gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-16 15:03:30 +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

12
ebook_converter/ebooks/metadata/__init__.py
View File

@@ -11,10 +11,10 @@ Provides abstraction for metadata reading.writing from a variety of ebook format
"""
import os, sys, re
from calibre import relpath, guess_type, prints, force_unicode
from calibre.utils.config_base import tweaks
from polyglot.builtins import codepoint_to_chr, unicode_type, range, map, zip, getcwd, iteritems, itervalues, as_unicode
from polyglot.urllib import quote, unquote, urlparse
from ebook_converter import relpath, guess_type, prints, force_unicode
from ebook_converter.utils.config_base import tweaks
from ebook_converter.polyglot.builtins import codepoint_to_chr, unicode_type, range, map, zip, getcwd, iteritems, itervalues, as_unicode
from ebook_converter.polyglot.urllib import quote, unquote, urlparse
try:
@@ -131,7 +131,7 @@ def get_title_sort_pat(lang=None):
if ans is not None:
return ans
q = lang
from calibre.utils.localization import canonicalize_lang, get_lang
from ebook_converter.utils.localization import canonicalize_lang, get_lang
if lang is None:
q = tweaks['default_language_for_title_sort']
if q is None:
@@ -348,7 +348,7 @@ def MetaInformation(title, authors=(_('Unknown'),)):
@param title: title or ``_('Unknown')`` or a MetaInformation object
@param authors: List of strings or []
'''
from calibre.ebooks.metadata.book.base import Metadata
from ebook_converter.ebooks.metadata.book.base import Metadata
mi = None
if hasattr(title, 'title') and hasattr(title, 'authors'):
mi = title

22
ebook_converter/ebooks/metadata/archive.py
View File

@@ -9,9 +9,9 @@ __docformat__ = 'restructuredtext en'
import os
from contextlib import closing
from calibre.customize import FileTypePlugin
from calibre.utils.localization import canonicalize_lang
from polyglot.builtins import filter, unicode_type
from ebook_converter.customize import FileTypePlugin
from ebook_converter.utils.localization import canonicalize_lang
from ebook_converter.polyglot.builtins import filter, unicode_type
def is_comic(list_of_names):
@@ -22,7 +22,7 @@ def is_comic(list_of_names):
def archive_type(stream):
from calibre.utils.zipfile import stringFileHeader
from ebook_converter.utils.zipfile import stringFileHeader
try:
pos = stream.tell()
except:
@@ -51,7 +51,7 @@ class KPFExtract(FileTypePlugin):
on_import = True
def run(self, archive):
from calibre.utils.zipfile import ZipFile
from ebook_converter.utils.zipfile import ZipFile
with ZipFile(archive, 'r') as zf:
fnames = zf.namelist()
candidates = [x for x in fnames if x.lower().endswith('.docx')]
@@ -74,10 +74,10 @@ class ArchiveExtract(FileTypePlugin):
on_import = True
def run(self, archive):
from calibre.utils.zipfile import ZipFile
from ebook_converter.utils.zipfile import ZipFile
is_rar = archive.lower().endswith('.rar')
if is_rar:
from calibre.utils.unrar import extract_member, names
from ebook_converter.utils.unrar import extract_member, names
else:
zf = ZipFile(archive, 'r')
@@ -166,7 +166,7 @@ def get_comic_book_info(d, mi, series_index='volume'):
mi.comments = comments.strip()
pubm, puby = d.get('publicationMonth', None), d.get('publicationYear', None)
if puby is not None:
from calibre.utils.date import parse_only_date
from ebook_converter.utils.date import parse_only_date
from datetime import date
try:
dt = date(puby, 6 if pubm is None else pubm, 15)
@@ -178,7 +178,7 @@ def get_comic_book_info(d, mi, series_index='volume'):
def parse_comic_comment(comment, series_index='volume'):
# See http://code.google.com/p/comicbookinfo/wiki/Example
from calibre.ebooks.metadata import MetaInformation
from ebook_converter.ebooks.metadata import MetaInformation
import json
mi = MetaInformation(None, None)
m = json.loads(comment)
@@ -193,11 +193,11 @@ def parse_comic_comment(comment, series_index='volume'):
def get_comic_metadata(stream, stream_type, series_index='volume'):
comment = None
if stream_type == 'cbz':
from calibre.utils.zipfile import ZipFile
from ebook_converter.utils.zipfile import ZipFile
zf = ZipFile(stream)
comment = zf.comment
elif stream_type == 'cbr':
from calibre.utils.unrar import comment as get_comment
from ebook_converter.utils.unrar import comment as get_comment
comment = get_comment(stream)
return parse_comic_comment(comment or b'{}', series_index=series_index)

