gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-01-01 07:22:26 +01:00
Code Issues Projects Releases Wiki Activity

Enable mobi write support.

Browse Source
This commit is contained in:
gryf
2020-04-13 15:25:19 +02:00
parent 32b86ab224
commit a4533957f7
15 changed files with 77 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.rst
View File

@@ -66,6 +66,7 @@ Currently, following formats are supported:
- lrf (for Sony readers)
- epub
- mobi
Installation

14
ebook_converter/ebooks/mobi/mobiml.py
View File

@@ -11,13 +11,13 @@ import copy
import re
import numbers
from lxml import etree
from calibre.ebooks.oeb.base import namespace, barename
from calibre.ebooks.oeb.base import XHTML, XHTML_NS, urlnormalize
from calibre.ebooks.oeb.stylizer import Stylizer
from calibre.ebooks.oeb.transforms.flatcss import KeyMapper
from calibre.ebooks.mobi.utils import convert_color_for_font_tag
from calibre.utils.imghdr import identify
from polyglot.builtins import unicode_type, string_or_bytes
from ebook_converter.ebooks.oeb.base import namespace, barename
from ebook_converter.ebooks.oeb.base import XHTML, XHTML_NS, urlnormalize
from ebook_converter.ebooks.oeb.stylizer import Stylizer
from ebook_converter.ebooks.oeb.transforms.flatcss import KeyMapper
from ebook_converter.ebooks.mobi.utils import convert_color_for_font_tag
from ebook_converter.utils.imghdr import identify
from ebook_converter.polyglot.builtins import unicode_type, string_or_bytes
MBP_NS = 'http://mobipocket.com/ns/mbp'

4
ebook_converter/ebooks/mobi/utils.py
View File

@@ -175,9 +175,9 @@ def rescale_image(data, maxsizeb=IMAGE_MAX_SIZE, dimen=None):
else:
width = height = dimen
data = scale_image(data, width=width, height=height, compression_quality=90)[-1]
else:
# else:
# Replace transparent pixels with white pixels and convert to JPEG
data = save_cover_data_to(data)
#data = save_cover_data_to(data)
if len(data) <= maxsizeb:
return data
orig_data = data # save it in case compression fails

4
ebook_converter/ebooks/mobi/writer2/indexer.py
View File

@@ -11,9 +11,9 @@ from struct import pack
import io
from collections import OrderedDict, defaultdict
from calibre.ebooks.mobi.utils import (encint, encode_number_as_hex,
from ebook_converter.ebooks.mobi.utils import (encint, encode_number_as_hex,
encode_tbs, align_block, RECORD_SIZE, CNCX as CNCX_)
from polyglot.builtins import filter, iteritems, itervalues, map, range
from ebook_converter.polyglot.builtins import filter, iteritems, itervalues, map, range
class CNCX(CNCX_): # {{{

24
ebook_converter/ebooks/mobi/writer2/main.py
View File

@@ -9,16 +9,16 @@ __docformat__ = 'restructuredtext en'
import io, random, time
from struct import pack
from calibre.ebooks import normalize
from calibre.ebooks.mobi.writer2.serializer import Serializer
from calibre.ebooks.compression.palmdoc import compress_doc
from calibre.ebooks.mobi.langcodes import iana2mobi
from calibre.utils.filenames import ascii_filename
from calibre.ebooks.mobi.writer2 import (PALMDOC, UNCOMPRESSED)
from calibre.ebooks.mobi.utils import (encint, encode_trailing_data,
from ebook_converter.ebooks import normalize
from ebook_converter.ebooks.mobi.writer2.serializer import Serializer
from ebook_converter.ebooks.compression.palmdoc import compress_doc
from ebook_converter.ebooks.mobi.langcodes import iana2mobi
from ebook_converter.utils.filenames import ascii_filename
from ebook_converter.ebooks.mobi.writer2 import (PALMDOC, UNCOMPRESSED)
from ebook_converter.ebooks.mobi.utils import (encint, encode_trailing_data,
align_block, detect_periodical, RECORD_SIZE, create_text_record)
from calibre.ebooks.mobi.writer2.indexer import Indexer
from polyglot.builtins import iteritems, unicode_type, range
from ebook_converter.ebooks.mobi.writer2.indexer import Indexer
from ebook_converter.polyglot.builtins import iteritems, unicode_type, range
# Disabled as I dont care about uncrossable breaks
WRITE_UNCROSSABLE_BREAKS = False
@@ -201,7 +201,7 @@ class MobiWriter(object):
# header as well
bt = 0x103 if self.indexer.is_flat_periodical else 0x101
from calibre.ebooks.mobi.writer8.exth import build_exth
from ebook_converter.ebooks.mobi.writer8.exth import build_exth
exth = build_exth(metadata,
prefer_author_sort=self.opts.prefer_author_sort,
is_periodical=self.is_periodical,
@@ -374,9 +374,9 @@ class MobiWriter(object):
# }}}
def generate_joint_record0(self): # {{{
from calibre.ebooks.mobi.writer8.mobi import (MOBIHeader,
from ebook_converter.ebooks.mobi.writer8.mobi import (MOBIHeader,
HEADER_FIELDS)
from calibre.ebooks.mobi.writer8.exth import build_exth
from ebook_converter.ebooks.mobi.writer8.exth import build_exth
# Insert resource records
first_image_record = None

