def convert(self, oeb_book, output_path, input_plugin, opts, log):
from calibre.gui2 import must_use_qt, load_builtin_fonts
from calibre.ebooks.oeb.transforms.split import Split
# Turn off hinting in WebKit (requires a patched build of QtWebKit)
os.environ['CALIBRE_WEBKIT_NO_HINTING'] = '1'
self.filtered_font_warnings = set()
try:
# split on page breaks, as the JS code to convert page breaks to
# column breaks will not work because of QWebSettings.LocalContentCanAccessFileUrls
Split()(oeb_book, opts)
must_use_qt()
load_builtin_fonts()
self.oeb = oeb_book
self.input_plugin, self.opts, self.log = input_plugin, opts, log
self.output_path = output_path
from calibre.ebooks.oeb.base import OPF, OPF2_NS
from lxml import etree
from io import BytesIO
package = etree.Element(OPF('package'),
attrib={'version': '2.0', 'unique-identifier': 'dummy'},
nsmap={None: OPF2_NS})
from calibre.ebooks.metadata.opf2 import OPF
self.oeb.metadata.to_opf2(package)
self.metadata = OPF(BytesIO(etree.tostring(package))).to_book_metadata()
self.cover_data = None
if input_plugin.is_image_collection:
log.debug('Converting input as an image collection...')
self.convert_images(input_plugin.get_images())
else:
log.debug('Converting input as a text based book...')
self.convert_text(oeb_book)
finally:
os.environ.pop('CALIBRE_WEBKIT_NO_HINTING', None)
def convert(self, oeb, output_path, input_plugin, opts, log):
from calibre.ebooks.mobi.writer2.resources import Resources
from calibre.ebooks.mobi.writer8.main import create_kf8_book
from calibre.ebooks.mobi.writer8.cleanup import remove_duplicate_anchors
self.oeb, self.opts, self.log = oeb, opts, log
opts.mobi_periodical = self.is_periodical
passthrough = getattr(opts, 'mobi_passthrough', False)
remove_duplicate_anchors(oeb)
resources = Resources(self.oeb,
self.opts,
self.is_periodical,
add_fonts=True,
process_images=False)
if not passthrough:
remove_html_cover(self.oeb, self.log)
# Split on pagebreaks so that the resulting KF8 is faster to load
from calibre.ebooks.oeb.transforms.split import Split
Split()(self.oeb, self.opts)
kf8 = create_kf8_book(self.oeb, self.opts, resources, for_joint=False)
kf8.write(output_path)
extract_mobi(output_path, opts)
def convert(self, oeb, output_path, input_plugin, opts, log):
from calibre.ebooks.mobi.writer2.resources import Resources
self.log, self.opts, self.oeb = log, opts, oeb
mobi_type = opts.mobi_file_type
if self.is_periodical:
mobi_type = 'old' # Amazon does not support KF8 periodicals
create_kf8 = mobi_type in ('new', 'both')
remove_html_cover(self.oeb, self.log)
resources = Resources(oeb,
opts,
self.is_periodical,
add_fonts=create_kf8)
self.check_for_periodical()
if create_kf8:
from calibre.ebooks.mobi.writer8.cleanup import remove_duplicate_anchors
remove_duplicate_anchors(self.oeb)
# Split on pagebreaks so that the resulting KF8 is faster to load
from calibre.ebooks.oeb.transforms.split import Split
Split()(self.oeb, self.opts)
kf8 = self.create_kf8(resources, for_joint=mobi_type
== 'both') if create_kf8 else None
if mobi_type == 'new':
kf8.write(output_path)
extract_mobi(output_path, opts)
return
self.log('Creating MOBI 6 output')
self.write_mobi(input_plugin, output_path, kf8, resources)
def convert(self, oeb, output_path, opts, log):
from calibre.ebooks.mobi.writer2.resources import Resources
self.log, self.opts, self.oeb = log, opts, oeb
mobi_type = opts.mobi_file_type
if self.is_periodical:
mobi_type = 'old' # Amazon does not support KF8 periodicals
create_kf8 = mobi_type in ('new', 'both')
remove_html_cover(self.oeb, self.log)
resources = Resources(oeb,
opts,
self.is_periodical,
add_fonts=create_kf8,
process_images=opts.process_images)
self.check_for_periodical()
if create_kf8:
# Split on pagebreaks so that the resulting KF8 works better with
# calibre's viewer, which does not support CSS page breaks
from calibre.ebooks.oeb.transforms.split import Split
