def remove_first_image(self):
deleted_item = None
for item in self.oeb.spine:
if XPath(JACKET_XPATH)(item.data):
continue
removed = self.remove_images(item)
if removed > 0:
self.log('Removed first image')
body = XPath('//h:body')(item.data)
if body:
raw = xml2text(body[0]).strip()
imgs = XPath('//h:img|//svg:svg')(item.data)
if not raw and not imgs:
self.log('Removing %s as it has no content'%item.href)
self.oeb.manifest.remove(item)
deleted_item = item
break
else:
self.log.warn('Could not find first image to remove')
if deleted_item is not None:
for item in list(self.oeb.toc):
href = urldefrag(item.href)[0]
if href == deleted_item.href:
self.oeb.toc.remove(item)
self.oeb.guide.remove_by_href(deleted_item.href)
def remove_first_image(self):
deleted_item = None
for item in self.oeb.spine:
if XPath(JACKET_XPATH)(item.data):
continue
removed = self.remove_images(item)
if removed > 0:
self.log('Removed first image')
body = XPath('//h:body')(item.data)
if body:
raw = xml2text(body[0]).strip()
imgs = XPath('//h:img|//svg:svg')(item.data)
if not raw and not imgs:
self.log('Removing %s as it has no content' %
item.href)
self.oeb.manifest.remove(item)
deleted_item = item
break
else:
self.log.warn('Could not find first image to remove')
if deleted_item is not None:
for item in list(self.oeb.toc):
href = urldefrag(item.href)[0]
if href == deleted_item.href:
self.oeb.toc.remove(item)
self.oeb.guide.remove_by_href(deleted_item.href)
def fix_toc_entry(toc):
if toc.href:
href, frag = urldefrag(toc.href)
if href == self.item.href:
nhref = self.anchor_map[frag if frag else None]
if frag:
nhref = '#'.join((nhref, frag))
toc.href = nhref
for x in toc:
fix_toc_entry(x)
def fix_toc_entry(toc):
if toc.href:
href, frag = urldefrag(toc.href)
if href == self.item.href:
nhref = self.anchor_map[frag if frag else None]
if frag:
nhref = '#'.join((nhref, frag))
toc.href = nhref
for x in toc:
fix_toc_entry(x)
def simplify_toc_entry(toc):
if toc.href:
href, frag = urldefrag(toc.href)
if frag:
for x in self.oeb.spine:
if x.href == href:
if frag_is_at_top(x.data, frag):
self.log.debug("Removing anchor from TOC href:", href + "#" + frag)
toc.href = href
break
for x in toc:
simplify_toc_entry(x)
def simplify_toc_entry(toc):
if toc.href:
href, frag = urldefrag(toc.href)
if frag:
for x in self.oeb.spine:
if x.href == href:
if frag_is_at_top(x.data, frag):
self.log.debug('Removing anchor from TOC href:',
href+'#'+frag)
toc.href = href
break
for x in toc:
simplify_toc_entry(x)
def insert_cover(self):
from calibre.ebooks.oeb.base import urldefrag
g, m = self.oeb.guide, self.oeb.manifest
item = None
if 'titlepage' not in g:
if 'cover' in g:
href = g['cover'].href
else:
href = self.default_cover()
if href is None:
return
width, height = self.inspect_cover(href)
if width is None or height is None:
self.log.warning('Failed to read cover dimensions')
width, height = 600, 800
#if self.preserve_aspect_ratio:
# width, height = 600, 800
self.svg_template = self.svg_template.replace(
'__viewbox__', '0 0 %d %d' % (width, height))
self.svg_template = self.svg_template.replace(
'__width__', str(width))
self.svg_template = self.svg_template.replace(
'__height__', str(height))
if href is not None:
templ = self.non_svg_template if self.no_svg_cover \
else self.svg_template
tp = templ % unquote(href)
id, href = m.generate('titlepage', u'titlepage.xhtml')
item = m.add(id,
href,
guess_type('t.xhtml')[0],
data=etree.fromstring(tp))
else:
item = self.oeb.manifest.hrefs[urldefrag(
self.oeb.guide['titlepage'].href)[0]]
if item is not None:
self.oeb.spine.insert(0, item, False)
if 'cover' not in self.oeb.guide.refs:
self.oeb.guide.add('cover', 'Title Page', 'a')
self.oeb.guide.refs['cover'].href = item.href