47
ebook_converter/ebooks/metadata/book/base.py
View File

@@ -8,14 +8,14 @@ __docformat__ = 'restructuredtext en'
import copy, traceback
from calibre import prints
from calibre.constants import DEBUG, ispy3
from calibre.ebooks.metadata.book import (SC_COPYABLE_FIELDS,
from ebook_converter import prints
from ebook_converter.constants import DEBUG, ispy3
from ebook_converter.ebooks.metadata.book import (SC_COPYABLE_FIELDS,
SC_FIELDS_COPY_NOT_NULL, STANDARD_METADATA_FIELDS,
TOP_LEVEL_IDENTIFIERS, ALL_METADATA_FIELDS)
from calibre.library.field_metadata import FieldMetadata
from calibre.utils.icu import sort_key
from polyglot.builtins import iteritems, unicode_type, filter, map
from ebook_converter.library.field_metadata import FieldMetadata
from ebook_converter.utils.icu import sort_key
from ebook_converter.polyglot.builtins import iteritems, unicode_type, filter, map
# Special sets used to optimize the performance of getting and setting
# attributes on Metadata objects
@@ -52,7 +52,7 @@ def reset_field_metadata():
field_metadata = FieldMetadata()
ck = lambda typ: icu_lower(typ).strip().replace(':', '').replace(',', '')
ck = lambda typ: typ.lower().strip().replace(':', '').replace(',', '')
cv = lambda val: val.strip().replace(',', '|')
@@ -97,7 +97,7 @@ class Metadata(object):
# List of strings or []
self.author = list(authors) if authors else [] # Needed for backward compatibility
self.authors = list(authors) if authors else []
from calibre.ebooks.metadata.book.formatter import SafeFormat
from ebook_converter.ebooks.metadata.book.formatter import SafeFormat
self.formatter = SafeFormat() if formatter is None else formatter
self.template_cache = template_cache
@@ -441,7 +441,7 @@ class Metadata(object):
'''
if not ops:
return
from calibre.ebooks.metadata.book.formatter import SafeFormat
from ebook_converter.ebooks.metadata.book.formatter import SafeFormat
formatter = SafeFormat()
for op in ops:
try:
@@ -584,14 +584,15 @@ class Metadata(object):
for attr in TOP_LEVEL_IDENTIFIERS:
copy_not_none(self, other, attr)
other_lang = getattr(other, 'languages', [])
if other_lang and other_lang != ['und']:
self.languages = list(other_lang)
# other_lang = getattr(other, 'languages', [])
# if other_lang and other_lang != ['und']:
# self.languages = list(other_lang)
self.languages = []
if not getattr(self, 'series', None):
self.series_index = None
def format_series_index(self, val=None):
from calibre.ebooks.metadata import fmt_sidx
from ebook_converter.ebooks.metadata import fmt_sidx
v = self.series_index if val is None else val
try:
x = float(v)
@@ -600,11 +601,11 @@ class Metadata(object):
return fmt_sidx(x)
def authors_from_string(self, raw):
from calibre.ebooks.metadata import string_to_authors
from ebook_converter.ebooks.metadata import string_to_authors
self.authors = string_to_authors(raw)
def format_authors(self):
from calibre.ebooks.metadata import authors_to_string
from ebook_converter.ebooks.metadata import authors_to_string
return authors_to_string(self.authors)
def format_tags(self):
@@ -625,12 +626,12 @@ class Metadata(object):
return (name, val)
def format_field_extended(self, key, series_with_index=True):
from calibre.ebooks.metadata import authors_to_string
from ebook_converter.ebooks.metadata import authors_to_string
'''
returns the tuple (display_name, formatted_value, original_value,
field_metadata)
'''
from calibre.utils.date import format_date
from ebook_converter.utils.date import format_date
# Handle custom series index
if key.startswith('#') and key.endswith('_index'):
@@ -715,8 +716,8 @@ class Metadata(object):
A string representation of this object, suitable for printing to
console
'''
from calibre.utils.date import isoformat
from calibre.ebooks.metadata import authors_to_string
from ebook_converter.utils.date import isoformat
from ebook_converter.ebooks.metadata import authors_to_string
ans = []
def fmt(x, y):
@@ -765,8 +766,8 @@ class Metadata(object):
'''
A HTML representation of this object.
'''
from calibre.ebooks.metadata import authors_to_string
from calibre.utils.date import isoformat
from ebook_converter.ebooks.metadata import authors_to_string
from ebook_converter.utils.date import isoformat
ans = [(_('Title'), unicode_type(self.title))]
ans += [(_('Author(s)'), (authors_to_string(self.authors) if self.authors else _('Unknown')))]
ans += [(_('Publisher'), unicode_type(self.publisher))]
@@ -817,7 +818,7 @@ def field_from_string(field, raw, field_metadata):
elif dt == 'rating':
val = float(raw) * 2
elif dt == 'datetime':
from calibre.utils.date import parse_only_date
from ebook_converter.utils.date import parse_only_date
val = parse_only_date(raw)
elif dt == 'bool':
if raw.lower() in {'true', 'yes', 'y'}:
@@ -833,7 +834,7 @@ def field_from_string(field, raw, field_metadata):
if field == 'identifiers':
val = {x.partition(':')[0]:x.partition(':')[-1] for x in val}
elif field == 'languages':
from calibre.utils.localization import canonicalize_lang
from ebook_converter.utils.localization import canonicalize_lang
val = [canonicalize_lang(x) for x in val]
val = [x for x in val if x]
if val is object:

