gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-04 15:55:52 +01:00
Code Issues Projects Releases Wiki Activity

Sorted out mime initialization.

Browse Source 
Every mime related function in main __init__.py has a flag check for the
check if initialization has already done. This is nonsense, since it
should be done implicitly early on the converter is starting.

This commit straight the things out, and initialization is done in cli
module.

Also, function guess_type was removed, since it's just a proxy for
mimetypes.guess_type function.
This commit is contained in:
gryf
2020-06-14 15:41:18 +02:00
parent b23a59f223
commit 1465e4267f
22 changed files with 94 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
ebook_converter/__init__.py
View File

@@ -1,12 +1,10 @@
import math import math
import os import os
import pkg_resources import pkg_resources
import random
import re import re
import sys import sys
import time import time
import urllib.parse import mimetypes
import urllib.request
from functools import partial from functools import partial
@@ -28,35 +26,17 @@ if False:
fcntl, win32event, isfrozen, __author__ fcntl, win32event, isfrozen, __author__
winerror, win32api, isbsd, config_dir winerror, win32api, isbsd, config_dir
_mt_inited = False
def init_mimetypes():
def _init_mimetypes():
global _mt_inited
import mimetypes
mimetypes.init([pkg_resources.resource_filename('ebook_converter', mimetypes.init([pkg_resources.resource_filename('ebook_converter',
'data/mime.types')]) 'data/mime.types')])
_mt_inited = True
def guess_type(*args, **kwargs):
import mimetypes
if not _mt_inited:
_init_mimetypes()
return mimetypes.guess_type(*args, **kwargs)
def guess_all_extensions(*args, **kwargs): def guess_all_extensions(*args, **kwargs):
import mimetypes
if not _mt_inited:
_init_mimetypes()
return mimetypes.guess_all_extensions(*args, **kwargs) return mimetypes.guess_all_extensions(*args, **kwargs)
def guess_extension(*args, **kwargs): def guess_extension(*args, **kwargs):
import mimetypes
if not _mt_inited:
_init_mimetypes()
ext = mimetypes.guess_extension(*args, **kwargs) ext = mimetypes.guess_extension(*args, **kwargs)
if not ext and args and args[0] == 'application/x-palmreader': if not ext and args and args[0] == 'application/x-palmreader':
ext = '.pdb' ext = '.pdb'
@@ -64,9 +44,6 @@ def guess_extension(*args, **kwargs):
def get_types_map(): def get_types_map():
import mimetypes
if not _mt_inited:
_init_mimetypes()
return mimetypes.types_map return mimetypes.types_map

