From: Senthil Kumaran Date: Tue, 28 Dec 2010 15:55:16 +0000 (+0000) Subject: Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax X-Git-Tag: v3.2rc1~300 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=164540fee1f5909364e0758bbb948ee6f7387f14;p=python Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax --- diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 8d275ab315..21ebbc3eaf 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -434,13 +434,16 @@ class HTMLParser(_markupbase.ParserBase): 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 chr(c) + try: + if s[0] == "#": + s = s[1:] + if s[0] in ['x','X']: + c = int(s[1:], 16) + else: + c = int(s) + return chr(c) + except ValueError: + return '&#'+ s +';' else: # Cannot use name2codepoint directly, because HTMLParser # supports apos, which is not part of HTML 4 diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index beaf6b63a2..5ecd016084 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -356,6 +356,11 @@ class HTMLParserTolerantTestCase(TestCaseBase): [('action', 'bogus|&#()value')])], collector = self.collector) + def test_unescape_function(self): + p = html.parser.HTMLParser() + self.assertEqual(p.unescape('&#bad;'),'&#bad;') + self.assertEqual(p.unescape('&'),'&') + def test_main(): support.run_unittest(HTMLParserTestCase, HTMLParserTolerantTestCase)