if 'titlepage' in self.oeb.guide.refs:
self.oeb.guide.refs['titlepage'].href = item.href
titem = getattr(self.oeb.toc, 'item_that_refers_to_cover', None)
if titem is not None:
titem.href = item.href
def rewrite_links(self, url):
href, frag = urldefrag(url)
try:
href = self.current_item.abshref(href)
except ValueError:
# Unparseable URL
return url
href = urlnormalize(href)
if href in self.map:
anchor_map = self.map[href]
nhref = anchor_map[frag if frag else None]
nhref = self.current_item.relhref(nhref)
if frag:
nhref = '#'.join((urlunquote(nhref), frag))
return nhref
return url
def rewrite_links(self, url):
href, frag = urldefrag(url)
try:
href = self.current_item.abshref(href)
except ValueError:
# Unparseable URL
return url
href = urlnormalize(href)
if href in self.map:
anchor_map = self.map[href]
nhref = anchor_map[frag if frag else None]
nhref = self.current_item.relhref(nhref)
if frag:
nhref = '#'.join((urlunquote(nhref), frag))
return nhref
return url
def insert_cover(self):
from calibre.ebooks.oeb.base import urldefrag
g, m = self.oeb.guide, self.oeb.manifest
item = None
if 'titlepage' not in g:
if 'cover' in g:
href = g['cover'].href
else:
href = self.default_cover()
if href is None:
return
width, height = self.inspect_cover(href)
if width is None or height is None:
self.log.warning('Failed to read cover dimensions')
width, height = 600, 800
# if self.preserve_aspect_ratio:
# width, height = 600, 800
self.svg_template = self.svg_template.replace('__viewbox__',
'0 0 %d %d'%(width, height))
self.svg_template = self.svg_template.replace('__width__',
str(width))
self.svg_template = self.svg_template.replace('__height__',
str(height))
if href is not None:
templ = self.non_svg_template if self.no_svg_cover \
else self.svg_template
tp = templ%unquote(href)
id, href = m.generate('titlepage', u'titlepage.xhtml')
item = m.add(id, href, guess_type('t.xhtml')[0],
data=etree.fromstring(tp))
else:
item = self.oeb.manifest.hrefs[
urldefrag(self.oeb.guide['titlepage'].href)[0]]
if item is not None:
self.oeb.spine.insert(0, item, True)
if 'cover' not in self.oeb.guide.refs:
self.oeb.guide.add('cover', 'Title Page', 'a')
self.oeb.guide.refs['cover'].href = item.href
if 'titlepage' in self.oeb.guide.refs:
self.oeb.guide.refs['titlepage'].href = item.href
titem = getattr(self.oeb.toc, 'item_that_refers_to_cover', None)
if titem is not None:
titem.href = item.href
def remove_first_image(self):
deleted_item = None
for item in self.oeb.spine:
removed = self.remove_images(item)
if removed > 0:
self.log('Removed first image')
body = XPath('//h:body')(item.data)
if body:
raw = xml2text(body[0]).strip()
imgs = XPath('//h:img|//svg:svg')(item.data)
if not raw and not imgs:
self.log('Removing %s as it has no content'%item.href)
self.oeb.manifest.remove(item)
deleted_item = item
break
if deleted_item is not None:
for item in list(self.oeb.toc):
href = urldefrag(item.href)[0]
if href == deleted_item.href:
self.oeb.toc.remove(item)
def remove_first_image(self):
deleted_item = None
for item in self.oeb.spine:
removed = self.remove_images(item)
if removed > 0:
self.log('Removed first image')
body = XPath('//h:body')(item.data)
if body:
raw = xml2text(body[0]).strip()
imgs = XPath('//h:img|//svg:svg')(item.data)
if not raw and not imgs:
self.log('Removing %s as it has no content'%item.href)
self.oeb.manifest.remove(item)
deleted_item = item
break
if deleted_item is not None:
for item in list(self.oeb.toc):
href = urldefrag(item.href)[0]
if href == deleted_item.href:
self.oeb.toc.remove(item)
def commit(self):
'''
Commit all changes caused by the split. Calculates an *anchor_map* for
all anchors in the original tree. Internal links are re-directed. The
original file is deleted and the split files are saved.
