Convert calibre modules to ebook_converter.

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.

ebook_converter/ebooks/docx/block_styles.py

@@ -7,7 +7,7 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 
 import numbers
 from collections import OrderedDict
-from polyglot.builtins import iteritems
+from ebook_converter.polyglot.builtins import iteritems
 
 
 class Inherit(object):

ebook_converter/ebooks/docx/char_styles.py

@@ -6,7 +6,7 @@ __license__ = 'GPL v3'
 __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 
 from collections import OrderedDict
-from calibre.ebooks.docx.block_styles import (  # noqa
+from ebook_converter.ebooks.docx.block_styles import (  # noqa
     inherit, simple_color, LINE_STYLES, simple_float, binary_property, read_shd)
 
 # Read from XML {{{
@@ -89,7 +89,7 @@ def read_lang(parent, dest, XPath, get):
         except (ValueError, TypeError):
             ans = val
         else:
-            from calibre.ebooks.docx.lcid import lcid
+            from ebook_converter.ebooks.docx.lcid import lcid
             val = lcid.get(code, None)
             if val:
                 ans = val

ebook_converter/ebooks/docx/cleanup.py

@@ -6,7 +6,7 @@ __license__ = 'GPL v3'
 __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 
 import os
-from polyglot.builtins import itervalues, range
+from ebook_converter.polyglot.builtins import itervalues, range
 
 NBSP = '\xa0'
 
@@ -218,7 +218,7 @@ def cleanup_markup(log, root, styles, dest_dir, detect_cover, XPath):
             img = img[0]
             path = os.path.join(dest_dir, img.get('src'))
             if os.path.exists(path) and before_count(root, img, limit=10) < 5:
-                from calibre.utils.imghdr import identify
+                from ebook_converter.utils.imghdr import identify
                 try:
                     with lopen(path, 'rb') as imf:
                         fmt, width, height = identify(imf)

ebook_converter/ebooks/docx/container.py

@@ -9,16 +9,16 @@ import os, sys, shutil
 
 from lxml import etree
 
-from calibre import walk, guess_type
-from calibre.ebooks.metadata import string_to_authors, authors_to_sort_string
-from calibre.ebooks.metadata.book.base import Metadata
-from calibre.ebooks.docx import InvalidDOCX
-from calibre.ebooks.docx.names import DOCXNamespace
-from calibre.ptempfile import PersistentTemporaryDirectory
-from calibre.utils.localization import canonicalize_lang
-from calibre.utils.logging import default_log
-from calibre.utils.zipfile import ZipFile
-from calibre.utils.xml_parse import safe_xml_fromstring
+from ebook_converter import walk, guess_type
+from ebook_converter.ebooks.metadata import string_to_authors, authors_to_sort_string
+from ebook_converter.ebooks.metadata.book.base import Metadata
+from ebook_converter.ebooks.docx import InvalidDOCX
+from ebook_converter.ebooks.docx.names import DOCXNamespace
+from ebook_converter.ptempfile import PersistentTemporaryDirectory
+from ebook_converter.utils.localization import canonicalize_lang
+from ebook_converter.utils.logging import default_log
+from ebook_converter.utils.zipfile import ZipFile
+from ebook_converter.utils.xml_parse import safe_xml_fromstring
 
 
 def fromstring(raw, parser=None):
@@ -113,7 +113,7 @@ class DOCX(object):
         except:
             self.log.exception('DOCX 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, self.tdir)
 

ebook_converter/ebooks/docx/fields.py

@@ -7,8 +7,8 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 
 import re
 
-from calibre.ebooks.docx.index import process_index, polish_index_markup
-from polyglot.builtins import iteritems, native_string_type
+from ebook_converter.ebooks.docx.index import process_index, polish_index_markup
+from ebook_converter.polyglot.builtins import iteritems, native_string_type
 
 
 class Field(object):

ebook_converter/ebooks/docx/fonts.py

@@ -8,12 +8,12 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 import os, re
 from collections import namedtuple
 
-from calibre.ebooks.docx.block_styles import binary_property, inherit
-from calibre.utils.filenames import ascii_filename
-from calibre.utils.fonts.scanner import font_scanner, NoFonts
-from calibre.utils.fonts.utils import panose_to_css_generic_family, is_truetype_font
-from calibre.utils.icu import ord_string
-from polyglot.builtins import codepoint_to_chr, iteritems, range
+from ebook_converter.ebooks.docx.block_styles import binary_property, inherit
+from ebook_converter.utils.filenames import ascii_filename
+from ebook_converter.utils.fonts.scanner import font_scanner, NoFonts
+from ebook_converter.utils.fonts.utils import panose_to_css_generic_family, is_truetype_font
+from ebook_converter.utils.icu import ord_string
+from ebook_converter.polyglot.builtins import codepoint_to_chr, iteritems, range
 
