_OFFSET - 30)
+#define LEADING_BYTE_MOJIKYO_PJ_13 (CHARSET_ID_OFFSET - 31)
+#define LEADING_BYTE_MOJIKYO_PJ_14 (CHARSET_ID_OFFSET - 32)
+#define LEADING_BYTE_MOJIKYO_PJ_15 (CHARSET_ID_OFFSET - 33)
+#define LEADING_BYTE_MOJIKYO_PJ_16 (CHARSET_ID_OFFSET - 34)
+#define LEADING_BYTE_MOJIKYO_PJ_17 (CHARSET_ID_OFFSET - 35)
+#define LEADING_BYTE_MOJIKYO_PJ_18 (CHARSET_ID_OFFSET - 36)
+#define LEADING_BYTE_MOJIKYO_PJ_19 (CHARSET_ID_OFFSET - 37)
+#define LEADING_BYTE_MOJIKYO_PJ_20 (CHARSET_ID_OFFSET - 38)
+#define LEADING_BYTE_MOJIKYO_PJ_21 (CHARSET_ID_OFFSET - 39)
#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 - 40)
/* #define CHARSET_ID_OFFSET_94 (CHARSET_ID_OFFSET - '0') */
/* TIS620-2533 */
#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 CHARSET_ID_OFFSET_94x94 (CHARSET_ID_OFFSET_96 + 80) */
+/* #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) */
int id;
Lisp_Object name;
- Lisp_Object doc_string, registry, short_name, long_name;
+ Lisp_Object doc_string;
+ Lisp_Object registry;
+ Lisp_Object short_name;
+ Lisp_Object long_name;
Lisp_Object reverse_direction_charset;
/* Direction of this character set */
unsigned int direction;
- /* Type of this character set (94, 96, 94x94, 96x96) */
- unsigned int type;
-
- /* Number of bytes used in encoding of this character set (1 or 2) */
- unsigned int dimension;
+ /* Number of bytes used in encoding of this character set (1 .. 4) */
+ unsigned short dimension;
- /* Number of chars in each dimension (usually 94 or 96) */
- unsigned int chars;
+ /* Number of chars in each dimension (94, 96, 128, 256) */
+ unsigned short chars;
/* Which half of font to be used to display this character set */
unsigned int graphic;
- /* Byte->character mapping table */
+ /* Code-point->character mapping table */
Lisp_Object decoding_table;
- /* Character->byte mapping table */
+ /* Character->code-point mapping table */
Lisp_Object encoding_table;
/* Range of character code */
/* Offset for each byte */
Emchar byte_offset;
};
+typedef struct Lisp_Charset Lisp_Charset;
-DECLARE_LRECORD (charset, struct Lisp_Charset);
-#define XCHARSET(x) XRECORD (x, charset, struct Lisp_Charset)
+DECLARE_LRECORD (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_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
#define CHARSET_LONG_NAME(cs) ((cs)->long_name)
#define CHARSET_COLUMNS(cs) ((cs)->columns)
#define CHARSET_GRAPHIC(cs) ((cs)->graphic)
-#define CHARSET_TYPE(cs) ((cs)->type)
#define CHARSET_DIRECTION(cs) ((cs)->direction)
#define CHARSET_FINAL(cs) ((cs)->final)
#define CHARSET_DOC_STRING(cs) ((cs)->doc_string)
#define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
#define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
#define XCHARSET_GRAPHIC(cs) CHARSET_GRAPHIC (XCHARSET (cs))
-#define XCHARSET_TYPE(cs) CHARSET_TYPE (XCHARSET (cs))
#define XCHARSET_DIRECTION(cs) CHARSET_DIRECTION (XCHARSET (cs))
#define XCHARSET_FINAL(cs) CHARSET_FINAL (XCHARSET (cs))
#define XCHARSET_DOC_STRING(cs) CHARSET_DOC_STRING (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];
+ Charset_ID next_allocated_leading_byte;
+};
+
+extern struct charset_lookup *chlook;
#ifdef ERROR_CHECK_TYPECHECK
/* int not Bufbyte even though that is the actual type of a leading byte.