6
ebook_converter/ebooks/metadata/book/formatter.py
View File

@@ -5,9 +5,9 @@ from __future__ import absolute_import, division, print_function, unicode_litera
__license__ = 'GPL v3'
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
from calibre.ebooks.metadata.book import TOP_LEVEL_IDENTIFIERS, ALL_METADATA_FIELDS
from ebook_converter.ebooks.metadata.book import TOP_LEVEL_IDENTIFIERS, ALL_METADATA_FIELDS
from calibre.utils.formatter import TemplateFormatter
from ebook_converter.utils.formatter import TemplateFormatter
class SafeFormat(TemplateFormatter):
@@ -21,7 +21,7 @@ class SafeFormat(TemplateFormatter):
key = orig_key = orig_key.lower()
if (key != 'title_sort' and key not in TOP_LEVEL_IDENTIFIERS and
key not in ALL_METADATA_FIELDS):
from calibre.ebooks.metadata.book.base import field_metadata
from ebook_converter.ebooks.metadata.book.base import field_metadata
key = field_metadata.search_term_to_field_key(key)
if key is None or (self.book and
key not in self.book.all_field_keys()):

18
ebook_converter/ebooks/metadata/book/json_codec.py
View File

@@ -9,19 +9,19 @@ Created on 4 Jun 2010
import json, traceback
from datetime import datetime, time
from calibre.ebooks.metadata.book import SERIALIZABLE_FIELDS
from calibre.constants import filesystem_encoding, preferred_encoding
from calibre.library.field_metadata import FieldMetadata
from calibre import isbytestring
from polyglot.builtins import iteritems, itervalues, as_bytes
from polyglot.binary import as_base64_unicode, from_base64_bytes
from ebook_converter.ebooks.metadata.book import SERIALIZABLE_FIELDS
from ebook_converter.constants import filesystem_encoding, preferred_encoding
from ebook_converter.library.field_metadata import FieldMetadata
from ebook_converter import isbytestring
from ebook_converter.polyglot.builtins import iteritems, itervalues, as_bytes
from ebook_converter.polyglot.binary import as_base64_unicode, from_base64_bytes
# Translate datetimes to and from strings. The string form is the datetime in
# UTC. The returned date is also UTC
def string_to_datetime(src):
from calibre.utils.iso8601 import parse_iso8601
from ebook_converter.utils.iso8601 import parse_iso8601
if src != "None":
try:
return parse_iso8601(src)
@@ -31,7 +31,7 @@ def string_to_datetime(src):
def datetime_to_string(dateval):
from calibre.utils.date import isoformat, UNDEFINED_DATE, local_tz
from ebook_converter.utils.date import isoformat, UNDEFINED_DATE, local_tz
if dateval is None:
return "None"
if not isinstance(dateval, datetime):
@@ -47,7 +47,7 @@ def encode_thumbnail(thumbnail):
'''
Encode the image part of a thumbnail, then return the 3 part tuple
'''
from calibre.utils.imghdr import identify
from ebook_converter.utils.imghdr import identify
if thumbnail is None:
return None
if not isinstance(thumbnail, (tuple, list)):

