Update the UTF-8 explanation table.

p4raw-id: //depot/perl@14900

diff --git a/pod/perlunicode.pod b/pod/perlunicode.pod
index 7fb473e..7ea8714 100644 (file)
--- a/pod/perlunicode.pod
+++ b/pod/perlunicode.pod
@@ -700,18 +700,23 @@ UTF-8 is a variable-length (1 to 6 bytes, current character allocations
 require 4 bytes), byteorder independent encoding. For ASCII, UTF-8 is
 transparent (and we really do mean 7-bit ASCII, not another 8-bit encoding).
 
-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+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+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.
 Or, another way to look at it, as bits:
 
  Code Points                    1st Byte   2nd Byte  3rd Byte  4th Byte
@@ -722,7 +727,7 @@ Or, another way to look at it, as bits:
   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 tells how many bytes the are in the
+leading bits of the start byte tell how many bytes the are in the
 encoded character.
 
 =item

diff --git a/utf8.h b/utf8.h
index feff1b4..2e0b5fd 100644 (file)
--- 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+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))