Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

EPUB Input: Fix handling of EPUB files that contain images with non-ascii filenames. Fixes #1171186 (Private bug)

Browse Source
This commit is contained in:
Kovid Goyal 2013-04-22 18:23:36 +05:30
parent 763c921108
commit 6dbd826c51
3 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -1,7 +1,6 @@
'''
Basic support for manipulating OEB 1.x/2.0 content and metadata.
'''
from __future__ import with_statement
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
@ -11,7 +10,7 @@ import os, re, uuid, logging
from collections import defaultdict
from itertools import count
from urlparse import urldefrag, urlparse, urlunparse, urljoin
from urllib import unquote as urlunquote
from urllib import unquote
from lxml import etree, html
from calibre.constants import filesystem_encoding, __version__
@ -372,6 +371,19 @@ def urlquote(href):
result.append(char)
return ''.join(result)
def urlunquote(href):
# unquote must run on a bytestring and will return a bytestring
# If it runs on a unicode object, it returns a double encoded unicode
# string: unquote(u'%C3%A4') != unquote(b'%C3%A4').decode('utf-8')
# and the latter is correct
want_unicode = isinstance(href, unicode)
if want_unicode:
href = href.encode('utf-8')
href = unquote(href)
if want_unicode:
href = href.decode('utf-8')
return href
def urlnormalize(href):
"""Convert a URL into normalized form, with all and only URL-unsafe
characters URL quoted.
@ -468,7 +480,7 @@ class DirContainer(object):
return
def _unquote(self, path):
# urlunquote must run on a bytestring and will return a bytestring
# unquote must run on a bytestring and will return a bytestring
# If it runs on a unicode object, it returns a double encoded unicode
# string: unquote(u'%C3%A4') != unquote(b'%C3%A4').decode('utf-8')
# and the latter is correct

2
src/calibre/ebooks/oeb/reader.py
View File

@ -196,6 +196,8 @@ class OEBReader(object):
item.media_type[-4:] in ('/xml', '+xml')):
hrefs = [r[2] for r in iterlinks(data)]
for href in hrefs:
if isinstance(href, bytes):
href = href.decode('utf-8')
href, _ = urldefrag(href)
if not href:
continue

2
src/calibre/ebooks/oeb/transforms/trimmanifest.py
View File

@ -47,6 +47,8 @@ class ManifestTrimmer(object):
item.data is not None:
hrefs = [r[2] for r in iterlinks(item.data)]
for href in hrefs:
if isinstance(href, bytes):
href = href.decode('utf-8')
try:
href = item.abshref(urlnormalize(href))
except: