Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'py3' of https://github.com/eli-schwartz/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2019-06-01 08:34:49 +05:30
commit d9fcdbe1a2
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
33 changed files with 267 additions and 264 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
src/calibre/ebooks/conversion/plugins/comic_input.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
@ -102,7 +103,8 @@ class ComicInput(InputFormatPlugin):
'%s is not a valid comic collection' '%s is not a valid comic collection'
' no comics.txt was found in the file') ' no comics.txt was found in the file')
%stream.name) %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): if raw.startswith(codecs.BOM_UTF16_BE):
raw = raw.decode('utf-16-be')[1:] raw = raw.decode('utf-16-be')[1:]
elif raw.startswith(codecs.BOM_UTF16_LE): elif raw.startswith(codecs.BOM_UTF16_LE):
@ -176,7 +178,7 @@ class ComicInput(InputFormatPlugin):
comics = [] comics = []
for i, x in enumerate(comics_): for i, x in enumerate(comics_):
title, fname = x 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) cdir = os.path.abspath(cdir)
if not os.path.exists(cdir): if not os.path.exists(cdir):
os.makedirs(cdir) os.makedirs(cdir)
@ -230,14 +232,14 @@ class ComicInput(InputFormatPlugin):
_('Page')+' %d'%(i+1), play_order=po) _('Page')+' %d'%(i+1), play_order=po)
po += 1 po += 1
opf.set_toc(toc) opf.set_toc(toc)
m, n = open(u'metadata.opf', 'wb'), open('toc.ncx', 'wb') with open('metadata.opf', 'wb') as m, open('toc.ncx', 'wb') as n:
opf.render(m, n, u'toc.ncx') opf.render(m, n, 'toc.ncx')
return os.path.abspath(u'metadata.opf') return os.path.abspath('metadata.opf')
def create_wrappers(self, pages): def create_wrappers(self, pages):
from calibre.ebooks.oeb.base import XHTML_NS from calibre.ebooks.oeb.base import XHTML_NS
wrappers = [] wrappers = []
WRAPPER = textwrap.dedent(u'''\ WRAPPER = textwrap.dedent('''\
<html xmlns="%s"> <html xmlns="%s">
<head> <head>
<meta charset="utf-8"/> <meta charset="utf-8"/>
@ -258,7 +260,7 @@ class ComicInput(InputFormatPlugin):
dir = os.path.dirname(pages[0]) dir = os.path.dirname(pages[0])
for i, page in enumerate(pages): for i, page in enumerate(pages):
wrapper = WRAPPER%(XHTML_NS, i+1, os.path.basename(page), i+1) 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: with open(page, 'wb') as f:
f.write(wrapper.encode('utf-8')) f.write(wrapper.encode('utf-8'))
wrappers.append(page) wrappers.append(page)

