Closed
Description
This snippet works in 0.999 but not in 0.9999
from html5lib import HTMLParser, sanitizer, serializer, treebuilders, treewalkers
opts = {}
opts['tokenizer'] = sanitizer.HTMLSanitizer
parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"), **opts)
data = u'Hello World<img src="/static/cms/img/icons/plugins/link.png" alt="Link - A Link" title="Link - A Link" id="plugin_obj_2" />'
dom_tree = parser.parseFragment(data)
walker = treewalkers.getTreeWalker("dom")
stream = walker(dom_tree)
s = serializer.htmlserializer.HTMLSerializer()
text = ''.join(s.serialize(stream))
assert text == data
Issue is not present when not using the sanitiser