diff --git a/src/calibre/ebooks/conversion/plugins/comic_input.py b/src/calibre/ebooks/conversion/plugins/comic_input.py
index 13301d96f8..f47c200082 100644
--- a/src/calibre/ebooks/conversion/plugins/comic_input.py
+++ b/src/calibre/ebooks/conversion/plugins/comic_input.py
@@ -1,4 +1,5 @@
-from __future__ import with_statement
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
@@ -102,7 +103,8 @@ class ComicInput(InputFormatPlugin):
'%s is not a valid comic collection'
' no comics.txt was found in the file')
%stream.name)
- raw = open('comics.txt', 'rb').read()
+ with open('comics.txt', 'rb') as f:
+ raw = f.read()
if raw.startswith(codecs.BOM_UTF16_BE):
raw = raw.decode('utf-16-be')[1:]
elif raw.startswith(codecs.BOM_UTF16_LE):
@@ -176,7 +178,7 @@ class ComicInput(InputFormatPlugin):
comics = []
for i, x in enumerate(comics_):
title, fname = x
- cdir = u'comic_%d'%(i+1) if len(comics_) > 1 else u'.'
+ cdir = 'comic_%d'%(i+1) if len(comics_) > 1 else '.'
cdir = os.path.abspath(cdir)
if not os.path.exists(cdir):
os.makedirs(cdir)
@@ -230,14 +232,14 @@ class ComicInput(InputFormatPlugin):
_('Page')+' %d'%(i+1), play_order=po)
po += 1
opf.set_toc(toc)
- m, n = open(u'metadata.opf', 'wb'), open('toc.ncx', 'wb')
- opf.render(m, n, u'toc.ncx')
- return os.path.abspath(u'metadata.opf')
+ with open('metadata.opf', 'wb') as m, open('toc.ncx', 'wb') as n:
+ opf.render(m, n, 'toc.ncx')
+ return os.path.abspath('metadata.opf')
def create_wrappers(self, pages):
from calibre.ebooks.oeb.base import XHTML_NS
wrappers = []
- WRAPPER = textwrap.dedent(u'''\
+ WRAPPER = textwrap.dedent('''\
@@ -258,7 +260,7 @@ class ComicInput(InputFormatPlugin):
dir = os.path.dirname(pages[0])
for i, page in enumerate(pages):
wrapper = WRAPPER%(XHTML_NS, i+1, os.path.basename(page), i+1)
- page = os.path.join(dir, u'page_%d.xhtml'%(i+1))
+ page = os.path.join(dir, 'page_%d.xhtml'%(i+1))
with open(page, 'wb') as f:
f.write(wrapper.encode('utf-8'))
wrappers.append(page)
diff --git a/src/calibre/ebooks/conversion/plugins/epub_output.py b/src/calibre/ebooks/conversion/plugins/epub_output.py
index 7af7f9ed4c..aaa8739225 100644
--- a/src/calibre/ebooks/conversion/plugins/epub_output.py
+++ b/src/calibre/ebooks/conversion/plugins/epub_output.py
@@ -1,6 +1,6 @@
#!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
-from __future__ import with_statement
+from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal '
@@ -233,7 +233,7 @@ class EPUBOutput(OutputFormatPlugin):
if uuid is None:
self.log.warn('No UUID identifier found')
from uuid import uuid4
- uuid = str(uuid4())
+ uuid = unicode_type(uuid4())
oeb.metadata.add('identifier', uuid, scheme='uuid', id=uuid)
if encrypted_fonts and not uuid.startswith('urn:uuid:'):
@@ -244,7 +244,7 @@ class EPUBOutput(OutputFormatPlugin):
if unicode_type(x) == uuid:
x.content = 'urn:uuid:'+uuid
- with TemporaryDirectory(u'_epub_output') as tdir:
+ with TemporaryDirectory('_epub_output') as tdir:
from calibre.customize.ui import plugin_for_output_format
metadata_xml = None
extra_entries = []
@@ -252,7 +252,7 @@ class EPUBOutput(OutputFormatPlugin):
if self.opts.output_profile.epub_periodical_format == 'sony':
from calibre.ebooks.epub.periodical import sony_metadata
metadata_xml, atom_xml = sony_metadata(oeb)
- extra_entries = [(u'atom.xml', 'application/atom+xml', atom_xml)]
+ extra_entries = [('atom.xml', 'application/atom+xml', atom_xml)]
oeb_output = plugin_for_output_format('oeb')
oeb_output.convert(oeb, tdir, input_plugin, opts, log)
opf = [x for x in os.listdir(tdir) if x.endswith('.opf')][0]
@@ -338,7 +338,7 @@ class EPUBOutput(OutputFormatPlugin):
self.log.warn('Font', path, 'is invalid, ignoring')
if not isinstance(uri, unicode_type):
uri = uri.decode('utf-8')
- fonts.append(u'''
+ fonts.append('''
@@ -347,13 +347,13 @@ class EPUBOutput(OutputFormatPlugin):
'''%(uri.replace('"', '\\"')))
if fonts:
- ans = '''
'''
- ans += (u'\n'.join(fonts)).encode('utf-8')
- ans += '\n'
+ ans += '\n'.join(fonts).encode('utf-8')
+ ans += b'\n'
return ans
# }}}
@@ -367,7 +367,8 @@ class EPUBOutput(OutputFormatPlugin):
if tag.tail:
tag.tail = tag.tail.strip()
compressed = etree.tostring(tree.getroot(), encoding='utf-8')
- open(ncx_path, 'wb').write(compressed)
+ with open(ncx_path, 'wb') as f:
+ f.write(compressed)
# }}}
def workaround_ade_quirks(self): # {{{
@@ -430,7 +431,7 @@ class EPUBOutput(OutputFormatPlugin):
if priortext:
priortext = priortext.strip()
br.tag = XHTML('p')
- br.text = u'\u00a0'
+ br.text = '\u00a0'
style = br.get('style', '').split(';')
style = list(filter(None, map(lambda x: x.strip(), style)))
style.append('margin:0pt; border:0pt')
@@ -483,14 +484,14 @@ class EPUBOutput(OutputFormatPlugin):
tag.tag = XHTML('div')
# ADE fails to render non breaking hyphens/soft hyphens/zero width spaces
- special_chars = re.compile(u'[\u200b\u00ad]')
+ special_chars = re.compile('[\u200b\u00ad]')
for elem in root.iterdescendants('*'):
if elem.text:
elem.text = special_chars.sub('', elem.text)
- elem.text = elem.text.replace(u'\u2011', '-')
+ elem.text = elem.text.replace('\u2011', '-')
if elem.tail:
elem.tail = special_chars.sub('', elem.tail)
- elem.tail = elem.tail.replace(u'\u2011', '-')
+ elem.tail = elem.tail.replace('\u2011', '-')
if stylesheet is not None:
# ADE doesn't render lists correctly if they have left margins
diff --git a/src/calibre/ebooks/conversion/plugins/fb2_input.py b/src/calibre/ebooks/conversion/plugins/fb2_input.py
index 9ab3147e52..6ac300b655 100644
--- a/src/calibre/ebooks/conversion/plugins/fb2_input.py
+++ b/src/calibre/ebooks/conversion/plugins/fb2_input.py
@@ -1,4 +1,5 @@
-from __future__ import with_statement
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Anatoly Shipitsin '
"""
@@ -125,9 +126,9 @@ class FB2Input(InputFormatPlugin):
src = img.get('src')
img.set('src', self.binary_map.get(src, src))
index = transform.tostring(result)
- with open(u'index.xhtml', 'wb') as f:
+ with open('index.xhtml', 'wb') as f:
f.write(index.encode('utf-8'))
- with open(u'inline-styles.css', 'wb') as f:
+ with open('inline-styles.css', 'wb') as f:
f.write(css.encode('utf-8'))
stream.seek(0)
mi = get_metadata(stream, 'fb2')
@@ -137,9 +138,9 @@ class FB2Input(InputFormatPlugin):
mi.authors = [_('Unknown')]
cpath = None
if mi.cover_data and mi.cover_data[1]:
- with open(u'fb2_cover_calibre_mi.jpg', 'wb') as f:
+ with open('fb2_cover_calibre_mi.jpg', 'wb') as f:
f.write(mi.cover_data[1])
- cpath = os.path.abspath(u'fb2_cover_calibre_mi.jpg')
+ cpath = os.path.abspath('fb2_cover_calibre_mi.jpg')
else:
for img in doc.xpath('//f:coverpage/f:image', namespaces=NAMESPACES):
href = img.get('{%s}href'%XLINK_NS, img.get('href', None))
@@ -152,12 +153,12 @@ class FB2Input(InputFormatPlugin):
opf = OPFCreator(getcwd(), mi)
entries = [(f2, guess_type(f2)[0]) for f2 in os.listdir(u'.')]
opf.create_manifest(entries)
- opf.create_spine([u'index.xhtml'])
+ opf.create_spine(['index.xhtml'])
if cpath:
opf.guide.set_cover(cpath)
- with open(u'metadata.opf', 'wb') as f:
+ with open('metadata.opf', 'wb') as f:
opf.render(f)
- return os.path.join(getcwd(), u'metadata.opf')
+ return os.path.join(getcwd(), 'metadata.opf')
def extract_embedded_content(self, doc):
from calibre.ebooks.fb2 import base64_decode
diff --git a/src/calibre/ebooks/conversion/plugins/html_input.py b/src/calibre/ebooks/conversion/plugins/html_input.py
index a26e86be0a..a714036ef0 100644
--- a/src/calibre/ebooks/conversion/plugins/html_input.py
+++ b/src/calibre/ebooks/conversion/plugins/html_input.py
@@ -120,7 +120,7 @@ class HTMLInput(InputFormatPlugin):
if not metadata.language:
l = canonicalize_lang(getattr(opts, 'language', None))
if not l:
- oeb.logger.warn(u'Language not specified')
+ oeb.logger.warn('Language not specified')
l = get_lang().replace('_', '-')
metadata.add('language', l)
if not metadata.creator:
@@ -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 = str(uuid.uuid4())
+ bookid = unicode_type(uuid.uuid4())
metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
for ident in metadata.identifier:
if 'id' in ident.attrib:
diff --git a/src/calibre/ebooks/conversion/plugins/html_output.py b/src/calibre/ebooks/conversion/plugins/html_output.py
index ba2e922267..b45c3c61f0 100644
--- a/src/calibre/ebooks/conversion/plugins/html_output.py
+++ b/src/calibre/ebooks/conversion/plugins/html_output.py
@@ -1,4 +1,5 @@
-from __future__ import with_statement
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL 3'
__copyright__ = '2010, Fabian Grassl '
__docformat__ = 'restructuredtext en'
@@ -91,17 +92,20 @@ class HTMLOutput(OutputFormatPlugin):
# read template files
if opts.template_html_index is not None:
- template_html_index_data = open(opts.template_html_index, 'rb').read()
+ with open(opts.template_html_index, 'rb') as f:
+ template_html_index_data = f.read()
else:
template_html_index_data = P('templates/html_export_default_index.tmpl', data=True)
if opts.template_html is not None:
- template_html_data = open(opts.template_html, 'rb').read()
+ with open(opts.template_html, 'rb') as f:
+ template_html_data = f.read()
else:
template_html_data = P('templates/html_export_default.tmpl', data=True)
if opts.template_css is not None:
- template_css_data = open(opts.template_css, 'rb').read()
+ with open(opts.template_css, 'rb') as f:
+ template_css_data = f.read()
else:
template_css_data = P('templates/html_export_default.css', data=True)
diff --git a/src/calibre/ebooks/conversion/plugins/snb_input.py b/src/calibre/ebooks/conversion/plugins/snb_input.py
index c250466ff8..007adea1b9 100644
--- a/src/calibre/ebooks/conversion/plugins/snb_input.py
+++ b/src/calibre/ebooks/conversion/plugins/snb_input.py
@@ -1,4 +1,5 @@
# -*- coding: utf-8 -*-
+from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3'
__copyright__ = '2010, Li Fanxi '
@@ -9,12 +10,13 @@ import os
from calibre.customize.conversion import InputFormatPlugin
from calibre.ptempfile import TemporaryDirectory
from calibre.utils.filenames import ascii_filename
+from polyglot.builtins import unicode_type
-HTML_TEMPLATE = u'%s\n%s\n'
+HTML_TEMPLATE = '%s\n%s\n'
def html_encode(s):
- return s.replace(u'&', u'&').replace(u'<', u'<').replace(u'>', u'>').replace(u'"', u'"').replace(u"'", u''').replace(u'\n', u'
').replace(u' ', u' ') # noqa
+ return s.replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"').replace("'", ''').replace('\n', '
').replace(' ', ' ') # noqa
class SNBInput(InputFormatPlugin):
@@ -43,7 +45,7 @@ class SNBInput(InputFormatPlugin):
except:
raise ValueError("Invalid SNB file")
if not snbFile.IsValid():
- log.debug("Invaild SNB file")
+ log.debug("Invalid SNB file")
raise ValueError("Invalid SNB file")
log.debug("Handle meta data ...")
from calibre.ebooks.conversion.plumber import create_oebbook
@@ -74,7 +76,7 @@ class SNBInput(InputFormatPlugin):
if d['cover'] != '':
oeb.guide.add('cover', 'Cover', d['cover'])
- bookid = str(uuid.uuid4())
+ bookid = unicode_type(uuid.uuid4())
oeb.metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
for ident in oeb.metadata.identifier:
if 'id' in ident.attrib:
@@ -96,15 +98,14 @@ class SNBInput(InputFormatPlugin):
if data is None:
continue
snbc = etree.fromstring(data)
- outputFile = open(os.path.join(tdir, fname), 'wb')
lines = []
for line in snbc.find('.//body'):
if line.tag == 'text':
- lines.append(u'%s
' % html_encode(line.text))
+ lines.append('%s
' % html_encode(line.text))
elif line.tag == 'img':
- lines.append(u'
' % html_encode(line.text))
- outputFile.write((HTML_TEMPLATE % (chapterName, u'\n'.join(lines))).encode('utf-8', 'replace'))
- outputFile.close()
+ lines.append('
' % html_encode(line.text))
+ with open(os.path.join(tdir, fname), 'wb') as f:
+ f.write((HTML_TEMPLATE % (chapterName, '\n'.join(lines))).encode('utf-8', 'replace'))
oeb.toc.add(ch.text, fname)
id, href = oeb.manifest.generate(id='html',
href=ascii_filename(fname))
diff --git a/src/calibre/ebooks/conversion/plugins/snb_output.py b/src/calibre/ebooks/conversion/plugins/snb_output.py
index 5b4917fc7b..460e806999 100644
--- a/src/calibre/ebooks/conversion/plugins/snb_output.py
+++ b/src/calibre/ebooks/conversion/plugins/snb_output.py
@@ -1,4 +1,5 @@
# -*- coding: utf-8 -*-
+from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3'
__copyright__ = '2010, Li Fanxi '
@@ -113,9 +114,8 @@ class SNBOutput(OutputFormatPlugin):
etree.SubElement(headTree, "cover").text = ProcessFileName(href)
else:
etree.SubElement(headTree, "cover")
- bookInfoFile = open(os.path.join(snbfDir, 'book.snbf'), 'wb')
- bookInfoFile.write(etree.tostring(bookInfoTree, pretty_print=True, encoding='utf-8'))
- bookInfoFile.close()
+ with open(os.path.join(snbfDir, 'book.snbf'), 'wb') as f:
+ f.write(etree.tostring(bookInfoTree, pretty_print=True, encoding='utf-8'))
# Output TOC
tocInfoTree = etree.Element("toc-snbf")
@@ -168,9 +168,8 @@ class SNBOutput(OutputFormatPlugin):
etree.SubElement(tocHead, "chapters").text = '%d' % len(tocBody)
- tocInfoFile = open(os.path.join(snbfDir, 'toc.snbf'), 'wb')
- tocInfoFile.write(etree.tostring(tocInfoTree, pretty_print=True, encoding='utf-8'))
- tocInfoFile.close()
+ with open(os.path.join(snbfDir, 'toc.snbf'), 'wb') as f:
+ f.write(etree.tostring(tocInfoTree, pretty_print=True, encoding='utf-8'))
# Output Files
oldTree = None
@@ -185,9 +184,8 @@ class SNBOutput(OutputFormatPlugin):
else:
if oldTree is not None and mergeLast:
log.debug('Output the modified chapter again: %s' % lastName)
- outputFile = open(os.path.join(snbcDir, lastName), 'wb')
- outputFile.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
- outputFile.close()
+ with open(os.path.join(snbcDir, lastName), 'wb') as f:
+ f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
mergeLast = False
log.debug('Converting %s to snbc...' % item.href)
@@ -201,9 +199,8 @@ class SNBOutput(OutputFormatPlugin):
postfix = '_' + subName
lastName = ProcessFileName(item.href + postfix + ".snbc")
oldTree = snbcTrees[subName]
- outputFile = open(os.path.join(snbcDir, lastName), 'wb')
- outputFile.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
- outputFile.close()
+ with open(os.path.join(snbcDir, lastName), 'wb') as f:
+ f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
else:
log.debug('Merge %s with last TOC item...' % item.href)
snbwriter.merge_content(oldTree, oeb_book, item, [('', _("Start"))], opts)
@@ -211,9 +208,8 @@ class SNBOutput(OutputFormatPlugin):
# Output the last one if needed
log.debug('Output the last modified chapter again: %s' % lastName)
if oldTree is not None and mergeLast:
- outputFile = open(os.path.join(snbcDir, lastName), 'wb')
- outputFile.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
- outputFile.close()
+ with open(os.path.join(snbcDir, lastName), 'wb') as f:
+ f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
mergeLast = False
for item in m:
@@ -248,7 +244,7 @@ class SNBOutput(OutputFormatPlugin):
# TODO : intelligent image rotation
# img = img.rotate(90)
# x,y = y,x
- img = resize_image(img, x / scale, y / scale)
+ img = resize_image(img, x // scale, y // scale)
with lopen(imagePath, 'wb') as f:
f.write(image_to_data(img, fmt=imagePath.rpartition('.')[-1]))
diff --git a/src/calibre/ebooks/conversion/plugins/txt_input.py b/src/calibre/ebooks/conversion/plugins/txt_input.py
index e9f6fa54fe..66357c5fb7 100644
--- a/src/calibre/ebooks/conversion/plugins/txt_input.py
+++ b/src/calibre/ebooks/conversion/plugins/txt_input.py
@@ -1,5 +1,5 @@
# -*- coding: utf-8 -*-
-from __future__ import print_function
+from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3'
__copyright__ = '2009, John Schember '
diff --git a/src/calibre/ebooks/docx/fields.py b/src/calibre/ebooks/docx/fields.py
index 3a6be921ef..7400bcde51 100644
--- a/src/calibre/ebooks/docx/fields.py
+++ b/src/calibre/ebooks/docx/fields.py
@@ -8,7 +8,7 @@ __copyright__ = '2013, Kovid Goyal '
import re
from calibre.ebooks.docx.index import process_index, polish_index_markup
-from polyglot.builtins import iteritems
+from polyglot.builtins import iteritems, native_string_type
class Field(object):
@@ -75,7 +75,7 @@ def parser(name, field_map, default_field_name=None):
ans.pop(null, None)
return ans
- parse.__name__ = str('parse_' + name)
+ parse.__name__ = native_string_type('parse_' + name)
return parse
diff --git a/src/calibre/ebooks/docx/numbering.py b/src/calibre/ebooks/docx/numbering.py
index a75ca830e1..da33d6a584 100644
--- a/src/calibre/ebooks/docx/numbering.py
+++ b/src/calibre/ebooks/docx/numbering.py
@@ -14,7 +14,7 @@ from lxml.html.builder import OL, UL, SPAN
from calibre.ebooks.docx.block_styles import ParagraphStyle
from calibre.ebooks.docx.char_styles import RunStyle, inherit
from calibre.ebooks.metadata import roman
-from polyglot.builtins import iteritems
+from polyglot.builtins import iteritems, unicode_type
STYLE_MAP = {
'aiueo': 'hiragana',
@@ -291,7 +291,7 @@ class Numbering(object):
seen_instances.add(num_id)
p.tag = 'li'
p.set('value', '%s' % counter[ilvl])
- p.set('list-lvl', str(ilvl))
+ p.set('list-lvl', unicode_type(ilvl))
p.set('list-id', num_id)
if lvl.num_template is not None:
val = lvl.format_template(counter, ilvl, lvl.num_template)
diff --git a/src/calibre/ebooks/docx/to_html.py b/src/calibre/ebooks/docx/to_html.py
index 067e6d6bc9..42b55020e1 100644
--- a/src/calibre/ebooks/docx/to_html.py
+++ b/src/calibre/ebooks/docx/to_html.py
@@ -28,7 +28,7 @@ from calibre.ebooks.docx.fields import Fields
from calibre.ebooks.docx.settings import Settings
from calibre.ebooks.metadata.opf2 import OPFCreator
from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
-from polyglot.builtins import iteritems, itervalues, filter, getcwd, map
+from polyglot.builtins import iteritems, itervalues, filter, getcwd, map, unicode_type
NBSP = '\xa0'
@@ -480,7 +480,7 @@ class Convert(object):
current_hyperlink = x
elif x.tag.endswith('}instrText') and x.text and x.text.strip().startswith('TOC '):
old_anchor = current_anchor
- anchor = str(uuid.uuid4())
+ anchor = unicode_type(uuid.uuid4())
self.anchor_map[anchor] = current_anchor = generate_anchor('toc', frozenset(itervalues(self.anchor_map)))
self.toc_anchor = current_anchor
if old_anchor is not None:
@@ -693,9 +693,9 @@ class Convert(object):
ans.append(text.elem)
ans[-1].set('class', 'tab')
elif self.namespace.is_tag(child, 'w:noBreakHyphen'):
- text.buf.append(u'\u2011')
+ text.buf.append('\u2011')
elif self.namespace.is_tag(child, 'w:softHyphen'):
- text.buf.append(u'\u00ad')
+ text.buf.append('\u00ad')
if text.buf:
setattr(text.elem, text.attr, ''.join(text.buf))
diff --git a/src/calibre/ebooks/docx/writer/container.py b/src/calibre/ebooks/docx/writer/container.py
index 791e7527da..e28e5c41cb 100644
--- a/src/calibre/ebooks/docx/writer/container.py
+++ b/src/calibre/ebooks/docx/writer/container.py
@@ -18,7 +18,7 @@ from calibre.utils.date import utcnow
from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
from calibre.utils.zipfile import ZipFile
from calibre.ebooks.pdf.render.common import PAPER_SIZES
-from polyglot.builtins import iteritems, map
+from polyglot.builtins import iteritems, map, unicode_type
def xml2str(root, pretty_print=False, with_tail=False):
@@ -65,9 +65,9 @@ def create_skeleton(opts, namespaces=None):
def margin(which):
val = page_margin(opts, which)
- return w(which), str(int(val * 20))
+ return w(which), unicode_type(int(val * 20))
body.append(E.sectPr(
- E.pgSz(**{w('w'):str(width), w('h'):str(height)}),
+ E.pgSz(**{w('w'):unicode_type(width), w('h'):unicode_type(height)}),
E.pgMar(**dict(map(margin, 'left top right bottom'.split()))),
E.cols(**{w('space'):'720'}),
E.docGrid(**{w('linePitch'):"360"}),
@@ -243,7 +243,7 @@ class DOCX(object):
namespaces = self.namespace.namespaces
E = ElementMaker(namespace=namespaces['cp'], nsmap={x:namespaces[x] for x in 'cp dc dcterms xsi'.split()})
cp = E.coreProperties(E.revision("1"), E.lastModifiedBy('calibre'))
- ts = utcnow().isoformat(str('T')).rpartition('.')[0] + 'Z'
+ ts = utcnow().isoformat(unicode_type('T')).rpartition('.')[0] + 'Z'
for x in 'created modified'.split():
x = cp.makeelement('{%s}%s' % (namespaces['dcterms'], x), **{'{%s}type' % namespaces['xsi']:'dcterms:W3CDTF'})
x.text = ts
diff --git a/src/calibre/ebooks/docx/writer/from_html.py b/src/calibre/ebooks/docx/writer/from_html.py
index dea920d55b..a29ecef2f4 100644
--- a/src/calibre/ebooks/docx/writer/from_html.py
+++ b/src/calibre/ebooks/docx/writer/from_html.py
@@ -101,7 +101,7 @@ class TextRun(object):
for text, preserve_whitespace, bookmark in self.texts:
if bookmark is not None:
bid = links_manager.bookmark_id
- makeelement(r, 'w:bookmarkStart', w_id=str(bid), w_name=bookmark)
+ makeelement(r, 'w:bookmarkStart', w_id=unicode_type(bid), w_name=bookmark)
if text is None:
makeelement(r, 'w:br', w_clear=preserve_whitespace)
elif hasattr(text, 'xpath'):
@@ -112,7 +112,7 @@ class TextRun(object):
if preserve_whitespace:
t.set('{http://www.w3.org/XML/1998/namespace}space', 'preserve')
if bookmark is not None:
- makeelement(r, 'w:bookmarkEnd', w_id=str(bid))
+ makeelement(r, 'w:bookmarkEnd', w_id=unicode_type(bid))
def __repr__(self):
return repr(self.texts)
@@ -207,7 +207,7 @@ class Block(object):
p = makeelement(body, 'w:p')
end_bookmarks = []
for bmark in self.bookmarks:
- end_bookmarks.append(str(self.links_manager.bookmark_id))
+ end_bookmarks.append(unicode_type(self.links_manager.bookmark_id))
makeelement(p, 'w:bookmarkStart', w_id=end_bookmarks[-1], w_name=bmark)
if self.block_lang:
rpr = makeelement(p, 'w:rPr')
@@ -220,8 +220,8 @@ class Block(object):
self.float_spec.serialize(self, ppr)
if self.numbering_id is not None:
numpr = makeelement(ppr, 'w:numPr')
- makeelement(numpr, 'w:ilvl', w_val=str(self.numbering_id[1]))
- makeelement(numpr, 'w:numId', w_val=str(self.numbering_id[0]))
+ makeelement(numpr, 'w:ilvl', w_val=unicode_type(self.numbering_id[1]))
+ makeelement(numpr, 'w:numId', w_val=unicode_type(self.numbering_id[0]))
if self.linked_style is not None:
makeelement(ppr, 'w:pStyle', w_val=self.linked_style.id)
elif self.style.id:
diff --git a/src/calibre/ebooks/docx/writer/links.py b/src/calibre/ebooks/docx/writer/links.py
index bf89f1fc72..ba8bb8aeb4 100644
--- a/src/calibre/ebooks/docx/writer/links.py
+++ b/src/calibre/ebooks/docx/writer/links.py
@@ -9,6 +9,7 @@ import posixpath, re
from uuid import uuid4
from calibre.utils.filenames import ascii_text
+from polyglot.builtins import unicode_type
from polyglot.urllib import urlparse
@@ -35,7 +36,7 @@ class TOCItem(object):
p = makeelement(body, 'w:p', append=False)
ppr = makeelement(p, 'w:pPr')
makeelement(ppr, 'w:pStyle', w_val="Normal")
- makeelement(ppr, 'w:ind', w_left='0', w_firstLineChars='0', w_firstLine='0', w_leftChars=str(200 * self.level))
+ makeelement(ppr, 'w:ind', w_left='0', w_firstLineChars='0', w_firstLine='0', w_leftChars=unicode_type(200 * self.level))
if self.is_first:
makeelement(ppr, 'w:pageBreakBefore', w_val='off')
r = makeelement(p, 'w:r')
@@ -69,7 +70,7 @@ class LinksManager(object):
self.namespace = namespace
self.log = log
self.document_relationships = document_relationships
- self.top_anchor = type('')(uuid4().hex)
+ self.top_anchor = uuid4().hex
self.anchor_map = {}
self.used_bookmark_names = set()
self.bmark_id = 0
diff --git a/src/calibre/ebooks/docx/writer/lists.py b/src/calibre/ebooks/docx/writer/lists.py
index c71ebf9cb7..259cfb3539 100644
--- a/src/calibre/ebooks/docx/writer/lists.py
+++ b/src/calibre/ebooks/docx/writer/lists.py
@@ -8,7 +8,7 @@ __copyright__ = '2015, Kovid Goyal '
from collections import defaultdict
from operator import attrgetter
-from polyglot.builtins import iteritems, itervalues
+from polyglot.builtins import iteritems, itervalues, unicode_type
LIST_STYLES = frozenset(
'disc circle square decimal decimal-leading-zero lower-roman upper-roman'
@@ -83,7 +83,7 @@ class NumberingDefinition(object):
def serialize(self, parent):
makeelement = self.namespace.makeelement
- an = makeelement(parent, 'w:abstractNum', w_abstractNumId=str(self.num_id))
+ an = makeelement(parent, 'w:abstractNum', w_abstractNumId=unicode_type(self.num_id))
makeelement(an, 'w:multiLevelType', w_val='hybridMultilevel')
makeelement(an, 'w:name', w_val='List %d' % (self.num_id + 1))
for level in self.levels:
@@ -114,12 +114,12 @@ class Level(object):
return hash((self.start, self.num_fmt, self.lvl_text))
def serialize(self, parent, makeelement):
- lvl = makeelement(parent, 'w:lvl', w_ilvl=str(self.ilvl))
- makeelement(lvl, 'w:start', w_val=str(self.start))
+ lvl = makeelement(parent, 'w:lvl', w_ilvl=unicode_type(self.ilvl))
+ makeelement(lvl, 'w:start', w_val=unicode_type(self.start))
makeelement(lvl, 'w:numFmt', w_val=self.num_fmt)
makeelement(lvl, 'w:lvlText', w_val=self.lvl_text)
makeelement(lvl, 'w:lvlJc', w_val='left')
- makeelement(makeelement(lvl, 'w:pPr'), 'w:ind', w_hanging='360', w_left=str(1152 + self.ilvl * 360))
+ makeelement(makeelement(lvl, 'w:pPr'), 'w:ind', w_hanging='360', w_left=unicode_type(1152 + self.ilvl * 360))
if self.num_fmt == 'bullet':
ff = {'\uf0b7':'Symbol', '\uf0a7':'Wingdings'}.get(self.lvl_text, 'Courier New')
makeelement(makeelement(lvl, 'w:rPr'), 'w:rFonts', w_ascii=ff, w_hAnsi=ff, w_hint="default")
@@ -165,5 +165,5 @@ class ListsManager(object):
defn.serialize(parent)
makeelement = self.namespace.makeelement
for defn in self.definitions:
- n = makeelement(parent, 'w:num', w_numId=str(defn.num_id + 1))
- makeelement(n, 'w:abstractNumId', w_val=str(defn.num_id))
+ n = makeelement(parent, 'w:num', w_numId=unicode_type(defn.num_id + 1))
+ makeelement(n, 'w:abstractNumId', w_val=unicode_type(defn.num_id))
diff --git a/src/calibre/ebooks/docx/writer/styles.py b/src/calibre/ebooks/docx/writer/styles.py
index 4cea15d599..5d5e617538 100644
--- a/src/calibre/ebooks/docx/writer/styles.py
+++ b/src/calibre/ebooks/docx/writer/styles.py
@@ -14,7 +14,7 @@ from lxml import etree
from calibre.ebooks import parse_css_length
from calibre.ebooks.docx.writer.utils import convert_color, int_or_zero
from calibre.utils.localization import lang_as_iso639_1
-from polyglot.builtins import iteritems, filter
+from polyglot.builtins import iteritems, filter, unicode_type
from tinycss.css21 import CSS21Parser
css_parser = CSS21Parser()
@@ -76,7 +76,7 @@ class CombinedStyle(object):
pPr = makeelement(block, 'w:pPr')
self.bs.serialize_properties(pPr, normal_style.bs)
if self.outline_level is not None:
- makeelement(pPr, 'w:outlineLvl', w_val=str(self.outline_level + 1))
+ makeelement(pPr, 'w:outlineLvl', w_val=unicode_type(self.outline_level + 1))
rPr = makeelement(block, 'w:rPr')
self.rs.serialize_properties(rPr, normal_style.rs)
@@ -109,16 +109,16 @@ class FloatSpec(object):
def serialize(self, block, parent):
if self.is_dropcaps:
- attrs = dict(w_dropCap='drop', w_lines=str(self.dropcaps_lines), w_wrap='around', w_vAnchor='text', w_hAnchor='text')
+ attrs = dict(w_dropCap='drop', w_lines=unicode_type(self.dropcaps_lines), w_wrap='around', w_vAnchor='text', w_hAnchor='text')
else:
attrs = dict(
w_wrap='around', w_vAnchor='text', w_hAnchor='text', w_xAlign=self.x_align, w_y='1',
- w_hSpace=str(self.h_space), w_vSpace=str(self.v_space), w_hRule=self.h_rule
+ w_hSpace=unicode_type(self.h_space), w_vSpace=unicode_type(self.v_space), w_hRule=self.h_rule
)
if self.w is not None:
- attrs['w_w'] = str(self.w)
+ attrs['w_w'] = unicode_type(self.w)
if self.h is not None:
- attrs['w_h'] = str(self.h)
+ attrs['w_h'] = unicode_type(self.h)
self.makeelement(parent, 'w:framePr', **attrs)
# Margins are already applied by the frame style, so override them to
# be zero on individual blocks
@@ -137,7 +137,7 @@ class FloatSpec(object):
padding = getattr(self, 'padding_' + edge)
width = getattr(self, 'border_%s_width' % edge)
bstyle = getattr(self, 'border_%s_style' % edge)
- self.makeelement(bdr, 'w:'+edge, w_space=str(padding), w_val=bstyle, w_sz=str(width), w_color=getattr(self, 'border_%s_color' % edge))
+ self.makeelement(bdr, 'w:'+edge, w_space=unicode_type(padding), w_val=bstyle, w_sz=unicode_type(width), w_color=getattr(self, 'border_%s_color' % edge))
class DOCXStyle(object):
@@ -233,7 +233,7 @@ class TextStyle(DOCXStyle):
self.spacing = None
va = css.first_vertical_align
if isinstance(va, numbers.Number):
- self.vertical_align = str(int(va * 2))
+ self.vertical_align = unicode_type(int(va * 2))
else:
val = {
'top':'superscript', 'text-top':'superscript', 'sup':'superscript', 'super':'superscript',
@@ -289,9 +289,9 @@ class TextStyle(DOCXStyle):
w = self.w
is_normal_style = self is normal_style
if is_normal_style or self.padding != normal_style.padding:
- bdr.set(w('space'), str(self.padding))
+ bdr.set(w('space'), unicode_type(self.padding))
if is_normal_style or self.border_width != normal_style.border_width:
- bdr.set(w('sz'), str(self.border_width))
+ bdr.set(w('sz'), unicode_type(self.border_width))
if is_normal_style or self.border_style != normal_style.border_style:
bdr.set(w('val'), self.border_style)
if is_normal_style or self.border_color != normal_style.border_color:
@@ -341,7 +341,7 @@ class TextStyle(DOCXStyle):
if check_attr('shadow'):
rPr.append(makeelement(rPr, 'shadow', val=bmap(self.shadow)))
if check_attr('spacing'):
- rPr.append(makeelement(rPr, 'spacing', val=str(self.spacing or 0)))
+ rPr.append(makeelement(rPr, 'spacing', val=unicode_type(self.spacing or 0)))
if is_normal_style:
rPr.append(makeelement(rPr, 'vertAlign', val=self.vertical_align if self.vertical_align in {'superscript', 'subscript'} else 'baseline'))
elif self.vertical_align != normal_style.vertical_align:
@@ -379,7 +379,7 @@ class DescendantTextStyle(object):
for name, attr in (('sz', 'font_size'), ('b', 'bold'), ('i', 'italic')):
pval, cval = vals(attr)
if pval != cval:
- val = 'on' if attr in {'bold', 'italic'} else str(cval) # bold, italic are toggle properties
+ val = 'on' if attr in {'bold', 'italic'} else unicode_type(cval) # bold, italic are toggle properties
for suffix in ('', 'Cs'):
add(name + suffix, val=val)
@@ -400,7 +400,7 @@ class DescendantTextStyle(object):
if check('shadow'):
add('shadow', val='on') # toggle property
if check('spacing'):
- add('spacing', val=str(child_style.spacing or 0))
+ add('spacing', val=unicode_type(child_style.spacing or 0))
if check('vertical_align'):
val = child_style.vertical_align
if val in {'superscript', 'subscript', 'baseline'}:
@@ -410,9 +410,9 @@ class DescendantTextStyle(object):
bdr = {}
if check('padding'):
- bdr['space'] = str(child_style.padding)
+ bdr['space'] = unicode_type(child_style.padding)
if check('border_width'):
- bdr['sz'] = str(child_style.border_width)
+ bdr['sz'] = unicode_type(child_style.border_width)
if check('border_style'):
bdr['val'] = child_style.border_style
if check('border_color'):
@@ -536,14 +536,14 @@ class BlockStyle(DOCXStyle):
e = bdr.makeelement(w(edge))
padding = getattr(self, 'padding_' + edge)
if (self is normal_style and padding > 0) or (padding != getattr(normal_style, 'padding_' + edge)):
- e.set(w('space'), str(padding))
+ e.set(w('space'), unicode_type(padding))
width = getattr(self, 'border_%s_width' % edge)
bstyle = getattr(self, 'border_%s_style' % edge)
if (self is normal_style and width > 0 and bstyle != 'none'
) or width != getattr(normal_style, 'border_%s_width' % edge
) or bstyle != getattr(normal_style, 'border_%s_style' % edge):
e.set(w('val'), bstyle)
- e.set(w('sz'), str(width))
+ e.set(w('sz'), unicode_type(width))
e.set(w('color'), getattr(self, 'border_%s_color' % edge))
if e.attrib:
bdr.append(e)
@@ -567,15 +567,15 @@ class BlockStyle(DOCXStyle):
if css_unit in ('em', 'ex'):
lines = max(0, int(css_val * (50 if css_unit == 'ex' else 100)))
if (self is normal_style and lines > 0) or getter(self) != getter(normal_style):
- spacing.set(w(attr + 'Lines'), str(lines))
+ spacing.set(w(attr + 'Lines'), unicode_type(lines))
else:
getter = attrgetter('margin_' + edge)
val = getter(self)
if (self is normal_style and val > 0) or val != getter(normal_style):
- spacing.set(w(attr), str(val))
+ spacing.set(w(attr), unicode_type(val))
if self is normal_style or self.line_height != normal_style.line_height:
- spacing.set(w('line'), str(self.line_height))
+ spacing.set(w('line'), unicode_type(self.line_height))
spacing.set(w('lineRule'), 'atLeast')
if spacing.attrib:
@@ -588,31 +588,31 @@ class BlockStyle(DOCXStyle):
if css_unit in ('em', 'ex'):
chars = max(0, int(css_val * (50 if css_unit == 'ex' else 100)))
if (self is normal_style and chars > 0) or getter(self) != getter(normal_style):
- ind.set(w(edge + 'Chars'), str(chars))
+ ind.set(w(edge + 'Chars'), unicode_type(chars))
else:
getter = attrgetter('margin_' + edge)
val = getter(self)
if (self is normal_style and val > 0) or val != getter(normal_style):
- ind.set(w(edge), str(val))
+ ind.set(w(edge), unicode_type(val))
ind.set(w(edge + 'Chars'), '0') # This is needed to override any declaration in the parent style
css_val, css_unit = parse_css_length(self.css_text_indent)
if css_unit in ('em', 'ex'):
chars = int(css_val * (50 if css_unit == 'ex' else 100))
if css_val >= 0:
if (self is normal_style and chars > 0) or self.css_text_indent != normal_style.css_text_indent:
- ind.set(w('firstLineChars'), str(chars))
+ ind.set(w('firstLineChars'), unicode_type(chars))
else:
if (self is normal_style and chars < 0) or self.css_text_indent != normal_style.css_text_indent:
- ind.set(w('hangingChars'), str(abs(chars)))
+ ind.set(w('hangingChars'), unicode_type(abs(chars)))
else:
val = self.text_indent
if val >= 0:
if (self is normal_style and val > 0) or self.text_indent != normal_style.text_indent:
- ind.set(w('firstLine'), str(val))
+ ind.set(w('firstLine'), unicode_type(val))
ind.set(w('firstLineChars'), '0') # This is needed to override any declaration in the parent style
else:
if (self is normal_style and val < 0) or self.text_indent != normal_style.text_indent:
- ind.set(w('hanging'), str(abs(val)))
+ ind.set(w('hanging'), unicode_type(abs(val)))
ind.set(w('hangingChars'), '0')
if ind.attrib:
pPr.append(ind)
@@ -686,7 +686,7 @@ class StylesManager(object):
pure_block_styles.add(bs)
self.pure_block_styles = sorted(pure_block_styles, key=block_counts.__getitem__)
- bnum = len(str(max(1, len(pure_block_styles) - 1)))
+ bnum = len(unicode_type(max(1, len(pure_block_styles) - 1)))
for i, bs in enumerate(self.pure_block_styles):
bs.id = bs.name = '%0{}d Block'.format(bnum) % i
bs.seq = i
@@ -706,7 +706,7 @@ class StylesManager(object):
heading_style = styles[-1]
heading_style.outline_level = i
- snum = len(str(max(1, len(counts) - 1)))
+ snum = len(unicode_type(max(1, len(counts) - 1)))
heading_styles = []
for i, (style, count) in enumerate(counts.most_common()):
if i == 0:
@@ -734,7 +734,7 @@ class StylesManager(object):
if run.descendant_style is None:
run.descendant_style = descendant_style_map[ds] = ds
ds_counts[run.descendant_style] += run.style_weight
- rnum = len(str(max(1, len(ds_counts) - 1)))
+ rnum = len(unicode_type(max(1, len(ds_counts) - 1)))
for i, (text_style, count) in enumerate(ds_counts.most_common()):
text_style.id = 'Text%d' % i
text_style.name = '%0{}d Text'.format(rnum) % i
diff --git a/src/calibre/ebooks/epub/__init__.py b/src/calibre/ebooks/epub/__init__.py
index dc85db1e36..a750203b81 100644
--- a/src/calibre/ebooks/epub/__init__.py
+++ b/src/calibre/ebooks/epub/__init__.py
@@ -1,4 +1,5 @@
-from __future__ import with_statement
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
@@ -18,7 +19,7 @@ def rules(stylesheets):
def simple_container_xml(opf_path, extra_entries=''):
- return u'''\
+ return '''\
@@ -36,7 +37,7 @@ def initialize_container(path_to_container, opf_name='metadata.opf',
'''
rootfiles = ''
for path, mimetype, _ in extra_entries:
- rootfiles += u''.format(
+ rootfiles += ''.format(
path, mimetype)
CONTAINER = simple_container_xml(opf_name, rootfiles).encode('utf-8')
zf = ZipFile(path_to_container, 'w')
diff --git a/src/calibre/ebooks/epub/pages.py b/src/calibre/ebooks/epub/pages.py
index 200c5e03fe..613821337e 100644
--- a/src/calibre/ebooks/epub/pages.py
+++ b/src/calibre/ebooks/epub/pages.py
@@ -2,7 +2,7 @@
Add page mapping information to an EPUB book.
'''
-from __future__ import with_statement
+from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift '
@@ -13,6 +13,7 @@ from itertools import count
from calibre.ebooks.oeb.base import XHTML_NS
from calibre.ebooks.oeb.base import OEBBook
from lxml.etree import XPath
+from polyglot.builtins import unicode_type
NSMAP = {'h': XHTML_NS, 'html': XHTML_NS, 'xhtml': XHTML_NS}
PAGE_RE = re.compile(r'page', re.IGNORECASE)
@@ -32,7 +33,7 @@ def filter_name(name):
def build_name_for(expr):
if not expr:
counter = count(1)
- return lambda elem: str(next(counter))
+ return lambda elem: unicode_type(next(counter))
selector = XPath(expr, namespaces=NSMAP)
def name_for(elem):
diff --git a/src/calibre/ebooks/epub/periodical.py b/src/calibre/ebooks/epub/periodical.py
index b5943b7dff..ebadc990dc 100644
--- a/src/calibre/ebooks/epub/periodical.py
+++ b/src/calibre/ebooks/epub/periodical.py
@@ -1,5 +1,6 @@
#!/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__ = '2010, Kovid Goyal '
@@ -13,7 +14,7 @@ from calibre import strftime, prepare_string_for_xml as xml
from calibre.utils.date import parse_date
from polyglot.builtins import unicode_type, filter
-SONY_METADATA = u'''\
+SONY_METADATA = '''\
'''
-SONY_ATOM = u'''\
+SONY_ATOM = '''\
'''
-SONY_ATOM_SECTION = u'''\
+SONY_ATOM_SECTION = '''\
{title}
@@ -63,7 +64,7 @@ SONY_ATOM_SECTION = u'''\
'''
-SONY_ATOM_ENTRY = u'''\
+SONY_ATOM_ENTRY = '''\
{title}
{author}
@@ -86,7 +87,7 @@ def sony_metadata(oeb):
publisher = __appname__ + ' ' + __version__
try:
pt = unicode_type(oeb.metadata.publication_type[0])
- short_title = u':'.join(pt.split(':')[2:])
+ short_title = ':'.join(pt.split(':')[2:])
except:
pass
@@ -116,7 +117,7 @@ def sony_metadata(oeb):
try:
base_id = unicode_type(list(filter(cal_id, m.identifier))[0])
except:
- base_id = str(uuid4())
+ base_id = unicode_type(uuid4())
toc = oeb.toc
@@ -144,7 +145,7 @@ def sony_metadata(oeb):
d = 1
bsectitle = sectitle
while sectitle in seen_titles:
- sectitle = bsectitle + ' ' + str(d)
+ sectitle = bsectitle + ' ' + unicode_type(d)
d += 1
seen_titles.add(sectitle)
sectitle = xml(sectitle, True)
@@ -163,7 +164,7 @@ def sony_metadata(oeb):
btitle = atitle
d = 1
while atitle in seen_titles:
- atitle = btitle + ' ' + str(d)
+ atitle = btitle + ' ' + unicode_type(d)
d += 1
auth = article.author if article.author else ''
@@ -180,7 +181,7 @@ def sony_metadata(oeb):
short_title=short_title,
section_title=sectitle,
href=article.href,
- word_count=str(1),
+ word_count=unicode_type(1),
id=xml(base_id)+'/'+secid+'/'+aid
))
diff --git a/src/calibre/ebooks/fb2/fb2ml.py b/src/calibre/ebooks/fb2/fb2ml.py
index 9936ffad7e..a84cb84023 100644
--- a/src/calibre/ebooks/fb2/fb2ml.py
+++ b/src/calibre/ebooks/fb2/fb2ml.py
@@ -1,4 +1,5 @@
# -*- coding: utf-8 -*-
+from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3'
__copyright__ = '2009, John Schember '
@@ -62,12 +63,12 @@ class FB2MLizer(object):
output.append(self.get_text())
output.append(self.fb2mlize_images())
output.append(self.fb2_footer())
- output = self.clean_text(u''.join(output))
+ output = self.clean_text(''.join(output))
if self.opts.pretty_print:
- return u'\n%s' % etree.tostring(etree.fromstring(output), encoding='unicode', pretty_print=True)
+ return '\n%s' % etree.tostring(etree.fromstring(output), encoding='unicode', pretty_print=True)
else:
- return u'' + output
+ return '' + output
def clean_text(self, text):
# Condense empty paragraphs into a line break.
@@ -116,11 +117,11 @@ class FB2MLizer(object):
metadata['cover'] = self.get_cover()
metadata['genre'] = self.opts.fb2_genre
- metadata['author'] = u''
+ metadata['author'] = ''
for auth in self.oeb_book.metadata.creator:
- author_first = u''
- author_middle = u''
- author_last = u''
+ author_first = ''
+ author_middle = ''
+ author_last = ''
author_parts = auth.value.split(' ')
if len(author_parts) == 1:
author_last = author_parts[0]
@@ -138,22 +139,22 @@ class FB2MLizer(object):
metadata['author'] += '%s' % prepare_string_for_xml(author_last)
metadata['author'] += ''
if not metadata['author']:
- metadata['author'] = u''
+ metadata['author'] = ''
- metadata['keywords'] = u''
+ metadata['keywords'] = ''
tags = list(map(unicode_type, self.oeb_book.metadata.subject))
if tags:
tags = ', '.join(prepare_string_for_xml(x) for x in tags)
metadata['keywords'] = '%s'%tags
- metadata['sequence'] = u''
+ metadata['sequence'] = ''
if self.oeb_book.metadata.series:
index = '1'
if self.oeb_book.metadata.series_index:
index = self.oeb_book.metadata.series_index[0]
- metadata['sequence'] = u'' % (prepare_string_for_xml(u'%s' % self.oeb_book.metadata.series[0]), index)
+ metadata['sequence'] = '' % (prepare_string_for_xml('%s' % self.oeb_book.metadata.series[0]), index)
- year = publisher = isbn = u''
+ year = publisher = isbn = ''
identifiers = self.oeb_book.metadata['identifier']
for x in identifiers:
if x.get(OPF('scheme'), None).lower() == 'uuid' or unicode_type(x).startswith('urn:uuid:'):
@@ -161,7 +162,7 @@ class FB2MLizer(object):
break
if metadata['id'] is None:
self.log.warn('No UUID identifier found')
- metadata['id'] = str(uuid.uuid4())
+ metadata['id'] = unicode_type(uuid.uuid4())
try:
date = self.oeb_book.metadata['date'][0]
@@ -194,7 +195,7 @@ class FB2MLizer(object):
from calibre.utils.html2text import html2text
metadata['comments'] = '{}'.format(prepare_string_for_xml(html2text(comments.value.strip())))
- return textwrap.dedent(u'''
+ return textwrap.dedent('''
@@ -222,7 +223,7 @@ class FB2MLizer(object):
\n''') % metadata
def fb2_footer(self):
- return u'\n'
+ return '\n'
def get_cover(self):
from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
@@ -255,9 +256,9 @@ class FB2MLizer(object):
if cover_href in self.oeb_book.manifest.hrefs.keys():
if cover_href not in self.image_hrefs.keys():
self.image_hrefs[cover_href] = '_%s.jpg' % len(self.image_hrefs.keys())
- return u'' % self.image_hrefs[cover_href]
+ return '' % self.image_hrefs[cover_href]
- return u''
+ return ''
def get_text(self):
from calibre.ebooks.oeb.base import XHTML
diff --git a/src/calibre/ebooks/html/__init__.py b/src/calibre/ebooks/html/__init__.py
index ecd0329f82..720ff711e6 100644
--- a/src/calibre/ebooks/html/__init__.py
+++ b/src/calibre/ebooks/html/__init__.py
@@ -1,31 +1,7 @@
#!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
-from __future__ import with_statement
+from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal '
__docformat__ = 'restructuredtext en'
-
-import re
-
-
-def tostring(root, strip_comments=False, pretty_print=False):
- '''
- Serialize processed XHTML.
- '''
- from lxml.etree import tostring as _tostring
-
- root.set('xmlns', 'http://www.w3.org/1999/xhtml')
- root.set('{http://www.w3.org/1999/xhtml}xlink', 'http://www.w3.org/1999/xlink')
- for x in root.iter():
- if hasattr(x.tag, 'rpartition') and x.tag.rpartition('}')[-1].lower() == 'svg':
- x.set('xmlns', 'http://www.w3.org/2000/svg')
-
- ans = _tostring(root, encoding='utf-8', pretty_print=pretty_print)
- if strip_comments:
- ans = re.compile(r'', re.DOTALL).sub('', ans)
- ans = '\n'+ans
-
- return ans
-
-
diff --git a/src/calibre/ebooks/html/input.py b/src/calibre/ebooks/html/input.py
index 1b4d644cd2..91d02d7297 100644
--- a/src/calibre/ebooks/html/input.py
+++ b/src/calibre/ebooks/html/input.py
@@ -1,7 +1,6 @@
#!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
-from __future__ import with_statement
-from __future__ import print_function
+from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal '
@@ -18,7 +17,7 @@ from calibre.ebooks.oeb.base import urlunquote
from calibre.ebooks.chardet import detect_xml_encoding
from calibre.constants import iswindows
from calibre import unicode_path, as_unicode, replace_entities
-from polyglot.builtins import unicode_type
+from polyglot.builtins import is_py3, unicode_type
from polyglot.urllib import urlparse, urlunparse
@@ -68,6 +67,9 @@ class Link(object):
def __str__(self):
return u'Link: %s --> %s'%(self.url, self.path)
+ if not is_py3:
+ __unicode__ = __str__
+
class IgnoreFile(Exception):
@@ -149,10 +151,10 @@ class HTMLFile(object):
return hash(self.path)
def __str__(self):
- return u'HTMLFile:%d:%s:%s'%(self.level, 'b' if self.is_binary else 'a', self.path)
+ return 'HTMLFile:%d:%s:%s'%(self.level, 'b' if self.is_binary else 'a', self.path)
def __repr__(self):
- return str(self)
+ return unicode_type(self)
def find_links(self, src):
for match in self.LINK_PAT.finditer(src):
diff --git a/src/calibre/ebooks/html/meta.py b/src/calibre/ebooks/html/meta.py
index eebf9cdd6d..7cc9010a38 100644
--- a/src/calibre/ebooks/html/meta.py
+++ b/src/calibre/ebooks/html/meta.py
@@ -1,4 +1,5 @@
-from __future__ import with_statement
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL 3'
__copyright__ = '2010, Fabian Grassl '
__docformat__ = 'restructuredtext en'
diff --git a/src/calibre/ebooks/iterator/__init__.py b/src/calibre/ebooks/iterator/__init__.py
index 9a3d842248..4ddf412436 100644
--- a/src/calibre/ebooks/iterator/__init__.py
+++ b/src/calibre/ebooks/iterator/__init__.py
@@ -1,9 +1,7 @@
#!/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__ = '2010, Kovid Goyal '
__docformat__ = 'restructuredtext en'
-
-
-
diff --git a/src/calibre/ebooks/lit/__init__.py b/src/calibre/ebooks/lit/__init__.py
index 5be3cb9b6a..3a4904f419 100644
--- a/src/calibre/ebooks/lit/__init__.py
+++ b/src/calibre/ebooks/lit/__init__.py
@@ -1,3 +1,5 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift '
diff --git a/src/calibre/ebooks/lit/lzx.py b/src/calibre/ebooks/lit/lzx.py
index a1e447d797..aea602f6f9 100644
--- a/src/calibre/ebooks/lit/lzx.py
+++ b/src/calibre/ebooks/lit/lzx.py
@@ -1,7 +1,8 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
+
'''
LZX compression/decompression wrapper.
'''
-from __future__ import with_statement
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift '
diff --git a/src/calibre/ebooks/lit/maps/__init__.py b/src/calibre/ebooks/lit/maps/__init__.py
index b30974ba6b..e9997944e5 100644
--- a/src/calibre/ebooks/lit/maps/__init__.py
+++ b/src/calibre/ebooks/lit/maps/__init__.py
@@ -1,3 +1,5 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift '
diff --git a/src/calibre/ebooks/lit/maps/html.py b/src/calibre/ebooks/lit/maps/html.py
index c144d55ea8..9502092779 100644
--- a/src/calibre/ebooks/lit/maps/html.py
+++ b/src/calibre/ebooks/lit/maps/html.py
@@ -1,3 +1,5 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift '
diff --git a/src/calibre/ebooks/lit/maps/opf.py b/src/calibre/ebooks/lit/maps/opf.py
index 12dcaed4d8..8f5626842b 100644
--- a/src/calibre/ebooks/lit/maps/opf.py
+++ b/src/calibre/ebooks/lit/maps/opf.py
@@ -1,3 +1,5 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift '
diff --git a/src/calibre/ebooks/lrf/fonts.py b/src/calibre/ebooks/lrf/fonts.py
index 6729dfb5b2..c4300bec42 100644
--- a/src/calibre/ebooks/lrf/fonts.py
+++ b/src/calibre/ebooks/lrf/fonts.py
@@ -1,3 +1,5 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal '
diff --git a/src/calibre/ebooks/lrf/lrfparser.py b/src/calibre/ebooks/lrf/lrfparser.py
index 102c4ad2d5..923630c9c1 100644
--- a/src/calibre/ebooks/lrf/lrfparser.py
+++ b/src/calibre/ebooks/lrf/lrfparser.py
@@ -1,3 +1,5 @@
+from __future__ import absolute_import, division, print_function, unicode_literals
+
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal '
''''''
@@ -79,47 +81,49 @@ class LRFDocument(LRFMetaFile):
def write_files(self):
for obj in chain(itervalues(self.image_map), itervalues(self.font_map)):
- open(obj.file, 'wb').write(obj.stream)
+ with open(obj.file, 'wb') as f:
+ f.write(obj.stream)
def to_xml(self, write_files=True):
- bookinfo = u'\n\n\n'
- bookinfo += u'%s\n'%(self.metadata.title_reading, self.metadata.title)
- bookinfo += u'%s\n'%(self.metadata.author_reading, self.metadata.author)
- bookinfo += u'%s\n'%(self.metadata.book_id,)
- bookinfo += u'%s\n'%(self.metadata.publisher,)
- bookinfo += u'\n'%(self.metadata.label,)
- bookinfo += u'%s\n'%(self.metadata.category,)
- bookinfo += u'%s\n'%(self.metadata.classification,)
- bookinfo += u'%s\n\n\n'%(self.metadata.free_text,)
+ bookinfo = '\n\n\n'
+ bookinfo += '%s\n'%(self.metadata.title_reading, self.metadata.title)
+ bookinfo += '%s\n'%(self.metadata.author_reading, self.metadata.author)
+ bookinfo += '%s\n'%(self.metadata.book_id,)
+ bookinfo += '%s\n'%(self.metadata.publisher,)
+ bookinfo += '\n'%(self.metadata.label,)
+ bookinfo += '%s\n'%(self.metadata.category,)
+ bookinfo += '%s\n'%(self.metadata.classification,)
+ bookinfo += '%s\n\n\n'%(self.metadata.free_text,)
th = self.doc_info.thumbnail
if th:
prefix = ascii_filename(self.metadata.title)
- bookinfo += u'\n'%(prefix+'_thumbnail.'+self.doc_info.thumbnail_extension,)
+ bookinfo += '\n'%(prefix+'_thumbnail.'+self.doc_info.thumbnail_extension,)
if write_files:
- open(prefix+'_thumbnail.'+self.doc_info.thumbnail_extension, 'wb').write(th)
- bookinfo += u'%s\n'%(self.doc_info.language,)
- bookinfo += u'%s\n'%(self.doc_info.creator,)
- bookinfo += u'%s\n'%(self.doc_info.producer,)
- bookinfo += u'%s\n\n\n%s\n'%(self.doc_info.page,self.toc)
- pages = u''
+ with open(prefix+'_thumbnail.'+self.doc_info.thumbnail_extension, 'wb') as f:
+ f.write(th)
+ bookinfo += '%s\n'%(self.doc_info.language,)
+ bookinfo += '%s\n'%(self.doc_info.creator,)
+ bookinfo += '%s\n'%(self.doc_info.producer,)
+ bookinfo += '%s\n\n\n%s\n'%(self.doc_info.page,self.toc)
+ pages = ''
done_main = False
pt_id = -1
for page_tree in self:
if not done_main:
done_main = True
- pages += u'\n'
- close = u'\n'
+ pages += '\n'
+ close = '\n'
pt_id = page_tree.id
else:
- pages += u'\n'%(page_tree.id,)
- close = u'\n'
+ pages += '\n'%(page_tree.id,)
+ close = '\n'
for page in page_tree:
pages += unicode_type(page)
pages += close
traversed_objects = [int(i) for i in re.findall(r'objid="(\w+)"', pages)] + [pt_id]
- objects = u'\n\n'
- styles = u'\n