Split()(self.oeb, self.opts)
kf8 = self.create_kf8(resources, for_joint=mobi_type
== 'both') if create_kf8 else None
if mobi_type == 'new':
kf8.write(output_path)
extract_mobi(output_path, opts)
return
self.log.info('Creating MOBI 6 output')
self.write_mobi(output_path, kf8, resources)
def convert(self, oeb, output_path, input_plugin, opts, log):
from calibre.ebooks.mobi.writer2.resources import Resources
from calibre.ebooks.mobi.writer8.main import create_kf8_book
self.oeb, self.opts, self.log = oeb, opts, log
opts.mobi_periodical = self.is_periodical
passthrough = getattr(opts, 'mobi_passthrough', False)
resources = Resources(self.oeb,
self.opts,
self.is_periodical,
add_fonts=True,
process_images=False)
if not passthrough:
remove_html_cover(self.oeb, self.log)
# Split on pagebreaks so that the resulting KF8 works better with
# calibre's viewer, which does not support CSS page breaks
from calibre.ebooks.oeb.transforms.split import Split
Split()(self.oeb, self.opts)
kf8 = create_kf8_book(self.oeb, self.opts, resources, for_joint=False)
kf8.write(output_path)
extract_mobi(output_path, opts)
def convert(self, oeb, output_path, input_plugin, opts, log):
self.log, self.opts, self.oeb = log, opts, oeb
from calibre.ebooks.oeb.transforms.manglecase import CaseMangler
from calibre.ebooks.oeb.transforms.rasterize import SVGRasterizer
from calibre.ebooks.oeb.transforms.htmltoc import HTMLTOCAdder
from calibre.ebooks.lit.writer import LitWriter
from calibre.ebooks.oeb.transforms.split import Split
split = Split(split_on_page_breaks=True, max_flow_size=0,
remove_css_pagebreaks=False)
split(self.oeb, self.opts)
tocadder = HTMLTOCAdder()
tocadder(oeb, opts)
mangler = CaseMangler()
mangler(oeb, opts)
rasterizer = SVGRasterizer()
rasterizer(oeb, opts)
lit = LitWriter(self.opts)
lit(oeb, output_path)
def convert(self, oeb, output_path, input_plugin, opts, log):
self.log, self.opts, self.oeb = log, opts, oeb
if self.opts.epub_inline_toc:
from calibre.ebooks.mobi.writer8.toc import TOCAdder
opts.mobi_toc_at_start = not opts.epub_toc_at_end
opts.mobi_passthrough = False
opts.no_inline_toc = False
TOCAdder(oeb,
opts,
replace_previous_inline_toc=True,
ignore_existing_toc=True)
if self.opts.epub_flatten:
from calibre.ebooks.oeb.transforms.filenames import FlatFilenames
FlatFilenames()(oeb, opts)
else:
from calibre.ebooks.oeb.transforms.filenames import UniqueFilenames
UniqueFilenames()(oeb, opts)
self.workaround_ade_quirks()
self.workaround_webkit_quirks()
self.upshift_markup()
from calibre.ebooks.oeb.transforms.rescale import RescaleImages
RescaleImages(check_colorspaces=True)(oeb, opts)
from calibre.ebooks.oeb.transforms.split import Split
split = Split(not self.opts.dont_split_on_page_breaks,
max_flow_size=self.opts.flow_size * 1024)
split(self.oeb, self.opts)
from calibre.ebooks.oeb.transforms.cover import CoverManager
cm = CoverManager(
no_default_cover=self.opts.no_default_epub_cover,
no_svg_cover=self.opts.no_svg_cover,
preserve_aspect_ratio=self.opts.preserve_cover_aspect_ratio)
cm(self.oeb, self.opts, self.log)
self.workaround_sony_quirks()
if self.oeb.toc.count() == 0:
self.log.warn('This EPUB file has no Table of Contents. '
'Creating a default TOC')
first = next(iter(self.oeb.spine))
self.oeb.toc.add(_('Start'), first.href)
from calibre.ebooks.oeb.base import OPF
identifiers = oeb.metadata['identifier']
uuid = None
for x in identifiers:
if x.get(OPF('scheme'),
None).lower() == 'uuid' or str(x).startswith('urn:uuid:'):
uuid = str(x).split(':')[-1]
break
encrypted_fonts = getattr(input_plugin, 'encrypted_fonts', [])
if uuid is None:
self.log.warn('No UUID identifier found')
from uuid import uuid4
uuid = str(uuid4())
oeb.metadata.add('identifier', uuid, scheme='uuid', id=uuid)
if encrypted_fonts and not uuid.startswith('urn:uuid:'):
