Enable docx write support

README.rst

@@ -67,6 +67,7 @@ Currently, following formats are supported:
 - lrf (for Sony readers)
 - epub
 - mobi
+- docx
 
 
 Installation

ebook_converter/ebooks/docx/writer/__init__.py

@@ -1,9 +0,0 @@
-#!/usr/bin/env python2
-# vim:fileencoding=utf-8
-from __future__ import absolute_import, division, print_function, unicode_literals
-
-__license__ = 'GPL v3'
-__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
-
-
-

ebook_converter/ebooks/docx/writer/container.py

@@ -10,15 +10,15 @@ import textwrap, os
 from lxml import etree
 from lxml.builder import ElementMaker
 
-from calibre import guess_type
-from calibre.constants import numeric_version, __appname__
-from calibre.ebooks.docx.names import DOCXNamespace
-from calibre.ebooks.metadata import authors_to_string
-from calibre.ebooks.pdf.render.common import PAPER_SIZES
-from calibre.utils.date import utcnow
-from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
-from calibre.utils.zipfile import ZipFile
-from polyglot.builtins import iteritems, map, unicode_type, native_string_type
+from ebook_converter import guess_type
+from ebook_converter.constants import numeric_version, __appname__
+from ebook_converter.ebooks.docx.names import DOCXNamespace
+from ebook_converter.ebooks.metadata import authors_to_string
+from ebook_converter.ebooks.pdf.render.common import PAPER_SIZES
+from ebook_converter.utils.date import utcnow
+from ebook_converter.utils.localization import canonicalize_lang, lang_as_iso639_1
+from ebook_converter.utils.zipfile import ZipFile
+from ebook_converter.polyglot.builtins import iteritems, map, unicode_type, native_string_type
 
 
 def xml2str(root, pretty_print=False, with_tail=False):

ebook_converter/ebooks/docx/writer/fonts.py

@@ -8,9 +8,9 @@ __copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
 from collections import defaultdict
 from uuid import uuid4
 
-from calibre.ebooks.oeb.base import OEB_STYLES
-from calibre.ebooks.oeb.transforms.subset import find_font_face_rules
-from polyglot.builtins import range
+from ebook_converter.ebooks.oeb.base import OEB_STYLES
+from ebook_converter.ebooks.oeb.transforms.subset import find_font_face_rules
+from ebook_converter.polyglot.builtins import range
 
 
 def obfuscate_font_data(data, key):

ebook_converter/ebooks/docx/writer/from_html.py

@@ -8,17 +8,17 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 import re
 from collections import Counter
 
-from calibre.ebooks.docx.writer.container import create_skeleton, page_size, page_effective_area
-from calibre.ebooks.docx.writer.styles import StylesManager, FloatSpec
-from calibre.ebooks.docx.writer.links import LinksManager
-from calibre.ebooks.docx.writer.images import ImagesManager
-from calibre.ebooks.docx.writer.fonts import FontsManager
-from calibre.ebooks.docx.writer.tables import Table
-from calibre.ebooks.docx.writer.lists import ListsManager
-from calibre.ebooks.oeb.stylizer import Stylizer as Sz, Style as St
-from calibre.ebooks.oeb.base import XPath, barename
-from calibre.utils.localization import lang_as_iso639_1
-from polyglot.builtins import unicode_type, string_or_bytes
+from ebook_converter.ebooks.docx.writer.container import create_skeleton, page_size, page_effective_area
+from ebook_converter.ebooks.docx.writer.styles import StylesManager, FloatSpec
+from ebook_converter.ebooks.docx.writer.links import LinksManager
+from ebook_converter.ebooks.docx.writer.images import ImagesManager
+from ebook_converter.ebooks.docx.writer.fonts import FontsManager
+from ebook_converter.ebooks.docx.writer.tables import Table
+from ebook_converter.ebooks.docx.writer.lists import ListsManager
+from ebook_converter.ebooks.oeb.stylizer import Stylizer as Sz, Style as St
+from ebook_converter.ebooks.oeb.base import XPath, barename
+from ebook_converter.utils.localization import lang_as_iso639_1
+from ebook_converter.polyglot.builtins import unicode_type, string_or_bytes
 
 
 def lang_for_tag(tag):
@@ -424,7 +424,7 @@ class Convert(object):
         p.width_pts, p.height_pts = page_effective_area(self.opts)
 