 Embed = namedtuple('Embed', 'name key subsetted')
 

ebook_converter/ebooks/docx/footnotes.py

@@ -6,7 +6,7 @@ __license__ = 'GPL v3'
 __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 
 from collections import OrderedDict
-from polyglot.builtins import iteritems, unicode_type
+from ebook_converter.polyglot.builtins import iteritems, unicode_type
 
 
 class Note(object):

ebook_converter/ebooks/docx/images.py

@@ -9,12 +9,12 @@ import os
 
 from lxml.html.builder import IMG, HR
 
-from calibre.constants import iswindows
-from calibre.ebooks.docx.names import barename
-from calibre.utils.filenames import ascii_filename
-from calibre.utils.img import resize_to_fit, image_to_data
-from calibre.utils.imghdr import what
-from polyglot.builtins import iteritems, itervalues
+from ebook_converter.constants import iswindows
+from ebook_converter.ebooks.docx.names import barename
+from ebook_converter.utils.filenames import ascii_filename
+from ebook_converter.utils.img import resize_to_fit, image_to_data
+from ebook_converter.utils.imghdr import what
+from ebook_converter.polyglot.builtins import iteritems, itervalues
 
 
 class LinkedImageNotFound(ValueError):
@@ -143,7 +143,7 @@ class Images(object):
         if ext == 'emf':
             # For an example, see: https://bugs.launchpad.net/bugs/1224849
             self.log('Found an EMF image: %s, trying to extract embedded raster image' % fname)
-            from calibre.utils.wmf.emf import emf_unwrap
+            from ebook_converter.utils.wmf.emf import emf_unwrap
             try:
                 raw = emf_unwrap(raw)
             except Exception:

ebook_converter/ebooks/docx/index.py

@@ -9,8 +9,8 @@ from operator import itemgetter
 
 from lxml import etree
 
-from calibre.utils.icu import partition_by_first_letter, sort_key
-from polyglot.builtins import iteritems, filter
+from ebook_converter.utils.icu import partition_by_first_letter, sort_key
+from ebook_converter.polyglot.builtins import iteritems, filter
 
 
 def get_applicable_xe_fields(index, xe_fields, XPath, expand):

ebook_converter/ebooks/docx/names.py

@@ -9,8 +9,8 @@ import re
 
 from lxml.etree import XPath as X
 
-from calibre.utils.filenames import ascii_text
-from polyglot.builtins import iteritems
+from ebook_converter.utils.filenames import ascii_text
+from ebook_converter.polyglot.builtins import iteritems
 
 # Names {{{
 TRANSITIONAL_NAMES = {

ebook_converter/ebooks/docx/numbering.py

@@ -11,10 +11,10 @@ from functools import partial
 
 from lxml.html.builder import OL, UL, SPAN
 
-from calibre.ebooks.docx.block_styles import ParagraphStyle
-from calibre.ebooks.docx.char_styles import RunStyle, inherit
-from calibre.ebooks.metadata import roman
-from polyglot.builtins import iteritems, unicode_type
+from ebook_converter.ebooks.docx.block_styles import ParagraphStyle
+from ebook_converter.ebooks.docx.char_styles import RunStyle, inherit
+from ebook_converter.ebooks.metadata import roman
+from ebook_converter.polyglot.builtins import iteritems, unicode_type
 
 STYLE_MAP = {
     'aiueo': 'hiragana',

ebook_converter/ebooks/docx/styles.py

@@ -8,10 +8,10 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 import textwrap
 from collections import OrderedDict, Counter
 
-from calibre.ebooks.docx.block_styles import ParagraphStyle, inherit, twips
-from calibre.ebooks.docx.char_styles import RunStyle
-from calibre.ebooks.docx.tables import TableStyle
-from polyglot.builtins import iteritems, itervalues
+from ebook_converter.ebooks.docx.block_styles import ParagraphStyle, inherit, twips
+from ebook_converter.ebooks.docx.char_styles import RunStyle
+from ebook_converter.ebooks.docx.tables import TableStyle
+from ebook_converter.polyglot.builtins import iteritems, itervalues
 
 
 class PageProperties(object):

ebook_converter/ebooks/docx/tables.py

@@ -7,9 +7,9 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 
 from lxml.html.builder import TABLE, TR, TD
 