30
ebook_converter/customize/builtins.py
View File

@@ -1,16 +1,19 @@
import os, glob, re import glob
import mimetypes
import os
import re
from ebook_converter import guess_type
from ebook_converter.customize import (FileTypePlugin, MetadataReaderPlugin,
MetadataWriterPlugin, PreferencesPlugin, InterfaceActionBase, StoreBase)
from ebook_converter.constants_old import numeric_version from ebook_converter.constants_old import numeric_version
from ebook_converter.ebooks.metadata.archive import ArchiveExtract, KPFExtract, get_comic_metadata from ebook_converter.customize import FileTypePlugin
from ebook_converter.customize import InterfaceActionBase
from ebook_converter.customize import MetadataReaderPlugin
from ebook_converter.customize import MetadataWriterPlugin
from ebook_converter.ebooks.html.to_zip import HTML2ZIP from ebook_converter.ebooks.html.to_zip import HTML2ZIP
from ebook_converter.ebooks.metadata.archive import ArchiveExtract
from ebook_converter.ebooks.metadata.archive import KPFExtract
from ebook_converter.ebooks.metadata.archive import get_comic_metadata
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
plugins = [] plugins = []
# To archive plugins {{{ # To archive plugins {{{
@@ -36,12 +39,13 @@ class PML2PMLZ(FileTypePlugin):
pmlz.write(pmlfile, os.path.basename(pmlfile), zipfile.ZIP_DEFLATED) pmlz.write(pmlfile, os.path.basename(pmlfile), zipfile.ZIP_DEFLATED)
pml_img = os.path.splitext(pmlfile)[0] + '_img' pml_img = os.path.splitext(pmlfile)[0] + '_img'
i_img = os.path.join(os.path.dirname(pmlfile),'images') i_img = os.path.join(os.path.dirname(pmlfile), 'images')
img_dir = pml_img if os.path.isdir(pml_img) else i_img if \ img_dir = pml_img if os.path.isdir(pml_img) else i_img if \
os.path.isdir(i_img) else '' os.path.isdir(i_img) else ''
if img_dir: if img_dir:
for image in glob.glob(os.path.join(img_dir, '*.png')): for image in glob.glob(os.path.join(img_dir, '*.png')):
pmlz.write(image, os.path.join('images', (os.path.basename(image)))) pmlz.write(image, os.path.join('images',
(os.path.basename(image))))
pmlz.close() pmlz.close()
return of.name return of.name
@@ -67,13 +71,13 @@ class TXT2TXTZ(FileTypePlugin):
# Textile # Textile
for m in re.finditer(r'(?mu)(?:[\[{])?\!(?:\. )?(?P<path>[^\s(!]+)\s?(?:\(([^\)]+)\))?\!(?::(\S+))?(?:[\]}]|(?=\s|$))', txt): for m in re.finditer(r'(?mu)(?:[\[{])?\!(?:\. )?(?P<path>[^\s(!]+)\s?(?:\(([^\)]+)\))?\!(?::(\S+))?(?:[\]}]|(?=\s|$))', txt):
path = m.group('path') path = m.group('path')
if path and not os.path.isabs(path) and guess_type(path)[0] in OEB_IMAGES and os.path.exists(os.path.join(base_dir, path)): if path and not os.path.isabs(path) and mimetypes.guess_type(path)[0] in OEB_IMAGES and os.path.exists(os.path.join(base_dir, path)):
images.append(path) images.append(path)
# Markdown inline # Markdown inline
for m in re.finditer(r'(?mu)\!\[([^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*)\]\s*\((?P<path>[^\)]*)\)', txt): # noqa for m in re.finditer(r'(?mu)\!\[([^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*)\]\s*\((?P<path>[^\)]*)\)', txt): # noqa
path = m.group('path') path = m.group('path')
if path and not os.path.isabs(path) and guess_type(path)[0] in OEB_IMAGES and os.path.exists(os.path.join(base_dir, path)): if path and not os.path.isabs(path) and mimetypes.guess_type(path)[0] in OEB_IMAGES and os.path.exists(os.path.join(base_dir, path)):
images.append(path) images.append(path)
# Markdown reference # Markdown reference
@@ -83,7 +87,7 @@ class TXT2TXTZ(FileTypePlugin):
refs[m.group('id')] = m.group('path') refs[m.group('id')] = m.group('path')
for m in re.finditer(r'(?mu)\!\[([^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*)\]\s*\[(?P<id>[^\]]*)\]', txt): # noqa for m in re.finditer(r'(?mu)\!\[([^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*(\[[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*\])*[^\]\[]*)\]\s*\[(?P<id>[^\]]*)\]', txt): # noqa
path = refs.get(m.group('id'), None) path = refs.get(m.group('id'), None)
if path and not os.path.isabs(path) and guess_type(path)[0] in OEB_IMAGES and os.path.exists(os.path.join(base_dir, path)): if path and not os.path.isabs(path) and mimetypes.guess_type(path)[0] in OEB_IMAGES and os.path.exists(os.path.join(base_dir, path)):
images.append(path) images.append(path)
# Remove duplicates # Remove duplicates

2
ebook_converter/ebooks/conversion/cli.py
View File

@@ -11,6 +11,7 @@ from ebook_converter.utils.config import OptionParser
from ebook_converter.utils.logging import Log from ebook_converter.utils.logging import Log
from ebook_converter.customize.conversion import OptionRecommendation from ebook_converter.customize.conversion import OptionRecommendation
from ebook_converter import patheq from ebook_converter import patheq
from ebook_converter import init_mimetypes
from ebook_converter.utils.localization import localize_user_manual_link from ebook_converter.utils.localization import localize_user_manual_link
@@ -361,6 +362,7 @@ def read_sr_patterns(path, log=None):
def main(args=sys.argv): def main(args=sys.argv):
log = Log() log = Log()
init_mimetypes()
parser, plumber = create_option_parser(args, log) parser, plumber = create_option_parser(args, log)
opts, leftover_args = parser.parse_args(args) opts, leftover_args = parser.parse_args(args)
if len(leftover_args) > 3: if len(leftover_args) > 3:

5
ebook_converter/ebooks/conversion/plugins/fb2_input.py
View File

@@ -1,6 +1,7 @@
""" """
Convert .fb2 files to .lrf Convert .fb2 files to .lrf
""" """
import mimetypes
import os import os
import pkg_resources import pkg_resources
import re import re
@@ -10,7 +11,6 @@ from lxml import etree
from ebook_converter import constants as const from ebook_converter import constants as const
from ebook_converter.customize.conversion import InputFormatPlugin from ebook_converter.customize.conversion import InputFormatPlugin
from ebook_converter.customize.conversion import OptionRecommendation from ebook_converter.customize.conversion import OptionRecommendation
from ebook_converter import guess_type
FB2NS = 'http://www.gribuser.ru/xml/fictionbook/2.0' FB2NS = 'http://www.gribuser.ru/xml/fictionbook/2.0'
@@ -152,7 +152,8 @@ class FB2Input(InputFormatPlugin):
break break
opf = OPFCreator(os.getcwd(), mi) opf = OPFCreator(os.getcwd(), mi)
entries = [(f2, guess_type(f2)[0]) for f2 in os.listdir(u'.')] entries = [(f2, mimetypes.guess_type(f2)[0])
for f2 in os.listdir(u'.')]
opf.create_manifest(entries) opf.create_manifest(entries)
opf.create_spine(['index.xhtml']) opf.create_spine(['index.xhtml'])
if cpath: if cpath:

