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 #2612 (AttributeError: 'str' object has no attribute 'xpath')

Browse Source
This commit is contained in:
Kovid Goyal 2009-06-17 15:04:52 -07:00
parent d96ad4bfe5
commit 19a05d4d4f
3 changed files with 43 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -370,7 +370,7 @@ class ManifestItem(object):
def __init__(self, original, internal, mime_type, offset, root, state):
self.original = original
self.internal = internal
self.mime_type = mime_type
self.mime_type = mime_type.lower() if hasattr(mime_type, 'lower') else mime_type
self.offset = offset
self.root = root
self.state = state

43
src/calibre/ebooks/oeb/base.py
View File

@ -849,6 +849,38 @@ class Manifest(object):
return data
def _parse_txt(self, data):
if '<html>' in data:
return self._parse_xhtml(data)
from xml.sax.saxutils import escape
self.oeb.log.debug('Converting', self.href, '...')
paras = []
lines = []
for l in data.splitlines():
if not l:
if lines:
paras.append('<p>'+'\n'.join(lines)+'</p>')
lines = []
lines.append(escape(l))
if lines:
paras.append('<p>'+'\n'.join(lines)+'</p>')
title = self.oeb.metadata.title
if title:
title = unicode(title[0])
else:
title = 'No title'
data = '''\
<html>
<head><title>%s</title></head>
<body>%s</body>
</html>
'''%(title, '\n'.join(paras))
data = self._parse_xhtml(data)
print etree.tostring(data)
return data
def _parse_css(self, data):
self.oeb.log.debug('Parsing', self.href, '...')
data = self.oeb.decode(data)
@ -895,12 +927,17 @@ class Manifest(object):
data = self._loader(self.href)
if not isinstance(data, basestring):
pass # already parsed
elif self.media_type in OEB_DOCS:
elif self.media_type.lower() in OEB_DOCS:
data = self._parse_xhtml(data)
elif self.media_type[-4:] in ('+xml', '/xml'):
elif self.media_type.lower()[-4:] in ('+xml', '/xml'):
data = etree.fromstring(data)
elif self.media_type in OEB_STYLES:
elif self.media_type.lower() in OEB_STYLES:
data = self._parse_css(data)
elif 'text' in self.media_type.lower():
self.oeb.log.warn('%s contains data in TXT format'%self.href,
'converting to HTML')
data = self._parse_txt(data)
self.media_type = XHTML_MIME
self._data = data
return data
def fset(self, value):

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

@ -247,6 +247,8 @@ class OEBReader(object):
if media_type is None or media_type == 'text/xml':
guessed = guess_type(href)[0]
media_type = guessed or media_type or BINARY_MIME
if hasattr(media_type, 'lower'):
media_type = media_type.lower()
fallback = elem.get('fallback')
if href in manifest.hrefs:
self.logger.warn(u'Duplicate manifest entry for %r' % href)