gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-04-18 12:03:33 +02:00
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

10
ebook_converter/ebooks/oeb/polish/__init__.py
View File

@@ -1,10 +0,0 @@
#!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
__docformat__ = 'restructuredtext en'

68
ebook_converter/ebooks/oeb/polish/container.py
View File

@@ -19,42 +19,42 @@ from itertools import count
from css_parser import getUrls, replaceUrls
from calibre import CurrentDir, walk
from calibre.constants import iswindows
from calibre.customize.ui import plugin_for_input_format, plugin_for_output_format
from calibre.ebooks import escape_xpath_attr
from calibre.ebooks.chardet import xml_to_unicode
from calibre.ebooks.conversion.plugins.epub_input import (
from ebook_converter import CurrentDir, walk
from ebook_converter.constants import iswindows
from ebook_converter.customize.ui import plugin_for_input_format, plugin_for_output_format
from ebook_converter.ebooks import escape_xpath_attr
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.ebooks.conversion.plugins.epub_input import (
ADOBE_OBFUSCATION, IDPF_OBFUSCATION, decrypt_font_data
)
from calibre.ebooks.conversion.preprocess import (
from ebook_converter.ebooks.conversion.preprocess import (
CSSPreProcessor as cssp, HTMLPreProcessor
)
from calibre.ebooks.metadata.opf3 import (
from ebook_converter.ebooks.metadata.opf3 import (
CALIBRE_PREFIX, ensure_prefix, items_with_property, read_prefixes
)
from calibre.ebooks.metadata.utils import parse_opf_version
from calibre.ebooks.mobi import MobiError
from calibre.ebooks.mobi.reader.headers import MetadataHeader
from calibre.ebooks.mobi.tweak import set_cover
from calibre.ebooks.oeb.base import (
from ebook_converter.ebooks.metadata.utils import parse_opf_version
from ebook_converter.ebooks.mobi import MobiError
from ebook_converter.ebooks.mobi.reader.headers import MetadataHeader
from ebook_converter.ebooks.mobi.tweak import set_cover
from ebook_converter.ebooks.oeb.base import (
DC11_NS, OEB_DOCS, OEB_STYLES, OPF, OPF2_NS, Manifest, itercsslinks, iterlinks,
rewrite_links, serialize, urlquote, urlunquote
)
from calibre.ebooks.oeb.parse_utils import NotHTML, parse_html
from calibre.ebooks.oeb.polish.errors import DRMError, InvalidBook
from calibre.ebooks.oeb.polish.parsing import parse as parse_html_tweak
from calibre.ebooks.oeb.polish.utils import (
from ebook_converter.ebooks.oeb.parse_utils import NotHTML, parse_html
from ebook_converter.ebooks.oeb.polish.errors import DRMError, InvalidBook
from ebook_converter.ebooks.oeb.polish.parsing import parse as parse_html_tweak
from ebook_converter.ebooks.oeb.polish.utils import (
CommentFinder, PositionFinder, guess_type, parse_css
)
from calibre.ptempfile import PersistentTemporaryDirectory, PersistentTemporaryFile
from calibre.utils.filenames import hardlink_file, nlinks_file
from calibre.utils.ipc.simple_worker import WorkerError, fork_job
from calibre.utils.logging import default_log
from calibre.utils.xml_parse import safe_xml_fromstring
from calibre.utils.zipfile import ZipFile
from polyglot.builtins import iteritems, map, unicode_type, zip
from polyglot.urllib import urlparse
from ebook_converter.ptempfile import PersistentTemporaryDirectory, PersistentTemporaryFile
from ebook_converter.utils.filenames import hardlink_file, nlinks_file
from ebook_converter.utils.ipc.simple_worker import WorkerError, fork_job
from ebook_converter.utils.logging import default_log
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.utils.zipfile import ZipFile
from ebook_converter.polyglot.builtins import iteritems, map, unicode_type, zip
from ebook_converter.polyglot.urllib import urlparse
exists, join, relpath = os.path.exists, os.path.join, os.path.relpath
@@ -432,7 +432,7 @@ class Container(ContainerBase): # {{{
if current_name == self.opf_name:
self.opf_name = new_name
if os.path.dirname(old_path) != os.path.dirname(new_path):
from calibre.ebooks.oeb.polish.replace import LinkRebaser
from ebook_converter.ebooks.oeb.polish.replace import LinkRebaser
repl = LinkRebaser(self, current_name, new_name)
self.replace_links(new_name, repl)
self.dirty(new_name)
@@ -641,7 +641,7 @@ class Container(ContainerBase): # {{{
''' The metadata of this book as a Metadata object. Note that this
object is constructed on the fly every time this property is requested,
so use it sparingly. '''
from calibre.ebooks.metadata.opf2 import OPF as O
from ebook_converter.ebooks.metadata.opf2 import OPF as O
mi = self.serialize_item(self.opf_name)
return O(BytesIO(mi), basedir=self.opf_dir, unquote_urls=False,
populate_spine=False).to_book_metadata()
@@ -1158,7 +1158,7 @@ class EpubContainer(Container):
except:
log.exception('EPUB appears to be invalid ZIP file, trying a'
' more forgiving ZIP parser')
from calibre.utils.localunzip import extractall
from ebook_converter.utils.localunzip import extractall
stream.seek(0)
extractall(stream, path=tdir)
try:
@@ -1320,7 +1320,7 @@ class EpubContainer(Container):
self.obfuscated_fonts[font] = (alg, tkey)
def update_modified_timestamp(self):
from calibre.ebooks.metadata.opf3 import set_last_modified_in_opf
from ebook_converter.ebooks.metadata.opf3 import set_last_modified_in_opf
set_last_modified_in_opf(self.opf)
self.dirty(self.opf_name)
@@ -1372,7 +1372,7 @@ class EpubContainer(Container):
shutil.copyfileobj(src, dest)
else:
from calibre.ebooks.tweak import zip_rebuilder
from ebook_converter.ebooks.tweak import zip_rebuilder
with lopen(join(self.root, 'mimetype'), 'wb') as f:
et = guess_type('a.epub')
if not isinstance(et, bytes):
@@ -1401,8 +1401,8 @@ class InvalidMobi(InvalidBook):
def do_explode(path, dest):
from calibre.ebooks.mobi.reader.mobi6 import MobiReader
from calibre.ebooks.mobi.reader.mobi8 import Mobi8Reader
from ebook_converter.ebooks.mobi.reader.mobi6 import MobiReader
from ebook_converter.ebooks.mobi.reader.mobi8 import Mobi8Reader
with lopen(path, 'rb') as stream:
mr = MobiReader(stream, default_log, None, None)
@@ -1415,7 +1415,7 @@ def do_explode(path, dest):
def opf_to_azw3(opf, outpath, container):
from calibre.ebooks.conversion.plumber import Plumber, create_oebbook
from ebook_converter.ebooks.conversion.plumber import Plumber, create_oebbook
class Item(Manifest.Item):
@@ -1489,7 +1489,7 @@ class AZW3Container(Container):
try:
opf_path, obfuscated_fonts = fork_job(
'calibre.ebooks.oeb.polish.container', 'do_explode',
'ebook_converter.ebooks.oeb.polish.container', 'do_explode',
args=(pathtoazw3, tdir), no_output=True)['result']
except WorkerError as e:
log(e.orig_tb)