17
ebook_converter/ebooks/conversion/plugins/html_input.py
View File

@@ -1,23 +1,19 @@
import functools import functools
import mimetypes
import os import os
import re import re
import tempfile import tempfile
import urllib.parse import urllib.parse
from ebook_converter.constants_old import islinux, isbsd from ebook_converter.constants_old import islinux, isbsd
from ebook_converter.customize.conversion import (InputFormatPlugin, from ebook_converter.customize.conversion import InputFormatPlugin
OptionRecommendation) from ebook_converter.customize.conversion import OptionRecommendation
from ebook_converter.utils.localization import get_lang from ebook_converter.utils.localization import get_lang
from ebook_converter.utils.filenames import ascii_filename from ebook_converter.utils.filenames import ascii_filename
from ebook_converter.utils.imghdr import what from ebook_converter.utils.imghdr import what
from ebook_converter.polyglot.builtins import as_unicode from ebook_converter.polyglot.builtins import as_unicode
__license__ = 'GPL v3'
__copyright__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
def sanitize_file_name(x): def sanitize_file_name(x):
ans = re.sub(r'\s+', ' ', re.sub(r'[?&=;#]', '_', ascii_filename(x))).strip().rstrip('.') ans = re.sub(r'\s+', ' ', re.sub(r'[?&=;#]', '_', ascii_filename(x))).strip().rstrip('.')
ans, ext = ans.rpartition('.')[::2] ans, ext = ans.rpartition('.')[::2]
@@ -99,7 +95,6 @@ class HTMLInput(InputFormatPlugin):
from ebook_converter.ebooks.oeb.base import (DirContainer, from ebook_converter.ebooks.oeb.base import (DirContainer,
rewrite_links, urlnormalize, BINARY_MIME, OEB_STYLES, rewrite_links, urlnormalize, BINARY_MIME, OEB_STYLES,
xpath, urlquote) xpath, urlquote)
from ebook_converter import guess_type
from ebook_converter.ebooks.oeb.transforms.metadata import \ from ebook_converter.ebooks.oeb.transforms.metadata import \
meta_info_to_oeb_metadata meta_info_to_oeb_metadata
from ebook_converter.ebooks.html.input import get_filelist from ebook_converter.ebooks.html.input import get_filelist
@@ -164,7 +159,7 @@ class HTMLInput(InputFormatPlugin):
self.added_resources[path] = href self.added_resources[path] = href
self.urlnormalize, self.DirContainer = urlnormalize, DirContainer self.urlnormalize, self.DirContainer = urlnormalize, DirContainer
self.urldefrag = urllib.parse.urldefrag self.urldefrag = urllib.parse.urldefrag
self.guess_type, self.BINARY_MIME = guess_type, BINARY_MIME self.BINARY_MIME = BINARY_MIME
self.log('Rewriting HTML links') self.log('Rewriting HTML links')
for f in filelist: for f in filelist:
@@ -262,7 +257,7 @@ class HTMLInput(InputFormatPlugin):
if link not in self.added_resources: if link not in self.added_resources:
bhref = os.path.basename(link) bhref = os.path.basename(link)
id, href = self.oeb.manifest.generate(id='added', href=sanitize_file_name(bhref)) id, href = self.oeb.manifest.generate(id='added', href=sanitize_file_name(bhref))
guessed = self.guess_type(href)[0] guessed = mimetypes.guess_type(href)[0]
media_type = guessed or self.BINARY_MIME media_type = guessed or self.BINARY_MIME
if media_type == 'text/plain': if media_type == 'text/plain':
self.log.warn('Ignoring link to text file %r'%link_) self.log.warn('Ignoring link to text file %r'%link_)
@@ -275,7 +270,7 @@ class HTMLInput(InputFormatPlugin):
pass pass
else: else:
if img: if img:
media_type = self.guess_type('dummy.'+img)[0] or self.BINARY_MIME media_type = mimetypes.guess_type('dummy.'+img)[0] or self.BINARY_MIME
self.oeb.log.debug('Added', link) self.oeb.log.debug('Added', link)
self.oeb.container = self.DirContainer(os.path.dirname(link), self.oeb.container = self.DirContainer(os.path.dirname(link),

