X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=659319e82d68f91f9ad2eecb32f1687e6878e21d;hb=133fac12ff7e3894deb31a204a9a12453b87bbf0;hp=837f7fb826699a7e6eaab645e5ee3ec5fcbe4da8;hpb=1754c1a12c44346c579c5581660df4064b19f4a0;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.h b/utf8.h
index 837f7fb..659319e 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.
@@ -16,12 +16,17 @@
 #    define USE_UTF8_IN_NAMES (PL_hints & HINT_UTF8)
 #endif
 
+/* Source backward compatibility. */
+#define uvuni_to_utf8(d, uv)		uvuni_to_utf8_flags(d, uv, 0)
+#define is_utf8_string_loc(s, len, ep)	is_utf8_string_loclen(s, len, ep, 0)
+
 #ifdef EBCDIC
 /* The equivalent of these macros but implementing UTF-EBCDIC
    are in the following header file:
  */
 
 #include "utfebcdic.h"
+
 #else
 START_EXTERN_C
 
@@ -46,6 +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)
@@ -112,8 +118,8 @@ encoded character.
 #define UTF8_IS_CONTINUED(c) 		(((U8)c) &  0x80)
 #define UTF8_IS_DOWNGRADEABLE_START(c)	(((U8)c & 0xfc) == 0xc0)
 
-#define UTF_START_MARK(len) ((len >  7) ? 0xFF : (0xFE << (7-len)))
-#define UTF_START_MASK(len) ((len >= 7) ? 0x00 : (0x1F >> (len-2)))
+#define UTF_START_MARK(len) (((len) >  7) ? 0xFF : (0xFE << (7-(len))))
+#define UTF_START_MASK(len) (((len) >= 7) ? 0x00 : (0x1F >> ((len)-2)))
 
 #define UTF_CONTINUATION_MARK		0x80
 #define UTF_ACCUMULATION_SHIFT		6
@@ -145,7 +151,7 @@ encoded character.
  * Note: we try to be careful never to call the isXXX_utf8() functions
  * unless we're pretty sure we've seen the beginning of a UTF-8 character
  * (that is, the two high bits are set).  Otherwise we risk loading in the
- * heavy-duty SWASHINIT and SWASHGET routines unnecessarily.
+ * heavy-duty swash_init and swash_fetch routines unnecessarily.
  */
 #define isIDFIRST_lazy_if(p,c) ((IN_BYTES || (!c || (*((const U8*)p) < 0xc0))) \
 				? isIDFIRST(*(p)) \
@@ -183,21 +189,23 @@ encoded character.
  * SpecialCasing.txt. */
 #define UTF8_MAXBYTES_CASE	6
 
-#define IN_BYTES (PL_curcop->op_private & HINT_BYTES)
+#define IN_BYTES (CopHINTS_get(PL_curcop) & HINT_BYTES)
 #define DO_UTF8(sv) (SvUTF8(sv) && !IN_BYTES)
 
 #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
@@ -206,13 +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 && \
@@ -332,7 +340,14 @@ encoded character.
 
 #define IS_UTF8_CHAR_FAST(n) ((n) <= 4)
 
-#define uvuni_to_utf8(d, uv)		uvuni_to_utf8_flags(d, uv, 0)
-#define is_utf8_string_loc(s, len, ep)	is_utf8_string_loclen(s, len, ep, 0)
-
 #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:
+ */