gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-13 13:15:53 +01:00
Code Issues Projects Releases Wiki Activity

Removed polyglots unicode_type usage

Browse Source
This commit is contained in:
gryf
2020-04-20 19:25:28 +02:00
parent ef7e2b10be
commit 128705f258
130 changed files with 657 additions and 716 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ebook_converter/ebooks/conversion/plugins/chm_input.py
View File

@@ -10,7 +10,7 @@ from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.customize.conversion import InputFormatPlugin
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.constants import filesystem_encoding
from ebook_converter.polyglot.builtins import unicode_type, as_bytes
from ebook_converter.polyglot.builtins import as_bytes
__license__ = 'GPL v3'
__copyright__ = ('2008, Kovid Goyal <kovid at kovidgoyal.net>, '
@@ -41,7 +41,7 @@ class CHMInput(InputFormatPlugin):
log.debug('Processing CHM...')
with TemporaryDirectory('_chm2oeb') as tdir:
if not isinstance(tdir, unicode_type):
if not isinstance(tdir, str):
tdir = tdir.decode(filesystem_encoding)
html_input = plugin_for_input_format('html')
for opt in html_input.options:
@@ -129,7 +129,7 @@ class CHMInput(InputFormatPlugin):
base = os.path.dirname(os.path.abspath(htmlpath))
def unquote(x):
if isinstance(x, unicode_type):
if isinstance(x, str):
x = x.encode('utf-8')
return _unquote(x).decode('utf-8')

12
ebook_converter/ebooks/conversion/plugins/epub_output.py
View File

@@ -7,7 +7,7 @@ from ebook_converter.customize.conversion import (OutputFormatPlugin,
OptionRecommendation)
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter import CurrentDir
from ebook_converter.polyglot.builtins import unicode_type, as_bytes
from ebook_converter.polyglot.builtins import as_bytes
__license__ = 'GPL v3'
@@ -225,15 +225,15 @@ class EPUBOutput(OutputFormatPlugin):
identifiers = oeb.metadata['identifier']
uuid = None
for x in identifiers:
if x.get(OPF('scheme'), None).lower() == 'uuid' or unicode_type(x).startswith('urn:uuid:'):
uuid = unicode_type(x).split(':')[-1]
if x.get(OPF('scheme'), None).lower() == 'uuid' or str(x).startswith('urn:uuid:'):
uuid = str(x).split(':')[-1]
break
encrypted_fonts = getattr(input_plugin, 'encrypted_fonts', [])
if uuid is None:
self.log.warn('No UUID identifier found')
from uuid import uuid4
uuid = unicode_type(uuid4())
uuid = str(uuid4())
oeb.metadata.add('identifier', uuid, scheme='uuid', id=uuid)
if encrypted_fonts and not uuid.startswith('urn:uuid:'):
@@ -241,7 +241,7 @@ class EPUBOutput(OutputFormatPlugin):
# for some absurd reason, or it will throw a hissy fit and refuse
# to use the obfuscated fonts.
for x in identifiers:
if unicode_type(x) == uuid:
if str(x) == uuid:
x.content = 'urn:uuid:'+uuid
with TemporaryDirectory('_epub_output') as tdir:
@@ -336,7 +336,7 @@ class EPUBOutput(OutputFormatPlugin):
f.write(bytes(bytearray(data[i] ^ key[i%16] for i in range(1024))))
else:
self.log.warn('Font', path, 'is invalid, ignoring')
if not isinstance(uri, unicode_type):
if not isinstance(uri, str):
uri = uri.decode('utf-8')
fonts.append('''
<enc:EncryptedData>

8
ebook_converter/ebooks/conversion/plugins/html_input.py
View File

@@ -10,7 +10,7 @@ from ebook_converter.customize.conversion import (InputFormatPlugin,
from ebook_converter.utils.localization import get_lang
from ebook_converter.utils.filenames import ascii_filename
from ebook_converter.utils.imghdr import what
from ebook_converter.polyglot.builtins import unicode_type, getcwd, as_unicode
from ebook_converter.polyglot.builtins import getcwd, as_unicode
__license__ = 'GPL v3'
@@ -135,7 +135,7 @@ class HTMLInput(InputFormatPlugin):
if not metadata.title:
oeb.logger.warn('Title not specified')
metadata.add('title', self.oeb.translate(__('Unknown')))
bookid = unicode_type(uuid.uuid4())
bookid = str(uuid.uuid4())
metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
for ident in metadata.identifier:
if 'id' in ident.attrib:
@@ -225,7 +225,7 @@ class HTMLInput(InputFormatPlugin):
def link_to_local_path(self, link_, base=None):
from ebook_converter.ebooks.html.input import Link
if not isinstance(link_, unicode_type):
if not isinstance(link_, str):
try:
link_ = link_.decode('utf-8', 'error')
except:
@@ -288,7 +288,7 @@ class HTMLInput(InputFormatPlugin):
# bhref refers to an already existing file. The read() method of
# DirContainer will call unquote on it before trying to read the
# file, therefore we quote it here.
if isinstance(bhref, unicode_type):
if isinstance(bhref, str):
bhref = bhref.encode('utf-8')
item.html_input_href = as_unicode(urllib.parse.quote(bhref))
if guessed in self.OEB_STYLES:

3
ebook_converter/ebooks/conversion/plugins/html_output.py
View File

@@ -8,7 +8,6 @@ from lxml import etree
from ebook_converter import CurrentDir
from ebook_converter.customize.conversion import OutputFormatPlugin, OptionRecommendation
from ebook_converter.ebooks.oeb.base import element
from ebook_converter.polyglot.builtins import unicode_type
from ebook_converter.polyglot.urllib import unquote
from ebook_converter.ptempfile import PersistentTemporaryDirectory
from ebook_converter.utils.cleantext import clean_xml_chars
@@ -155,7 +154,7 @@ class HTMLOutput(OutputFormatPlugin):
toc=html_toc, meta=meta, nextLink=nextLink,
tocUrl=tocUrl, cssLink=cssLink,
firstContentPageLink=nextLink)
if isinstance(t, unicode_type):
if isinstance(t, str):
t = t.encode('utf-8')
f.write(t)

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

@@ -4,7 +4,6 @@ import os
from ebook_converter.customize.conversion import OutputFormatPlugin, \
OptionRecommendation
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL 3'
@@ -78,9 +77,9 @@ class HTMLZOutput(OutputFormatPlugin):
fname = u'index'
if opts.htmlz_title_filename:
from ebook_converter.utils.filenames import shorten_components_to
fname = shorten_components_to(100, (ascii_filename(unicode_type(oeb_book.metadata.title[0])),))[0]
fname = shorten_components_to(100, (ascii_filename(str(oeb_book.metadata.title[0])),))[0]
with open(os.path.join(tdir, fname+u'.html'), 'wb') as tf:
if isinstance(html, unicode_type):
if isinstance(html, str):
html = html.encode('utf-8')
tf.write(html)

11
ebook_converter/ebooks/conversion/plugins/lrf_output.py
View File

@@ -2,7 +2,6 @@ import sys, os
from ebook_converter.customize.conversion import OutputFormatPlugin
from ebook_converter.customize.conversion import OptionRecommendation
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL v3'
@@ -15,7 +14,7 @@ class LRFOptions(object):
def __init__(self, output, opts, oeb):
def f2s(f):
try:
return unicode_type(f[0])
return str(f[0])
except:
return ''
m = oeb.metadata
@@ -29,13 +28,13 @@ class LRFOptions(object):
self.title_sort = self.author_sort = ''
for x in m.creator:
if x.role == 'aut':
self.author = unicode_type(x)
fa = unicode_type(getattr(x, 'file_as', ''))
self.author = str(x)
fa = str(getattr(x, 'file_as', ''))
if fa:
self.author_sort = fa
for x in m.title:
if unicode_type(x.file_as):
self.title_sort = unicode_type(x.file_as)
if str(x.file_as):
self.title_sort = str(x.file_as)
self.freetext = f2s(m.description)
self.category = f2s(m.subject)
self.cover = None

3
ebook_converter/ebooks/conversion/plugins/mobi_input.py
View File

@@ -1,7 +1,6 @@
import os
from ebook_converter.customize.conversion import InputFormatPlugin
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL 3'
@@ -50,7 +49,7 @@ class MOBIInput(InputFormatPlugin):
raw = parse_cache.pop('calibre_raw_mobi_markup', False)
if raw:
if isinstance(raw, unicode_type):
if isinstance(raw, str):
raw = raw.encode('utf-8')
with lopen('debug-raw.html', 'wb') as f:
f.write(raw)

