gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-17 07:13:42 +01:00
Code Issues Projects Releases Wiki Activity

Convert calibre modules to ebook_converter.

Browse Source 
Here is the first batch of modules, which are needed for converting
several formats to LRF. Some of the logic has been change, more cleanups
will follow.
This commit is contained in:
gryf
2020-04-11 19:33:43 +02:00
parent 69d2e536c5
commit 0f9792df36
252 changed files with 1925 additions and 2344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
ebook_converter/ebooks/oeb/transforms/__init__.py
View File

@@ -1,7 +0,0 @@
#!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'

10
ebook_converter/ebooks/oeb/transforms/data_url.py
View File

@@ -6,14 +6,14 @@ __license__ = 'GPL v3'
__copyright__ = '2014, Kovid Goyal <kovid at kovidgoyal.net>'
import re
from calibre.ebooks.oeb.base import XPath, urlunquote
from polyglot.builtins import as_bytes
from ebook_converter.ebooks.oeb.base import XPath, urlunquote
from ebook_converter.polyglot.builtins import as_bytes
class DataURL(object):
def __call__(self, oeb, opts):
from calibre.utils.imghdr import what
from ebook_converter.utils.imghdr import what
self.log = oeb.log
attr_path = XPath('//h:img[@src]')
for item in oeb.spine:
@@ -29,7 +29,7 @@ class DataURL(object):
continue
if ';base64' in header:
data = re.sub(r'\s+', '', data)
from polyglot.binary import from_base64_bytes
from ebook_converter.polyglot.binary import from_base64_bytes
try:
data = from_base64_bytes(data)
except Exception:
@@ -46,7 +46,7 @@ class DataURL(object):
def convert_image_data_uri(self, data, fmt, oeb):
self.log('Found image encoded as data URI converting it to normal image')
from calibre import guess_type
from ebook_converter import guess_type
item_id, item_href = oeb.manifest.generate('data-url-image', 'data-url-image.' + fmt)
oeb.manifest.add(item_id, item_href, guess_type(item_href)[0], data=data)
return item_href

28
ebook_converter/ebooks/oeb/transforms/flatcss.py
View File

@@ -14,14 +14,14 @@ from lxml import etree
import css_parser
from css_parser.css import Property
from calibre import guess_type
from calibre.ebooks import unit_convert
from calibre.ebooks.oeb.base import (XHTML, XHTML_NS, CSS_MIME, OEB_STYLES,
from ebook_converter import guess_type
from ebook_converter.ebooks import unit_convert
from ebook_converter.ebooks.oeb.base import (XHTML, XHTML_NS, CSS_MIME, OEB_STYLES,
namespace, barename, XPath, css_text)
from calibre.ebooks.oeb.stylizer import Stylizer
from calibre.utils.filenames import ascii_filename, ascii_text
from calibre.utils.icu import numeric_sort_key
from polyglot.builtins import iteritems, unicode_type, string_or_bytes, map
from ebook_converter.ebooks.oeb.stylizer import Stylizer
from ebook_converter.utils.filenames import ascii_filename, ascii_text
from ebook_converter.utils.icu import numeric_sort_key
from ebook_converter.polyglot.builtins import iteritems, unicode_type, string_or_bytes, map
COLLAPSE = re.compile(r'[ \t\r\n\v]+')
STRIPNUM = re.compile(r'[-0-9]+$')
@@ -139,7 +139,7 @@ class CSSFlattener(object):
self.fbase = fbase
self.transform_css_rules = transform_css_rules
if self.transform_css_rules:
from calibre.ebooks.css_transform_rules import compile_rules
from ebook_converter.ebooks.css_transform_rules import compile_rules
self.transform_css_rules = compile_rules(self.transform_css_rules)
self.fkey = fkey
self.lineh = lineh
@@ -180,7 +180,7 @@ class CSSFlattener(object):
except:
self.oeb.log.warning('Failed to parse filter_css, ignoring')
else:
from calibre.ebooks.oeb.normalize_css import normalize_filter_css
from ebook_converter.ebooks.oeb.normalize_css import normalize_filter_css
self.filter_css = frozenset(normalize_filter_css(self.filter_css))
self.oeb.log.debug('Filtering CSS properties: %s'%
', '.join(self.filter_css))
@@ -223,8 +223,8 @@ class CSSFlattener(object):
body_font_family = None
if not family:
return body_font_family, efi
from calibre.utils.fonts.scanner import font_scanner, NoFonts
from calibre.utils.fonts.utils import panose_to_css_generic_family
from ebook_converter.utils.fonts.scanner import font_scanner, NoFonts
from ebook_converter.utils.fonts.utils import panose_to_css_generic_family
try:
faces = font_scanner.fonts_for_family(family)
except NoFonts:
@@ -610,7 +610,7 @@ class CSSFlattener(object):
id, href = manifest.generate('css', 'stylesheet.css')
sheet = css_parser.parseString(css, validate=False)
if self.transform_css_rules:
from calibre.ebooks.css_transform_rules import transform_sheet
from ebook_converter.ebooks.css_transform_rules import transform_sheet
transform_sheet(self.transform_css_rules, sheet)
item = manifest.add(id, href, CSS_MIME, data=sheet)
self.oeb.manifest.main_stylesheet = item
@@ -642,7 +642,7 @@ class CSSFlattener(object):
id_, href = manifest.generate('page_css', 'page_styles.css')
sheet = css_parser.parseString(css, validate=False)
if self.transform_css_rules:
from calibre.ebooks.css_transform_rules import transform_sheet
from ebook_converter.ebooks.css_transform_rules import transform_sheet
transform_sheet(self.transform_css_rules, sheet)
manifest.add(id_, href, CSS_MIME, data=sheet)
gc_map[css] = href
@@ -664,7 +664,7 @@ class CSSFlattener(object):
fsize = self.context.dest.fbase
self.flatten_node(html, stylizer, names, styles, pseudo_styles, fsize, item.id, recurse=False)
self.flatten_node(html.find(XHTML('body')), stylizer, names, styles, pseudo_styles, fsize, item.id)
items = sorted(((key, val) for (val, key) in iteritems(styles)), key=lambda x:numeric_sort_key(x[0]))
items = sorted(((key, val) for (val, key) in iteritems(styles)))
# :hover must come after link and :active must come after :hover
psels = sorted(pseudo_styles, key=lambda x :
{'hover':1, 'active':2}.get(x, 0))