12
ebook_converter/ebooks/metadata/html.py
View File

@@ -15,12 +15,12 @@ from collections import defaultdict
from html5_parser import parse
from lxml.etree import Comment
from calibre.ebooks.metadata import string_to_authors, authors_to_string
from calibre.ebooks.metadata.book.base import Metadata
from calibre.ebooks.chardet import xml_to_unicode
from calibre import replace_entities, isbytestring
from calibre.utils.date import parse_date, is_date_undefined
from polyglot.builtins import iteritems
from ebook_converter.ebooks.metadata import string_to_authors, authors_to_string
from ebook_converter.ebooks.metadata.book.base import Metadata
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter import replace_entities, isbytestring
from ebook_converter.utils.date import parse_date, is_date_undefined
from ebook_converter.polyglot.builtins import iteritems
def get_metadata(stream):

18
ebook_converter/ebooks/metadata/meta.py
View File

@@ -5,13 +5,13 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
import os, re, collections
from calibre.utils.config import prefs
from calibre.constants import filesystem_encoding
from calibre.ebooks.metadata.opf2 import OPF
from calibre import isbytestring
from calibre.customize.ui import get_file_type_metadata, set_file_type_metadata
from calibre.ebooks.metadata import MetaInformation, string_to_authors
from polyglot.builtins import getcwd, unicode_type
from ebook_converter.utils.config import prefs
from ebook_converter.constants import filesystem_encoding
from ebook_converter.ebooks.metadata.opf2 import OPF
from ebook_converter import isbytestring
from ebook_converter.customize.ui import get_file_type_metadata, set_file_type_metadata
from ebook_converter.ebooks.metadata import MetaInformation, string_to_authors
from ebook_converter.polyglot.builtins import getcwd, unicode_type
# The priorities for loading metadata from different file types
# Higher values should be used to update metadata from lower values
@@ -184,7 +184,7 @@ def metadata_from_filename(name, pat=None, fallback_pat=None):
try:
pubdate = match.group('published')
if pubdate:
from calibre.utils.date import parse_only_date
from ebook_converter.utils.date import parse_only_date
mi.pubdate = parse_only_date(pubdate)
except:
pass
@@ -224,7 +224,7 @@ def opf_metadata(opfpath):
def forked_read_metadata(path, tdir):
from calibre.ebooks.metadata.opf2 import metadata_to_opf
from ebook_converter.ebooks.metadata.opf2 import metadata_to_opf
with lopen(path, 'rb') as f:
fmt = os.path.splitext(path)[1][1:].lower()
f.seek(0, 2)

12
ebook_converter/ebooks/metadata/odt.py
View File

@@ -27,17 +27,17 @@ import re
from lxml.etree import fromstring, tostring
from calibre.ebooks.metadata import (
from ebook_converter.ebooks.metadata import (
MetaInformation, authors_to_string, check_isbn, string_to_authors
)
from calibre.utils.date import isoformat, parse_date
from calibre.utils.imghdr import identify
from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
from calibre.utils.zipfile import ZipFile, safe_replace
from ebook_converter.utils.date import isoformat, parse_date
from ebook_converter.utils.imghdr import identify
from ebook_converter.utils.localization import canonicalize_lang, lang_as_iso639_1
from ebook_converter.utils.zipfile import ZipFile, safe_replace
from odf.draw import Frame as odFrame, Image as odImage
from odf.namespaces import DCNS, METANS, OFFICENS
from odf.opendocument import load as odLoad
from polyglot.builtins import as_unicode
from ebook_converter.polyglot.builtins import as_unicode
fields = {
'title': (DCNS, 'title'),