27
src/calibre/ebooks/conversion/plugins/epub_output.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # 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' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
@ -233,7 +233,7 @@ class EPUBOutput(OutputFormatPlugin):
if uuid is None: if uuid is None:
self.log.warn('No UUID identifier found') self.log.warn('No UUID identifier found')
from uuid import uuid4 from uuid import uuid4
uuid = str(uuid4()) uuid = unicode_type(uuid4())
oeb.metadata.add('identifier', uuid, scheme='uuid', id=uuid) oeb.metadata.add('identifier', uuid, scheme='uuid', id=uuid)
if encrypted_fonts and not uuid.startswith('urn:uuid:'): if encrypted_fonts and not uuid.startswith('urn:uuid:'):
@ -244,7 +244,7 @@ class EPUBOutput(OutputFormatPlugin):
if unicode_type(x) == uuid: if unicode_type(x) == uuid:
x.content = 'urn:uuid:'+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 from calibre.customize.ui import plugin_for_output_format
metadata_xml = None metadata_xml = None
extra_entries = [] extra_entries = []
@ -252,7 +252,7 @@ class EPUBOutput(OutputFormatPlugin):
if self.opts.output_profile.epub_periodical_format == 'sony': if self.opts.output_profile.epub_periodical_format == 'sony':
from calibre.ebooks.epub.periodical import sony_metadata from calibre.ebooks.epub.periodical import sony_metadata
metadata_xml, atom_xml = sony_metadata(oeb) 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 = plugin_for_output_format('oeb')
oeb_output.convert(oeb, tdir, input_plugin, opts, log) oeb_output.convert(oeb, tdir, input_plugin, opts, log)
opf = [x for x in os.listdir(tdir) if x.endswith('.opf')][0] 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') self.log.warn('Font', path, 'is invalid, ignoring')
if not isinstance(uri, unicode_type): if not isinstance(uri, unicode_type):
uri = uri.decode('utf-8') uri = uri.decode('utf-8')
fonts.append(u''' fonts.append('''
<enc:EncryptedData> <enc:EncryptedData>
<enc:EncryptionMethod Algorithm="http://ns.adobe.com/pdf/enc#RC"/> <enc:EncryptionMethod Algorithm="http://ns.adobe.com/pdf/enc#RC"/>
<enc:CipherData> <enc:CipherData>
@ -347,13 +347,13 @@ class EPUBOutput(OutputFormatPlugin):
</enc:EncryptedData> </enc:EncryptedData>
'''%(uri.replace('"', '\\"'))) '''%(uri.replace('"', '\\"')))
if fonts: if fonts:
ans = '''<encryption ans = b'''<encryption
xmlns="urn:oasis:names:tc:opendocument:xmlns:container" xmlns="urn:oasis:names:tc:opendocument:xmlns:container"
xmlns:enc="http://www.w3.org/2001/04/xmlenc#" xmlns:enc="http://www.w3.org/2001/04/xmlenc#"
xmlns:deenc="http://ns.adobe.com/digitaleditions/enc"> xmlns:deenc="http://ns.adobe.com/digitaleditions/enc">
''' '''
ans += (u'\n'.join(fonts)).encode('utf-8') ans += '\n'.join(fonts).encode('utf-8')
ans += '\n</encryption>' ans += b'\n</encryption>'
return ans return ans
# }}} # }}}
@ -367,7 +367,8 @@ class EPUBOutput(OutputFormatPlugin):
if tag.tail: if tag.tail:
tag.tail = tag.tail.strip() tag.tail = tag.tail.strip()
compressed = etree.tostring(tree.getroot(), encoding='utf-8') 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): # {{{ def workaround_ade_quirks(self): # {{{
@ -430,7 +431,7 @@ class EPUBOutput(OutputFormatPlugin):
if priortext: if priortext:
priortext = priortext.strip() priortext = priortext.strip()
br.tag = XHTML('p') br.tag = XHTML('p')
br.text = u'\u00a0' br.text = '\u00a0'
style = br.get('style', '').split(';') style = br.get('style', '').split(';')
style = list(filter(None, map(lambda x: x.strip(), style))) style = list(filter(None, map(lambda x: x.strip(), style)))
style.append('margin:0pt; border:0pt') style.append('margin:0pt; border:0pt')
@ -483,14 +484,14 @@ class EPUBOutput(OutputFormatPlugin):
tag.tag = XHTML('div') tag.tag = XHTML('div')
# ADE fails to render non breaking hyphens/soft hyphens/zero width spaces # 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('*'): for elem in root.iterdescendants('*'):
if elem.text: if elem.text:
elem.text = special_chars.sub('', 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: if elem.tail:
elem.tail = special_chars.sub('', 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: if stylesheet is not None:
# ADE doesn't render lists correctly if they have left margins # ADE doesn't render lists correctly if they have left margins

