Here are the long-expected Unicode/UTF-8 modifications.

p4raw-id: //depot/utfperl@1651

1 files changed, 48 insertions, 0 deletions

diff --git a/handy.h b/handy.h
index e74a3069a8..bda9d5ca28 100644
--- a/handy.h
+++ b/handy.h
@@ -238,6 +238,54 @@ typedef unsigned short	U16;
 #  endif
 #endif /* USE_NEXT_CTYPE */
 
+#define isALNUM_uni(c)		is_uni_alnum(c)
+#define isIDFIRST_uni(c)	is_uni_idfirst(c)
+#define isALPHA_uni(c)		is_uni_alpha(c)
+#define isSPACE_uni(c)		is_uni_space(c)
+#define isDIGIT_uni(c)		is_uni_digit(c)
+#define isUPPER_uni(c)		is_uni_upper(c)
+#define isLOWER_uni(c)		is_uni_lower(c)
+#define isPRINT_uni(c)		is_uni_print(c)
+#define toUPPER_uni(c)		to_uni_upper(c)
+#define toTITLE_uni(c)		to_uni_title(c)
+#define toLOWER_uni(c)		to_uni_lower(c)
+
+#define isALNUM_LC_uni(c)	(c < 256 ? isALNUM_LC(c) : is_uni_alnum_lc(c))
+#define isIDFIRST_LC_uni(c)	(c < 256 ? isIDFIRST_LC(c) : is_uni_idfirst_lc(c))
+#define isALPHA_LC_uni(c)	(c < 256 ? isALPHA_LC(c) : is_uni_alpha_lc(c))
+#define isSPACE_LC_uni(c)	(c < 256 ? isSPACE_LC(c) : is_uni_space_lc(c))
+#define isDIGIT_LC_uni(c)	(c < 256 ? isDIGIT_LC(c) : is_uni_digit_lc(c))
+#define isUPPER_LC_uni(c)	(c < 256 ? isUPPER_LC(c) : is_uni_upper_lc(c))
+#define isLOWER_LC_uni(c)	(c < 256 ? isLOWER_LC(c) : is_uni_lower_lc(c))
+#define isPRINT_LC_uni(c)	(c < 256 ? isPRINT_LC(c) : is_uni_print_lc(c))
+#define toUPPER_LC_uni(c)	(c < 256 ? toUPPER_LC(c) : to_uni_upper_lc(c))
+#define toTITLE_LC_uni(c)	(c < 256 ? toUPPER_LC(c) : to_uni_title_lc(c))
+#define toLOWER_LC_uni(c)	(c < 256 ? toLOWER_LC(c) : to_uni_lower_lc(c))
+
+#define isALNUM_utf8(p)		is_utf8_alnum(p)
+#define isIDFIRST_utf8(p)	is_utf8_idfirst(p)
+#define isALPHA_utf8(p)		is_utf8_alpha(p)
+#define isSPACE_utf8(p)		is_utf8_space(p)
+#define isDIGIT_utf8(p)		is_utf8_digit(p)
+#define isUPPER_utf8(p)		is_utf8_upper(p)
+#define isLOWER_utf8(p)		is_utf8_lower(p)
+#define isPRINT_utf8(p)		is_utf8_print(p)
+#define toUPPER_utf8(p)		to_utf8_upper(p)
+#define toTITLE_utf8(p)		to_utf8_title(p)
+#define toLOWER_utf8(p)		to_utf8_lower(p)
+
+#define isALNUM_LC_utf8(p)	isALNUM_LC_uni(utf8_to_uv(p, 0))
+#define isIDFIRST_LC_utf8(p)	isIDFIRST_LC_uni(utf8_to_uv(p, 0))
+#define isALPHA_LC_utf8(p)	isALPHA_LC_uni(utf8_to_uv(p, 0))
+#define isSPACE_LC_utf8(p)	isSPACE_LC_uni(utf8_to_uv(p, 0))
+#define isDIGIT_LC_utf8(p)	isDIGIT_LC_uni(utf8_to_uv(p, 0))
+#define isUPPER_LC_utf8(p)	isUPPER_LC_uni(utf8_to_uv(p, 0))
+#define isLOWER_LC_utf8(p)	isLOWER_LC_uni(utf8_to_uv(p, 0))
+#define isPRINT_LC_utf8(p)	isPRINT_LC_uni(utf8_to_uv(p, 0))
+#define toUPPER_LC_utf8(p)	toUPPER_LC_uni(utf8_to_uv(p, 0))
+#define toTITLE_LC_utf8(p)	toTITLE_LC_uni(utf8_to_uv(p, 0))
+#define toLOWER_LC_utf8(p)	toLOWER_LC_uni(utf8_to_uv(p, 0))
+
 /* This conversion works both ways, strangely enough. */
 #define toCTRL(c)    (toUPPER(c) ^ 64)