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

Use same decoding logic for OPF as for (X)HTML.

Browse Source
This commit is contained in:
Marshall T. Vandegrift 2009-02-02 11:46:52 -05:00
parent 7b2064221e
commit cecfa09b95
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/calibre/ebooks/oeb/base.py
View File

@ -1009,13 +1009,16 @@ class OEBBook(object):
return nroot return nroot
def _read_opf(self, opfpath): def _read_opf(self, opfpath):
opf = self.container.read(opfpath) data = self.container.read(opfpath)
data = self.decode(data)
data = XMLDECL_RE.sub('', data)
data = data.replace('\r\n', '\n').replace('\r', '\n')
try: try:
opf = etree.fromstring(opf) opf = etree.fromstring(data)
except etree.XMLSyntaxError: except etree.XMLSyntaxError:
repl = lambda m: ENTITYDEFS.get(m.group(1), m.group(0)) repl = lambda m: ENTITYDEFS.get(m.group(1), m.group(0))
opf = ENTITY_RE.sub(repl, opf) data = ENTITY_RE.sub(repl, data)
opf = etree.fromstring(opf) opf = etree.fromstring(data)
self.logger.warn('OPF contains invalid HTML named entities') self.logger.warn('OPF contains invalid HTML named entities')
ns = namespace(opf.tag) ns = namespace(opf.tag)
if ns not in ('', OPF1_NS, OPF2_NS): if ns not in ('', OPF1_NS, OPF2_NS):