Character set Encoding (PC == position-code)
------------- -------- (LB == leading-byte)
- ASCII PC1 |
+ ASCII PC1 |
Control-1 LB | PC1 + 0xA0
Dimension-1 official LB | PC1 + 0x80
Dimension-1 private 0x9E | LB | PC1 + 0x80
/* Definition of leading bytes */
/************************************************************************/
+typedef int Charset_ID;
+
#define MIN_LEADING_BYTE 0x80
/* These need special treatment in a string and/or character */
#define LEADING_BYTE_ASCII 0x8E /* Omitted in a buffer */
CHARSET_REVERSE_DIRECTION_CHARSET (XCHARSET (cs))
struct charset_lookup {
- /* Table of charsets indexed by leading byte. */
- Lisp_Object charset_by_leading_byte[128];
+ /* Table of charsets indexed by (leading byte - MIN_LEADING_BYTE). */
+ 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][2];
extern struct charset_lookup *chlook;
-/* Table of number of bytes in the string representation of a character
- indexed by the first byte of that representation.
-
- This value can be derived other ways -- e.g. something like
-
- (BYTE_ASCII_P (first_byte) ? 1 :
- XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (first_byte)))
-
- but it's faster this way. */
-extern Bytecount rep_bytes_by_first_byte[0xA0];
-
#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
INLINE Lisp_Object
CHARSET_BY_LEADING_BYTE (int lb)
{
- assert (lb >= 0x80 && lb <= 0xFF);
- return chlook->charset_by_leading_byte[lb - 128];
+ assert (lb >= MIN_LEADING_BYTE &&
+ lb < (MIN_LEADING_BYTE + NUM_LEADING_BYTES));
+ return chlook->charset_by_leading_byte[lb - MIN_LEADING_BYTE];
}
#else
-#define CHARSET_BY_LEADING_BYTE(lb) (chlook->charset_by_leading_byte[(lb) - 128])
+#define CHARSET_BY_LEADING_BYTE(lb) \
+ (chlook->charset_by_leading_byte[(lb) - MIN_LEADING_BYTE])
#endif
#define CHARSET_BY_ATTRIBUTES(type, final, dir) \
(chlook->charset_by_attributes[type][final][dir])
-#ifdef ERROR_CHECK_TYPECHECK
-/* Number of bytes in the string representation of a character */
+/* Table of number of bytes in the string representation of a character
+ indexed by the first byte of that representation.
+
+ This value can be derived in other ways -- e.g. something like
+ XCHARSET_REP_BYTES (CHARSET_BY_LEADING_BYTE (first_byte))
+ but it's faster this way. */
+extern const Bytecount rep_bytes_by_first_byte[0xA0];
+
+/* Number of bytes in the string representation of a character. */
INLINE int REP_BYTES_BY_FIRST_BYTE (int fb);
INLINE int
REP_BYTES_BY_FIRST_BYTE (int fb)
{
- assert (fb >= 0 && fb < 0xA0);
+#ifdef ERROR_CHECK_TYPECHECK
+ assert (0 <= fb && fb < 0xA0);
+#endif
return rep_bytes_by_first_byte[fb];
}
-#else
-#define REP_BYTES_BY_FIRST_BYTE(fb) (rep_bytes_by_first_byte[fb])
-#endif
-
\f
/************************************************************************/
/* Dealing with characters */
/************************************************************************/
-/* Is this character represented by more than one byte in a string? */
-
-#define CHAR_MULTIBYTE_P(c) ((c) >= 0x80)
-
-#define CHAR_ASCII_P(c) (!CHAR_MULTIBYTE_P (c))
+#define CHAR_ASCII_P(ch) ((ch) <= 0x7F)
/* The bit fields of character are divided into 3 parts:
FIELD1(5bits):FIELD2(7bits):FIELD3(7bits) */