10
ebook_converter/ebooks/conversion/plugins/htmlz_input.py
View File

@@ -1,14 +1,9 @@
import mimetypes
import os import os
from ebook_converter import guess_type
from ebook_converter.customize.conversion import InputFormatPlugin from ebook_converter.customize.conversion import InputFormatPlugin
__license__ = 'GPL 3'
__copyright__ = '2011, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
class HTMLZInput(InputFormatPlugin): class HTMLZInput(InputFormatPlugin):
name = 'HTLZ Input' name = 'HTLZ Input'
@@ -124,7 +119,8 @@ class HTMLZInput(InputFormatPlugin):
cdata = cf.read() cdata = cf.read()
cover_name = os.path.basename(cover_path) cover_name = os.path.basename(cover_path)
id, href = oeb.manifest.generate('cover', cover_name) id, href = oeb.manifest.generate('cover', cover_name)
oeb.manifest.add(id, href, guess_type(cover_name)[0], data=cdata) oeb.manifest.add(id, href, mimetypes.guess_type(cover_name)[0],
data=cdata)
oeb.guide.add('cover', 'Cover', href) oeb.guide.add('cover', 'Cover', href)
return oeb return oeb

3
ebook_converter/ebooks/conversion/plumber.py
View File

@@ -14,7 +14,7 @@ from ebook_converter.ebooks.conversion.preprocess import HTMLPreProcessor
from ebook_converter.ptempfile import PersistentTemporaryDirectory from ebook_converter.ptempfile import PersistentTemporaryDirectory
from ebook_converter.utils.date import parse_date from ebook_converter.utils.date import parse_date
from ebook_converter.utils.zipfile import ZipFile from ebook_converter.utils.zipfile import ZipFile
from ebook_converter import extract, walk, filesystem_encoding, get_types_map from ebook_converter import extract, walk, filesystem_encoding
from ebook_converter.constants_old import __version__ from ebook_converter.constants_old import __version__
@@ -1010,7 +1010,6 @@ OptionRecommendation(name='search_replace',
from ebook_converter.utils.fonts.scanner import font_scanner # noqa from ebook_converter.utils.fonts.scanner import font_scanner # noqa
import css_parser, logging import css_parser, logging
css_parser.log.setLevel(logging.WARN) css_parser.log.setLevel(logging.WARN)
get_types_map() # Ensure the mimetypes module is intialized
if self.opts.debug_pipeline is not None: if self.opts.debug_pipeline is not None:
self.opts.verbose = max(self.opts.verbose, 4) self.opts.verbose = max(self.opts.verbose, 4)

5
ebook_converter/ebooks/docx/container.py
View File

@@ -1,10 +1,11 @@
import mimetypes
import os import os
import shutil import shutil
import sys import sys
from lxml import etree from lxml import etree
from ebook_converter import walk, guess_type from ebook_converter import walk
from ebook_converter.ebooks.metadata import authors_to_sort_string from ebook_converter.ebooks.metadata import authors_to_sort_string
from ebook_converter.ebooks.metadata import string_to_authors from ebook_converter.ebooks.metadata import string_to_authors
from ebook_converter.ebooks.metadata.book.base import Metadata from ebook_converter.ebooks.metadata.book.base import Metadata
@@ -150,7 +151,7 @@ class DOCX(object):
ext = name.rpartition('.')[-1].lower() ext = name.rpartition('.')[-1].lower()
if ext in self.default_content_types: if ext in self.default_content_types:
return self.default_content_types[ext] return self.default_content_types[ext]
return guess_type(name)[0] return mimetypes.guess_type(name)[0]
def read_package_relationships(self): def read_package_relationships(self):
try: try:

5
ebook_converter/ebooks/docx/to_html.py
View File

@@ -1,5 +1,6 @@
import sys, os, re, math, errno, uuid, numbers import sys, os, re, math, errno, uuid, numbers
from collections import OrderedDict, defaultdict from collections import OrderedDict, defaultdict
import mimetypes
from lxml import etree from lxml import etree
from lxml import html from lxml import html
@@ -24,8 +25,6 @@ from ebook_converter.ebooks.metadata.opf2 import OPFCreator
from ebook_converter.utils.localization import canonicalize_lang, lang_as_iso639_1 from ebook_converter.utils.localization import canonicalize_lang, lang_as_iso639_1
__license__ = 'GPL v3'
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
NBSP = '\xa0' NBSP = '\xa0'
@@ -384,7 +383,7 @@ class Convert(object):
opf.create_manifest_from_files_in([self.dest_dir]) opf.create_manifest_from_files_in([self.dest_dir])
for item in opf.manifest: for item in opf.manifest:
if item.media_type == 'text/html': if item.media_type == 'text/html':
item.media_type = guess_type('a.xhtml')[0] item.media_type = mimetypes.guess_type('a.xhtml')[0]
opf.create_spine(['index.html']) opf.create_spine(['index.html'])
if self.cover_image is not None: if self.cover_image is not None:
opf.guide.set_cover(self.cover_image) opf.guide.set_cover(self.cover_image)