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

@@ -1,6 +1,5 @@
from ebook_converter.customize.conversion import (OutputFormatPlugin,
OptionRecommendation)
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL v3'
@@ -119,7 +118,7 @@ class MOBIOutput(OutputFormatPlugin):
if not found:
from ebook_converter.ebooks import generate_masthead
self.oeb.log.debug('No masthead found in manifest, generating default mastheadImage...')
raw = generate_masthead(unicode_type(self.oeb.metadata['title'][0]))
raw = generate_masthead(str(self.oeb.metadata['title'][0]))
id, href = self.oeb.manifest.generate('masthead', 'masthead')
self.oeb.manifest.add(id, href, 'image/gif', data=raw)
self.oeb.guide.add('masthead', 'Masthead Image', href)
@@ -163,7 +162,7 @@ class MOBIOutput(OutputFormatPlugin):
sec.nodes.remove(a)
root = TOC(klass='periodical', href=self.oeb.spine[0].href,
title=unicode_type(self.oeb.metadata.title[0]))
title=str(self.oeb.metadata.title[0]))
for s in sections:
if articles[id(s)]:

6
ebook_converter/ebooks/conversion/plugins/pdf_output.py
View File

@@ -6,7 +6,7 @@ import glob, os
from ebook_converter.customize.conversion import (OutputFormatPlugin,
OptionRecommendation)
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.polyglot.builtins import iteritems, unicode_type
from ebook_converter.polyglot.builtins import iteritems
__license__ = 'GPL 3'
@@ -190,8 +190,8 @@ class PDFOutput(OutputFormatPlugin):
def get_cover_data(self):
oeb = self.oeb
if (oeb.metadata.cover and unicode_type(oeb.metadata.cover[0]) in oeb.manifest.ids):
cover_id = unicode_type(oeb.metadata.cover[0])
if (oeb.metadata.cover and str(oeb.metadata.cover[0]) in oeb.manifest.ids):
cover_id = str(oeb.metadata.cover[0])
item = oeb.manifest.ids[cover_id]
self.cover_data = item.data

3
ebook_converter/ebooks/conversion/plugins/pml_output.py
View File

@@ -3,7 +3,6 @@ import os, io
from ebook_converter.customize.conversion import (OutputFormatPlugin,
OptionRecommendation)
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL 3'
@@ -40,7 +39,7 @@ class PMLOutput(OutputFormatPlugin):
with TemporaryDirectory('_pmlz_output') as tdir:
pmlmlizer = PMLMLizer(log)
pml = unicode_type(pmlmlizer.extract_content(oeb_book, opts))
pml = str(pmlmlizer.extract_content(oeb_book, opts))
with lopen(os.path.join(tdir, 'index.pml'), 'wb') as out:
out.write(pml.encode(opts.pml_output_encoding, 'replace'))

3
ebook_converter/ebooks/conversion/plugins/recipe_input.py
View File

@@ -3,7 +3,6 @@ import os
from ebook_converter.customize.conversion import InputFormatPlugin, OptionRecommendation
from ebook_converter.constants import numeric_version
from ebook_converter import walk
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL v3'
@@ -161,6 +160,6 @@ class RecipeInput(InputFormatPlugin):
def save_download(self, zf):
raw = self.recipe_source
if isinstance(raw, unicode_type):
if isinstance(raw, str):
raw = raw.encode('utf-8')
zf.writestr('download.recipe', raw)

3
ebook_converter/ebooks/conversion/plugins/snb_input.py
View File

@@ -3,7 +3,6 @@ import os
from ebook_converter.customize.conversion import InputFormatPlugin
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.utils.filenames import ascii_filename
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL 3'
@@ -73,7 +72,7 @@ class SNBInput(InputFormatPlugin):
if d['cover'] != '':
oeb.guide.add('cover', 'Cover', d['cover'])
bookid = unicode_type(uuid.uuid4())
bookid = str(uuid.uuid4())
oeb.metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
for ident in oeb.metadata.identifier:
if 'id' in ident.attrib:

11
ebook_converter/ebooks/conversion/plugins/snb_output.py
View File

@@ -3,7 +3,6 @@ import os
from ebook_converter.customize.conversion import OutputFormatPlugin, OptionRecommendation
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.constants import __appname__, __version__
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL 3'
@@ -73,20 +72,20 @@ class SNBOutput(OutputFormatPlugin):
# Process Meta data
meta = oeb_book.metadata
if meta.title:
title = unicode_type(meta.title[0])
title = str(meta.title[0])
else:
title = ''
authors = [unicode_type(x) for x in meta.creator if x.role == 'aut']
authors = [str(x) for x in meta.creator if x.role == 'aut']
if meta.publisher:
publishers = unicode_type(meta.publisher[0])
publishers = str(meta.publisher[0])
else:
publishers = ''
if meta.language:
lang = unicode_type(meta.language[0]).upper()
lang = str(meta.language[0]).upper()
else:
lang = ''
if meta.description:
abstract = unicode_type(meta.description[0])
abstract = str(meta.description[0])
else:
abstract = ''