17
src/calibre/ebooks/conversion/plugins/fb2_input.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Anatoly Shipitsin <norguhtar at gmail.com>' __copyright__ = '2008, Anatoly Shipitsin <norguhtar at gmail.com>'
""" """
@ -125,9 +126,9 @@ class FB2Input(InputFormatPlugin):
src = img.get('src') src = img.get('src')
img.set('src', self.binary_map.get(src, src)) img.set('src', self.binary_map.get(src, src))
index = transform.tostring(result) 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')) 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')) f.write(css.encode('utf-8'))
stream.seek(0) stream.seek(0)
mi = get_metadata(stream, 'fb2') mi = get_metadata(stream, 'fb2')
@ -137,9 +138,9 @@ class FB2Input(InputFormatPlugin):
mi.authors = [_('Unknown')] mi.authors = [_('Unknown')]
cpath = None cpath = None
if mi.cover_data and mi.cover_data[1]: 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]) 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: else:
for img in doc.xpath('//f:coverpage/f:image', namespaces=NAMESPACES): for img in doc.xpath('//f:coverpage/f:image', namespaces=NAMESPACES):
href = img.get('{%s}href'%XLINK_NS, img.get('href', None)) href = img.get('{%s}href'%XLINK_NS, img.get('href', None))
@ -152,12 +153,12 @@ class FB2Input(InputFormatPlugin):
opf = OPFCreator(getcwd(), mi) opf = OPFCreator(getcwd(), mi)
entries = [(f2, guess_type(f2)[0]) for f2 in os.listdir(u'.')] entries = [(f2, guess_type(f2)[0]) for f2 in os.listdir(u'.')]
opf.create_manifest(entries) opf.create_manifest(entries)
opf.create_spine([u'index.xhtml']) opf.create_spine(['index.xhtml'])
if cpath: if cpath:
opf.guide.set_cover(cpath) opf.guide.set_cover(cpath)
with open(u'metadata.opf', 'wb') as f: with open('metadata.opf', 'wb') as f:
opf.render(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): def extract_embedded_content(self, doc):
from calibre.ebooks.fb2 import base64_decode from calibre.ebooks.fb2 import base64_decode

4
src/calibre/ebooks/conversion/plugins/html_input.py
View File

@ -120,7 +120,7 @@ class HTMLInput(InputFormatPlugin):
if not metadata.language: if not metadata.language:
l = canonicalize_lang(getattr(opts, 'language', None)) l = canonicalize_lang(getattr(opts, 'language', None))
if not l: if not l:
oeb.logger.warn(u'Language not specified') oeb.logger.warn('Language not specified')
l = get_lang().replace('_', '-') l = get_lang().replace('_', '-')
metadata.add('language', l) metadata.add('language', l)
if not metadata.creator: if not metadata.creator:
@ -135,7 +135,7 @@ class HTMLInput(InputFormatPlugin):
if not metadata.title: if not metadata.title:
oeb.logger.warn('Title not specified') oeb.logger.warn('Title not specified')
metadata.add('title', self.oeb.translate(__('Unknown'))) 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') metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
for ident in metadata.identifier: for ident in metadata.identifier:
if 'id' in ident.attrib: if 'id' in ident.attrib:

12
src/calibre/ebooks/conversion/plugins/html_output.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2010, Fabian Grassl <fg@jusmeum.de>' __copyright__ = '2010, Fabian Grassl <fg@jusmeum.de>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
@ -91,17 +92,20 @@ class HTMLOutput(OutputFormatPlugin):
# read template files # read template files
if opts.template_html_index is not None: 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: else:
template_html_index_data = P('templates/html_export_default_index.tmpl', data=True) template_html_index_data = P('templates/html_export_default_index.tmpl', data=True)
if opts.template_html is not None: 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: else:
template_html_data = P('templates/html_export_default.tmpl', data=True) template_html_data = P('templates/html_export_default.tmpl', data=True)
if opts.template_css is not None: 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: else:
template_css_data = P('templates/html_export_default.css', data=True) template_css_data = P('templates/html_export_default.css', data=True)