14
ebook_converter/ebooks/docx/writer/container.py
View File

@@ -1,9 +1,9 @@
import mimetypes
import textwrap, os import textwrap, os
from lxml import etree from lxml import etree
from lxml.builder import ElementMaker from lxml.builder import ElementMaker
from ebook_converter import guess_type
from ebook_converter.constants_old import numeric_version, __appname__ from ebook_converter.constants_old import numeric_version, __appname__
from ebook_converter.ebooks.docx.names import DOCXNamespace from ebook_converter.ebooks.docx.names import DOCXNamespace
from ebook_converter.ebooks.metadata import authors_to_string from ebook_converter.ebooks.metadata import authors_to_string
@@ -179,16 +179,20 @@ class DOCX(object):
types.append(E.Override(PartName=partname, ContentType=mt)) types.append(E.Override(PartName=partname, ContentType=mt))
added = {'png', 'gif', 'jpeg', 'jpg', 'svg', 'xml'} added = {'png', 'gif', 'jpeg', 'jpg', 'svg', 'xml'}
for ext in added: for ext in added:
types.append(E.Default(Extension=ext, ContentType=guess_type('a.'+ext)[0])) types.append(E.Default(Extension=ext,
for ext, mt in {"rels": "application/vnd.openxmlformats-package.relationships+xml", ContentType=mimetypes.guess_type('a.' +
"odttf": "application/vnd.openxmlformats-officedocument.obfuscatedFont"}.items(): ext)[0]))
for ext, mt in {"rels": "application/vnd.openxmlformats-package"
".relationships+xml",
"odttf": "application/vnd.openxmlformats-"
"officedocument.obfuscatedFont"}.items():
added.add(ext) added.add(ext)
types.append(E.Default(Extension=ext, ContentType=mt)) types.append(E.Default(Extension=ext, ContentType=mt))
for fname in self.images: for fname in self.images:
ext = fname.rpartition(os.extsep)[-1] ext = fname.rpartition(os.extsep)[-1]
if ext not in added: if ext not in added:
added.add(ext) added.add(ext)
mt = guess_type('a.' + ext)[0] mt = mimetypes.guess_type('a.' + ext)[0]
if mt: if mt:
types.append(E.Default(Extension=ext, ContentType=mt)) types.append(E.Default(Extension=ext, ContentType=mt))
return xml2str(types) return xml2str(types)

13
ebook_converter/ebooks/lrf/input.py
View File

@@ -1,9 +1,10 @@
import textwrap, operator import copy
from copy import deepcopy, copy import mimetypes
import operator
import textwrap
from lxml import etree from lxml import etree
from ebook_converter import guess_type
from ebook_converter.polyglot.builtins import as_bytes from ebook_converter.polyglot.builtins import as_bytes
@@ -87,7 +88,7 @@ class MediaType(etree.XSLTExtension):
def execute(self, context, self_node, input_node, output_parent): def execute(self, context, self_node, input_node, output_parent):
name = input_node.get('file', None) name = input_node.get('file', None)
typ = guess_type(name)[0] typ = mimetypes.guess_type(name)[0]
if not typ: if not typ:
typ = 'application/octet-stream' typ = 'application/octet-stream'
output_parent.text = typ output_parent.text = typ
@@ -120,7 +121,7 @@ class TextBlock(etree.XSLTExtension):
self.plot_map = plot_map self.plot_map = plot_map
def execute(self, context, self_node, input_node, output_parent): def execute(self, context, self_node, input_node, output_parent):
input_node = deepcopy(input_node) input_node = copy.deepcopy(input_node)
div = etree.Element('div') div = etree.Element('div')
self.render_block(input_node, div) self.render_block(input_node, div)
output_parent.append(div) output_parent.append(div)
@@ -190,7 +191,7 @@ class TextBlock(etree.XSLTExtension):
for child in children: for child in children:
p.remove(child) p.remove(child)
if pattrib and child.tag == "Span": if pattrib and child.tag == "Span":
attrib = copy(pattrib) attrib = copy.copy(pattrib)
attrib.update(child.attrib) attrib.update(child.attrib)
child.attrib.update(attrib) child.attrib.update(attrib)

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

@@ -2,22 +2,18 @@
Provides abstraction for metadata reading.writing from a variety of ebook Provides abstraction for metadata reading.writing from a variety of ebook
formats. formats.
""" """
import mimetypes
import os import os
import re import re
import sys import sys
import urllib.parse import urllib.parse
from ebook_converter import relpath, guess_type, prints, force_unicode from ebook_converter import relpath, prints, force_unicode
from ebook_converter.utils.config_base import tweaks from ebook_converter.utils.config_base import tweaks
from ebook_converter.polyglot.builtins import as_unicode from ebook_converter.polyglot.builtins import as_unicode
from ebook_converter.polyglot.urllib import unquote from ebook_converter.polyglot.urllib import unquote
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
try: try:
_author_pat = re.compile(tweaks['authors_split_regex']) _author_pat = re.compile(tweaks['authors_split_regex'])
except Exception: except Exception:
@@ -231,7 +227,7 @@ class Resource(object):
self.path = None self.path = None
self.fragment = '' self.fragment = ''
try: try:
self.mime_type = guess_type(href_or_path)[0] self.mime_type = mimetypes.guess_type(href_or_path)[0]
except: except:
self.mime_type = None self.mime_type = None
if self.mime_type is None: if self.mime_type is None:

3
ebook_converter/ebooks/metadata/fb2.py
View File

@@ -1,6 +1,7 @@
""" """
Read meta information from fb2 files Read meta information from fb2 files
""" """
import mimetypes
import functools import functools
import os import os
import random import random
@@ -225,7 +226,7 @@ def _parse_cover_data(root, imgid, mi, ctx):
mime_extensions = guess_all_extensions(mimetype) mime_extensions = guess_all_extensions(mimetype)
if not mime_extensions and mimetype.startswith('image/'): if not mime_extensions and mimetype.startswith('image/'):
mimetype_fromid = guess_type(imgid)[0] mimetype_fromid = mimetypes.guess_type(imgid)[0]
if mimetype_fromid and mimetype_fromid.startswith('image/'): if mimetype_fromid and mimetype_fromid.startswith('image/'):
mime_extensions = guess_all_extensions(mimetype_fromid) mime_extensions = guess_all_extensions(mimetype_fromid)

7
ebook_converter/ebooks/metadata/opf2.py
View File

@@ -6,6 +6,7 @@ import functools
import glob import glob
import io import io
import json import json
import mimetypes
import os import os
import re import re
import sys import sys
@@ -74,7 +75,7 @@ class Resource(object): # {{{
self.path = None self.path = None
self.fragment = '' self.fragment = ''
try: try:
self.mime_type = guess_type(href_or_path)[0] self.mime_type = mimetypes.guess_type(href_or_path)[0]
except Exception: except Exception:
self.mime_type = None self.mime_type = None
if self.mime_type is None: if self.mime_type is None:
@@ -1304,8 +1305,8 @@ class OPF(object): # {{{
'other.ms-coverimage'): 'other.ms-coverimage'):
for item in self.guide: for item in self.guide:
if item.type.lower() == t: if item.type.lower() == t:
self.create_manifest_item(item.href(), self.create_manifest_item(
guess_type(path)[0]) item.href(), mimetypes.guess_type(path)[0])
def get_metadata_element(self, name): def get_metadata_element(self, name):
matches = self.metadata_elem_path(self.metadata, name=name) matches = self.metadata_elem_path(self.metadata, name=name)

4
ebook_converter/ebooks/mobi/reader/mobi6.py
View File

@@ -1,5 +1,6 @@
import shutil, os, re, struct, textwrap, io import shutil, os, re, struct, textwrap, io
import logging import logging
import mimetypes
from lxml import html, etree from lxml import html, etree
@@ -674,7 +675,8 @@ class MobiReader(object):
for i in getattr(self, 'image_names', []): for i in getattr(self, 'image_names', []):
path = os.path.join(bp, 'images', i) path = os.path.join(bp, 'images', i)
added.add(path) added.add(path)
manifest.append((path, guess_type(path)[0] or 'image/jpeg')) manifest.append((path,
mimetypes.guess_type(path)[0] or 'image/jpeg'))
if cover_copied is not None: if cover_copied is not None:
manifest.append((cover_copied, 'image/jpeg')) manifest.append((cover_copied, 'image/jpeg'))

9
ebook_converter/ebooks/oeb/polish/utils.py
View File

@@ -1,12 +1,9 @@
import bisect import bisect
import os import os
import re import re
import mimetypes
from ebook_converter import guess_type as _guess_type, replace_entities from ebook_converter import replace_entities
__license__ = 'GPL v3'
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
def _upper(string): def _upper(string):
@@ -14,7 +11,7 @@ def _upper(string):
def guess_type(x): def guess_type(x):
return _guess_type(x)[0] or 'application/octet-stream' return mimetypes.guess_type(x)[0] or 'application/octet-stream'
def setup_css_parser_serialization(tab_width=2): def setup_css_parser_serialization(tab_width=2):

