#define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
\f
+typedef struct
+{
+ unsigned char *base;
+ size_t offset;
+ size_t size;
+} Emchar_to_byte_table;
+
+unsigned char
+get_byte_from_character_table (Emchar ch, Emchar_to_byte_table* table);
+
+
+extern Lisp_Object Vcharset_ucs_bmp;
+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 */
/************************************************************************/
#define LEADING_BYTE_CONTROL_1 0x81 /* represent normal 80-9F */
-#define CHARSET_ID_OFFSET_94 0x60
+#define CHARSET_ID_OFFSET_94 0x55
#define MIN_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '0')
#define MAX_CHARSET_ID_PRIVATE_94 (CHARSET_ID_OFFSET_94 + '?')
#define CHARSET_ID_OFFSET_96 0x70
+#define LEADING_BYTE_LATIN_VISCII_LOWER (CHARSET_ID_OFFSET_96 + '1')
+#define LEADING_BYTE_LATIN_VISCII_UPPER (CHARSET_ID_OFFSET_96 + '2')
+
/* Right half of ISO 8859-1 */
#define LEADING_BYTE_LATIN_ISO8859_1 (CHARSET_ID_OFFSET_96 + 'A')
\f
/************************************************************************/
-/* Operations on individual bytes */
-/* of any format */
-/************************************************************************/
-
-/* Argument `c' should be (unsigned int) or (unsigned char). */
-/* Note that SP and DEL are not included. */
-
-#define BYTE_ASCII_P(c) ((c) < 0x80)
-#define BYTE_C0_P(c) ((c) < 0x20)
-/* Do some forced casting just to make *sure* things are gotten right. */
-#define BYTE_C1_P(c) ((unsigned int) ((unsigned int) (c) - 0x80) < 0x20)
-
-\f
-/************************************************************************/
/* Information about a particular character set */
/************************************************************************/
/* Final byte of this character set in ISO2022 designating escape sequence */
Bufbyte final;
- /* Number of bytes (1 - 4) required in the internal representation
- for characters in this character set. This is *not* the
- same as the dimension of the character set). */
- unsigned int rep_bytes;
-
/* Number of columns a character in this charset takes up, on TTY
devices. Not used for X devices. */
unsigned int columns;
/* Which half of font to be used to display this character set */
unsigned int graphic;
+
+ /* Byte->character mapping table */
+ Emchar* decoding_table;
+
+ /* Character->byte mapping table */
+ Emchar_to_byte_table* to_byte1_table;
+ Emchar_to_byte_table* to_byte2_table;
+
+ /* Range of character code */
+ Emchar ucs_min, ucs_max;
+
+ /* Offset for external representation */
+ Emchar code_offset;
};
DECLARE_LRECORD (charset, struct Lisp_Charset);
#define CHARSET_NAME(cs) ((cs)->name)
#define CHARSET_SHORT_NAME(cs) ((cs)->short_name)
#define CHARSET_LONG_NAME(cs) ((cs)->long_name)
-#define CHARSET_REP_BYTES(cs) ((cs)->rep_bytes)
#define CHARSET_COLUMNS(cs) ((cs)->columns)
#define CHARSET_GRAPHIC(cs) ((cs)->graphic)
