[Python-checkins] r82468 - python/branches/py3k/Objects/unicodeobject.c

[ezio.melotti]

Author: ezio.melotti
Date: Sat Jul  3 06:52:19 2010
New Revision: 82468

Log:
Update comment about surrogates.

Modified:
   python/branches/py3k/Objects/unicodeobject.c

Modified: python/branches/py3k/Objects/unicodeobject.c
==============================================================================
--- python/branches/py3k/Objects/unicodeobject.c	(original)
+++ python/branches/py3k/Objects/unicodeobject.c	Sat Jul  3 06:52:19 2010
@@ -2450,11 +2450,11 @@
             break;
 
         case 3:
-            /* XXX: surrogates shouldn't be valid UTF-8!
-               see http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf
-               (table 3-7) and http://www.rfc-editor.org/rfc/rfc3629.txt
-               Uncomment the 2 lines below to make them invalid,
-               codepoints: d800-dfff; UTF-8: \xed\xa0\x80-\xed\xbf\xbf. */
+            /* Decoding UTF-8 sequences in range \xed\xa0\x80-\xed\xbf\xbf
+               will result in surrogates in range d800-dfff. Surrogates are
+               not valid UTF-8 so they are rejected.
+               See http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf
+               (table 3-7) and http://www.rfc-editor.org/rfc/rfc3629.txt */
             if ((s[1] & 0xc0) != 0x80 ||
                 (s[2] & 0xc0) != 0x80 ||
                 ((unsigned char)s[0] == 0xE0 &&