def pretty_html(container, name, raw):
"""
Pretty print the HTML represented as a string in raw
"""
root = container.parse_xhtml(raw)
pretty_html_tree(container, root)
return base.serialize(root, 'text/html')
def fix_html(container, raw):
"""
Fix any parsing errors in the HTML represented as a string in raw. Fixing
is done using the HTML5 parsing algorithm.
"""
root = container.parse_xhtml(raw)
return base.serialize(root, 'text/html')
def create_inline_toc(container, title=None):
"""
Create an inline (HTML) Table of Contents from an existing NCX Table of
Contents.
:param title: The title for this table of contents.
"""
lang = get_book_language(container)
default_title = 'Table of Contents'
title = title or default_title
toc = get_toc(container)
if len(toc) == 0:
return None
toc_name = find_inline_toc(container)
name = toc_name
html = toc_to_html(toc, container, name, title, lang)
raw = base.serialize(html, 'text/html')
if name is None:
name, c = 'toc.xhtml', 0
while container.has_name(name):
c += 1
name = 'toc%d.xhtml' % c
container.add_file(name, raw, spine_index=0)
else:
with container.open(name, 'wb') as f:
f.write(raw)
set_guide_item(container,
'toc',
title,
name,
frag='calibre_generated_inline_toc')
return name
def pretty_xml(container, name, raw):
"""
Pretty print the XML represented as a string in raw. If ``name`` is the
name of the OPF, extra OPF-specific prettying is performed.
"""
root = container.parse_xml(raw)
if name == container.opf_name:
pretty_opf(root)
pretty_xml_tree(root)
return base.serialize(root, 'text/xml')
def pretty_css(container, name, raw):
"""
Pretty print the CSS represented as a string in raw
"""
sheet = container.parse_css(raw)
return base.serialize(sheet, 'text/css')
def convert_epub3_nav(self, nav_path, opf, log, opts):
from lxml import etree
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.ebooks.oeb.polish.parsing import parse
from ebook_converter.ebooks.oeb.base import \
serialize
from ebook_converter.ebooks.oeb.polish.toc import first_child
from tempfile import NamedTemporaryFile
with open(nav_path, 'rb') as f:
raw = f.read()
raw = xml_to_unicode(raw, strip_encoding_pats=True,
assume_utf8=True)[0]
root = parse(raw, log=log)
ncx = etree.fromstring('<ncx xmlns="http://www.daisy.org/z3986/2005/'
'ncx/" version="2005-1" xml:lang="eng">'
'<navMap/></ncx>')
navmap = ncx[0]
et = '{%s}type' % const.EPUB_NS
bn = os.path.basename(nav_path)
def add_from_li(li, parent):
href = text = None
for x in li.iterchildren(base.tag('xhtml', 'a'),
base.tag('xhtml', 'span')):
text = etree.tostring(
x, method='text', encoding='unicode',
with_tail=False).strip() or ' '.join(
x.xpath('descendant-or-self::*/@title')).strip()
href = x.get('href')
if href:
if href.startswith('#'):
href = bn + href
break
np = parent.makeelement(base.tag('ncx', 'navPoint'))
parent.append(np)
np.append(np.makeelement(base.tag('ncx', 'navLabel')))
np[0].append(np.makeelement(base.tag('ncx', 'text')))
np[0][0].text = text
if href:
np.append(
np.makeelement(base.tag('ncx', 'content'),
attrib={'src': href}))
return np
def process_nav_node(node, toc_parent):
for li in node.iterchildren(base.tag('xhtml', 'li')):
child = add_from_li(li, toc_parent)
ol = first_child(li, base.tag('xhtml', 'ol'))
if child is not None and ol is not None:
process_nav_node(ol, child)
for nav in root.iterdescendants(base.tag('xhtml', 'nav')):
if nav.get(et) == 'toc':
ol = first_child(nav, base.tag('xhtml', 'ol'))
if ol is not None:
process_nav_node(ol, navmap)
break
else:
return
with NamedTemporaryFile(suffix='.ncx',
dir=os.path.dirname(nav_path),
delete=False) as f:
f.write(etree.tostring(ncx, encoding='utf-8'))
ncx_href = os.path.relpath(f.name, os.getcwd()).replace(os.sep, '/')
ncx_id = opf.create_manifest_item(ncx_href, base.NCX_MIME,
append=True).get('id')
for spine in opf.root.xpath('//*[local-name()="spine"]'):
spine.set('toc', ncx_id)
url = os.path.relpath(nav_path).replace(os.sep, '/')
opts.epub3_nav_href = base.urlnormalize(url)
opts.epub3_nav_parsed = root
if getattr(self, 'removed_cover', None):
changed = False
base_path = os.path.dirname(nav_path)
for elem in root.xpath('//*[@href]'):
href, frag = elem.get('href').partition('#')[::2]
link_path = (os.path.relpath(
os.path.join(base_path, urllib.parse.unquote(href)),
base_path))
abs_href = base.urlnormalize(link_path)
if abs_href == self.removed_cover:
changed = True
elem.set('data-calibre-removed-titlepage', '1')
if changed:
with open(nav_path, 'wb') as f:
f.write(base.serialize(root, 'application/xhtml+xml'))