19
src/calibre/ebooks/conversion/plugins/snb_input.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2010, Li Fanxi <lifanxi@freemindworld.com>' __copyright__ = '2010, Li Fanxi <lifanxi@freemindworld.com>'
@ -9,12 +10,13 @@ import os
from calibre.customize.conversion import InputFormatPlugin from calibre.customize.conversion import InputFormatPlugin
from calibre.ptempfile import TemporaryDirectory from calibre.ptempfile import TemporaryDirectory
from calibre.utils.filenames import ascii_filename from calibre.utils.filenames import ascii_filename
from polyglot.builtins import unicode_type
HTML_TEMPLATE = u'<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/><title>%s</title></head><body>\n%s\n</body></html>' HTML_TEMPLATE = '<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/><title>%s</title></head><body>\n%s\n</body></html>'
def html_encode(s): def html_encode(s):
return s.replace(u'&', u'&amp;').replace(u'<', u'&lt;').replace(u'>', u'&gt;').replace(u'"', u'&quot;').replace(u"'", u'&apos;').replace(u'\n', u'<br/>').replace(u' ', u'&nbsp;') # noqa return s.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;').replace('"', '&quot;').replace("'", '&apos;').replace('\n', '<br/>').replace(' ', '&nbsp;') # noqa
class SNBInput(InputFormatPlugin): class SNBInput(InputFormatPlugin):
@ -43,7 +45,7 @@ class SNBInput(InputFormatPlugin):
except: except:
raise ValueError("Invalid SNB file") raise ValueError("Invalid SNB file")
if not snbFile.IsValid(): if not snbFile.IsValid():
log.debug("Invaild SNB file") log.debug("Invalid SNB file")
raise ValueError("Invalid SNB file") raise ValueError("Invalid SNB file")
log.debug("Handle meta data ...") log.debug("Handle meta data ...")
from calibre.ebooks.conversion.plumber import create_oebbook from calibre.ebooks.conversion.plumber import create_oebbook
@ -74,7 +76,7 @@ class SNBInput(InputFormatPlugin):
if d['cover'] != '': if d['cover'] != '':
oeb.guide.add('cover', 'Cover', 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') oeb.metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
for ident in oeb.metadata.identifier: for ident in oeb.metadata.identifier:
if 'id' in ident.attrib: if 'id' in ident.attrib:
@ -96,15 +98,14 @@ class SNBInput(InputFormatPlugin):
if data is None: if data is None:
continue continue
snbc = etree.fromstring(data) snbc = etree.fromstring(data)
outputFile = open(os.path.join(tdir, fname), 'wb')
lines = [] lines = []
for line in snbc.find('.//body'): for line in snbc.find('.//body'):
if line.tag == 'text': if line.tag == 'text':
lines.append(u'<p>%s</p>' % html_encode(line.text)) lines.append('<p>%s</p>' % html_encode(line.text))
elif line.tag == 'img': elif line.tag == 'img':
lines.append(u'<p><img src="%s" /></p>' % html_encode(line.text)) lines.append('<p><img src="%s" /></p>' % html_encode(line.text))
outputFile.write((HTML_TEMPLATE % (chapterName, u'\n'.join(lines))).encode('utf-8', 'replace')) with open(os.path.join(tdir, fname), 'wb') as f:
outputFile.close() f.write((HTML_TEMPLATE % (chapterName, '\n'.join(lines))).encode('utf-8', 'replace'))
oeb.toc.add(ch.text, fname) oeb.toc.add(ch.text, fname)
id, href = oeb.manifest.generate(id='html', id, href = oeb.manifest.generate(id='html',
href=ascii_filename(fname)) href=ascii_filename(fname))