This way, out-ot-range values will get caught rather than automatically
truncated. */
-INLINE Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
-INLINE Lisp_Object
+INLINE_HEADER Lisp_Object CHARSET_BY_LEADING_BYTE (Charset_ID lb);
+INLINE_HEADER Lisp_Object
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])
+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 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 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_MOJIKYO 0x60000000
+/* #define MAX_CHAR_MOJIKYO 0xE9093F */
+#define MAX_CHAR_MOJIKYO (MIN_CHAR_MOJIKYO + 94 * 60 * 22)
#define MIN_CHAR_94 0xE90940
#define MAX_CHAR_94 (MIN_CHAR_94 + 94 * 80 - 1)
#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)
-/* Return a character whose charset is CHARSET and position-codes
- are C1 and C2. TYPE9N character ignores C2. */
+Emchar make_builtin_char (Lisp_Object charset, int c1, int c2);
-INLINE Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
-INLINE Emchar
-MAKE_CHAR (Lisp_Object charset, int c1, int c2)
+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;
+}
+
+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;
- if (!EQ (decoding_table, Qnil)
- && (0 <= (idx = c1 - XCHARSET_BYTE_OFFSET (charset)))
- && (idx < XVECTOR_LENGTH (decoding_table))
- && !EQ (ch = XVECTOR_DATA(decoding_table)[idx], Qnil))
+ while (dim > 0)
{
- if (VECTORP (ch))
+ 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 ((0 <= (idx = c2 - XCHARSET_BYTE_OFFSET (charset)))
- && (idx < XVECTOR_LENGTH (ch))
- && !EQ (ch = XVECTOR_DATA(ch)[idx], Qnil))
+ if (CHARP (ch))
return XCHAR (ch);
+ else
+ decoding_table = ch;
}
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))
- {
- Emchar code
- = (XCHARSET_DIMENSION (charset) == 1
- ?
- c1 - XCHARSET_BYTE_OFFSET (charset)
- :
- (c1 - XCHARSET_BYTE_OFFSET (charset)) * XCHARSET_CHARS (charset)
- + c2 - XCHARSET_BYTE_OFFSET (charset))
- - XCHARSET_CODE_OFFSET (charset) + XCHARSET_UCS_MIN (charset);
- if ((code < XCHARSET_UCS_MIN (charset))
- || (XCHARSET_UCS_MAX (charset) < code))
- signal_simple_error ("Arguments makes invalid character",
- make_char (code));
- return code;
+ break;
}
- else if (XCHARSET_DIMENSION (charset) == 1)
+ if (XCHARSET_DIMENSION (charset) == 1)
+ return make_builtin_char (charset, code_point, 0);
+ else if (EQ (charset, Vcharset_mojikyo_2022_1))
{
- switch (XCHARSET_CHARS (charset))
- {
- case 94:
- return MIN_CHAR_94
- + (XCHARSET_FINAL (charset) - '0') * 94 + (c1 - 33);
- case 96:
- return MIN_CHAR_96
- + (XCHARSET_FINAL (charset) - '0') * 96 + (c1 - 32);
- default:
- abort ();
- }
+ 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
{
- switch (XCHARSET_CHARS (charset))
+ int plane = LEADING_BYTE_MOJIKYO_PJ_1 - XCHARSET_ID (charset);
+
+ if ( (0 <= plane) && (plane <= 21) )
{
- case 94:
- return MIN_CHAR_94x94
- + (XCHARSET_FINAL (charset) - '0') * 94 * 94
- + (c1 - 33) * 94 + (c2 - 33);
- case 96:
- return MIN_CHAR_96x96
- + (XCHARSET_FINAL (charset) - '0') * 96 * 96
- + (c1 - 32) * 96 + (c2 - 32);
- default:
- abort ();
+ 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 a character whose charset is CHARSET and position-codes
+ are C1 and C2. TYPE9N character ignores C2. */
+