8
ebook_converter/ebooks/oeb/reader.py
View File

@@ -4,6 +4,7 @@ Container-/OPF-based input OEBBook reader.
import collections import collections
import copy import copy
import io import io
import mimetypes
import os import os
import re import re
import sys import sys
@@ -22,7 +23,7 @@ from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.utils.localization import get_lang from ebook_converter.utils.localization import get_lang
from ebook_converter.ptempfile import TemporaryDirectory from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.constants_old import __appname__, __version__ from ebook_converter.constants_old import __appname__, __version__
from ebook_converter import guess_type, xml_replace_entities from ebook_converter import xml_replace_entities
from ebook_converter.polyglot.urllib import unquote from ebook_converter.polyglot.urllib import unquote
@@ -130,7 +131,6 @@ class OEBReader(object):
meta_info_to_oeb_metadata meta_info_to_oeb_metadata
stream = io.BytesIO(etree.tostring(opf, xml_declaration=True, stream = io.BytesIO(etree.tostring(opf, xml_declaration=True,
encoding='utf-8')) encoding='utf-8'))
# o = opf_meta.OPF(stream)
o = OPF(stream) o = OPF(stream)
pwm = o.primary_writing_mode pwm = o.primary_writing_mode
if pwm: if pwm:
@@ -251,7 +251,7 @@ class OEBReader(object):
href) href)
warned.add(href) warned.add(href)
id, _ = manifest.generate(id='added') id, _ = manifest.generate(id='added')
guessed = guess_type(href)[0] guessed = mimetypes.guess_type(href)[0]
media_type = guessed or base.BINARY_MIME media_type = guessed or base.BINARY_MIME
added = manifest.add(id, href, media_type) added = manifest.add(id, href, media_type)
unchecked.add(added) unchecked.add(added)
@@ -268,7 +268,7 @@ class OEBReader(object):
if media_type is None: if media_type is None:
media_type = elem.get('mediatype', None) media_type = elem.get('mediatype', None)
if not media_type or media_type == 'text/xml': if not media_type or media_type == 'text/xml':
guessed = guess_type(href)[0] guessed = mimetypes.guess_type(href)[0]
media_type = guessed or media_type or base.BINARY_MIME media_type = guessed or media_type or base.BINARY_MIME
if hasattr(media_type, 'lower'): if hasattr(media_type, 'lower'):
media_type = media_type.lower() media_type = media_type.lower()

4
ebook_converter/ebooks/oeb/transforms/cover.py
View File

@@ -1,9 +1,9 @@
import mimetypes
import textwrap import textwrap
import urllib.parse import urllib.parse
from lxml import etree from lxml import etree
from ebook_converter import guess_type
from ebook_converter.utils.imghdr import identify from ebook_converter.utils.imghdr import identify
from ebook_converter.polyglot.urllib import unquote from ebook_converter.polyglot.urllib import unquote
@@ -115,7 +115,7 @@ class CoverManager(object):
else self.svg_template else self.svg_template
tp = templ % unquote(href) tp = templ % unquote(href)
id, href = m.generate('titlepage', 'titlepage.xhtml') id, href = m.generate('titlepage', 'titlepage.xhtml')
item = m.add(id, href, guess_type('t.xhtml')[0], item = m.add(id, href, mimetypes.guess_type('t.xhtml')[0],
data=etree.fromstring(tp)) data=etree.fromstring(tp))
else: else:
key = urllib.parse.urldefrag(self.oeb.guide['titlepage'].href)[0] key = urllib.parse.urldefrag(self.oeb.guide['titlepage'].href)[0]

4
ebook_converter/ebooks/oeb/transforms/data_url.py
View File

@@ -1,3 +1,4 @@
import mimetypes
import re import re
from ebook_converter.ebooks.oeb.base import XPath, urlunquote from ebook_converter.ebooks.oeb.base import XPath, urlunquote
from ebook_converter.polyglot.builtins import as_bytes from ebook_converter.polyglot.builtins import as_bytes
@@ -45,5 +46,6 @@ class DataURL(object):
self.log('Found image encoded as data URI converting it to normal image') self.log('Found image encoded as data URI converting it to normal image')
from ebook_converter import guess_type from ebook_converter import guess_type
item_id, item_href = oeb.manifest.generate('data-url-image', 'data-url-image.' + fmt) 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) oeb.manifest.add(item_id, item_href,
mimetypes.guess_type(item_href)[0], data=data)
return item_href return item_href