22
ebook_converter/ebooks/oeb/transforms/jacket.py
View File

@@ -10,15 +10,15 @@ import sys, os, re
from xml.sax.saxutils import escape
from string import Formatter
from calibre import guess_type, strftime
from calibre.constants import iswindows
from calibre.ebooks.oeb.base import XPath, XHTML_NS, XHTML, xml2text, urldefrag, urlnormalize
from calibre.library.comments import comments_to_html, markdown
from calibre.utils.date import is_date_undefined, as_local_time
from calibre.utils.icu import sort_key
from calibre.ebooks.chardet import strip_encoding_declarations
from calibre.ebooks.metadata import fmt_sidx, rating_to_stars
from polyglot.builtins import unicode_type, map
from ebook_converter import guess_type, strftime
from ebook_converter.constants import iswindows
from ebook_converter.ebooks.oeb.base import XPath, XHTML_NS, XHTML, xml2text, urldefrag, urlnormalize
from ebook_converter.library.comments import comments_to_html, markdown
from ebook_converter.utils.date import is_date_undefined, as_local_time
from ebook_converter.utils.icu import sort_key
from ebook_converter.ebooks.chardet import strip_encoding_declarations
from ebook_converter.ebooks.metadata import fmt_sidx, rating_to_stars
from ebook_converter.polyglot.builtins import unicode_type, map
JACKET_XPATH = '//h:meta[@name="calibre-content" and @content="jacket"]'
@@ -346,7 +346,7 @@ def render_jacket(mi, output_profile,
return strip_encoding_declarations(generated_html)
from calibre.ebooks.oeb.polish.parsing import parse
from ebook_converter.ebooks.oeb.polish.parsing import parse
raw = generate_html(comments)
root = parse(raw, line_numbers=False, force_html5_parse=True)
@@ -367,7 +367,7 @@ def render_jacket(mi, output_profile,
fw.append(child)
body.append(fw)
postprocess_jacket(root, output_profile, has_data)
from calibre.ebooks.oeb.polish.pretty import pretty_html_tree
from ebook_converter.ebooks.oeb.polish.pretty import pretty_html_tree
pretty_html_tree(None, root)
return root

10
ebook_converter/ebooks/oeb/transforms/metadata.py
View File

@@ -7,13 +7,13 @@ __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import os, re
from calibre.utils.date import isoformat, now
from calibre import guess_type
from polyglot.builtins import iteritems
from ebook_converter.utils.date import isoformat, now
from ebook_converter import guess_type
from ebook_converter.polyglot.builtins import iteritems
def meta_info_to_oeb_metadata(mi, m, log, override_input_metadata=False):
from calibre.ebooks.oeb.base import OPF
from ebook_converter.ebooks.oeb.base import OPF
if not mi.is_null('title'):
m.clear('title')
m.add('title', mi.title)
@@ -167,7 +167,7 @@ class MergeMetadata(object):
return id
def remove_old_cover(self, cover_item, new_cover_href=None):
from calibre.ebooks.oeb.base import XPath, XLINK
from ebook_converter.ebooks.oeb.base import XPath, XLINK
from lxml import etree
self.oeb.manifest.remove(cover_item)

4
ebook_converter/ebooks/oeb/transforms/page_margin.py
View File

@@ -9,8 +9,8 @@ __docformat__ = 'restructuredtext en'
import numbers
from collections import Counter
from calibre.ebooks.oeb.base import barename, XPath
from polyglot.builtins import iteritems
from ebook_converter.ebooks.oeb.base import barename, XPath
from ebook_converter.polyglot.builtins import iteritems
class RemoveAdobeMargins(object):

8
ebook_converter/ebooks/oeb/transforms/structure.py
View File

@@ -11,10 +11,10 @@ import re, uuid
from lxml import etree
from collections import OrderedDict, Counter
from calibre.ebooks.oeb.base import XPNSMAP, TOC, XHTML, xml2text, barename
from calibre.ebooks import ConversionError
from polyglot.builtins import itervalues, unicode_type
from polyglot.urllib import urlparse
from ebook_converter.ebooks.oeb.base import XPNSMAP, TOC, XHTML, xml2text, barename
from ebook_converter.ebooks import ConversionError
from ebook_converter.polyglot.builtins import itervalues, unicode_type
from ebook_converter.polyglot.urllib import urlparse
def XPath(x):

6
ebook_converter/ebooks/oeb/transforms/trimmanifest.py
View File

@@ -6,9 +6,9 @@ from __future__ import absolute_import, division, print_function, unicode_litera
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
from calibre.ebooks.oeb.base import CSS_MIME, OEB_DOCS
from calibre.ebooks.oeb.base import urlnormalize, iterlinks
from polyglot.urllib import urldefrag
from ebook_converter.ebooks.oeb.base import CSS_MIME, OEB_DOCS
from ebook_converter.ebooks.oeb.base import urlnormalize, iterlinks
from ebook_converter.polyglot.urllib import urldefrag
class ManifestTrimmer(object):