} while (0)
/* Return the character code of character whose multibyte form is at
- P. */
+ P. Note that this macro unifies CJK characters whose codepoints
+ are in the Private Use Areas (PUAs), so it might return a different
+ codepoint from the one actually stored at P. */
#define STRING_CHAR(p) \
(!((p)[0] & 0x80) \
/* Like STRING_CHAR, but set ACTUAL_LEN to the length of multibyte
- form. */
+ form.
+
+ Note: This macro returns the actual length of the character's
+ multibyte sequence as it is stored in a buffer or string. The
+ character it returns might have a different codepoint that has a
+ different multibyte sequence of a different length, due to possible
+ unification of CJK characters inside string_char. Therefore do NOT
+ assume that the length returned by this macro is identical to the
+ length of the multibyte sequence of the character it returns. */
#define STRING_CHAR_AND_LENGTH(p, actual_len) \
(!((p)[0] & 0x80) \
unsigned char *chp = BYTE_POS_ADDR (BYTEIDX); \
int chlen; \
\
- OUTPUT= STRING_CHAR_AND_LENGTH (chp, chlen); \
+ OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \
BYTEIDX += chlen; \
} \
else \
UNICODE_CATEGORY_Cn
} unicode_category_t;
-extern EMACS_INT char_resolve_modifier_mask (EMACS_INT);
+extern EMACS_INT char_resolve_modifier_mask (EMACS_INT) ATTRIBUTE_CONST;
extern int char_string (unsigned, unsigned char *);
extern int string_char (const unsigned char *,
const unsigned char **, int *);