     def __call__(self):
-        from calibre.ebooks.oeb.transforms.rasterize import SVGRasterizer
+        from ebook_converter.ebooks.oeb.transforms.rasterize import SVGRasterizer
         self.svg_rasterizer = SVGRasterizer(base_css=self.base_css)
         self.svg_rasterizer(self.oeb, self.opts)
 

ebook_converter/ebooks/docx/writer/images.py

@@ -9,15 +9,15 @@ import os
 import posixpath
 from collections import namedtuple
 from functools import partial
-from polyglot.builtins import iteritems, itervalues, map, unicode_type
+from ebook_converter.polyglot.builtins import iteritems, itervalues, map, unicode_type
 
 from lxml import etree
 
-from calibre import fit_image
-from calibre.ebooks.oeb.base import urlunquote
-from calibre.ebooks.docx.images import pt_to_emu
-from calibre.utils.filenames import ascii_filename
-from calibre.utils.imghdr import identify
+from ebook_converter import fit_image
+from ebook_converter.ebooks.oeb.base import urlunquote
+from ebook_converter.ebooks.docx.images import pt_to_emu
+from ebook_converter.utils.filenames import ascii_filename
+from ebook_converter.utils.imghdr import identify
 
 Image = namedtuple('Image', 'rid fname width height fmt item')
 

ebook_converter/ebooks/docx/writer/links.py

@@ -8,9 +8,9 @@ __copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
 import posixpath, re
 from uuid import uuid4
 
-from calibre.utils.filenames import ascii_text
-from polyglot.builtins import unicode_type
-from polyglot.urllib import urlparse
+from ebook_converter.utils.filenames import ascii_text
+from ebook_converter.polyglot.builtins import unicode_type
+from ebook_converter.polyglot.urllib import urlparse
 
 
 def start_text(tag, prefix_len=0, top_level=True):

ebook_converter/ebooks/docx/writer/lists.py

@@ -8,7 +8,7 @@ __copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
 from collections import defaultdict
 from operator import attrgetter
 
-from polyglot.builtins import iteritems, itervalues, unicode_type
+from ebook_converter.polyglot.builtins import iteritems, itervalues, unicode_type
 
 LIST_STYLES = frozenset(
     'disc circle square decimal decimal-leading-zero lower-roman upper-roman'

ebook_converter/ebooks/docx/writer/styles.py

@@ -11,10 +11,10 @@ from operator import attrgetter
 
 from lxml import etree
 
-from calibre.ebooks import parse_css_length
-from calibre.ebooks.docx.writer.utils import convert_color, int_or_zero
-from calibre.utils.localization import lang_as_iso639_1
-from polyglot.builtins import iteritems, filter, unicode_type
+from ebook_converter.ebooks import parse_css_length
+from ebook_converter.ebooks.docx.writer.utils import convert_color, int_or_zero
+from ebook_converter.utils.localization import lang_as_iso639_1
+from ebook_converter.polyglot.builtins import iteritems, filter, unicode_type
 from tinycss.css21 import CSS21Parser
 
 css_parser = CSS21Parser()

ebook_converter/ebooks/docx/writer/tables.py

@@ -7,9 +7,9 @@ __copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
 
 from collections import namedtuple
 
-from calibre.ebooks.docx.writer.utils import convert_color
-from calibre.ebooks.docx.writer.styles import read_css_block_borders as rcbb, border_edges
-from polyglot.builtins import iteritems, range, unicode_type
+from ebook_converter.ebooks.docx.writer.utils import convert_color
+from ebook_converter.ebooks.docx.writer.styles import read_css_block_borders as rcbb, border_edges
+from ebook_converter.polyglot.builtins import iteritems, range, unicode_type
 
 
 class Dummy(object):

ebook_converter/ebooks/oeb/transforms/subset.py

@@ -8,10 +8,10 @@ __docformat__ = 'restructuredtext en'
 
 from collections import defaultdict
 
-from calibre.ebooks.oeb.base import urlnormalize, css_text
-from calibre.utils.fonts.sfnt.subset import subset, NoGlyphs, UnsupportedFont
-from polyglot.builtins import iteritems, itervalues, unicode_type, range
-from tinycss.fonts3 import parse_font_family
+from ebook_converter.ebooks.oeb.base import urlnormalize, css_text
+from ebook_converter.utils.fonts.sfnt.subset import subset, NoGlyphs, UnsupportedFont
+from ebook_converter.polyglot.builtins import iteritems, itervalues, unicode_type, range
+from ebook_converter.tinycss.fonts3 import parse_font_family
 
 
 def get_font_properties(rule, default=None):

ebook_converter/ebooks/pdf/render/__init__.py

@@ -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__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
-__docformat__ = 'restructuredtext en'
-
-
-

ebook_converter/ebooks/pdf/render/common.py

@@ -10,12 +10,12 @@ import codecs, zlib, numbers
 from io import BytesIO
 from datetime import datetime
 
