yul
/
bookwyrm-mastodon
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Tests and fixes whitespace bugs in sanitizer

This commit is contained in:
Mouse Reeve 2020-05-09 18:30:24 -07:00
parent ab7acc6db6
commit db898e362b
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
fedireads/sanitize_html.py
View File

@ -19,19 +19,19 @@ class InputHtmlParser(HTMLParser):
self.output.append(('tag', self.get_starttag_text())) self.output.append(('tag', self.get_starttag_text()))
self.tag_stack.append(tag) self.tag_stack.append(tag)
else: else:
self.output.append(('data', ' ')) self.output.append(('data', ''))
def handle_endtag(self, tag): def handle_endtag(self, tag):
''' keep the close tag ''' ''' keep the close tag '''
if not self.allow_html or tag not in self.whitelist: if not self.allow_html or tag not in self.whitelist:
self.output.append(('data', ' ')) self.output.append(('data', ''))
return return
if not self.tag_stack or self.tag_stack[-1] != tag: if not self.tag_stack or self.tag_stack[-1] != tag:
# the end tag doesn't match the most recent start tag # the end tag doesn't match the most recent start tag
self.allow_html = False self.allow_html = False
self.output.append(('data', ' ')) self.output.append(('data', ''))
return return
self.tag_stack = self.tag_stack[:-1] self.tag_stack = self.tag_stack[:-1]
@ -45,6 +45,8 @@ class InputHtmlParser(HTMLParser):
def get_output(self): def get_output(self):
''' convert the output from a list of tuples to a string ''' ''' convert the output from a list of tuples to a string '''
if self.tag_stack:
self.allow_html = False
if not self.allow_html: if not self.allow_html:
return ''.join(v for (k, v) in self.output if k == 'data') return ''.join(v for (k, v) in self.output if k == 'data')
return ''.join(v for (k, v) in self.output) return ''.join(v for (k, v) in self.output)