9
ebook_converter/ebooks/oeb/transforms/flatcss.py
View File

@@ -3,6 +3,7 @@ CSS flattening transform.
""" """
import collections import collections
import math import math
import mimetypes
import numbers import numbers
import operator import operator
import re import re
@@ -13,7 +14,6 @@ import css_parser
from css_parser import css as cp_css from css_parser import css as cp_css
from ebook_converter import constants as const from ebook_converter import constants as const
from ebook_converter import guess_type
from ebook_converter.ebooks import unit_convert from ebook_converter.ebooks import unit_convert
from ebook_converter.ebooks.oeb import base from ebook_converter.ebooks.oeb import base
from ebook_converter.ebooks.oeb import parse_utils from ebook_converter.ebooks.oeb import parse_utils
@@ -125,8 +125,9 @@ class EmbedFontsCSSRules(object):
rules = [base.css_text(x) for x in self.rules] rules = [base.css_text(x) for x in self.rules]
rules = '\n\n'.join(rules) rules = '\n\n'.join(rules)
sheet = css_parser.parseString(rules, validate=False) sheet = css_parser.parseString(rules, validate=False)
self.href = oeb.manifest.add(iid, href, guess_type(href)[0], self.href = oeb.manifest.add(iid, href,
data=sheet).href mimetypes.guess_type(href)[0],
data=sheet).href
return self.href return self.href
@@ -244,7 +245,7 @@ class CSSFlattener(object):
fid, href = self.oeb.manifest.generate(id=u'font', fid, href = self.oeb.manifest.generate(id=u'font',
href='fonts/%s.%s'%(ascii_filename(font['full_name']).replace(' ', '-'), ext)) href='fonts/%s.%s'%(ascii_filename(font['full_name']).replace(' ', '-'), ext))
item = self.oeb.manifest.add(fid, href, item = self.oeb.manifest.add(fid, href,
guess_type('dummy.'+ext)[0], mimetypes.guess_type('dummy.'+ext)[0],
data=font_scanner.get_font_data(font)) data=font_scanner.get_font_data(font))
item.unload_data_from_memory() item.unload_data_from_memory()

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

@@ -1,3 +1,4 @@
import mimetypes
import sys, os, re import sys, os, re
from xml.sax.saxutils import escape from xml.sax.saxutils import escape
from string import Formatter from string import Formatter
@@ -5,7 +6,7 @@ import pkg_resources
import urllib.parse import urllib.parse
from ebook_converter import constants as const from ebook_converter import constants as const
from ebook_converter import guess_type, strftime from ebook_converter import strftime
from ebook_converter.constants_old import iswindows from ebook_converter.constants_old import iswindows
from ebook_converter.ebooks.oeb import base from ebook_converter.ebooks.oeb import base
from ebook_converter.ebooks.oeb.base import XPath, xml2text, urlnormalize from ebook_converter.ebooks.oeb.base import XPath, xml2text, urlnormalize
@@ -124,7 +125,8 @@ class Jacket(Base):
alt_comments=comments, rescale_fonts=True) alt_comments=comments, rescale_fonts=True)
id, href = self.oeb.manifest.generate('calibre_jacket', 'jacket.xhtml') id, href = self.oeb.manifest.generate('calibre_jacket', 'jacket.xhtml')
jacket = self.oeb.manifest.add(id, href, guess_type(href)[0], data=root) jacket = self.oeb.manifest.add(id, href, mimetypes.guess_type(href)[0],
data=root)
self.oeb.spine.insert(0, jacket, True) self.oeb.spine.insert(0, jacket, True)
self.oeb.inserted_metadata_jacket = jacket self.oeb.inserted_metadata_jacket = jacket
for img, path in referenced_images(root): for img, path in referenced_images(root):
@@ -132,7 +134,9 @@ class Jacket(Base):
ext = path.rpartition('.')[-1].lower() ext = path.rpartition('.')[-1].lower()
item_id, href = self.oeb.manifest.generate('jacket_image', 'jacket_img.'+ext) item_id, href = self.oeb.manifest.generate('jacket_image', 'jacket_img.'+ext)
with open(path, 'rb') as f: with open(path, 'rb') as f:
item = self.oeb.manifest.add(item_id, href, guess_type(href)[0], data=f.read()) item = self.oeb.manifest.add(
item_id, href, mimetypes.guess_type(href)[0],
data=f.read())
item.unload_data_from_memory() item.unload_data_from_memory()
img.set('src', jacket.relhref(item.href)) img.set('src', jacket.relhref(item.href))

7
ebook_converter/ebooks/oeb/transforms/metadata.py
View File

@@ -1,9 +1,9 @@
import mimetypes
import os import os
import re import re
from ebook_converter.ebooks.oeb import base from ebook_converter.ebooks.oeb import base
from ebook_converter.utils.date import isoformat, now from ebook_converter.utils.date import isoformat, now
from ebook_converter import guess_type
def meta_info_to_oeb_metadata(mi, m, log, override_input_metadata=False): def meta_info_to_oeb_metadata(mi, m, log, override_input_metadata=False):
@@ -156,9 +156,8 @@ class MergeMetadata(object):
new_cover_item = None new_cover_item = None
if cdata: if cdata:
id, href = self.oeb.manifest.generate('cover', 'cover.'+ext) id, href = self.oeb.manifest.generate('cover', 'cover.'+ext)
new_cover_item = self.oeb.manifest.add(id, href, new_cover_item = self.oeb.manifest.add(
guess_type('cover.'+ext)[0], id, href, mimetypes.guess_type('cover.'+ext)[0], data=cdata)
data=cdata)
self.oeb.guide.add('cover', 'Cover', href) self.oeb.guide.add('cover', 'Cover', href)
if do_remove_old_cover: if do_remove_old_cover:
self.remove_old_cover(item, new_cover_item.href) self.remove_old_cover(item, new_cover_item.href)