traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax

This commit is contained in:
Senthil Kumaran 2010-12-28 15:55:16 +00:00
parent 3b4499c5c7
commit 164540fee1
2 changed files with 15 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
Lib/html/parser.py
View File

@ -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

5
Lib/test/test_htmlparser.py
View File

@ -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)