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

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
........
This commit is contained in:
Senthil Kumaran 2010-12-28 16:10:56 +00:00
parent 18f6b1987f
commit 6c85838489
2 changed files with 14 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

@ -367,13 +367,16 @@ 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

4
Lib/test/test_htmlparser.py
View File

@ -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():