-from calibre.constants import plugins, ispy3
-from calibre.utils.logging import default_log
-from polyglot.builtins import iteritems, unicode_type, codepoint_to_chr
-from polyglot.binary import as_hex_bytes
+from ebook_converter.constants import ispy3
+from ebook_converter.utils.logging import default_log
+from ebook_converter.polyglot.builtins import iteritems, unicode_type, codepoint_to_chr
+from ebook_converter.polyglot.binary import as_hex_bytes
 
-pdf_float = plugins['speedup'][0].pdf_float
+pdf_float = lambda x: f"{x:.1f}"
 
 EOL = b'\n'
 

ebook_converter/utils/fonts/sfnt/__init__.py

@@ -75,6 +75,6 @@ def load_font(stream_or_path):
     raw = stream_or_path
     if hasattr(raw, 'read'):
         raw = raw.read()
-    from calibre.utils.fonts.sfnt.container import Sfnt
+    from ebook_converter.utils.fonts.sfnt.container import Sfnt
     return Sfnt(raw)
 

ebook_converter/utils/fonts/sfnt/cff/__init__.py

@@ -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__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
-__docformat__ = 'restructuredtext en'
-
-
-

ebook_converter/utils/fonts/sfnt/cff/dict_data.py

@@ -7,7 +7,7 @@ __copyright__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
 from struct import pack, unpack_from
-from polyglot.builtins import range, unicode_type
+from ebook_converter.polyglot.builtins import range, unicode_type
 
 t1_operand_encoding = [None] * 256
 t1_operand_encoding[0:32] = (32) * ["do_operator"]

ebook_converter/utils/fonts/sfnt/cff/table.py

@@ -9,12 +9,12 @@ __docformat__ = 'restructuredtext en'
 from struct import unpack_from, unpack, calcsize
 from functools import partial
 
-from calibre.utils.fonts.sfnt import UnknownTable
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont, NoGlyphs
-from calibre.utils.fonts.sfnt.cff.dict_data import TopDict, PrivateDict
-from calibre.utils.fonts.sfnt.cff.constants import (cff_standard_strings,
+from ebook_converter.utils.fonts.sfnt import UnknownTable
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont, NoGlyphs
+from ebook_converter.utils.fonts.sfnt.cff.dict_data import TopDict, PrivateDict
+from ebook_converter.utils.fonts.sfnt.cff.constants import (cff_standard_strings,
         STANDARD_CHARSETS)
-from polyglot.builtins import iteritems, itervalues, range
+from ebook_converter.polyglot.builtins import iteritems, itervalues, range
 
 # Useful links
 # http://www.adobe.com/content/dam/Adobe/en/devnet/font/pdfs/5176.CFF.pdf
@@ -194,7 +194,7 @@ class CFFTable(UnknownTable):
         self.cff = CFF(self.raw)
 
     def subset(self, character_map, extra_glyphs):
-        from calibre.utils.fonts.sfnt.cff.writer import Subset
+        from ebook_converter.utils.fonts.sfnt.cff.writer import Subset
         # Map codes from the cmap table to glyph names, this will be used to
         # reconstruct character_map for the subset font
         charset_map = {code:self.cff.charset.safe_lookup(glyph_id) for code,

ebook_converter/utils/fonts/sfnt/cmap.py

@@ -12,10 +12,10 @@ __docformat__ = 'restructuredtext en'
 from struct import unpack_from, calcsize, pack
 from collections import OrderedDict
 