-from calibre.ebooks.docx.block_styles import inherit, read_shd as rs, read_border, binary_property, border_props, ParagraphStyle, border_to_css
-from calibre.ebooks.docx.char_styles import RunStyle
-from polyglot.builtins import filter, iteritems, itervalues, range, unicode_type
+from ebook_converter.ebooks.docx.block_styles import inherit, read_shd as rs, read_border, binary_property, border_props, ParagraphStyle, border_to_css
+from ebook_converter.ebooks.docx.char_styles import RunStyle
+from ebook_converter.polyglot.builtins import filter, iteritems, itervalues, range, unicode_type
 
 # Read from XML {{{
 read_shd = rs

ebook_converter/ebooks/docx/to_html.py

@@ -12,23 +12,23 @@ from lxml import html
 from lxml.html.builder import (
     HTML, HEAD, TITLE, BODY, LINK, META, P, SPAN, BR, DIV, A, DT, DL, DD, H1)
 
-from calibre import guess_type
-from calibre.ebooks.docx.container import DOCX, fromstring
-from calibre.ebooks.docx.names import XML, generate_anchor
-from calibre.ebooks.docx.styles import Styles, inherit, PageProperties
-from calibre.ebooks.docx.numbering import Numbering
-from calibre.ebooks.docx.fonts import Fonts, is_symbol_font, map_symbol_text
-from calibre.ebooks.docx.images import Images
-from calibre.ebooks.docx.tables import Tables
-from calibre.ebooks.docx.footnotes import Footnotes
-from calibre.ebooks.docx.cleanup import cleanup_markup
-from calibre.ebooks.docx.theme import Theme
-from calibre.ebooks.docx.toc import create_toc
-from calibre.ebooks.docx.fields import Fields
-from calibre.ebooks.docx.settings import Settings
-from calibre.ebooks.metadata.opf2 import OPFCreator
-from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
-from polyglot.builtins import iteritems, itervalues, filter, getcwd, map, unicode_type
+from ebook_converter import guess_type
+from ebook_converter.ebooks.docx.container import DOCX, fromstring
+from ebook_converter.ebooks.docx.names import XML, generate_anchor
+from ebook_converter.ebooks.docx.styles import Styles, inherit, PageProperties
+from ebook_converter.ebooks.docx.numbering import Numbering
+from ebook_converter.ebooks.docx.fonts import Fonts, is_symbol_font, map_symbol_text
+from ebook_converter.ebooks.docx.images import Images
+from ebook_converter.ebooks.docx.tables import Tables
+from ebook_converter.ebooks.docx.footnotes import Footnotes
+from ebook_converter.ebooks.docx.cleanup import cleanup_markup
+from ebook_converter.ebooks.docx.theme import Theme
+from ebook_converter.ebooks.docx.toc import create_toc
+from ebook_converter.ebooks.docx.fields import Fields
+from ebook_converter.ebooks.docx.settings import Settings
+from ebook_converter.ebooks.metadata.opf2 import OPFCreator
+from ebook_converter.utils.localization import canonicalize_lang, lang_as_iso639_1
+from ebook_converter.polyglot.builtins import iteritems, itervalues, filter, getcwd, map, unicode_type
 
 
 NBSP = '\xa0'
@@ -830,7 +830,7 @@ class Convert(object):
 
 if __name__ == '__main__':
     import shutil
-    from calibre.utils.logging import default_log
+    from ebook_converter.utils.logging import default_log
     default_log.filter_level = default_log.DEBUG
     dest_dir = os.path.join(getcwd(), 'docx_input')
     if os.path.exists(dest_dir):

ebook_converter/ebooks/docx/toc.py

@@ -10,9 +10,9 @@ from itertools import count
 
 from lxml.etree import tostring
 
-from calibre.ebooks.metadata.toc import TOC
-from calibre.ebooks.oeb.polish.toc import elem_to_toc_text
-from polyglot.builtins import iteritems, range
+from ebook_converter.ebooks.metadata.toc import TOC
+from ebook_converter.ebooks.oeb.polish.toc import elem_to_toc_text
+from ebook_converter.polyglot.builtins import iteritems, range
 
 
 def from_headings(body, log, namespace, num_levels=3):