+INLINE_HEADER Emchar MAKE_CHAR (Lisp_Object charset, int c1, int c2);
+INLINE_HEADER Emchar
+MAKE_CHAR (Lisp_Object charset, int c1, int c2)
+{
+ if (XCHARSET_DIMENSION (charset) == 1)
+ return DECODE_CHAR (charset, c1);
+ else
+ return DECODE_CHAR (charset, (c1 << 8) | c2);
+}
+
extern Lisp_Object Vcharacter_attribute_table;
-unsigned char charset_get_byte1 (Lisp_Object charset, Emchar ch);
-unsigned char charset_get_byte2 (Lisp_Object charset, Emchar ch);
+int encode_builtin_char_1 (Emchar c, Lisp_Object* charset);
+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_ID_TABLE_P (encoding_table)
+ && INTP (ret = get_char_id_table (ch, encoding_table)) )
+ return XINT (ret);
+ else
+ return range_charset_code_point (charset, ch);
+}
extern Lisp_Object Vdefault_coded_charset_priority_list;
EXFUN (Ffind_charset, 1);
-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)
+INLINE_HEADER int encode_char_1 (Emchar ch, Lisp_Object* charset);
+INLINE_HEADER int
+encode_char_1 (Emchar ch, Lisp_Object* charset)
{
- Lisp_Object cdef = get_char_code_table (c, Vcharacter_attribute_table);
-
- if (!EQ (cdef, Qnil))
- {
- Lisp_Object charsets = Vdefault_coded_charset_priority_list;
- Lisp_Object field;
+ Lisp_Object charsets = Vdefault_coded_charset_priority_list;
- while (!EQ (charsets, Qnil))
- {
- *charset = Ffind_charset (Fcar (charsets));
- if (!EQ (*charset, Qnil))
- {
- if (!EQ (field = Fcdr (Fassq (*charset, cdef)), Qnil))
- {
- Lisp_Object ret = Fcar (field);
- if (INTP (ret))
- {
- *c1 = XINT (ret);
- if (INTP (ret = Fcar (Fcdr (field))))
- *c2 = XINT (ret);
- return;
- }
- }
- else if ((*c1 = charset_get_byte1 (*charset, c)))
- {
- *c2 = charset_get_byte2 (*charset, c);
- return;
- }
- }
- charsets = Fcdr (charsets);
- }
- }
- if (c < MIN_CHAR_OBS_94x94)
+ while (!NILP (charsets))
{
-#if 0
- Lisp_Object charsets = Vdefault_coded_charset_priority_list;
- while (!EQ (charsets, Qnil))
+ *charset = Ffind_charset (Fcar (charsets));
+ if (!NILP (*charset))
{
- *charset = Ffind_charset (Fcar (charsets));
- if (!EQ (*charset, Qnil)
- && (*c1 = charset_get_byte1 (*charset, c)) )
+ Lisp_Object encoding_table = XCHARSET_ENCODING_TABLE (*charset);
+ Lisp_Object ret;
+
+ if ( CHAR_ID_TABLE_P (encoding_table)
+ && INTP (ret = get_char_id_table (ch, encoding_table)) )
+ return XINT (ret);
+ else
{
- *c2 = charset_get_byte2 (*charset, c);
- return;
+ int code_point = range_charset_code_point (*charset, ch);
+
+ if (code_point >= 0)
+ return code_point;
}
- charsets = Fcdr (charsets);
- }
-#endif
- /* otherwise --- maybe for bootstrap */
- if (c <= MAX_CHAR_BASIC_LATIN)
- {
- *charset = Vcharset_ascii;
- *c1 = charset_get_byte1 (*charset, c);
- *c2 = charset_get_byte2 (*charset, c);
- }
- else if (c < 0xA0)
- {
- *charset = Vcharset_control_1;
- *c1 = charset_get_byte1 (*charset, c);
- *c2 = charset_get_byte2 (*charset, c);
- }
- else if (c <= 0xff)
- {
- *charset = Vcharset_latin_iso8859_1;
- *c1 = charset_get_byte1 (*charset, c);
- *c2 = charset_get_byte2 (*charset, c);
- }
- else if ((MIN_CHAR_GREEK <= c) && (c <= MAX_CHAR_GREEK))
- {
- *charset = Vcharset_greek_iso8859_7;
- *c1 = c - MIN_CHAR_GREEK + 0x20;
- *c2 = 0;
- }
- else if ((MIN_CHAR_CYRILLIC <= c) && (c <= MAX_CHAR_CYRILLIC))
- {
