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

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 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>' __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import os, re, uuid, logging, functools import os, re, uuid, logging
from mimetypes import types_map from mimetypes import types_map
from collections import defaultdict from collections import defaultdict
from itertools import count from itertools import count
@ -808,17 +808,17 @@ class Manifest(object):
pat = re.compile(r'&(%s);'%('|'.join(user_entities.keys()))) pat = re.compile(r'&(%s);'%('|'.join(user_entities.keys())))
data = pat.sub(lambda m:user_entities[m.group(1)], data) 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 # Try with more & more drastic measures to parse
def first_pass(data): def first_pass(data):
try: try:
data = fromstring(data) data = etree.fromstring(data, parser=parser)
except etree.XMLSyntaxError, err: except etree.XMLSyntaxError, err:
self.oeb.log.exception('Initial parse failed:') self.oeb.log.exception('Initial parse failed:')
repl = lambda m: ENTITYDEFS.get(m.group(1), m.group(0)) repl = lambda m: ENTITYDEFS.get(m.group(1), m.group(0))
data = ENTITY_RE.sub(repl, data) data = ENTITY_RE.sub(repl, data)
try: try:
data = fromstring(data) data = etree.fromstring(data, parser=parser)
except etree.XMLSyntaxError, err: except etree.XMLSyntaxError, err:
self.oeb.logger.warn('Parsing file %r as HTML' % self.href) self.oeb.logger.warn('Parsing file %r as HTML' % self.href)
if err.args and err.args[0].startswith('Excessive depth'): if err.args and err.args[0].startswith('Excessive depth'):
@ -832,9 +832,9 @@ class Manifest(object):
elem.text = elem.text.strip('-') elem.text = elem.text.strip('-')
data = etree.tostring(data, encoding=unicode) data = etree.tostring(data, encoding=unicode)
try: try:
data = fromstring(data) data = etree.fromstring(data, parser=parser)
except etree.XMLSyntaxError: except etree.XMLSyntaxError:
data = fromstring(data) data = etree.fromstring(data, parser=RECOVER_PARSER)
return data return data
data = first_pass(data) data = first_pass(data)
@ -866,12 +866,12 @@ class Manifest(object):
data = etree.tostring(data, encoding=unicode) data = etree.tostring(data, encoding=unicode)
try: try:
data = fromstring(data) data = etree.fromstring(data, parser=parser)
except: except:
data = data.replace(':=', '=').replace(':>', '>') data = data.replace(':=', '=').replace(':>', '>')
data = data.replace('<http:/>', '') data = data.replace('<http:/>', '')
try: try:
data = fromstring(data) data = etree.fromstring(data, parser=parser)
except etree.XMLSyntaxError: except etree.XMLSyntaxError:
self.oeb.logger.warn('Stripping comments and meta tags from %s'% self.oeb.logger.warn('Stripping comments and meta tags from %s'%
self.href) self.href)
@ -882,7 +882,7 @@ class Manifest(object):
"<?xml version='1.0' encoding='utf-8'?><o:p></o:p>", "<?xml version='1.0' encoding='utf-8'?><o:p></o:p>",
'') '')
data = data.replace("<?xml version='1.0' encoding='utf-8'??>", '') data = data.replace("<?xml version='1.0' encoding='utf-8'??>", '')
data = fromstring(data) data = etree.fromstring(data)
elif namespace(data.tag) != XHTML_NS: elif namespace(data.tag) != XHTML_NS:
# OEB_DOC_NS, but possibly others # OEB_DOC_NS, but possibly others
ns = namespace(data.tag) ns = namespace(data.tag)