gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-04-27 01:01:28 +02:00
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
ebook_converter/ebooks/oeb/base.py
+28 -28
View File
@@ -17,7 +17,7 @@ from ebook_converter import (isbytestring, as_unicode, get_types_map)
from ebook_converter.ebooks.oeb.parse_utils import barename, XHTML_NS, namespace, XHTML, parse_html, NotHTML
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.utils.short_uuid import uuid4
from ebook_converter.polyglot.builtins import iteritems, unicode_type, string_or_bytes, itervalues, codepoint_to_chr
from ebook_converter.polyglot.builtins import iteritems, string_or_bytes, itervalues, codepoint_to_chr
from ebook_converter.polyglot.urllib import unquote as urlunquote
@@ -121,7 +121,7 @@ def as_string_type(pat, for_unicode):
if isinstance(pat, bytes):
pat = pat.decode('utf-8')
else:
if isinstance(pat, unicode_type):
if isinstance(pat, str):
pat = pat.encode('utf-8')
return pat
@@ -140,7 +140,7 @@ def self_closing_pat(for_unicode):
def close_self_closing_tags(raw):
for_unicode = isinstance(raw, unicode_type)
for_unicode = isinstance(raw, str)
repl = as_string_type(r'<\g<tag>\g<arg>></\g<tag>>', for_unicode)
pat = self_closing_pat(for_unicode)
return pat.sub(repl, raw)
@@ -421,11 +421,11 @@ def serialize(data, media_type, pretty_print=False):
# incorrectly by some browser based renderers
ans = close_self_closing_tags(ans)
return ans
if isinstance(data, unicode_type):
if isinstance(data, str):
return data.encode('utf-8')
if hasattr(data, 'cssText'):
data = data.cssText
if isinstance(data, unicode_type):
if isinstance(data, str):
data = data.encode('utf-8')
return data + b'\n'
return bytes(data)
@@ -567,7 +567,7 @@ class DirContainer(object):
# If it runs on a unicode object, it returns a double encoded unicode
# string: unquote(u'%C3%A4') != unquote(b'%C3%A4').decode('utf-8')
# and the latter is correct
if isinstance(path, unicode_type):
if isinstance(path, str):
path = path.encode('utf-8')
return urlunquote(path).decode('utf-8')
@@ -759,7 +759,7 @@ class Metadata(object):
return as_unicode(self.value)
else:
def __str__(self):
return unicode_type(self.value).encode('ascii', 'xmlcharrefreplace')
return str(self.value).encode('ascii', 'xmlcharrefreplace')
def __unicode__(self):
return as_unicode(self.value)
@@ -918,9 +918,9 @@ class Manifest(object):
"""
def __init__(self, oeb, id, href, media_type,
fallback=None, loader=unicode_type, data=None):
fallback=None, loader=str, data=None):
if href:
href = unicode_type(href)
href = str(href)
self.oeb = oeb
self.id = id
self.href = self.path = urlnormalize(href)
@@ -973,7 +973,7 @@ class Manifest(object):
title = self.oeb.metadata.title
if title:
title = unicode_type(title[0])
title = str(title[0])
else:
title = _('Unknown')
@@ -1006,7 +1006,7 @@ class Manifest(object):
self.oeb.logger.warn('CSS import of non-CSS file %r' % path)
return (None, None)
data = item.data.cssText
enc = None if isinstance(data, unicode_type) else 'utf-8'
enc = None if isinstance(data, str) else 'utf-8'
return (enc, data)
# }}}
@@ -1087,11 +1087,11 @@ class Manifest(object):
data = self.data
if isinstance(data, etree._Element):
return xml2text(data, pretty_print=self.oeb.pretty_print)
if isinstance(data, unicode_type):
if isinstance(data, str):
return data
if hasattr(data, 'cssText'):
return css_text(data)
return unicode_type(data)
return str(data)
@property
def bytes_representation(self):
@@ -1211,7 +1211,7 @@ class Manifest(object):
base = id
index = 1
while id in self.ids:
id = base + unicode_type(index)
id = base + str(index)
index += 1
if href is not None:
href = urlnormalize(href)
@@ -1219,9 +1219,9 @@ class Manifest(object):
index = 1
lhrefs = {x.lower() for x in self.hrefs}
while href.lower() in lhrefs:
href = base + unicode_type(index) + ext
href = base + str(index) + ext
index += 1
return id, unicode_type(href)
return id, str(href)
def __iter__(self):
for item in self.items:
@@ -1435,7 +1435,7 @@ class Guide(object):
def add(self, type, title, href):
"""Add a new reference to the `Guide`."""