'''
if not self.was_split:
return
self.anchor_map = collections.defaultdict(lambda :self.base%0)
self.files = []
for i, tree in enumerate(self.trees):
root = tree.getroot()
self.files.append(self.base%i)
for elem in root.xpath('//*[@id or @name]'):
for anchor in elem.get('id', ''), elem.get('name', ''):
if anchor != '' and anchor not in self.anchor_map:
self.anchor_map[anchor] = self.files[-1]
for elem in root.xpath('//*[@%s]'%SPLIT_POINT_ATTR):
elem.attrib.pop(SPLIT_POINT_ATTR, '0')
spine_pos = self.item.spine_position
for current, tree in zip(*map(reversed, (self.files, self.trees))):
for a in tree.getroot().xpath('//h:a[@href]', namespaces=NAMESPACES):
href = a.get('href').strip()
if href.startswith('#'):
anchor = href[1:]
file = self.anchor_map[anchor]
file = self.item.relhref(file)
if file != current:
a.set('href', file+href)
new_id = self.oeb.manifest.generate(id=self.item.id)[0]
new_item = self.oeb.manifest.add(new_id, current,
self.item.media_type, data=tree.getroot())
self.oeb.spine.insert(spine_pos, new_item, self.item.linear)
if self.oeb.guide:
for ref in self.oeb.guide.values():
href, frag = urldefrag(ref.href)
if href == self.item.href:
nhref = self.anchor_map[frag if frag else None]
if frag:
nhref = '#'.join((nhref, frag))
ref.href = nhref
def fix_toc_entry(toc):
if toc.href:
href, frag = urldefrag(toc.href)
if href == self.item.href:
nhref = self.anchor_map[frag if frag else None]
if frag:
nhref = '#'.join((nhref, frag))
toc.href = nhref
for x in toc:
fix_toc_entry(x)
if self.oeb.toc:
fix_toc_entry(self.oeb.toc)
if self.oeb.pages:
for page in self.oeb.pages:
href, frag = urldefrag(page.href)
if href == self.item.href:
nhref = self.anchor_map[frag if frag else None]
if frag:
nhref = '#'.join((nhref, frag))
page.href = nhref
self.oeb.manifest.remove(self.item)
def commit(self):
'''
Commit all changes caused by the split. Calculates an *anchor_map* for
all anchors in the original tree. Internal links are re-directed. The
original file is deleted and the split files are saved.
'''
if not self.was_split:
return
self.anchor_map = collections.defaultdict(lambda: self.base % 0)
self.files = []
for i, tree in enumerate(self.trees):
root = tree.getroot()
self.files.append(self.base % i)
for elem in root.xpath('//*[@id or @name]'):
for anchor in elem.get('id', ''), elem.get('name', ''):
if anchor != '' and anchor not in self.anchor_map:
self.anchor_map[anchor] = self.files[-1]
for elem in root.xpath('//*[@%s]' % SPLIT_POINT_ATTR):
elem.attrib.pop(SPLIT_POINT_ATTR, '0')
spine_pos = self.item.spine_position
for current, tree in zip(
*list(map(reversed, (self.files, self.trees)))):
for a in tree.getroot().xpath('//h:a[@href]',
namespaces=NAMESPACES):
href = a.get('href').strip()
if href.startswith('#'):
anchor = href[1:]
file = self.anchor_map[anchor]
file = self.item.relhref(file)
if file != current:
a.set('href', file + href)
new_id = self.oeb.manifest.generate(id=self.item.id)[0]
new_item = self.oeb.manifest.add(new_id,
current,
self.item.media_type,
data=tree.getroot())
self.oeb.spine.insert(spine_pos, new_item, self.item.linear)
if self.oeb.guide:
for ref in list(self.oeb.guide.values()):
href, frag = urldefrag(ref.href)
if href == self.item.href:
nhref = self.anchor_map[frag if frag else None]
if frag:
nhref = '#'.join((nhref, frag))
ref.href = nhref
def fix_toc_entry(toc):
if toc.href:
href, frag = urldefrag(toc.href)
if href == self.item.href:
nhref = self.anchor_map[frag if frag else None]
if frag:
nhref = '#'.join((nhref, frag))
toc.href = nhref
for x in toc:
fix_toc_entry(x)
if self.oeb.toc:
fix_toc_entry(self.oeb.toc)
if self.oeb.pages:
for page in self.oeb.pages:
href, frag = urldefrag(page.href)
if href == self.item.href:
nhref = self.anchor_map[frag if frag else None]
if frag:
nhref = '#'.join((nhref, frag))
page.href = nhref
self.oeb.manifest.remove(self.item)