# Apparently ADE requires this value to start with urn:uuid:
# for some absurd reason, or it will throw a hissy fit and refuse
# to use the obfuscated fonts.
for x in identifiers:
if str(x) == uuid:
x.content = 'urn:uuid:' + uuid
with TemporaryDirectory('_epub_output') as tdir:
from calibre.customize.ui import plugin_for_output_format
metadata_xml = None
extra_entries = []
if self.is_periodical:
if self.opts.output_profile.epub_periodical_format == 'sony':
from calibre.ebooks.epub.periodical import sony_metadata
metadata_xml, atom_xml = sony_metadata(oeb)
extra_entries = [('atom.xml', 'application/atom+xml',
atom_xml)]
oeb_output = plugin_for_output_format('oeb')
oeb_output.convert(oeb, tdir, input_plugin, opts, log)
opf = [x for x in os.listdir(tdir) if x.endswith('.opf')][0]
self.condense_ncx([
os.path.join(tdir, x) for x in os.listdir(tdir)
if x.endswith('.ncx')
][0])
encryption = None
if encrypted_fonts:
encryption = self.encrypt_fonts(encrypted_fonts, tdir, uuid)
from calibre.ebooks.epub import initialize_container
with initialize_container(output_path,
os.path.basename(opf),
extra_entries=extra_entries) as epub:
epub.add_dir(tdir)
if encryption is not None:
epub.writestr('META-INF/encryption.xml', encryption)
if metadata_xml is not None:
epub.writestr('META-INF/metadata.xml',
metadata_xml.encode('utf-8'))
if opts.extract_to is not None:
from calibre.utils.zipfile import ZipFile
if os.path.exists(opts.extract_to):
if os.path.isdir(opts.extract_to):
shutil.rmtree(opts.extract_to)
else:
os.remove(opts.extract_to)
os.mkdir(opts.extract_to)
with ZipFile(output_path) as zf:
zf.extractall(path=opts.extract_to)
self.log.info('EPUB extracted to', opts.extract_to)
def convert(self, oeb, output_path, opts, log):
self.log, self.opts, self.oeb = log, opts, oeb
if self.opts.epub_flatten:
from calibre.ebooks.oeb.transforms.filenames import FlatFilenames
FlatFilenames()(oeb, opts)
else:
from calibre.ebooks.oeb.transforms.filenames import UniqueFilenames
UniqueFilenames()(oeb, opts)
self.workaround_ade_quirks()
self.workaround_webkit_quirks()
self.upshift_markup()
#from calibre.ebooks.oeb.transforms.rescale import RescaleImages
#RescaleImages()(oeb, opts)
from calibre.ebooks.oeb.transforms.split import Split
split = Split(not self.opts.dont_split_on_page_breaks,
max_flow_size=self.opts.flow_size * 1024)
split(self.oeb, self.opts)
#from calibre.ebooks.oeb.transforms.cover import CoverManager
#cm = CoverManager(
# no_default_cover=self.opts.no_default_epub_cover,
# no_svg_cover=self.opts.no_svg_cover,
# preserve_aspect_ratio=self.opts.preserve_cover_aspect_ratio)
#cm(self.oeb, self.opts, self.log)
self.workaround_sony_quirks()
if self.oeb.toc.count() == 0:
self.log.warn('This EPUB file has no Table of Contents. '
'Creating a default TOC')
first = iter(self.oeb.spine).next()
self.oeb.toc.add(_('Start'), first.href)
from calibre.ebooks.oeb.base import OPF_MIME, NCX_MIME, PAGE_MAP_MIME
results = oeb.to_opf2(page_map=True)
epub = zipfile.ZipFile(output_path, "w", zipfile.ZIP_STORED)
epub.writestr('mimetype', "application/epub+zip")
CONTAINER = u'''\
<?xml version="1.0"?>
<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
<rootfiles>
<rootfile full-path="{0}" media-type="application/oebps-package+xml"/>
</rootfiles>
</container>
'''
if hasattr(self.opts,
"epub_dont_compress") and self.opts.epub_dont_compress:
compress = zipfile.ZIP_STORED
else:
compress = zipfile.ZIP_DEFLATED
from lxml import etree
for key in (OPF_MIME, NCX_MIME, PAGE_MAP_MIME):
href, root = results.pop(key, [None, None])
if root is not None:
if key == OPF_MIME:
epub.writestr('META-INF/container.xml',
CONTAINER.format('OEBPS/%s' %
href).encode('utf-8'),
compress_type=compress)
raw = etree.tostring(root,
pretty_print=True,
encoding='utf-8',
xml_declaration=True)
epub.writestr('OEBPS/%s' % href, raw)
from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
for item in oeb.manifest:
if item.media_type in OEB_RASTER_IMAGES:
try:
img = self.process_image(str(item))
except:
self.log.warn('Bad image file %r.' % item.href)
else:
epub.writestr('OEBPS/%s' % item.href,
img,
compress_type=compress)
else:
epub.writestr('OEBPS/%s' % item.href,
str(item),
compress_type=compress)