54
ebook_converter/ebooks/metadata/opf2.py
View File

@@ -12,20 +12,20 @@ import re, sys, unittest, functools, os, uuid, glob, io, json, copy
from lxml import etree
from calibre.ebooks import escape_xpath_attr
from calibre.constants import __appname__, __version__, filesystem_encoding, ispy3
from calibre.ebooks.metadata.toc import TOC
from calibre.ebooks.metadata.utils import parse_opf, pretty_print_opf as _pretty_print
from calibre.ebooks.metadata import string_to_authors, MetaInformation, check_isbn
from calibre.ebooks.metadata.book.base import Metadata
from calibre.utils.date import parse_date, isoformat
from calibre.utils.localization import get_lang, canonicalize_lang
from calibre import prints, guess_type
from calibre.utils.cleantext import clean_ascii_chars, clean_xml_chars
from calibre.utils.config import tweaks
from calibre.utils.xml_parse import safe_xml_fromstring
from polyglot.builtins import iteritems, unicode_type, getcwd, map
from polyglot.urllib import unquote, urlparse
from ebook_converter.ebooks import escape_xpath_attr
from ebook_converter.constants import __appname__, __version__, filesystem_encoding, ispy3
from ebook_converter.ebooks.metadata.toc import TOC
from ebook_converter.ebooks.metadata.utils import parse_opf, pretty_print_opf as _pretty_print
from ebook_converter.ebooks.metadata import string_to_authors, MetaInformation, check_isbn
from ebook_converter.ebooks.metadata.book.base import Metadata
from ebook_converter.utils.date import parse_date, isoformat
from ebook_converter.utils.localization import get_lang, canonicalize_lang
from ebook_converter import prints, guess_type
from ebook_converter.utils.cleantext import clean_ascii_chars, clean_xml_chars
from ebook_converter.utils.config import tweaks
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.polyglot.builtins import iteritems, unicode_type, getcwd, map
from ebook_converter.polyglot.urllib import unquote, urlparse
pretty_print_opf = False
@@ -487,8 +487,8 @@ class TitleSortField(MetadataField):
def serialize_user_metadata(metadata_elem, all_user_metadata, tail='\n'+(' '*8)):
from calibre.utils.config import to_json
from calibre.ebooks.metadata.book.json_codec import (object_to_unicode,
from ebook_converter.utils.config import to_json
from ebook_converter.ebooks.metadata.book.json_codec import (object_to_unicode,
encode_is_multiple)
for name, fm in all_user_metadata.items():
@@ -512,7 +512,7 @@ def serialize_user_metadata(metadata_elem, all_user_metadata, tail='\n'+(' '*8))
def dump_dict(cats):
if not cats:
cats = {}
from calibre.ebooks.metadata.book.json_codec import object_to_unicode
from ebook_converter.ebooks.metadata.book.json_codec import object_to_unicode
return json.dumps(object_to_unicode(cats), ensure_ascii=False,
skipkeys=True)
@@ -620,8 +620,8 @@ class OPF(object): # {{{
def read_user_metadata(self):
self._user_metadata_ = {}
temp = Metadata('x', ['x'])
from calibre.utils.config import from_json
from calibre.ebooks.metadata.book.json_codec import decode_is_multiple
from ebook_converter.utils.config import from_json
from ebook_converter.ebooks.metadata.book.json_codec import decode_is_multiple
elems = self.root.xpath('//*[name() = "meta" and starts-with(@name,'
'"calibre:user_metadata:") and @content]')
for elem in elems:
@@ -643,7 +643,7 @@ class OPF(object): # {{{
def to_book_metadata(self):
if self.package_version >= 3.0:
from calibre.ebooks.metadata.opf3 import read_metadata
from ebook_converter.ebooks.metadata.opf3 import read_metadata
return read_metadata(self.root)
ans = MetaInformation(self)
for n, v in self._user_metadata_.items():
@@ -964,7 +964,7 @@ class OPF(object): # {{{
found_scheme = False
for attr, val in iteritems(x.attrib):
if attr.endswith('scheme'):
typ = icu_lower(val)
typ = val.lower()
val = etree.tostring(x, with_tail=False, encoding='unicode',
method='text').strip()
if val and typ not in ('calibre', 'uuid'):
@@ -1447,7 +1447,7 @@ class OPFCreator(Metadata):
# Actual rendering
from lxml.builder import ElementMaker
from calibre.ebooks.oeb.base import OPF2_NS, DC11_NS, CALIBRE_NS
from ebook_converter.ebooks.oeb.base import OPF2_NS, DC11_NS, CALIBRE_NS
DNS = OPF2_NS+'___xx___'
E = ElementMaker(namespace=DNS, nsmap={None:DNS})
M = ElementMaker(namespace=DNS,
@@ -1494,7 +1494,7 @@ class OPFCreator(Metadata):
if self.publisher:
a(DC_ELEM('publisher', self.publisher))
for key, val in iteritems(self.get_identifiers()):
a(DC_ELEM('identifier', val, opf_attrs={'scheme':icu_upper(key)}))
a(DC_ELEM('identifier', val, opf_attrs={'scheme':key.upper()}))
if self.rights:
a(DC_ELEM('rights', self.rights))
if self.tags:
@@ -1513,7 +1513,7 @@ class OPFCreator(Metadata):
if self.publication_type is not None:
a(CAL_ELEM('calibre:publication_type', self.publication_type))
if self.user_categories:
from calibre.ebooks.metadata.book.json_codec import object_to_unicode
from ebook_converter.ebooks.metadata.book.json_codec import object_to_unicode
a(CAL_ELEM('calibre:user_categories',
json.dumps(object_to_unicode(self.user_categories))))
if self.primary_writing_mode:
@@ -1572,7 +1572,7 @@ class OPFCreator(Metadata):
def metadata_to_opf(mi, as_string=True, default_lang=None):
from lxml import etree
import textwrap
from calibre.ebooks.oeb.base import OPF, DC
from ebook_converter.ebooks.oeb.base import OPF, DC
if not mi.application_id:
mi.application_id = unicode_type(uuid.uuid4())
@@ -1641,7 +1641,7 @@ def metadata_to_opf(mi, as_string=True, default_lang=None):
if mi.publisher:
factory(DC('publisher'), mi.publisher)
for key, val in iteritems(mi.get_identifiers()):
factory(DC('identifier'), val, scheme=icu_upper(key))
factory(DC('identifier'), val, scheme=key.upper())
if mi.rights:
factory(DC('rights'), mi.rights)
for lang in mi.languages:
@@ -1689,7 +1689,7 @@ def metadata_to_opf(mi, as_string=True, default_lang=None):
def test_m2o():
from calibre.utils.date import now as nowf
from ebook_converter.utils.date import now as nowf
mi = MetaInformation('test & title', ['a"1', "a'2"])
mi.title_sort = 'a\'"b'
mi.author_sort = 'author sort'

