Skip to content

make compatible with python 3.6 #318

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 18, 2017
Merged

make compatible with python 3.6 #318

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1e61483
make compatible with python 3.6
moben Feb 18, 2017
5fcd461
Merge branch 'master' into master
gsnedders Feb 18, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions html5lib/filters/sanitizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -782,7 +782,7 @@ def allowed_token(self, token):
# characters, nor why we call unescape. I just know it's always been here.
# Should you be worried by this comment in a sanitizer? Yes. On the other hand, all
# this will do is remove *more* than it otherwise would.
val_unescaped = re.sub("[`\x00-\x20\x7f-\xa0\s]+", '',
val_unescaped = re.sub("[`\x00-\x20\x7f-\xa0\\s]+", '',
unescape(attrs[attr])).lower()
# remove replacement characters from unescaped characters
val_unescaped = val_unescaped.replace("\ufffd", "")
Expand All @@ -807,7 +807,7 @@ def allowed_token(self, token):
' ',
unescape(attrs[attr]))
if (token["name"] in self.svg_allow_local_href and
(namespaces['xlink'], 'href') in attrs and re.search('^\s*[^#\s].*',
(namespaces['xlink'], 'href') in attrs and re.search(r'^\s*[^#\s].*',
attrs[(namespaces['xlink'], 'href')])):
del attrs[(namespaces['xlink'], 'href')]
if (None, 'style') in attrs:
Expand Down Expand Up @@ -837,16 +837,16 @@ def disallowed_token(self, token):

def sanitize_css(self, style):
# disallow urls
style = re.compile('url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style)
style = re.compile(r'url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style)

# gauntlet
if not re.match("""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style):
if not re.match(r"""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style):
return ''
if not re.match("^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style):
if not re.match(r"^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style):
return ''

clean = []
for prop, value in re.findall("([-\w]+)\s*:\s*([^:;]*)", style):
for prop, value in re.findall(r"([-\w]+)\s*:\s*([^:;]*)", style):
if not value:
continue
if prop.lower() in self.allowed_css_properties:
Expand All @@ -855,7 +855,7 @@ def sanitize_css(self, style):
'padding']:
for keyword in value.split():
if keyword not in self.allowed_css_keywords and \
not re.match("^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword): # noqa
not re.match(r"^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword): # noqa
break
else:
clean.append(prop + ': ' + value + ';')
Expand Down