Mercurial > cpython-lru_cache-weakref
diff Lib/HTMLParser.py @ 67188:05cccd4257a2 2.7
Fix Issue10759 - HTMLParser.unescape() to handle malform charrefs.
| author | Senthil Kumaran <orsenthil@gmail.com> |
|---|---|
| date | Tue, 28 Dec 2010 16:05:07 +0000 |
| parents | ebda6803f8d5 |
| children | 7d4dea76c476 |
line wrap: on
line diff
--- a/Lib/HTMLParser.py Tue Dec 28 16:04:06 2010 +0000 +++ b/Lib/HTMLParser.py Tue Dec 28 16:05:07 2010 +0000 @@ -367,13 +367,16 @@ return s def replaceEntities(s): s = s.groups()[0] - if s[0] == "#": - s = s[1:] - if s[0] in ['x','X']: - c = int(s[1:], 16) - else: - c = int(s) - return unichr(c) + try: + if s[0] == "#": + s = s[1:] + if s[0] in ['x','X']: + c = int(s[1:], 16) + else: + c = int(s) + return unichr(c) + except ValueError: + return '&#'+s+';' else: # Cannot use name2codepoint directly, because HTMLParser supports apos, # which is not part of HTML 4