Backup_Repos/calibre
1
0
Fork 0
mirror of git://github.com/kovidgoyal/calibre.git synced 2026-02-02 07:33:35 +01:00
Code Issues Projects Releases Wiki Activity

Fix #5991 (Import of HTML With Embedded Stylesheet Broken In 0.7.5)

Browse source
This commit is contained in:
Kovid Goyal 2010-06-26 19:48:36 -06:00
parent 5e25f706d2
commit ce736fa6ea
1 changed files with 9 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
src/calibre/ebooks/oeb/base.py
View file

@ -7,7 +7,7 @@
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
__docformat__ = 'restructuredtext en'
import os, re, uuid, logging, functools
import os, re, uuid, logging
from mimetypes import types_map
from collections import defaultdict
from itertools import count
@ -808,17 +808,17 @@ def _parse_xhtml(self, data):
pat = re.compile(r'&(%s);'%('|'.join(user_entities.keys())))
data = pat.sub(lambda m:user_entities[m.group(1)], data)
fromstring = functools.partial(etree.fromstring, parser=RECOVER_PARSER)
parser = etree.XMLParser(no_network=True, huge_tree=True)
# Try with more & more drastic measures to parse
def first_pass(data):
try:
data = fromstring(data)
data = etree.fromstring(data, parser=parser)
except etree.XMLSyntaxError, err:
self.oeb.log.exception('Initial parse failed:')
repl = lambda m: ENTITYDEFS.get(m.group(1), m.group(0))
data = ENTITY_RE.sub(repl, data)
try:
data = fromstring(data)
data = etree.fromstring(data, parser=parser)
except etree.XMLSyntaxError, err:
self.oeb.logger.warn('Parsing file %r as HTML' % self.href)
if err.args and err.args[0].startswith('Excessive depth'):
@ -832,9 +832,9 @@ def first_pass(data):
elem.text = elem.text.strip('-')
data = etree.tostring(data, encoding=unicode)
try:
data = fromstring(data)
data = etree.fromstring(data, parser=parser)
except etree.XMLSyntaxError:
data = fromstring(data)
data = etree.fromstring(data, parser=RECOVER_PARSER)
return data
data = first_pass(data)
@ -866,12 +866,12 @@ def first_pass(data):
data = etree.tostring(data, encoding=unicode)
try:
data = fromstring(data)
data = etree.fromstring(data, parser=parser)
except:
data = data.replace(':=', '=').replace(':>', '>')
data = data.replace('<http:/>', '')
try:
data = fromstring(data)
data = etree.fromstring(data, parser=parser)
except etree.XMLSyntaxError:
self.oeb.logger.warn('Stripping comments and meta tags from %s'%
self.href)
@ -882,7 +882,7 @@ def first_pass(data):
"<?xml version='1.0' encoding='utf-8'?><o:p></o:p>",
'')
data = data.replace("<?xml version='1.0' encoding='utf-8'??>", '')
data = fromstring(data)
data = etree.fromstring(data)
elif namespace(data.tag) != XHTML_NS:
# OEB_DOC_NS, but possibly others
ns = namespace(data.tag)