- *charset = Vcharset_cyrillic_iso8859_5;
- *c1 = c - MIN_CHAR_CYRILLIC + 0x20;
- *c2 = 0;
- }
- else if ((MIN_CHAR_HEBREW <= c) && (c <= MAX_CHAR_HEBREW))
- {
- *charset = Vcharset_hebrew_iso8859_8;
- *c1 = c - MIN_CHAR_HEBREW + 0x20;
- *c2 = 0;
- }
- else if ((MIN_CHAR_THAI <= c) && (c <= MAX_CHAR_THAI))
- {
- *charset = Vcharset_thai_tis620;
- *c1 = c - MIN_CHAR_THAI + 0x20;
- *c2 = 0;
- }
- else if ((MIN_CHAR_HALFWIDTH_KATAKANA <= c)
- && (c <= MAX_CHAR_HALFWIDTH_KATAKANA))
- {
- *charset = Vcharset_katakana_jisx0201;
- *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 33;
- *c2 = 0;
- }
- else
- {
- *charset = Vcharset_ucs_bmp;
- *c1 = c >> 8;
- *c2 = c & 0xff;
}
+ charsets = Fcdr (charsets);
}
- 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
- = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94,
- ((c - MIN_CHAR_94) / 94) + '0',
- CHARSET_LEFT_TO_RIGHT);
- *c1 = ((c - MIN_CHAR_94) % 94) + 33;
- *c2 = 0;
- }
- else if (c <= MAX_CHAR_96)
- {
- *charset
- = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96,
- ((c - MIN_CHAR_96) / 96) + '0',
- CHARSET_LEFT_TO_RIGHT);
- *c1 = ((c - MIN_CHAR_96) % 96) + 32;
- *c2 = 0;
- }
- else if (c <= MAX_CHAR_94x94)
- {
- *charset
- = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_94X94,
- ((c - MIN_CHAR_94x94) / (94 * 94)) + '0',
- CHARSET_LEFT_TO_RIGHT);
- *c1 = (((c - MIN_CHAR_94x94) / 94) % 94) + 33;
- *c2 = ((c - MIN_CHAR_94x94) % 94) + 33;
- }
- else if (c <= MAX_CHAR_96x96)
- {
- *charset
- = CHARSET_BY_ATTRIBUTES (CHARSET_TYPE_96X96,
- ((c - MIN_CHAR_96x96) / (96 * 96)) + '0',
- CHARSET_LEFT_TO_RIGHT);
- *c1 = (((c - MIN_CHAR_96x96) / 96) % 96) + 32;
- *c2 = ((c - MIN_CHAR_96x96) % 96) + 32;
- }
- else
+
+ /* otherwise --- maybe for bootstrap */
+ return encode_builtin_char_1 (ch, charset);
+}
+
+#define ENCODE_CHAR(ch, charset) encode_char_1 (ch, &(charset))
+
+INLINE_HEADER void
+breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2);
+INLINE_HEADER void
+breakup_char_1 (Emchar c, Lisp_Object *charset, int *c1, int *c2)
+{
+ int code_point = encode_char_1 (c, charset);
+
+ if (code_point >= 0)
{
- printf("u+%x", c);
- abort();
+ int dim = XCHARSET_DIMENSION (*charset);
+
+ if (dim == 1)
+ {
+ *c1 = code_point;
+ *c2 = 0;
+ }
+ else /* if (dim == 2) */
+ {
+ *c1 = code_point >> 8;
+ *c2 = code_point & 255;
+ }
}
+ else{
+ *c1 = *c2 = 0;
+ }
}
#define BREAKUP_CHAR(ch, charset, b1, b2) \
breakup_char_1 (ch, &(charset), &(b1), &(b2))
-INLINE Lisp_Object CHAR_CHARSET (Emchar ch);
-INLINE Lisp_Object
+INLINE_HEADER Lisp_Object CHAR_CHARSET (Emchar ch);
+INLINE_HEADER Lisp_Object
CHAR_CHARSET (Emchar ch)
{
Lisp_Object charset;
- int b1, b2;
-
- BREAKUP_CHAR(ch, charset, b1, b2);
+
+ ENCODE_CHAR (ch, charset);
return charset;
}
#define CHAR_CHARSET_ID(c) (XCHARSET_ID(CHAR_CHARSET(c)))
#define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
+
+typedef struct Charc
+{
+ Lisp_Object charset;
+ int code_point;
+} Charc;
+
+INLINE_HEADER Charc CHAR_TO_CHARC (Emchar ch);
+INLINE_HEADER Charc
+CHAR_TO_CHARC (Emchar ch)
+{
+ 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 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;
-#endif /* _XEMACS_CHAR_UCS_H */
+#endif /* INCLUDED_char_ucs_h_ */