-from calibre.utils.fonts.utils import read_bmp_prefix
-from calibre.utils.fonts.sfnt import UnknownTable, max_power_of_two
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont
-from polyglot.builtins import range
+from ebook_converter.utils.fonts.utils import read_bmp_prefix
+from ebook_converter.utils.fonts.sfnt import UnknownTable, max_power_of_two
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont
+from ebook_converter.polyglot.builtins import range
 
 
 def split_range(start_code, end_code, cmap):  # {{{

ebook_converter/utils/fonts/sfnt/common.py

@@ -9,8 +9,8 @@ __docformat__ = 'restructuredtext en'
 from struct import unpack_from, calcsize
 from collections import OrderedDict, namedtuple
 
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont
-from polyglot.builtins import range, iteritems
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont
+from ebook_converter.polyglot.builtins import range, iteritems
 
 
 class Unpackable(object):

ebook_converter/utils/fonts/sfnt/container.py

@@ -7,19 +7,19 @@ from collections import OrderedDict
 from io import BytesIO
 from struct import calcsize, pack
 
-from calibre.utils.fonts.sfnt import UnknownTable, align_block, max_power_of_two
-from calibre.utils.fonts.sfnt.cff.table import CFFTable
-from calibre.utils.fonts.sfnt.cmap import CmapTable
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont
-from calibre.utils.fonts.sfnt.glyf import GlyfTable
-from calibre.utils.fonts.sfnt.gsub import GSUBTable
-from calibre.utils.fonts.sfnt.head import (
+from ebook_converter.utils.fonts.sfnt import UnknownTable, align_block, max_power_of_two
+from ebook_converter.utils.fonts.sfnt.cff.table import CFFTable
+from ebook_converter.utils.fonts.sfnt.cmap import CmapTable
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont
+from ebook_converter.utils.fonts.sfnt.glyf import GlyfTable
+from ebook_converter.utils.fonts.sfnt.gsub import GSUBTable
+from ebook_converter.utils.fonts.sfnt.head import (
     HeadTable, HorizontalHeader, OS2Table, PostTable, VerticalHeader
 )
-from calibre.utils.fonts.sfnt.kern import KernTable
-from calibre.utils.fonts.sfnt.loca import LocaTable
-from calibre.utils.fonts.sfnt.maxp import MaxpTable
-from calibre.utils.fonts.utils import checksum_of_block, get_tables, verify_checksums
+from ebook_converter.utils.fonts.sfnt.kern import KernTable
+from ebook_converter.utils.fonts.sfnt.loca import LocaTable
+from ebook_converter.utils.fonts.sfnt.maxp import MaxpTable
+from ebook_converter.utils.fonts.utils import checksum_of_block, get_tables, verify_checksums
 
 # OpenType spec: http://www.microsoft.com/typography/otspec/otff.htm
 

ebook_converter/utils/fonts/sfnt/glyf.py

@@ -9,8 +9,8 @@ __docformat__ = 'restructuredtext en'
 from struct import unpack_from
 from collections import OrderedDict
 
-from calibre.utils.fonts.sfnt import UnknownTable
-from polyglot.builtins import iteritems
+from ebook_converter.utils.fonts.sfnt import UnknownTable
+from ebook_converter.polyglot.builtins import iteritems
 
 ARG_1_AND_2_ARE_WORDS      = 0x0001  # if set args are words otherwise they are bytes
 ARGS_ARE_XY_VALUES         = 0x0002  # if set args are xy values, otherwise they are points

ebook_converter/utils/fonts/sfnt/gsub.py

@@ -9,12 +9,12 @@ __docformat__ = 'restructuredtext en'
 from struct import unpack_from
 from functools import partial
 
-from calibre.utils.fonts.sfnt import UnknownTable, FixedProperty
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont
-from calibre.utils.fonts.sfnt.common import (ScriptListTable, FeatureListTable,
+from ebook_converter.utils.fonts.sfnt import UnknownTable, FixedProperty
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont
+from ebook_converter.utils.fonts.sfnt.common import (ScriptListTable, FeatureListTable,
         SimpleListTable, LookupTable, ExtensionSubstitution,
         UnknownLookupSubTable)
-from polyglot.builtins import iteritems, itervalues
+from ebook_converter.polyglot.builtins import iteritems, itervalues
 
 
 class SingleSubstitution(UnknownLookupSubTable):

ebook_converter/utils/fonts/sfnt/head.py

@@ -8,10 +8,10 @@ __docformat__ = 'restructuredtext en'
 
