X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=0b3dc6a826ebc6dcf81d02d8495b90017020a69d;hb=049aabcba31f7c58d7cadff7bb84dd748ced2750;hp=9bf39286c884dc0501c865fdf65f2085d8b096a7;hpb=a98fe34d09e2476f1a21bfb9dc730dc9ab02b0b4;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.h b/utf8.h
index 9bf3928..0b3dc6a 100644
--- a/utf8.h
+++ b/utf8.h
@@ -1,6 +1,6 @@
 /*    utf8.h
  *
- *    Copyright (C) 2000, 2001, 2002, 2005 by Larry Wall and others
+ *    Copyright (C) 2000, 2001, 2002, 2005, 2006, 2007, 2009 by Larry Wall and others
  *
  *    You may distribute under the terms of either the GNU General Public
  *    License or the Artistic License, as specified in the README file.
@@ -51,6 +51,7 @@ END_EXTERN_C
 
 /* Native character to iso-8859-1 */
 #define NATIVE_TO_ASCII(ch)      (ch)
+#define NATIVE8_TO_UNI(ch)        (ch)
 #define ASCII_TO_NATIVE(ch)      (ch)
 /* Transform after encoding */
 #define NATIVE_TO_UTF(ch)        (ch)
@@ -194,15 +195,17 @@ encoded character.
 #define UTF8_ALLOW_EMPTY		0x0001
 #define UTF8_ALLOW_CONTINUATION		0x0002
 #define UTF8_ALLOW_NON_CONTINUATION	0x0004
-#define UTF8_ALLOW_FE_FF		0x0008
+#define UTF8_ALLOW_FE_FF		0x0008 /* Allow above 0x7fffFFFF */
 #define UTF8_ALLOW_SHORT		0x0010
 #define UTF8_ALLOW_SURROGATE		0x0020
-#define UTF8_ALLOW_FFFF			0x0040 /* Allows also FFFE. */
+#define UTF8_ALLOW_FFFF			0x0040 /* Allow UNICODE_ILLEGAL */
 #define UTF8_ALLOW_LONG			0x0080
 #define UTF8_ALLOW_ANYUV		(UTF8_ALLOW_EMPTY|UTF8_ALLOW_FE_FF|\
 					 UTF8_ALLOW_SURROGATE|UTF8_ALLOW_FFFF)
 #define UTF8_ALLOW_ANY			0x00FF
 #define UTF8_CHECK_ONLY			0x0200
+#define UTF8_ALLOW_DEFAULT		(ckWARN(WARN_UTF8) ? 0 : \
+					 UTF8_ALLOW_ANYUV)
 
 #define UNICODE_SURROGATE_FIRST		0xD800
 #define UNICODE_SURROGATE_LAST		0xDFFF
@@ -211,13 +214,13 @@ encoded character.
 #define UNICODE_ILLEGAL			0xFFFF
 
 /* Though our UTF-8 encoding can go beyond this,
- * let's be conservative and do as Unicode 3.2 says. */
+ * let's be conservative and do as Unicode 5.1 says. */
 #define PERL_UNICODE_MAX	0x10FFFF
 
 #define UNICODE_ALLOW_SURROGATE 0x0001	/* Allow UTF-16 surrogates (EVIL) */
 #define UNICODE_ALLOW_FDD0	0x0002	/* Allow the U+FDD0...U+FDEF */
-#define UNICODE_ALLOW_FFFF	0x0004	/* Allow 0xFFF[EF], 0x1FFF[EF], ... */
-#define UNICODE_ALLOW_SUPER	0x0008	/* Allow past 10xFFFF */
+#define UNICODE_ALLOW_FFFF	0x0004	/* Allow U+FFF[EF], U+1FFF[EF], ... */
+#define UNICODE_ALLOW_SUPER	0x0008	/* Allow past 0x10FFFF */
 #define UNICODE_ALLOW_ANY	0x000F
 
 #define UNICODE_IS_SURROGATE(c)		((c) >= UNICODE_SURROGATE_FIRST && \
@@ -338,3 +341,13 @@ encoded character.
 #define IS_UTF8_CHAR_FAST(n) ((n) <= 4)
 
 #endif /* IS_UTF8_CHAR() for UTF-8 */
+
+/*
+ * Local variables:
+ * c-indentation-style: bsd
+ * c-basic-offset: 4
+ * indent-tabs-mode: t
+ * End:
+ *
+ * ex: set ts=8 sts=4 sw=4 noet:
+ */