28
src/calibre/ebooks/conversion/plugins/snb_output.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2010, Li Fanxi <lifanxi@freemindworld.com>' __copyright__ = '2010, Li Fanxi <lifanxi@freemindworld.com>'
@ -113,9 +114,8 @@ class SNBOutput(OutputFormatPlugin):
etree.SubElement(headTree, "cover").text = ProcessFileName(href) etree.SubElement(headTree, "cover").text = ProcessFileName(href)
else: else:
etree.SubElement(headTree, "cover") etree.SubElement(headTree, "cover")
bookInfoFile = open(os.path.join(snbfDir, 'book.snbf'), 'wb') with open(os.path.join(snbfDir, 'book.snbf'), 'wb') as f:
bookInfoFile.write(etree.tostring(bookInfoTree, pretty_print=True, encoding='utf-8')) f.write(etree.tostring(bookInfoTree, pretty_print=True, encoding='utf-8'))
bookInfoFile.close()
# Output TOC # Output TOC
tocInfoTree = etree.Element("toc-snbf") tocInfoTree = etree.Element("toc-snbf")
@ -168,9 +168,8 @@ class SNBOutput(OutputFormatPlugin):
etree.SubElement(tocHead, "chapters").text = '%d' % len(tocBody) etree.SubElement(tocHead, "chapters").text = '%d' % len(tocBody)
tocInfoFile = open(os.path.join(snbfDir, 'toc.snbf'), 'wb') with open(os.path.join(snbfDir, 'toc.snbf'), 'wb') as f:
tocInfoFile.write(etree.tostring(tocInfoTree, pretty_print=True, encoding='utf-8')) f.write(etree.tostring(tocInfoTree, pretty_print=True, encoding='utf-8'))
tocInfoFile.close()
# Output Files # Output Files
oldTree = None oldTree = None
@ -185,9 +184,8 @@ class SNBOutput(OutputFormatPlugin):
else: else:
if oldTree is not None and mergeLast: if oldTree is not None and mergeLast:
log.debug('Output the modified chapter again: %s' % lastName) log.debug('Output the modified chapter again: %s' % lastName)
outputFile = open(os.path.join(snbcDir, lastName), 'wb') with open(os.path.join(snbcDir, lastName), 'wb') as f:
outputFile.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8')) f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
outputFile.close()
mergeLast = False mergeLast = False
log.debug('Converting %s to snbc...' % item.href) log.debug('Converting %s to snbc...' % item.href)
@ -201,9 +199,8 @@ class SNBOutput(OutputFormatPlugin):
postfix = '_' + subName postfix = '_' + subName
lastName = ProcessFileName(item.href + postfix + ".snbc") lastName = ProcessFileName(item.href + postfix + ".snbc")
oldTree = snbcTrees[subName] oldTree = snbcTrees[subName]
outputFile = open(os.path.join(snbcDir, lastName), 'wb') with open(os.path.join(snbcDir, lastName), 'wb') as f:
outputFile.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8')) f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
outputFile.close()
else: else:
log.debug('Merge %s with last TOC item...' % item.href) log.debug('Merge %s with last TOC item...' % item.href)
snbwriter.merge_content(oldTree, oeb_book, item, [('', _("Start"))], opts) snbwriter.merge_content(oldTree, oeb_book, item, [('', _("Start"))], opts)
@ -211,9 +208,8 @@ class SNBOutput(OutputFormatPlugin):
# Output the last one if needed # Output the last one if needed
log.debug('Output the last modified chapter again: %s' % lastName) log.debug('Output the last modified chapter again: %s' % lastName)
if oldTree is not None and mergeLast: if oldTree is not None and mergeLast:
outputFile = open(os.path.join(snbcDir, lastName), 'wb') with open(os.path.join(snbcDir, lastName), 'wb') as f:
outputFile.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8')) f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
outputFile.close()
mergeLast = False mergeLast = False
for item in m: for item in m:
@ -248,7 +244,7 @@ class SNBOutput(OutputFormatPlugin):
# TODO : intelligent image rotation # TODO : intelligent image rotation
# img = img.rotate(90) # img = img.rotate(90)
# x,y = y,x # 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: with lopen(imagePath, 'wb') as f:
f.write(image_to_data(img, fmt=imagePath.rpartition('.')[-1])) f.write(image_to_data(img, fmt=imagePath.rpartition('.')[-1]))

2
src/calibre/ebooks/conversion/plugins/txt_input.py
View File

@ -1,5 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import print_function from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'

4
src/calibre/ebooks/docx/fields.py
View File

@ -8,7 +8,7 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
import re import re
from calibre.ebooks.docx.index import process_index, polish_index_markup 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): class Field(object):
@ -75,7 +75,7 @@ def parser(name, field_map, default_field_name=None):
ans.pop(null, None) ans.pop(null, None)
return ans return ans
parse.__name__ = str('parse_' + name) parse.__name__ = native_string_type('parse_' + name)
return parse return parse