 from struct import unpack_from, pack, calcsize
 
-from calibre.utils.fonts.sfnt import UnknownTable, DateTimeProperty, FixedProperty
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont
-from calibre.utils.fonts.sfnt.loca import read_array
-from polyglot.builtins import zip
+from ebook_converter.utils.fonts.sfnt import UnknownTable, DateTimeProperty, FixedProperty
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont
+from ebook_converter.utils.fonts.sfnt.loca import read_array
+from ebook_converter.polyglot.builtins import zip
 
 
 class HeadTable(UnknownTable):

ebook_converter/utils/fonts/sfnt/kern.py

@@ -8,10 +8,10 @@ __docformat__ = 'restructuredtext en'
 
 from struct import unpack_from, calcsize, pack, error as struct_error
 
-from calibre.utils.fonts.sfnt import (UnknownTable, FixedProperty,
+from ebook_converter.utils.fonts.sfnt import (UnknownTable, FixedProperty,
         max_power_of_two)
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont
-from polyglot.builtins import range
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont
+from ebook_converter.polyglot.builtins import range
 
 
 class KernTable(UnknownTable):

ebook_converter/utils/fonts/sfnt/loca.py

@@ -10,8 +10,8 @@ import array, sys
 from operator import itemgetter
 from itertools import repeat
 
-from calibre.utils.fonts.sfnt import UnknownTable
-from polyglot.builtins import iteritems, range
+from ebook_converter.utils.fonts.sfnt import UnknownTable
+from ebook_converter.polyglot.builtins import iteritems, range
 
 
 def four_byte_type_code():

ebook_converter/utils/fonts/sfnt/maxp.py

@@ -8,9 +8,9 @@ __docformat__ = 'restructuredtext en'
 
 from struct import unpack_from, pack
 
-from calibre.utils.fonts.sfnt import UnknownTable, FixedProperty
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont
-from polyglot.builtins import zip
+from ebook_converter.utils.fonts.sfnt import UnknownTable, FixedProperty
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont
+from ebook_converter.polyglot.builtins import zip
 
 
 class MaxpTable(UnknownTable):

ebook_converter/utils/fonts/sfnt/subset.py

@@ -11,10 +11,10 @@ from collections import OrderedDict
 from operator import itemgetter
 from functools import partial
 
-from calibre.utils.icu import safe_chr, ord_string
-from calibre.utils.fonts.sfnt.container import Sfnt
-from calibre.utils.fonts.sfnt.errors import UnsupportedFont, NoGlyphs
-from polyglot.builtins import unicode_type, range, iteritems, itervalues, map
+from ebook_converter.utils.icu import safe_chr, ord_string
+from ebook_converter.utils.fonts.sfnt.container import Sfnt
+from ebook_converter.utils.fonts.sfnt.errors import UnsupportedFont, NoGlyphs
+from ebook_converter.polyglot.builtins import unicode_type, range, iteritems, itervalues, map
 
 # TrueType outlines {{{
 
@@ -193,7 +193,7 @@ def subset(raw, individual_chars, ranges=(), warnings=None):
 
 def option_parser():
     import textwrap
-    from calibre.utils.config import OptionParser
+    from ebook_converter.utils.config import OptionParser
     parser = OptionParser(usage=textwrap.dedent('''\
             %prog [options] input_font_file output_font_file characters_to_keep
 
@@ -212,7 +212,7 @@ def option_parser():
 
 
 def print_stats(old_stats, new_stats):
-    from calibre import prints
+    from ebook_converter import prints
     prints('========= Table comparison (original vs. subset) =========')
     prints('Table', ' ', '%10s'%'Size', '  ', 'Percent', '   ', '%10s'%'New Size',
             ' New Percent')
@@ -236,7 +236,7 @@ def print_stats(old_stats, new_stats):
 
 def main(args):
     import sys, time
-    from calibre import prints
+    from ebook_converter import prints
     parser = option_parser()
     opts, args = parser.parse_args(args)
     if len(args) < 4 or len(args) > 4:
@@ -303,7 +303,7 @@ if __name__ == '__main__':
 
 
 def test_mem():
-    from calibre.utils.mem import memory
+    from ebook_converter.utils.mem import memory
     import gc
     gc.collect()
     start_mem = memory()
@@ -325,7 +325,7 @@ def test():
 
 
 def all():
-    from calibre.utils.fonts.scanner import font_scanner
+    from ebook_converter.utils.fonts.scanner import font_scanner
     failed = []
     unsupported = []
     warnings = {}