X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.h;h=3787832f81da07a7c64d25d1b30c5161aabb9b99;hb=476a441165787891eee1a11432f6f97851212d34;hp=feff1b4696e2f1ae1919dadbe2a761555f74b403;hpb=3ec562b0bffb8b8b48df56ef7460b59729c19345;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.h b/utf8.h
index feff1b4..3787832 100644
--- a/utf8.h
+++ b/utf8.h
@@ -63,20 +63,43 @@ END_EXTERN_C
 
 /*
 
- The following table is from Unicode 3.1.
+ The following table is from Unicode 3.2.
 
  Code Points		1st Byte  2nd Byte  3rd Byte  4th Byte
 
-   U+0000..U+007F	00..7F   
-   U+0080..U+07FF	C2..DF    80..BF   
-   U+0800..U+0FFF	E0        A0..BF    80..BF  
-   U+1000..U+FFFF	E1..EF    80..BF    80..BF  
+   U+0000..U+007F	00..7F
+   U+0080..U+07FF	C2..DF    80..BF
+   U+0800..U+0FFF	E0        A0..BF    80..BF
+   U+1000..U+CFFF       E1..EC    80..BF    80..BF
+   U+D000..U+D7FF       ED        80..9F    80..BF
+   U+D800..U+DFFF       ******* ill-formed *******
+   U+E000..U+FFFF       EE..EF    80..BF    80..BF
   U+10000..U+3FFFF	F0        90..BF    80..BF    80..BF
   U+40000..U+FFFFF	F1..F3    80..BF    80..BF    80..BF
  U+100000..U+10FFFF	F4        80..8F    80..BF    80..BF
 
+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.
+
  */
 
+/*
+ Another way to look at it, as bits:
+
+ Code Points                    1st Byte   2nd Byte  3rd Byte  4th Byte
+
+                    0aaaaaaa     0aaaaaaa
+            00000bbbbbaaaaaa     110bbbbb  10aaaaaa
+            ccccbbbbbbaaaaaa     1110cccc  10bbbbbb  10aaaaaa
+  00000dddccccccbbbbbbaaaaaa     11110ddd  10cccccc  10bbbbbb  10aaaaaa
+
+As you can see, the continuation bytes all begin with C<10>, and the
+leading bits of the start byte tell how many bytes the are in the
+encoded character.
+
+*/
+
+
 #define UNI_IS_INVARIANT(c)		(((UV)c) <  0x80)
 #define UTF8_IS_INVARIANT(c)		UNI_IS_INVARIANT(NATIVE_TO_UTF(c))
 #define NATIVE_IS_INVARIANT(c)		UNI_IS_INVARIANT(NATIVE_TO_ASCII(c))
@@ -165,24 +188,24 @@ END_EXTERN_C
 #define UNICODE_SURROGATE_FIRST		0xd800
 #define UNICODE_SURROGATE_LAST		0xdfff
 #define UNICODE_REPLACEMENT		0xfffd
-#define UNICODE_BYTER_ORDER_MARK	0xfffe
+#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_BOM	0x0004	/* Allow 0xFEFF */
+#define UNICODE_ALLOW_FFFF	0x0008	/* Allow 0xFFFF, 0x1FFFF, ... */
 #define UNICODE_ALLOW_SUPER	0x0010	/* Allow past 10xFFFF */
 #define UNICODE_ALLOW_ANY	0xFFFF
 
 #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