2
ebook_converter/ebooks/oeb/polish/errors.py
View File

@@ -6,7 +6,7 @@ __license__ = 'GPL v3'
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from calibre.ebooks import DRMError as _DRMError
from ebook_converter.ebooks import DRMError as _DRMError
class InvalidBook(ValueError):

4
ebook_converter/ebooks/oeb/polish/opf.py
View File

@@ -7,8 +7,8 @@ __copyright__ = '2014, Kovid Goyal <kovid at kovidgoyal.net>'
from lxml import etree
from calibre.ebooks.oeb.polish.container import OPF_NAMESPACES
from calibre.utils.localization import canonicalize_lang
from ebook_converter.ebooks.oeb.polish.container import OPF_NAMESPACES
from ebook_converter.utils.localization import canonicalize_lang
def get_book_language(container):

10
ebook_converter/ebooks/oeb/polish/parsing.py
View File

@@ -10,11 +10,11 @@ import re
from lxml.etree import Element as LxmlElement
import html5_parser
from calibre import xml_replace_entities
from calibre.utils.xml_parse import safe_xml_fromstring
from calibre.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
from calibre.utils.cleantext import clean_xml_chars
from polyglot.builtins import unicode_type
from ebook_converter import xml_replace_entities
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.polyglot.builtins import unicode_type
XHTML_NS = 'http://www.w3.org/1999/xhtml'