if href:
href = unicode_type(href)
href = str(href)
ref = self.Reference(self.oeb, type, title, href)
self.refs[type] = ref
return ref
@@ -1641,7 +1641,7 @@ class TOC(object):
po = node.play_order
if po == 0:
po = 1
attrib = {'id': id, 'playOrder': unicode_type(po)}
attrib = {'id': id, 'playOrder': str(po)}
if node.klass:
attrib['class'] = node.klass
point = element(parent, NCX('navPoint'), attrib=attrib)
@@ -1712,7 +1712,7 @@ class PageList(object):
TYPES = {'front', 'normal', 'special'}
def __init__(self, name, href, type='normal', klass=None, id=None):
self.name = unicode_type(name)
self.name = str(name)
self.href = urlnormalize(href)
self.type = type if type in self.TYPES else 'normal'
self.id = id
@@ -1749,7 +1749,7 @@ class PageList(object):
for page in self.pages:
id = page.id or uuid_id()
type = page.type
value = unicode_type(next(values[type]))
value = str(next(values[type]))
attrib = {'id': id, 'value': value, 'type': type, 'playOrder': '0'}
if page.klass:
attrib['class'] = page.klass
@@ -1848,7 +1848,7 @@ class OEBBook(object):
"""Automatically decode :param:`data` into a `unicode` object."""
def fix_data(d):
return d.replace('\r\n', '\n').replace('\r', '\n')
if isinstance(data, unicode_type):
if isinstance(data, str):
return fix_data(data)
bom_enc = None
if data[:4] in (b'\0\0\xfe\xff', b'\xff\xfe\0\0'):
@@ -1922,36 +1922,36 @@ class OEBBook(object):
for i, elem in enumerate(xpath(ncx, '//*[@playOrder and ./ncx:content[@src]]')):
href = urlnormalize(selector(elem)[0])
order = playorder.get(href, i)
elem.attrib['playOrder'] = unicode_type(order)
elem.attrib['playOrder'] = str(order)
return
def _to_ncx(self):
lang = unicode_type(self.metadata.language[0])
lang = str(self.metadata.language[0])
lang = lang.replace('_', '-')
ncx = etree.Element(NCX('ncx'),
attrib={'version': '2005-1', XML('lang'): lang},
nsmap={None: NCX_NS})
head = etree.SubElement(ncx, NCX('head'))
etree.SubElement(head, NCX('meta'),
name='dtb:uid', content=unicode_type(self.uid))
name='dtb:uid', content=str(self.uid))
etree.SubElement(head, NCX('meta'),
name='dtb:depth', content=unicode_type(self.toc.depth()))
name='dtb:depth', content=str(self.toc.depth()))
generator = ''.join(['calibre (', __version__, ')'])
etree.SubElement(head, NCX('meta'),
name='dtb:generator', content=generator)
etree.SubElement(head, NCX('meta'),
name='dtb:totalPageCount', content=unicode_type(len(self.pages)))
name='dtb:totalPageCount', content=str(len(self.pages)))
maxpnum = etree.SubElement(head, NCX('meta'),
name='dtb:maxPageNumber', content='0')
title = etree.SubElement(ncx, NCX('docTitle'))
text = etree.SubElement(title, NCX('text'))
text.text = unicode_type(self.metadata.title[0])
text.text = str(self.metadata.title[0])
navmap = etree.SubElement(ncx, NCX('navMap'))
self.toc.to_ncx(navmap)
if len(self.pages) > 0:
plist = self.pages.to_ncx(ncx)
value = max(int(x) for x in xpath(plist, '//@value'))
maxpnum.attrib['content'] = unicode_type(value)
maxpnum.attrib['content'] = str(value)
