gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-22 18:33:34 +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

4
ebook_converter/ebooks/oeb/__init__.py
View File

@@ -1,4 +0,0 @@
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'

32
ebook_converter/ebooks/oeb/base.py
View File

@@ -13,19 +13,18 @@ from itertools import count
from operator import attrgetter
from lxml import etree, html
from calibre import force_unicode
from calibre.constants import filesystem_encoding, __version__, ispy3
from calibre.translations.dynamic import translate
from calibre.utils.xml_parse import safe_xml_fromstring
from calibre.ebooks.chardet import xml_to_unicode
from calibre.ebooks.conversion.preprocess import CSSPreProcessor
from calibre import (isbytestring, as_unicode, get_types_map)
from calibre.ebooks.oeb.parse_utils import barename, XHTML_NS, namespace, XHTML, parse_html, NotHTML
from calibre.utils.cleantext import clean_xml_chars
from calibre.utils.short_uuid import uuid4
from polyglot.builtins import iteritems, unicode_type, string_or_bytes, range, itervalues, filter, codepoint_to_chr
from polyglot.urllib import unquote as urlunquote, urldefrag, urljoin, urlparse, urlunparse
from calibre.utils.icu import numeric_sort_key
from ebook_converter import force_unicode
from ebook_converter.constants import filesystem_encoding, __version__, ispy3
from ebook_converter.translations.dynamic import translate
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.ebooks.conversion.preprocess import CSSPreProcessor
from ebook_converter import (isbytestring, as_unicode, get_types_map)
from ebook_converter.ebooks.oeb.parse_utils import barename, XHTML_NS, namespace, XHTML, parse_html, NotHTML
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.utils.short_uuid import uuid4
from ebook_converter.polyglot.builtins import iteritems, unicode_type, string_or_bytes, range, itervalues, filter, codepoint_to_chr
from ebook_converter.polyglot.urllib import unquote as urlunquote, urldefrag, urljoin, urlparse, urlunparse
XML_NS = 'http://www.w3.org/XML/1998/namespace'
OEB_DOC_NS = 'http://openebook.org/namespaces/oeb-document/1.0/'
@@ -971,7 +970,7 @@ class Manifest(object):
self.oeb.log.debug('Converting', self.href, '...')
from calibre.ebooks.txt.processor import convert_markdown
from ebook_converter.ebooks.txt.processor import convert_markdown
title = self.oeb.metadata.title
if title:
@@ -1064,7 +1063,7 @@ class Manifest(object):
def unload_data_from_memory(self, memory=None):
if isinstance(self._data, bytes):
if memory is None:
from calibre.ptempfile import PersistentTemporaryFile
from ebook_converter.ptempfile import PersistentTemporaryFile
pt = PersistentTemporaryFile(suffix='_oeb_base_mem_unloader.img')
with pt:
pt.write(self._data)
@@ -1124,7 +1123,8 @@ class Manifest(object):
if isinstance(href, bytes):
href = force_unicode(href)
sp = self.spine_position if isinstance(self.spine_position, numbers.Number) else sys.maxsize
return sp, (self.media_type or '').lower(), numeric_sort_key(href), self.id
return sp, (self.media_type or '').lower(), href, self.id
def relhref(self, href):
"""Convert the URL provided in :param:`href` from a book-absolute

6
ebook_converter/ebooks/oeb/normalize_css.py
View File

@@ -10,9 +10,9 @@ from functools import wraps
from css_parser.css import PropertyValue
from css_parser import profile as cssprofiles, CSSParser
from tinycss.fonts3 import parse_font, serialize_font_family
from calibre.ebooks.oeb.base import css_text
from polyglot.builtins import iteritems, string_or_bytes, unicode_type, zip
from ebook_converter.tinycss.fonts3 import parse_font, serialize_font_family
from ebook_converter.ebooks.oeb.base import css_text
from ebook_converter.polyglot.builtins import iteritems, string_or_bytes, unicode_type, zip
DEFAULTS = {'azimuth': 'center', 'background-attachment': 'scroll', # {{{
'background-color': 'transparent', 'background-image': 'none',

14
ebook_converter/ebooks/oeb/parse_utils.py
View File

@@ -10,11 +10,11 @@ import re
from lxml import etree, html
from calibre import xml_replace_entities, force_unicode
from calibre.utils.xml_parse import safe_xml_fromstring
from calibre.constants import filesystem_encoding
from calibre.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
from polyglot.builtins import iteritems, itervalues, unicode_type, string_or_bytes, map
from ebook_converter import xml_replace_entities, force_unicode
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.constants import filesystem_encoding
from ebook_converter.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
from ebook_converter.polyglot.builtins import iteritems, itervalues, unicode_type, string_or_bytes, map
RECOVER_PARSER = etree.XMLParser(recover=True, no_network=True, resolve_entities=False)
XHTML_NS = 'http://www.w3.org/1999/xhtml'
@@ -94,7 +94,7 @@ def node_depth(node):
def html5_parse(data, max_nesting_depth=100):
from html5_parser import parse
from calibre.utils.cleantext import clean_xml_chars
from ebook_converter.utils.cleantext import clean_xml_chars
data = parse(clean_xml_chars(data), maybe_xhtml=True, keep_doctype=False, sanitize_names=True)
# Check that the asinine HTML 5 algorithm did not result in a tree with
# insane nesting depths
@@ -160,7 +160,7 @@ def check_for_html5(prefix, root):
def parse_html(data, log=None, decoder=None, preprocessor=None,
filename='<string>', non_html_file_tags=frozenset()):
if log is None:
from calibre.utils.logging import default_log
from ebook_converter.utils.logging import default_log
log = default_log
filename = force_unicode(filename, enc=filesystem_encoding)