22
ebook_converter/ebooks/metadata/opf3.py
View File

@@ -8,28 +8,28 @@ import json
import re
from collections import defaultdict, namedtuple
from functools import wraps
from polyglot.builtins import iteritems, map, filter
from ebook_converter.polyglot.builtins import iteritems, map, filter
from lxml import etree
from calibre import prints
from calibre.ebooks.metadata import authors_to_string, check_isbn, string_to_authors
from calibre.ebooks.metadata.book.base import Metadata
from calibre.ebooks.metadata.book.json_codec import (
from ebook_converter import prints
from ebook_converter.ebooks.metadata import authors_to_string, check_isbn, string_to_authors
from ebook_converter.ebooks.metadata.book.base import Metadata
from ebook_converter.ebooks.metadata.book.json_codec import (
decode_is_multiple, encode_is_multiple, object_to_unicode
)
from calibre.ebooks.metadata.utils import (
from ebook_converter.ebooks.metadata.utils import (
create_manifest_item, ensure_unique, normalize_languages, parse_opf,
pretty_print_opf
)
from calibre.ebooks.oeb.base import DC, OPF, OPF2_NSMAP
from calibre.utils.config import from_json, to_json
from calibre.utils.date import (
from ebook_converter.ebooks.oeb.base import DC, OPF, OPF2_NSMAP
from ebook_converter.utils.config import from_json, to_json
from ebook_converter.utils.date import (
fix_only_date, is_date_undefined, isoformat, parse_date as parse_date_, utcnow,
w3cdtf
)
from calibre.utils.iso8601 import parse_iso8601
from calibre.utils.localization import canonicalize_lang
from ebook_converter.utils.iso8601 import parse_iso8601
from ebook_converter.utils.localization import canonicalize_lang
# Utils {{{
_xpath_cache = {}