self._update_playorder(ncx)
return ncx
ebook_converter/ebooks/oeb/normalize_css.py
+2 -2
View File
@@ -5,7 +5,7 @@ from css_parser.css import PropertyValue
from css_parser import profile as cssprofiles, CSSParser
from ebook_converter.tinycss.fonts3 import parse_font, serialize_font_family
from ebook_converter.ebooks.oeb.base import css_text
from ebook_converter.polyglot.builtins import iteritems, string_or_bytes, unicode_type
from ebook_converter.polyglot.builtins import iteritems, string_or_bytes
__license__ = 'GPL v3'
@@ -390,7 +390,7 @@ def test_normalization(return_tests=False): # {{{
tuple('0 0 0 0'.split()) : '0',
}):
for prefix in ('margin', 'padding'):
css = {'%s-%s' % (prefix, x) : unicode_type(y)+'pt' if isinstance(y, numbers.Number) else y
css = {'%s-%s' % (prefix, x) : str(y)+'pt' if isinstance(y, numbers.Number) else y
for x, y in zip(('left', 'top', 'right', 'bottom'), s)}
css = '; '.join(('%s:%s' % (k, v) for k, v in iteritems(css)))
style = parseStyle(css)
ebook_converter/ebooks/oeb/parse_utils.py
+3 -3
View File
@@ -6,7 +6,7 @@ from ebook_converter import xml_replace_entities, force_unicode
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.constants import filesystem_encoding
from ebook_converter.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
from ebook_converter.polyglot.builtins import iteritems, itervalues, unicode_type, string_or_bytes
from ebook_converter.polyglot.builtins import iteritems, itervalues, string_or_bytes
__license__ = 'GPL v3'
@@ -162,7 +162,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
filename = force_unicode(filename, enc=filesystem_encoding)
if not isinstance(data, unicode_type):
if not isinstance(data, str):
if decoder is not None:
data = decoder(data)
else:
@@ -244,7 +244,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
nroot = safe_xml_fromstring('<html></html>')
has_body = False
for child in list(data):
if isinstance(child.tag, (unicode_type, bytes)) and barename(child.tag) == 'body':
if isinstance(child.tag, (str, bytes)) and barename(child.tag) == 'body':
has_body = True
break
parent = nroot
ebook_converter/ebooks/oeb/polish/container.py
+3 -3
View File
@@ -49,7 +49,7 @@ from ebook_converter.utils.ipc.simple_worker import WorkerError, fork_job
from ebook_converter.utils.logging import default_log
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.utils.zipfile import ZipFile
from ebook_converter.polyglot.builtins import iteritems, unicode_type
from ebook_converter.polyglot.builtins import iteritems
exists, join, relpath = os.path.exists, os.path.join, os.path.relpath
@@ -163,7 +163,7 @@ class ContainerBase(object): # {{{
"""
def fix_data(d):
return d.replace('\r\n', '\n').replace('\r', '\n')
if isinstance(data, unicode_type):
if isinstance(data, str):
return fix_data(data)
bom_enc = None
if data[:4] in {b'\0\0\xfe\xff', b'\xff\xfe\0\0'}:
@@ -681,7 +681,7 @@ class Container(ContainerBase): # {{{
''' The names of all manifest items whose media-type matches predicate.
`predicate` can be a set, a list, a string or a function taking a single
argument, which will be called with the media-type. '''
if isinstance(predicate, unicode_type):
if isinstance(predicate, str):
predicate = predicate.__eq__
elif hasattr(predicate, '__contains__'):
predicate = predicate.__contains__
ebook_converter/ebooks/oeb/polish/css.py
+3 -3
View File
@@ -10,7 +10,7 @@ from ebook_converter.ebooks.oeb.normalize_css import normalize_filter_css, norma
from ebook_converter.ebooks.oeb.polish.pretty import pretty_script_or_style, pretty_xml_tree, serialize
from ebook_converter.utils.icu import numeric_sort_key
from ebook_converter.css_selectors import Select, SelectorError
from ebook_converter.polyglot.builtins import iteritems, itervalues, unicode_type
from ebook_converter.polyglot.builtins import iteritems, itervalues
__license__ = 'GPL v3'
@@ -342,10 +342,10 @@ def sort_sheet(container, sheet_or_text):
''' Sort the rules in a stylesheet. Note that in the general case this can
change the effective styles, but for most common sheets, it should be safe.
'''
sheet = container.parse_css(sheet_or_text) if isinstance(sheet_or_text, unicode_type) else sheet_or_text
sheet = container.parse_css(sheet_or_text) if isinstance(sheet_or_text, str) else sheet_or_text
def text_sort_key(x):
return numeric_sort_key(unicode_type(x or ''))
return numeric_sort_key(str(x or ''))
def selector_sort_key(x):
return (x.specificity, text_sort_key(x.selectorText))
ebook_converter/ebooks/oeb/polish/parsing.py
+1 -2
View File
@@ -7,7 +7,6 @@ from ebook_converter import xml_replace_entities
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.ebooks.chardet import xml_to_unicode, strip_encoding_declarations
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL v3'
@@ -81,7 +80,7 @@ def parse(raw, decoder=None, log=None, line_numbers=True, linenumber_attribute=N
if linenumber_attribute:
for elem in ans.iter(LxmlElement):
if elem.sourceline is not None:
elem.set(linenumber_attribute, unicode_type(elem.sourceline))
elem.set(linenumber_attribute, str(elem.sourceline))
return ans
except Exception:
if log is not None:
ebook_converter/ebooks/oeb/polish/split.py
+3 -3
View File
@@ -6,7 +6,7 @@ from ebook_converter.ebooks.oeb.base import barename, XPNSMAP, XPath, OPF, XHTML
from ebook_converter.ebooks.oeb.polish.errors import MalformedMarkup
from ebook_converter.ebooks.oeb.polish.toc import node_from_loc
from ebook_converter.ebooks.oeb.polish.replace import LinkRebaser
from ebook_converter.polyglot.builtins import iteritems, unicode_type
from ebook_converter.polyglot.builtins import iteritems
__license__ = 'GPL v3'
@@ -181,7 +181,7 @@ def split(container, name, loc_or_xpath, before=True, totals=None):
'''
root = container.parsed(name)
if isinstance(loc_or_xpath, unicode_type):
if isinstance(loc_or_xpath, str):
split_point = root.xpath(loc_or_xpath)[0]
else:
try:
@@ -279,7 +279,7 @@ def multisplit(container, name, xpath, before=True):
raise AbortError('Cannot split on the <body> tag')
for i, tag in enumerate(nodes):
tag.set('calibre-split-point', unicode_type(i))
tag.set('calibre-split-point', str(i))
current = name
all_names = [name]
ebook_converter/ebooks/oeb/polish/toc.py
+7 -7
View File
@@ -16,7 +16,7 @@ from ebook_converter.ebooks.oeb.polish.utils import guess_type, extract
from ebook_converter.ebooks.oeb.polish.opf import set_guide_item, get_book_language
from ebook_converter.ebooks.oeb.polish.pretty import pretty_html_tree
from ebook_converter.utils.localization import get_lang, canonicalize_lang, lang_as_iso639_1
from ebook_converter.polyglot.builtins import iteritems, unicode_type
from ebook_converter.polyglot.builtins import iteritems
__license__ = 'GPL v3'
@@ -170,11 +170,11 @@ def parse_ncx(container, ncx_name):
toc_root.lang = toc_root.uid = None
for attr, val in iteritems(root.attrib):
if attr.endswith('lang'):
toc_root.lang = unicode_type(val)
toc_root.lang = str(val)
break
for uid in root.xpath('//*[calibre:lower-case(local-name()) = "meta" and @name="dtb:uid"]/@content'):
if uid:
toc_root.uid = unicode_type(uid)
toc_root.uid = str(uid)
break
for pl in root.xpath('//*[calibre:lower-case(local-name()) = "pagelist"]'):
for pt in pl.xpath('descendant::*[calibre:lower-case(local-name()) = "pagetarget"]'):
@@ -581,9 +581,9 @@ def create_ncx(toc, to_href, btitle, lang, uid):
nsmap={None: NCX_NS})
head = etree.SubElement(ncx, NCX('head'))
etree.SubElement(head, NCX('meta'),
name='dtb:uid', content=unicode_type(uid))
name='dtb:uid', content=str(uid))
etree.SubElement(head, NCX('meta'),
name='dtb:depth', content=unicode_type(toc.depth))
name='dtb:depth', content=str(toc.depth))
generator = ''.join(['calibre (', __version__, ')'])
etree.SubElement(head, NCX('meta'),
name='dtb:generator', content=generator)
@@ -601,7 +601,7 @@ def create_ncx(toc, to_href, btitle, lang, uid):
for child in toc_parent:
play_order['c'] += 1
point = etree.SubElement(xml_parent, NCX('navPoint'), id='num_%d' % play_order['c'],
playOrder=unicode_type(play_order['c']))
playOrder=str(play_order['c']))
label = etree.SubElement(point, NCX('navLabel'))
title = child.title
if title:
@@ -770,7 +770,7 @@ def commit_nav_toc(container, toc, lang=None, landmarks=None, previous_nav=None)
for entry in toc.page_list:
if container.has_name(entry['dest']) and container.mime_map[entry['dest']] in OEB_DOCS:
a = create_li(ol, entry)
a.text = unicode_type(entry['pagenum'])
a.text = str(entry['pagenum'])
pretty_xml_tree(nav)
collapse_li(nav)
container.replace(tocname, root)
ebook_converter/ebooks/oeb/reader.py
+3 -4
View File
@@ -23,7 +23,6 @@ from ebook_converter.utils.localization import get_lang
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.constants import __appname__, __version__
from ebook_converter import guess_type, xml_replace_entities
from ebook_converter.polyglot.builtins import unicode_type
from ebook_converter.polyglot.urllib import unquote
@@ -144,7 +143,7 @@ class OEBReader(object):
dict(a=__appname__, v=__version__)
meta_info_to_oeb_metadata(mi, self.oeb.metadata, self.logger)
m = self.oeb.metadata
m.add('identifier', unicode_type(uuid.uuid4()), id='uuid_id', scheme='uuid')
m.add('identifier', str(uuid.uuid4()), id='uuid_id', scheme='uuid')
self.oeb.uid = self.oeb.metadata.identifier[-1]
if not m.title:
m.add('title', self.oeb.translate(__('Unknown')))
@@ -447,7 +446,7 @@ class OEBReader(object):
ncx = item.data
title = ''.join(xpath(ncx, 'ncx:docTitle/ncx:text/text()'))
title = COLLAPSE_RE.sub(' ', title.strip())
title = title or unicode_type(self.oeb.metadata.title[0])
title = title or str(self.oeb.metadata.title[0])
toc = self.oeb.toc
toc.title = title
navmaps = xpath(ncx, 'ncx:navMap')
@@ -634,7 +633,7 @@ class OEBReader(object):
def _locate_cover_image(self):
if self.oeb.metadata.cover:
id = unicode_type(self.oeb.metadata.cover[0])
id = str(self.oeb.metadata.cover[0])
item = self.oeb.manifest.ids.get(id, None)
if item is not None and item.media_type in OEB_IMAGES:
return item
ebook_converter/ebooks/oeb/stylizer.py
+8 -8
View File
@@ -15,7 +15,7 @@ from ebook_converter.ebooks import unit_convert
from ebook_converter.ebooks.oeb.base import XHTML, XHTML_NS, CSS_MIME, OEB_STYLES, xpath, urlnormalize
from ebook_converter.ebooks.oeb.normalize_css import DEFAULTS, normalizers
from ebook_converter.css_selectors import Select, SelectorError, INAPPROPRIATE_PSEUDO_CLASSES
from ebook_converter.polyglot.builtins import iteritems, unicode_type
from ebook_converter.polyglot.builtins import iteritems
from ebook_converter.tinycss.media3 import CSSMedia3Parser
@@ -317,7 +317,7 @@ class Stylizer(object):
for x in elem.iter('*'):
if x.text:
punctuation_chars = []
text = unicode_type(x.text)
text = str(x.text)
while text:
category = unicodedata.category(text[0])
if category[0] not in {'P', 'Z'}:
@@ -591,7 +591,7 @@ class Style(object):
x = self._style.get(attr)
if x is not None:
if x == 'auto':
ans = self._unit_convert(unicode_type(img_size) + 'px', base=base)
ans = self._unit_convert(str(img_size) + 'px', base=base)
else:
x = self._unit_convert(x, base=base)
if isinstance(x, numbers.Number):
@@ -603,7 +603,7 @@ class Style(object):
if isinstance(x, numbers.Number):
ans = x
if ans is None:
ans = self._unit_convert(unicode_type(img_size) + 'px', base=base)
ans = self._unit_convert(str(img_size) + 'px', base=base)
maa = self._style.get('max-' + attr)
if maa is not None:
x = self._unit_convert(maa, base=base)
@@ -639,12 +639,12 @@ class Style(object):
result = base
else:
result = self._unit_convert(width, base=base)
if isinstance(result, (unicode_type, bytes)):
if isinstance(result, (str, bytes)):
result = self._profile.width
self._width = result
if 'max-width' in self._style:
result = self._unit_convert(self._style['max-width'], base=base)
if isinstance(result, (unicode_type, bytes)):
if isinstance(result, (str, bytes)):
result = self._width
if result < self._width:
self._width = result
@@ -676,12 +676,12 @@ class Style(object):
result = base
else:
result = self._unit_convert(height, base=base)
if isinstance(result, (unicode_type, bytes)):
if isinstance(result, (str, bytes)):
result = self._profile.height
self._height = result
if 'max-height' in self._style:
result = self._unit_convert(self._style['max-height'], base=base)
if isinstance(result, (unicode_type, bytes)):
if isinstance(result, (str, bytes)):
result = self._height
if result < self._height:
self._height = result
ebook_converter/ebooks/oeb/transforms/cover.py
+2 -3
View File
@@ -4,7 +4,6 @@ import urllib.parse
from ebook_converter import guess_type
from ebook_converter.utils.imghdr import identify
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.polyglot.builtins import unicode_type
from ebook_converter.polyglot.urllib import unquote
@@ -111,9 +110,9 @@ class CoverManager(object):
self.svg_template = self.svg_template.replace('__viewbox__',
'0 0 %d %d'%(width, height))
self.svg_template = self.svg_template.replace('__width__',
unicode_type(width))
str(width))
self.svg_template = self.svg_template.replace('__height__',
unicode_type(height))
str(height))
if href is not None:
templ = self.non_svg_template if self.no_svg_cover \
ebook_converter/ebooks/oeb/transforms/flatcss.py
+5 -5
View File
@@ -16,7 +16,7 @@ from ebook_converter.ebooks.oeb.base import (XHTML, XHTML_NS, CSS_MIME, OEB_STYL
from ebook_converter.ebooks.oeb.stylizer import Stylizer
from ebook_converter.utils.filenames import ascii_filename, ascii_text
from ebook_converter.utils.icu import numeric_sort_key
from ebook_converter.polyglot.builtins import iteritems, unicode_type, string_or_bytes
from ebook_converter.polyglot.builtins import iteritems, string_or_bytes
__license__ = 'GPL v3'
@@ -250,7 +250,7 @@ class CSSFlattener(object):
cfont = {
'font-family': '"%s"'%font['font-family'],
'panose-1': ' '.join(map(unicode_type, font['panose'])),
'panose-1': ' '.join(map(str, font['panose'])),
'src': 'url(%s)'%item.href,
}
@@ -476,7 +476,7 @@ class CSSFlattener(object):
minlh = self.context.minimum_line_height / 100.
slh = style['line-height']
if not is_drop_cap and isinstance(slh, numbers.Number) and slh < minlh * fsize:
cssdict['line-height'] = unicode_type(minlh)
cssdict['line-height'] = str(minlh)
except Exception:
self.oeb.logger.exception('Failed to set minimum line-height')
@@ -538,7 +538,7 @@ class CSSFlattener(object):
if css in styles:
match = styles[css]
else:
match = klass + unicode_type(names[klass] or '')
match = klass + str(names[klass] or '')
styles[css] = match
names[klass] += 1
node.attrib['class'] = match
@@ -558,7 +558,7 @@ class CSSFlattener(object):
# then the class attribute for a.x tags will contain both
# that class and the class for a.x:hover, which is wrong.
klass = 'pcalibre'
match = klass + unicode_type(names[klass] or '')
match = klass + str(names[klass] or '')
pstyles[css] = match
names[klass] += 1
keep_classes.add(match)
ebook_converter/ebooks/oeb/transforms/htmltoc.py
+1 -2
View File
@@ -4,7 +4,6 @@ HTML-TOC-adding transform.
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']
@@ -93,7 +92,7 @@ class HTMLTOCAdder(object):
style = 'nested'
id, css_href = oeb.manifest.generate('tocstyle', 'tocstyle.css')
oeb.manifest.add(id, css_href, CSS_MIME, data=STYLE_CSS[style])
language = unicode_type(oeb.metadata.language[0])
language = str(oeb.metadata.language[0])
contents = element(None, XHTML('html'), nsmap={None: XHTML_NS},
attrib={XML('lang'): language})
head = element(contents, XHTML('head'))
ebook_converter/ebooks/oeb/transforms/jacket.py
+8 -9
View File
@@ -11,7 +11,6 @@ from ebook_converter.library.comments import comments_to_html, markdown
from ebook_converter.utils.date import is_date_undefined, as_local_time
from ebook_converter.ebooks.chardet import strip_encoding_declarations
from ebook_converter.ebooks.metadata import fmt_sidx, rating_to_stars
from ebook_converter.polyglot.builtins import unicode_type
__license__ = 'GPL v3'
@@ -99,22 +98,22 @@ class Jacket(Base):
self.log('Inserting metadata into book...')
try:
tags = list(map(unicode_type, self.oeb.metadata.subject))
tags = list(map(str, self.oeb.metadata.subject))
except Exception:
tags = []
try:
comments = unicode_type(self.oeb.metadata.description[0])
comments = str(self.oeb.metadata.description[0])
except:
comments = ''
try:
title = unicode_type(self.oeb.metadata.title[0])
title = str(self.oeb.metadata.title[0])
except:
title = _('Unknown')
try:
authors = list(map(unicode_type, self.oeb.metadata.creator))
authors = list(map(str, self.oeb.metadata.creator))
except:
authors = [_('Unknown')]
@@ -171,7 +170,7 @@ def get_rating(rating, rchar, e_rchar):
return ans
class Series(unicode_type):
class Series(str):
def __new__(self, series, series_index):
if series and series_index is not None:
@@ -181,7 +180,7 @@ class Series(unicode_type):
escape(series), escape(fmt_sidx(series_index, use_roman=False)))
else:
combined = roman = escape(series or u'')
s = unicode_type.__new__(self, combined)
s = str.__new__(self, combined)
s.roman = roman
s.name = escape(series or '')
s.number = escape(fmt_sidx(series_index or 1.0, use_roman=False))
@@ -189,11 +188,11 @@ class Series(unicode_type):
return s
class Tags(unicode_type):
class Tags(str):
def __new__(self, tags, output_profile):
tags = [escape(x) for x in tags or ()]
t = unicode_type.__new__(self, ', '.join(tags))
t = str.__new__(self, ', '.join(tags))
t.alphabetical = ', '.join(sorted(tags))
t.tags_list = tags
return t
ebook_converter/ebooks/oeb/transforms/rasterize.py
+3 -4
View File
@@ -15,7 +15,6 @@ 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
__license__ = 'GPL v3'
@@ -78,7 +77,7 @@ class SVGRasterizer(object):
logger.info('Found SVG image height in %, trying to convert...')
try:
h = float(image.get('height').replace('%', ''))/100.
image.set('height', unicode_type(h*sizes[1]))
image.set('height', str(h*sizes[1]))
except:
logger.exception('Failed to convert percentage height:',
image.get('height'))
@@ -224,11 +223,11 @@ class SVGRasterizer(object):
covers = self.oeb.metadata.cover
if not covers:
return
if unicode_type(covers[0]) not in self.oeb.manifest.ids:
if str(covers[0]) not in self.oeb.manifest.ids:
self.oeb.logger.warn('Cover not in manifest, skipping.')
self.oeb.metadata.clear('cover')
return
cover = self.oeb.manifest.ids[unicode_type(covers[0])]
cover = self.oeb.manifest.ids[str(covers[0])]
if not cover.media_type == SVG_MIME:
return
width = (self.profile.width / 72) * self.profile.dpi
ebook_converter/ebooks/oeb/transforms/split.py
+2 -2
View File
@@ -15,7 +15,7 @@ from ebook_converter.ebooks.epub import rules
from ebook_converter.ebooks.oeb.base import (OEB_STYLES, XPNSMAP as NAMESPACES,
rewrite_links, XHTML, urlnormalize)
from ebook_converter.ebooks.oeb.polish.split import do_split
from ebook_converter.polyglot.builtins import iteritems, unicode_type
from ebook_converter.polyglot.builtins import iteritems
from ebook_converter.polyglot.urllib import unquote
from ebook_converter.css_selectors import Select, SelectorError
@@ -122,7 +122,7 @@ class Split(object):
for i, elem in enumerate(item.data.iter('*')):
try:
elem.set('pb_order', unicode_type(i))
elem.set('pb_order', str(i))
except TypeError: # Cant set attributes on comment nodes etc.
continue
ebook_converter/ebooks/oeb/transforms/structure.py
+2 -2
View File
@@ -7,7 +7,7 @@ from collections import OrderedDict, Counter
from ebook_converter.ebooks.oeb.base import XPNSMAP, TOC, XHTML, xml2text, barename
from ebook_converter.ebooks import ConversionError
from ebook_converter.polyglot.builtins import itervalues, unicode_type
from ebook_converter.polyglot.builtins import itervalues
__license__ = 'GPL v3'
@@ -122,7 +122,7 @@ class DetectStructure(object):
elem = matches[0]
eid = elem.get('id', None)
if not eid:
eid = 'start_reading_at_'+unicode_type(uuid.uuid4()).replace('-', '')
eid = 'start_reading_at_'+str(uuid.uuid4()).replace('-', '')
elem.set('id', eid)
if 'text' in self.oeb.guide:
self.oeb.guide.remove('text')
ebook_converter/ebooks/oeb/transforms/subset.py
+3 -3
View File
@@ -2,7 +2,7 @@ from collections import defaultdict
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
from ebook_converter.polyglot.builtins import iteritems, itervalues
from ebook_converter.tinycss.fonts3 import parse_font_family
@@ -32,7 +32,7 @@ def get_font_properties(rule, default=None):
except (IndexError, KeyError, AttributeError, TypeError, ValueError):
val = None if q in {'src', 'font-family'} else default
if q in {'font-weight', 'font-stretch', 'font-style'}:
val = unicode_type(val).lower() if (val or val == 0) else val
val = str(val).lower() if (val or val == 0) else val
if val == 'inherit':
val = default
if q == 'font-weight':
@@ -233,7 +233,7 @@ class SubsetFonts(object):
no match is found (can happen if no family matches).
'''
ff = style.get('font-family', [])
lnames = {unicode_type(x).lower() for x in ff}
lnames = {str(x).lower() for x in ff}
matching_set = []
# Filter on font-family