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 ''

32
ebook_converter/ebooks/oeb/reader.py
View File

@@ -11,24 +11,24 @@ from collections import defaultdict
from lxml import etree
from calibre.ebooks.oeb.base import OPF1_NS, OPF2_NS, OPF2_NSMAP, DC11_NS, \
from ebook_converter.ebooks.oeb.base import OPF1_NS, OPF2_NS, OPF2_NSMAP, DC11_NS, \
DC_NSES, OPF, xml2text, XHTML_MIME
from calibre.ebooks.oeb.base import OEB_DOCS, OEB_STYLES, OEB_IMAGES, \
from ebook_converter.ebooks.oeb.base import OEB_DOCS, OEB_STYLES, OEB_IMAGES, \
PAGE_MAP_MIME, JPEG_MIME, NCX_MIME, SVG_MIME
from calibre.ebooks.oeb.base import XMLDECL_RE, COLLAPSE_RE, \
from ebook_converter.ebooks.oeb.base import XMLDECL_RE, COLLAPSE_RE, \
MS_COVER_TYPE, iterlinks
from calibre.ebooks.oeb.base import namespace, barename, XPath, xpath, \
from ebook_converter.ebooks.oeb.base import namespace, barename, XPath, xpath, \
urlnormalize, BINARY_MIME, \
OEBError, OEBBook, DirContainer
from calibre.ebooks.oeb.writer import OEBWriter
from calibre.utils.xml_parse import safe_xml_fromstring
from calibre.utils.cleantext import clean_xml_chars
from calibre.utils.localization import get_lang
from calibre.ptempfile import TemporaryDirectory
from calibre.constants import __appname__, __version__
from calibre import guess_type, xml_replace_entities
from polyglot.builtins import unicode_type, zip
from polyglot.urllib import unquote, urldefrag, urlparse
from ebook_converter.ebooks.oeb.writer import OEBWriter
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.utils.localization import get_lang
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.constants import __appname__, __version__
from ebook_converter import guess_type, xml_replace_entities
from ebook_converter.polyglot.builtins import unicode_type, zip
from ebook_converter.polyglot.urllib import unquote, urldefrag, urlparse
__all__ = ['OEBReader']
@@ -129,8 +129,8 @@ class OEBReader(object):
return opf
def _metadata_from_opf(self, opf):
from calibre.ebooks.metadata.opf2 import OPF
from calibre.ebooks.oeb.transforms.metadata import meta_info_to_oeb_metadata
from ebook_converter.ebooks.metadata.opf2 import OPF
from ebook_converter.ebooks.oeb.transforms.metadata import meta_info_to_oeb_metadata
stream = io.BytesIO(etree.tostring(opf, xml_declaration=True, encoding='utf-8'))
o = OPF(stream)
pwm = o.primary_writing_mode
@@ -621,7 +621,7 @@ class OEBReader(object):
return
def _cover_from_html(self, hcover):
from calibre.ebooks import render_html_svg_workaround
from ebook_converter.ebooks import render_html_svg_workaround
with TemporaryDirectory('_html_cover') as tdir:
writer = OEBWriter()
writer(self.oeb, tdir)

16
ebook_converter/ebooks/oeb/stylizer.py
View File

@@ -16,13 +16,13 @@ from css_parser.css import (CSSStyleRule, CSSPageRule, CSSFontFaceRule,
cssproperties)
from css_parser import (profile as cssprofiles, parseString, parseStyle, log as
css_parser_log, CSSParser, profiles, replaceUrls)
from calibre import force_unicode, as_unicode
from calibre.ebooks import unit_convert
from calibre.ebooks.oeb.base import XHTML, XHTML_NS, CSS_MIME, OEB_STYLES, xpath, urlnormalize
from calibre.ebooks.oeb.normalize_css import DEFAULTS, normalizers
from css_selectors import Select, SelectorError, INAPPROPRIATE_PSEUDO_CLASSES
from polyglot.builtins import iteritems, unicode_type, filter
from tinycss.media3 import CSSMedia3Parser
from ebook_converter import force_unicode, as_unicode
from ebook_converter.ebooks import unit_convert
from ebook_converter.ebooks.oeb.base import XHTML, XHTML_NS, CSS_MIME, OEB_STYLES, xpath, urlnormalize
from ebook_converter.ebooks.oeb.normalize_css import DEFAULTS, normalizers
from ebook_converter.css_selectors import Select, SelectorError, INAPPROPRIATE_PSEUDO_CLASSES
from ebook_converter.polyglot.builtins import iteritems, unicode_type, filter
from ebook_converter.tinycss.media3 import CSSMedia3Parser
css_parser_log.setLevel(logging.WARN)
@@ -194,7 +194,7 @@ class Stylizer(object):
# Use the default profile. This should really be using
# opts.output_profile, but I don't want to risk changing it, as
# doing so might well have hard to debug font size effects.
from calibre.customize.ui import output_profiles
from ebook_converter.customize.ui import output_profiles
for x in output_profiles():
if x.short_name == 'default':
self.profile = x

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):

4
ebook_converter/ebooks/oeb/writer.py
View File

@@ -7,8 +7,8 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
import os
from calibre.ebooks.oeb.base import OPF_MIME, xml2str
from calibre.ebooks.oeb.base import DirContainer, OEBError
from ebook_converter.ebooks.oeb.base import OPF_MIME, xml2str
from ebook_converter.ebooks.oeb.base import DirContainer, OEBError
__all__ = ['OEBWriter']