8
ebook_converter/ebooks/mobi/writer2/resources.py
View File

@@ -46,8 +46,14 @@ class Resources(object):
try:
return func(data)
except Exception:
if 'png' != what(None, data):
ext = what(None, data)
if ext not in ('png', 'gif'):
raise
if ext == 'gif':
with PersistentTemporaryFile(suffix='.gif') as pt:
pt.write(data)
return mobify_image(data)
with PersistentTemporaryFile(suffix='.png') as pt:
pt.write(data)
try:

10
ebook_converter/ebooks/mobi/writer2/serializer.py
View File

@@ -12,13 +12,13 @@ import unicodedata
from collections import defaultdict
from io import BytesIO
from calibre.ebooks.mobi.mobiml import MBP_NS
from calibre.ebooks.mobi.utils import is_guide_ref_start
from calibre.ebooks.oeb.base import (
from ebook_converter.ebooks.mobi.mobiml import MBP_NS
from ebook_converter.ebooks.mobi.utils import is_guide_ref_start
from ebook_converter.ebooks.oeb.base import (
OEB_DOCS, XHTML, XHTML_NS, XML_NS, namespace, prefixname, urlnormalize
)
from polyglot.builtins import unicode_type, string_or_bytes
from polyglot.urllib import urldefrag
from ebook_converter.polyglot.builtins import unicode_type, string_or_bytes
from ebook_converter.polyglot.urllib import urldefrag
class Buf(BytesIO):

10
ebook_converter/ebooks/mobi/writer8/__init__.py
View File

@@ -1,10 +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__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'

2
ebook_converter/ebooks/mobi/writer8/cleanup.py
View File

@@ -6,7 +6,7 @@ __license__ = 'GPL v3'
__copyright__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from calibre.ebooks.oeb.base import XPath
from ebook_converter.ebooks.oeb.base import XPath
class CSSCleanup(object):

12
ebook_converter/ebooks/mobi/writer8/exth.py
View File

@@ -10,11 +10,11 @@ import re
from struct import pack
from io import BytesIO
from calibre.constants import iswindows, isosx
from calibre.ebooks.mobi.utils import (utf8_text, to_base)
from calibre.utils.localization import lang_as_iso639_1
from calibre.ebooks.metadata import authors_to_sort_string
from polyglot.builtins import iteritems, unicode_type
from ebook_converter.constants import iswindows, isosx
from ebook_converter.ebooks.mobi.utils import (utf8_text, to_base)
from ebook_converter.utils.localization import lang_as_iso639_1
from ebook_converter.ebooks.metadata import authors_to_sort_string
from ebook_converter.polyglot.builtins import iteritems, unicode_type
EXTH_CODES = {
'creator': 100,
@@ -99,7 +99,7 @@ def build_exth(metadata, prefer_author_sort=False, is_periodical=False,
# Write UUID as ASIN
uuid = None
from calibre.ebooks.oeb.base import OPF
from ebook_converter.ebooks.oeb.base import OPF
for x in metadata['identifier']:
if (x.get(OPF('scheme'), None).lower() == 'uuid' or
unicode_type(x).startswith('urn:uuid:')):

10
ebook_converter/ebooks/oeb/transforms/htmltoc.py
View File

@@ -6,10 +6,10 @@ HTML-TOC-adding transform.
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
from calibre.ebooks.oeb.base import XML, XHTML, XHTML_NS
from calibre.ebooks.oeb.base import XHTML_MIME, CSS_MIME
from calibre.ebooks.oeb.base import element, XPath
from polyglot.builtins import unicode_type
from ebook_converter.ebooks.oeb.base import XML, XHTML, XHTML_NS
from ebook_converter.ebooks.oeb.base import XHTML_MIME, CSS_MIME
from ebook_converter.ebooks.oeb.base import element, XPath
from ebook_converter.polyglot.builtins import unicode_type
__all__ = ['HTMLTOCAdder']
@@ -69,7 +69,7 @@ class HTMLTOCAdder(object):
if 'toc' in oeb.guide:
# Ensure toc pointed to in <guide> is in spine
from calibre.ebooks.oeb.base import urlnormalize
from ebook_converter.ebooks.oeb.base import urlnormalize
href = urlnormalize(oeb.guide['toc'].href)
if href in oeb.manifest.hrefs:
item = oeb.manifest.hrefs[href]

10
ebook_converter/ebooks/oeb/transforms/manglecase.py
View File

@@ -7,11 +7,11 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
from lxml import etree
from calibre.ebooks.oeb.base import XHTML, XHTML_NS
from calibre.ebooks.oeb.base import CSS_MIME
from calibre.ebooks.oeb.base import namespace
from calibre.ebooks.oeb.stylizer import Stylizer
from polyglot.builtins import string_or_bytes
from ebook_converter.ebooks.oeb.base import XHTML, XHTML_NS
from ebook_converter.ebooks.oeb.base import CSS_MIME
from ebook_converter.ebooks.oeb.base import namespace
from ebook_converter.ebooks.oeb.stylizer import Stylizer
from ebook_converter.polyglot.builtins import string_or_bytes
CASE_MANGLER_CSS = """
.calibre_lowercase {

