Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix a couple of things I forgot to merge from upstream html5lib

Browse Source
This commit is contained in:
Kovid Goyal 2015-11-04 20:24:57 +05:30
parent 424a430d15
commit dbb4092b35
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/html5lib/sanitizer.py
View File

@ -212,7 +212,7 @@ class HTMLSanitizerMixin(object):
# remove replacement characters from unescaped characters # remove replacement characters from unescaped characters
val_unescaped = val_unescaped.replace("\ufffd", "") val_unescaped = val_unescaped.replace("\ufffd", "")
try: try:
uri = urlparse.urlparse(val_unescaped) uri = urlparse(val_unescaped)
except ValueError: except ValueError:
uri = None uri = None
del attrs[attr] del attrs[attr]
@ -291,11 +291,11 @@ class HTMLSanitizerMixin(object):
class HTMLSanitizer(HTMLTokenizer, HTMLSanitizerMixin): class HTMLSanitizer(HTMLTokenizer, HTMLSanitizerMixin):
def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True, def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
lowercaseElementName=False, lowercaseAttrName=False, parser=None): lowercaseElementName=False, lowercaseAttrName=False, parser=None, track_positions=False):
# Change case matching defaults as we only output lowercase html anyway # Change case matching defaults as we only output lowercase html anyway
# This solution doesn't seem ideal... # This solution doesn't seem ideal...
HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet, HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
lowercaseElementName, lowercaseAttrName, parser=parser) lowercaseElementName, lowercaseAttrName, parser=parser, track_positions=track_positions)
def __iter__(self): def __iter__(self):
for token in HTMLTokenizer.__iter__(self): for token in HTMLTokenizer.__iter__(self):