8
ebook_converter/ebooks/metadata/rtf.py
View File

@@ -9,9 +9,9 @@ from __future__ import absolute_import, division, print_function, unicode_litera
import codecs
import re
from calibre import force_unicode
from calibre.ebooks.metadata import MetaInformation
from polyglot.builtins import codepoint_to_chr, string_or_bytes, unicode_type, int_to_byte, filter
from ebook_converter import force_unicode
from ebook_converter.ebooks.metadata import MetaInformation
from ebook_converter.polyglot.builtins import codepoint_to_chr, string_or_bytes, unicode_type, int_to_byte, filter
title_pat = re.compile(br'\{\\info.*?\{\\title(.*?)(?<!\\)\}', re.DOTALL)
author_pat = re.compile(br'\{\\info.*?\{\\author(.*?)(?<!\\)\}', re.DOTALL)
@@ -232,7 +232,7 @@ def set_metadata(stream, options):
def find_tests():
import unittest
from io import BytesIO
from calibre.ebooks.metadata.book.base import Metadata
from ebook_converter.ebooks.metadata.book.base import Metadata
class Test(unittest.TestCase):

14
ebook_converter/ebooks/metadata/toc.py
View File

@@ -10,12 +10,12 @@ from collections import Counter
from lxml import etree
from lxml.builder import ElementMaker
from calibre.constants import __appname__, __version__
from calibre.ebooks.chardet import xml_to_unicode
from calibre.utils.xml_parse import safe_xml_fromstring
from calibre.utils.cleantext import clean_xml_chars
from polyglot.builtins import unicode_type, getcwd
from polyglot.urllib import unquote, urlparse
from ebook_converter.constants import __appname__, __version__
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.polyglot.builtins import unicode_type, getcwd
from ebook_converter.polyglot.urllib import unquote, urlparse
NCX_NS = "http://www.daisy.org/z3986/2005/ncx/"
CALIBRE_NS = "http://calibre.kovidgoyal.net/2009/metadata"
@@ -26,7 +26,7 @@ C = ElementMaker(namespace=CALIBRE_NS, nsmap=NSMAP)
def parse_html_toc(data):
from html5_parser import parse
from calibre.utils.cleantext import clean_xml_chars
from ebook_converter.utils.cleantext import clean_xml_chars
from lxml import etree
if isinstance(data, bytes):
data = xml_to_unicode(data, strip_encoding_pats=True, resolve_entities=True)[0]

18
ebook_converter/ebooks/metadata/utils.py
View File

@@ -6,14 +6,14 @@ from __future__ import absolute_import, division, print_function, unicode_litera
from collections import namedtuple
from calibre.ebooks.chardet import xml_to_unicode
from calibre.ebooks.oeb.base import OPF
from calibre.ebooks.oeb.polish.utils import guess_type
from calibre.spell import parse_lang_code
from calibre.utils.cleantext import clean_xml_chars
from calibre.utils.localization import lang_as_iso639_1
from calibre.utils.xml_parse import safe_xml_fromstring
from polyglot.builtins import filter, map
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.ebooks.oeb.base import OPF
from ebook_converter.ebooks.oeb.polish.utils import guess_type
from ebook_converter.spell import parse_lang_code
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.utils.localization import lang_as_iso639_1
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.polyglot.builtins import filter, map
OPFVersion = namedtuple('OPFVersion', 'major minor patch')
@@ -99,6 +99,6 @@ def create_manifest_item(root, href_template, id_template, media_type=None):
def pretty_print_opf(root):
from calibre.ebooks.oeb.polish.pretty import pretty_opf, pretty_xml_tree
from ebook_converter.ebooks.oeb.polish.pretty import pretty_opf, pretty_xml_tree
pretty_opf(root)
pretty_xml_tree(root)