26
ebook_converter/ebooks/oeb/transforms/rasterize.py
View File

@@ -8,17 +8,17 @@ __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
import os, re
from PyQt5.Qt import (
Qt, QByteArray, QBuffer, QIODevice, QColor, QImage, QPainter, QSvgRenderer)
from calibre.ebooks.oeb.base import XHTML, XLINK
from calibre.ebooks.oeb.base import SVG_MIME, PNG_MIME
from calibre.ebooks.oeb.base import xml2str, xpath
from calibre.ebooks.oeb.base import urlnormalize
from calibre.ebooks.oeb.stylizer import Stylizer
from calibre.ptempfile import PersistentTemporaryFile
from calibre.utils.imghdr import what
from polyglot.builtins import unicode_type
from polyglot.urllib import urldefrag
# from PyQt5.Qt import (
# Qt, QByteArray, QBuffer, QIODevice, QColor, QImage, QPainter, QSvgRenderer)
from ebook_converter.ebooks.oeb.base import XHTML, XLINK
from ebook_converter.ebooks.oeb.base import SVG_MIME, PNG_MIME
from ebook_converter.ebooks.oeb.base import xml2str, xpath
from ebook_converter.ebooks.oeb.base import urlnormalize
from ebook_converter.ebooks.oeb.stylizer import Stylizer
from ebook_converter.ptempfile import PersistentTemporaryFile
from ebook_converter.utils.imghdr import what
from ebook_converter.polyglot.builtins import unicode_type
from ebook_converter.polyglot.urllib import urldefrag
IMAGE_TAGS = {XHTML('img'), XHTML('object')}
KEEP_ATTRS = {'class', 'style', 'width', 'height', 'align'}
@@ -32,8 +32,8 @@ class SVGRasterizer(object):
def __init__(self, base_css=''):
self.base_css = base_css
from calibre.gui2 import must_use_qt
must_use_qt()
# from ebook_converter.gui2 import must_use_qt
# must_use_qt()
@classmethod
def config(cls, cfg):

10
ebook_converter/ebooks/pdf/__init__.py
View File

@@ -1,10 +0,0 @@
#!/usr/bin/env python2
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
'''
Used for pdf output for comic2pdf
'''

22
ebook_converter/ebooks/pdf/pdftohtml.py
View File

@@ -11,15 +11,15 @@ import shutil
import subprocess
import sys
from calibre import CurrentDir, xml_replace_entities, prints
from calibre.constants import (
from ebook_converter import CurrentDir, xml_replace_entities, prints
from ebook_converter.constants import (
filesystem_encoding, isbsd, islinux, isosx, ispy3, iswindows
)
from calibre.ebooks import ConversionError, DRMError
from calibre.ebooks.chardet import xml_to_unicode
from calibre.ptempfile import PersistentTemporaryFile
from calibre.utils.cleantext import clean_xml_chars
from calibre.utils.ipc import eintr_retry_call
from ebook_converter.ebooks import ConversionError, DRMError
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.ptempfile import PersistentTemporaryFile
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.utils.ipc import eintr_retry_call
PDFTOHTML = 'pdftohtml'
@@ -98,7 +98,7 @@ def pdftohtml(output_dir, pdf_path, no_images, as_xml=False):
with lopen(index, 'r+b') as i:
raw = i.read().decode('utf-8', 'replace')
raw = flip_images(raw)
raw = raw.replace('<head', '<!-- created by calibre\'s pdftohtml -->\n <head', 1)
raw = raw.replace('<head', '<!-- created by ebook_converter\'s pdftohtml -->\n <head', 1)
i.seek(0)
i.truncate()
# versions of pdftohtml >= 0.20 output self closing <br> tags, this
@@ -129,11 +129,11 @@ def pdftohtml(output_dir, pdf_path, no_images, as_xml=False):
def parse_outline(raw, output_dir):
from lxml import etree
from calibre.utils.xml_parse import safe_xml_fromstring
from ebook_converter.utils.xml_parse import safe_xml_fromstring
raw = clean_xml_chars(xml_to_unicode(raw, strip_encoding_pats=True, assume_utf8=True)[0])
outline = safe_xml_fromstring(raw).xpath('(//outline)[1]')
if outline:
from calibre.ebooks.oeb.polish.toc import TOC, create_ncx
from ebook_converter.ebooks.oeb.polish.toc import TOC, create_ncx
outline = outline[0]
toc = TOC()
count = [0]
@@ -156,7 +156,7 @@ def parse_outline(raw, output_dir):
def flip_image(img, flip):
from calibre.utils.img import flip_image, image_and_format_from_data, image_to_data
from ebook_converter.utils.img import flip_image, image_and_format_from_data, image_to_data
with lopen(img, 'r+b') as f:
img, fmt = image_and_format_from_data(f.read())
img = flip_image(img, horizontal='x' in flip, vertical='y' in flip)