12
ebook_converter/ebooks/oeb/polish/pretty.py
View File

@@ -6,16 +6,16 @@ __license__ = 'GPL v3'
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
import textwrap
from polyglot.builtins import iteritems, map
from ebook_converter.polyglot.builtins import iteritems, map
# from lxml.etree import Element
from calibre import force_unicode
from calibre.ebooks.oeb.base import (
from ebook_converter import force_unicode
from ebook_converter.ebooks.oeb.base import (
serialize, OEB_DOCS, barename, OEB_STYLES, XPNSMAP, XHTML, SVG)
from calibre.ebooks.oeb.polish.container import OPF_NAMESPACES
from calibre.ebooks.oeb.polish.utils import guess_type
from calibre.utils.icu import sort_key
from ebook_converter.ebooks.oeb.polish.container import OPF_NAMESPACES
from ebook_converter.ebooks.oeb.polish.utils import guess_type
from ebook_converter.utils.icu import sort_key
def isspace(x):

22
ebook_converter/ebooks/oeb/polish/toc.py
View File

@@ -14,17 +14,17 @@ from operator import itemgetter
from lxml import etree
from lxml.builder import ElementMaker
from calibre import __version__
from calibre.ebooks.oeb.base import (
from ebook_converter import __version__
from ebook_converter.ebooks.oeb.base import (
XPath, uuid_id, xml2text, NCX, NCX_NS, XML, XHTML, XHTML_NS, serialize, EPUB_NS, XML_NS, OEB_DOCS)
from calibre.ebooks.oeb.polish.errors import MalformedMarkup
from calibre.ebooks.oeb.polish.utils import guess_type, extract
from calibre.ebooks.oeb.polish.opf import set_guide_item, get_book_language
from calibre.ebooks.oeb.polish.pretty import pretty_html_tree
from calibre.translations.dynamic import translate
from calibre.utils.localization import get_lang, canonicalize_lang, lang_as_iso639_1
from polyglot.builtins import iteritems, map, unicode_type
from polyglot.urllib import urlparse
from ebook_converter.ebooks.oeb.polish.errors import MalformedMarkup
from ebook_converter.ebooks.oeb.polish.utils import guess_type, extract
from ebook_converter.ebooks.oeb.polish.opf import set_guide_item, get_book_language
from ebook_converter.ebooks.oeb.polish.pretty import pretty_html_tree
from ebook_converter.translations.dynamic import translate
from ebook_converter.utils.localization import get_lang, canonicalize_lang, lang_as_iso639_1
from ebook_converter.polyglot.builtins import iteritems, map, unicode_type
from ebook_converter.polyglot.urllib import urlparse
ns = etree.FunctionNamespace('calibre_xpath_extensions')
ns.prefix = 'calibre'
@@ -677,7 +677,7 @@ def ensure_single_nav_of_type(root, ntype='toc'):
def commit_nav_toc(container, toc, lang=None, landmarks=None, previous_nav=None):
from calibre.ebooks.oeb.polish.pretty import pretty_xml_tree
from ebook_converter.ebooks.oeb.polish.pretty import pretty_xml_tree
tocname = find_existing_nav_toc(container)
if previous_nav is not None:
nav_name = container.href_to_name(previous_nav[0])

10
ebook_converter/ebooks/oeb/polish/utils.py
View File

@@ -8,8 +8,8 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
import re, os
from bisect import bisect
from calibre import guess_type as _guess_type, replace_entities
from polyglot.builtins import filter
from ebook_converter import guess_type as _guess_type, replace_entities
from ebook_converter.polyglot.builtins import filter
def guess_type(x):
@@ -25,7 +25,7 @@ def setup_css_parser_serialization(tab_width=2):
def actual_case_for_name(container, name):
from calibre.utils.filenames import samefile
from ebook_converter.utils.filenames import samefile
if not container.exists(name):
raise ValueError('Cannot get actual case for %s as it does not exist' % name)
parts = name.split('/')
@@ -103,7 +103,7 @@ class CommentFinder(object):
def link_stylesheets(container, names, sheets, remove=False, mtype='text/css'):
from calibre.ebooks.oeb.base import XPath, XHTML
from ebook_converter.ebooks.oeb.base import XPath, XHTML
changed_names = set()
snames = set(sheets)
lp = XPath('//h:link[@href]')
@@ -164,7 +164,7 @@ def parse_css(data, fname='<string>', is_declaration=False, decode=None, log_lev
import logging
log_level = logging.WARNING
from css_parser import CSSParser, log
from calibre.ebooks.oeb.base import _css_logger
from ebook_converter.ebooks.oeb.base import _css_logger
log.setLevel(log_level)
log.raiseExceptions = False
data = data or ''