#define CHARSET_TYPE(cs) ((cs)->type)
#define CHARSET_DIMENSION(cs) ((cs)->dimension)
#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_TO_BYTE1_TABLE(cs) ((cs)->to_byte1_table)
+#define CHARSET_TO_BYTE2_TABLE(cs) ((cs)->to_byte2_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)
#define XCHARSET_ID(cs) CHARSET_ID (XCHARSET (cs))
#define XCHARSET_NAME(cs) CHARSET_NAME (XCHARSET (cs))
#define XCHARSET_SHORT_NAME(cs) CHARSET_SHORT_NAME (XCHARSET (cs))
#define XCHARSET_LONG_NAME(cs) CHARSET_LONG_NAME (XCHARSET (cs))
-#define XCHARSET_REP_BYTES(cs) CHARSET_REP_BYTES (XCHARSET (cs))
-#define XCHARSET_COLUMNS(cs) CHARSET_COLUMNS (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_CHARS(cs) CHARSET_CHARS (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_TO_BYTE1_TABLE(cs) CHARSET_TO_BYTE1_TABLE(XCHARSET(cs))
+#define XCHARSET_TO_BYTE2_TABLE(cs) CHARSET_TO_BYTE2_TABLE(XCHARSET(cs))
/* Table of charsets indexed by (leading byte - 128). */
extern Lisp_Object charset_by_leading_byte[NUM_LEADING_BYTES];
#define CHARSET_BY_ATTRIBUTES(type, final, dir) \
(charset_by_attributes[type][final])
-INLINE int REP_BYTES_BY_FIRST_BYTE (int fb);
-INLINE int
-REP_BYTES_BY_FIRST_BYTE (int fb)
-{
- if ( fb < 0xc0 )
- return 1;
- else if ( fb < 0xe0 )
- return 2;
- else if ( fb < 0xf0 )
- return 3;
- else if ( fb < 0xf8 )
- return 4;
- else if ( fb < 0xfc )
- return 5;
- else
- return 6;
-}
-
\f
/************************************************************************/
/* Dealing with characters */
#define MIN_CHAR_THAI 0x0E00
#define MAX_CHAR_THAI 0x0E5F
-#define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF60
+#define MIN_CHAR_HALFWIDTH_KATAKANA 0xFF61
#define MAX_CHAR_HALFWIDTH_KATAKANA 0xFF9F
#define MIN_CHAR_94 0xE90940
INLINE Emchar
MAKE_CHAR (Lisp_Object charset, int c1, int c2)
{
- if (EQ (charset, Vcharset_ascii))
- return c1;
- else if (EQ (charset, Vcharset_control_1))
- return c1 | 0x80;
- else if (EQ (charset, Vcharset_latin_iso8859_1))
- return c1 | 0x80;
- else if (EQ (charset, Vcharset_greek_iso8859_7))
- return c1 + MIN_CHAR_GREEK - 0x20;
- else if (EQ (charset, Vcharset_cyrillic_iso8859_5))
- return c1 + MIN_CHAR_CYRILLIC - 0x20;
- else if (EQ (charset, Vcharset_hebrew_iso8859_8))
- return c1 + MIN_CHAR_HEBREW - 0x20;
- else if (EQ (charset, Vcharset_thai_tis620))
- return c1 + MIN_CHAR_THAI - 0x20;
+ Emchar* decoding_table;
+
+ if ((decoding_table = XCHARSET_DECODING_TABLE (charset)) != NULL)
+ return decoding_table[c1 - (XCHARSET_CHARS (charset) == 94 ? 33 : 32)];
else if (EQ (charset, Vcharset_katakana_jisx0201))
if (c1 < 0x60)
- return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 0x20;
+ return c1 + MIN_CHAR_HALFWIDTH_KATAKANA - 33;
else
- return 32;
+ /* return MIN_CHAR_94 + ('I' - '0') * 94 + (c1 - 33); */
+ return ' ';
+ else if (CHARSET_UCS_MAX (XCHARSET (charset)))
+ return (XCHARSET_DIMENSION (charset) == 1
+ ?
