diff options
| author | Ezio Melotti <ezio.melotti@gmail.com> | 2010-07-03 04:52:19 (GMT) |
|---|---|---|
| committer | Ezio Melotti <ezio.melotti@gmail.com> | 2010-07-03 04:52:19 (GMT) |
| commit | 9bf2b3ae6a21c254bdd0d8f2dfbebd320494452e (patch) | |
| tree | 62e293d3bc58c483a5f92fce0b767f9df2995a45 /Objects | |
| parent | 2f194b906027db630e731021429746eb214b0a7a (diff) | |
| download | cpython-9bf2b3ae6a21c254bdd0d8f2dfbebd320494452e.zip cpython-9bf2b3ae6a21c254bdd0d8f2dfbebd320494452e.tar.gz cpython-9bf2b3ae6a21c254bdd0d8f2dfbebd320494452e.tar.bz2 | |
Update comment about surrogates.
Diffstat (limited to 'Objects')
| -rw-r--r-- | Objects/unicodeobject.c | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index 83bc422..dba3d36 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -2450,11 +2450,11 @@ PyObject *PyUnicode_DecodeUTF8Stateful(const char *s, 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 && |