Kaydet (Commit) 6c858384 authored tarafından Senthil Kumaran's avatar Senthil Kumaran

Merged revisions 87542 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/branches/py3k

........
  r87542 | senthil.kumaran | 2010-12-28 23:55:16 +0800 (Tue, 28 Dec 2010) | 3 lines

  Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax
........
üst 18f6b198
......@@ -367,6 +367,7 @@ class HTMLParser(_markupbase.ParserBase):
return s
def replaceEntities(s):
s = s.groups()[0]
try:
if s[0] == "#":
s = s[1:]
if s[0] in ['x','X']:
......@@ -374,6 +375,8 @@ class HTMLParser(_markupbase.ParserBase):
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
......
......@@ -319,6 +319,10 @@ DOCTYPE html [
self._run_check("<html foo='&euro;&amp;&#97;&#x61;&unsupported;'>", [
("starttag", "html", [("foo", "\u20AC&aa&unsupported;")])
])
def test_unescape_function(self):
p = html.parser.HTMLParser()
self.assertEqual(p.unescape('&#bad;'),'&#bad;')
self.assertEqual(p.unescape('&#0038;'),'&')
def test_main():
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment