X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=72dd15f075c9effe04cc63a35f75289e05c82a04;hb=96a925ab0077cdd24bd7d328f20be3d5373d4885;hp=a5312ca19e4d8580f927b4221ef7d78516c3912b;hpb=375122d71fe65bb12f4aac78313fa2d23fd511f3;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.h b/utf8.h
index a5312ca..72dd15f 100644
--- a/utf8.h
+++ b/utf8.h
@@ -1,6 +1,6 @@
 /*    utf8.h
  *
- *    Copyright (c) 1998-2002, Larry Wall
+ *    Copyright (C) 2000, 2001, 2002, 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.
@@ -80,6 +80,10 @@ END_EXTERN_C
 
 Note the A0..BF in U+0800..U+0FFF, the 80..9F in U+D000...U+D7FF,
 the 90..BF in U+10000..U+3FFFF, and the 80...8F in U+100000..U+10FFFF.
+The "gaps" are caused by legal UTF-8 avoiding non-shortest encodings:
+it is technically possible to UTF-8-encode a single code point in different
+ways, but that is explicitly forbidden, and the shortest possible encoding
+should always be used (and that is what Perl does).
 
  */
 
@@ -176,36 +180,34 @@ encoded character.
 #define UTF8_ALLOW_FE_FF		0x0008
 #define UTF8_ALLOW_SHORT		0x0010
 #define UTF8_ALLOW_SURROGATE		0x0020
-#define UTF8_ALLOW_BOM			0x0040
-#define UTF8_ALLOW_FFFF			0x0080
-#define UTF8_ALLOW_LONG			0x0100
+#define UTF8_ALLOW_FFFF			0x0040 /* Allows also FFFE. */
+#define UTF8_ALLOW_LONG			0x0080
 #define UTF8_ALLOW_ANYUV		(UTF8_ALLOW_EMPTY|UTF8_ALLOW_FE_FF|\
-					 UTF8_ALLOW_SURROGATE|UTF8_ALLOW_BOM|\
+					 UTF8_ALLOW_SURROGATE|\
 					 UTF8_ALLOW_FFFF|UTF8_ALLOW_LONG)
-#define UTF8_ALLOW_ANY			0x00ff
+#define UTF8_ALLOW_ANY			0x00FF
 #define UTF8_CHECK_ONLY			0x0200
 
-#define UNICODE_SURROGATE_FIRST		0xd800
-#define UNICODE_SURROGATE_LAST		0xdfff
-#define UNICODE_REPLACEMENT		0xfffd
-#define UNICODE_BYTER_ORDER_MARK	0xfffe
-#define UNICODE_ILLEGAL			0xffff
+#define UNICODE_SURROGATE_FIRST		0xD800
+#define UNICODE_SURROGATE_LAST		0xDFFF
+#define UNICODE_REPLACEMENT		0xFFFD
+#define UNICODE_BYTE_ORDER_MARK		0xFEFF
+#define UNICODE_ILLEGAL			0xFFFF
 
 /* Though our UTF-8 encoding can go beyond this,
- * let's be conservative. */
+ * let's be conservative and do as Unicode 3.2 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_FFFE	0x0004	/* Allow 0xFFFE, 0x1FFFE, ... */
-#define UNICODE_ALLOW_FFFF	0x0008	/* Allow 0xFFFE, 0x1FFFE, ... */
-#define UNICODE_ALLOW_SUPER	0x0010	/* Allow past 10xFFFF */
-#define UNICODE_ALLOW_ANY	0xFFFF
+#define UNICODE_ALLOW_FFFF	0x0004	/* Allow 0xFFF[EF], 0x1FFF[EF], ... */
+#define UNICODE_ALLOW_SUPER	0x0008	/* Allow past 10xFFFF */
+#define UNICODE_ALLOW_ANY	0x000F
 
 #define UNICODE_IS_SURROGATE(c)		((c) >= UNICODE_SURROGATE_FIRST && \
 					 (c) <= UNICODE_SURROGATE_LAST)
 #define UNICODE_IS_REPLACEMENT(c)	((c) == UNICODE_REPLACEMENT)
-#define UNICODE_IS_BYTE_ORDER_MARK(c)	((c) == UNICODE_BYTER_ORDER_MARK)
+#define UNICODE_IS_BYTE_ORDER_MARK(c)	((c) == UNICODE_BYTE_ORDER_MARK)
 #define UNICODE_IS_ILLEGAL(c)		((c) == UNICODE_ILLEGAL)
 
 #ifdef HAS_QUAD