Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

FB2 Output: Check image is in document and manifest before referencing and writing.

Browse Source
This commit is contained in:
John Schember 2010-12-04 22:04:37 -05:00
parent 1f7c291aeb
commit 0ea35abaf1
1 changed files with 15 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
src/calibre/ebooks/fb2/fb2ml.py
View File

@ -145,8 +145,14 @@ class FB2MLizer(object):
return ''.join(text) + '</body>' return ''.join(text) + '</body>'
def fb2mlize_images(self): def fb2mlize_images(self):
'''
This function uses the self.image_hrefs dictionary mapping. It is populated by the dump_text function.
'''
images = [] images = []
for item in self.oeb_book.manifest: for item in self.oeb_book.manifest:
# Don't write the image if it's not referenced in the document's text.
if item.href not in self.image_hrefs:
continue
if item.media_type in OEB_RASTER_IMAGES: if item.media_type in OEB_RASTER_IMAGES:
try: try:
im = Image.open(cStringIO.StringIO(item.data)).convert('RGB') im = Image.open(cStringIO.StringIO(item.data)).convert('RGB')
@ -164,7 +170,7 @@ class FB2MLizer(object):
col = 1 col = 1
col += 1 col += 1
data += char data += char
images.append('<binary id="%s" content-type="%s">%s\n</binary>' % (self.image_hrefs.get(item.href, '_0000.JPEG'), item.media_type, data)) images.append('<binary id="%s" content-type="%s">%s\n</binary>' % (self.image_hrefs[item.href], item.media_type, data))
except Exception as e: except Exception as e:
self.log.error('Error: Could not include file %s because ' \ self.log.error('Error: Could not include file %s because ' \
'%s.' % (item.href, e)) '%s.' % (item.href, e))
@ -245,14 +251,15 @@ class FB2MLizer(object):
fb2_out.append('<title>') fb2_out.append('<title>')
tags.append('title') tags.append('title')
if tag == 'img': if tag == 'img':
# TODO: Check that the image is in the manifest and only write the tag if it is.
if elem_tree.attrib.get('src', None): if elem_tree.attrib.get('src', None):
if page.abshref(elem_tree.attrib['src']) not in self.image_hrefs.keys(): # Only write the image tag if it is in the manifest.
self.image_hrefs[page.abshref(elem_tree.attrib['src'])] = '_%s.jpg' % len(self.image_hrefs.keys()) if page.abshref(elem_tree.attrib['src']) in self.oeb_book.manifest.hrefs.keys():
p_txt, p_tag = self.ensure_p() if page.abshref(elem_tree.attrib['src']) not in self.image_hrefs.keys():
fb2_out += p_txt self.image_hrefs[page.abshref(elem_tree.attrib['src'])] = '_%s.jpg' % len(self.image_hrefs.keys())
tags += p_tag p_txt, p_tag = self.ensure_p()
fb2_out.append('<image xlink:href="#%s" />' % self.image_hrefs[page.abshref(elem_tree.attrib['src'])]) fb2_out += p_txt
tags += p_tag
fb2_out.append('<image xlink:href="#%s" />' % self.image_hrefs[page.abshref(elem_tree.attrib['src'])])
elif tag == 'br': elif tag == 'br':
if self.in_p: if self.in_p:
closed_tags = [] closed_tags = []