Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Work around for error when parsing malformed documents containing annotation-xml tags

Browse Source
This commit is contained in:
Kovid Goyal 2016-01-09 08:21:00 +05:30
parent fe84fd3519
commit a82ff8b749
1 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
src/html5lib/html5parser.py
View File

@ -155,10 +155,17 @@ class HTMLParser(object):
def isHTMLIntegrationPoint(self, element): def isHTMLIntegrationPoint(self, element):
if (element.name == "annotation-xml" and if (element.name == "annotation-xml" and
element.namespace == namespaces["mathml"]): element.namespace == namespaces["mathml"]):
return ("encoding" in element.attributes and try:
element.attributes["encoding"].translate( return ("encoding" in element.attributes and
asciiUpper2Lower) in element.attributes["encoding"].translate(
("text/html", "application/xhtml+xml")) asciiUpper2Lower) in
("text/html", "application/xhtml+xml"))
except TypeError:
# This happens for some documents, for some reason
# lxml refuses to store a unicode representation of the
# encoding attribute.
return element.attributes["encoding"].lower().decode('utf-8', 'replace') in (
"text/html", "application/xhtml+xml")
else: else:
return (element.namespace, element.name) in htmlIntegrationPointElements return (element.namespace, element.name) in htmlIntegrationPointElements