+ c1 - CHARSET_CODE_OFFSET (XCHARSET (charset))
+ :
+ (c1 - CHARSET_CODE_OFFSET (XCHARSET (charset)))
+ * XCHARSET_CHARS (charset)
+ + c2 - CHARSET_CODE_OFFSET (XCHARSET (charset)))
+ + CHARSET_UCS_MIN (XCHARSET (charset));
else if (XCHARSET_DIMENSION (charset) == 1)
{
switch (XCHARSET_CHARS (charset))
}
}
-extern Charset_ID latin_a_char_to_charset[128];
-extern unsigned char latin_a_char_to_byte1[128];
-extern unsigned char latin_a_char_to_byte2[128];
+unsigned char charset_get_byte1 (Lisp_Object charset, Emchar ch);
+unsigned char charset_get_byte2 (Lisp_Object charset, Emchar 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)
{
- if (c <= MAX_CHAR_BASIC_LATIN)
- {
- *charset = Vcharset_ascii;
- *c1 = c;
- *c2 = 0;
- }
- else if (c < 0xA0)
- {
- *charset = Vcharset_control_1;
- *c1 = c & 0x7f;
- *c2 = 0;
- }
- else if (c <= 0xff)
- {
- *charset = Vcharset_latin_iso8859_1;
- *c1 = c & 0x7f;
- *c2 = 0;
- }
- else if (c <= 0x17f)
- {
- *charset
- = CHARSET_BY_LEADING_BYTE (latin_a_char_to_charset[c - 0x100]);
- *c1 = latin_a_char_to_byte1[c - 0x100];
- *c2 = latin_a_char_to_byte2[c - 0x100];
- }
- else if (c < MIN_CHAR_GREEK)
- {
- printf("not break up u+%x", c);
- abort ();
- }
- else if (c <= MAX_CHAR_GREEK)
- {
- *charset = Vcharset_greek_iso8859_7;
- *c1 = c - MIN_CHAR_GREEK + 0x20;
- *c2 = 0;
- }
- else if (c < MIN_CHAR_CYRILLIC)
- {
- printf("not break up u+%x", c);
- abort ();
- }
- else if (c <= MAX_CHAR_CYRILLIC)
+ if (c < MIN_CHAR_94)
{
- *charset = Vcharset_cyrillic_iso8859_5;
- *c1 = c - MIN_CHAR_CYRILLIC + 0x20;
- *c2 = 0;
- }
- else if (c < MIN_CHAR_HEBREW)
- {
- printf("not break up u+%x", c);
- abort ();
- }
- else if (c <= MAX_CHAR_HEBREW)
- {
- *charset = Vcharset_hebrew_iso8859_8;
- *c1 = c - MIN_CHAR_HEBREW + 0x20;
- *c2 = 0;
- }
- else if (c < MIN_CHAR_THAI)
- {
- printf("not break up u+%x", c);
- abort ();
- }
- else if (c <= MAX_CHAR_THAI)
- {
- *charset = Vcharset_thai_tis620;
- *c1 = c - MIN_CHAR_THAI + 0x20;
- *c2 = 0;
- }
- else if (c < MIN_CHAR_HALFWIDTH_KATAKANA)
- {
- printf("not break up u+%x", c);
- abort ();
- }
- else if (c <= MAX_CHAR_HALFWIDTH_KATAKANA)
- {
- *charset = Vcharset_katakana_jisx0201;
- *c1 = c - MIN_CHAR_HALFWIDTH_KATAKANA + 0x20;
- *c2 = 0;
+ Lisp_Object charsets = Vdefault_coded_charset_priority_list;
+ while (!EQ (charsets, Qnil))
+ {
+ *charset = Ffind_charset (Fcar (charsets));
+ if (!EQ (*charset, Qnil)
+ && (*c1 = charset_get_byte1 (*charset, c)) )
+ {
+ *c2 = charset_get_byte2 (*charset, c);
+ return;
+ }
+ charsets = Fcdr (charsets);
+ }
+ /* 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;
+ }
}
else if (c <= MAX_CHAR_94)
{
#define CHAR_LEADING_BYTE(c) (XCHARSET_LEADING_BYTE(CHAR_CHARSET(c)))
-\f
-#ifdef ENABLE_COMPOSITE_CHARS
-/************************************************************************/
-/* Composite characters */
-/************************************************************************/
-
-Emchar lookup_composite_char (Bufbyte *str, int len);
-Lisp_Object composite_char_string (Emchar ch);
-#endif /* ENABLE_COMPOSITE_CHARS */
+#define CHAR_COLUMNS(c) (CHARSET_COLUMNS(XCHARSET(CHAR_CHARSET(c))))
\f
/************************************************************************/
/* Exported functions */
/************************************************************************/
-EXFUN (Ffind_charset, 1);
EXFUN (Fget_charset, 1);
extern Lisp_Object Vcharset_chinese_big5_1;
extern Lisp_Object Vcharset_japanese_jisx0208;
extern Lisp_Object Vcharset_japanese_jisx0212;
-Emchar Lstream_get_emchar_1 (Lstream *stream, int first_char);
-int Lstream_fput_emchar (Lstream *stream, Emchar ch);
-void Lstream_funget_emchar (Lstream *stream, Emchar ch);
-
-int copy_internal_to_external (CONST Bufbyte *internal, Bytecount len,
- unsigned char *external);
-Bytecount copy_external_to_internal (CONST unsigned char *external,
- int len, Bufbyte *internal);
-
#endif /* _XEMACS_CHAR_UCS_H */