4
src/calibre/ebooks/docx/numbering.py
View File

@ -14,7 +14,7 @@ from lxml.html.builder import OL, UL, SPAN
from calibre.ebooks.docx.block_styles import ParagraphStyle from calibre.ebooks.docx.block_styles import ParagraphStyle
from calibre.ebooks.docx.char_styles import RunStyle, inherit from calibre.ebooks.docx.char_styles import RunStyle, inherit
from calibre.ebooks.metadata import roman from calibre.ebooks.metadata import roman
from polyglot.builtins import iteritems from polyglot.builtins import iteritems, unicode_type
STYLE_MAP = { STYLE_MAP = {
'aiueo': 'hiragana', 'aiueo': 'hiragana',
@ -291,7 +291,7 @@ class Numbering(object):
seen_instances.add(num_id) seen_instances.add(num_id)
p.tag = 'li' p.tag = 'li'
p.set('value', '%s' % counter[ilvl]) 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) p.set('list-id', num_id)
if lvl.num_template is not None: if lvl.num_template is not None:
val = lvl.format_template(counter, ilvl, lvl.num_template) val = lvl.format_template(counter, ilvl, lvl.num_template)

8
src/calibre/ebooks/docx/to_html.py
View File

@ -28,7 +28,7 @@ from calibre.ebooks.docx.fields import Fields
from calibre.ebooks.docx.settings import Settings from calibre.ebooks.docx.settings import Settings
from calibre.ebooks.metadata.opf2 import OPFCreator from calibre.ebooks.metadata.opf2 import OPFCreator
from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1 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' NBSP = '\xa0'
@ -480,7 +480,7 @@ class Convert(object):
current_hyperlink = x current_hyperlink = x
elif x.tag.endswith('}instrText') and x.text and x.text.strip().startswith('TOC '): elif x.tag.endswith('}instrText') and x.text and x.text.strip().startswith('TOC '):
old_anchor = current_anchor 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.anchor_map[anchor] = current_anchor = generate_anchor('toc', frozenset(itervalues(self.anchor_map)))
self.toc_anchor = current_anchor self.toc_anchor = current_anchor
if old_anchor is not None: if old_anchor is not None:
@ -693,9 +693,9 @@ class Convert(object):
ans.append(text.elem) ans.append(text.elem)
ans[-1].set('class', 'tab') ans[-1].set('class', 'tab')
elif self.namespace.is_tag(child, 'w:noBreakHyphen'): 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'): elif self.namespace.is_tag(child, 'w:softHyphen'):
text.buf.append(u'\u00ad') text.buf.append('\u00ad')
if text.buf: if text.buf:
setattr(text.elem, text.attr, ''.join(text.buf)) setattr(text.elem, text.attr, ''.join(text.buf))

8
src/calibre/ebooks/docx/writer/container.py
View File

@ -18,7 +18,7 @@ from calibre.utils.date import utcnow
from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1 from calibre.utils.localization import canonicalize_lang, lang_as_iso639_1
from calibre.utils.zipfile import ZipFile from calibre.utils.zipfile import ZipFile
from calibre.ebooks.pdf.render.common import PAPER_SIZES 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): def xml2str(root, pretty_print=False, with_tail=False):
@ -65,9 +65,9 @@ def create_skeleton(opts, namespaces=None):
def margin(which): def margin(which):
val = page_margin(opts, 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( 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.pgMar(**dict(map(margin, 'left top right bottom'.split()))),
E.cols(**{w('space'):'720'}), E.cols(**{w('space'):'720'}),
E.docGrid(**{w('linePitch'):"360"}), E.docGrid(**{w('linePitch'):"360"}),
@ -243,7 +243,7 @@ class DOCX(object):
namespaces = self.namespace.namespaces namespaces = self.namespace.namespaces
E = ElementMaker(namespace=namespaces['cp'], nsmap={x:namespaces[x] for x in 'cp dc dcterms xsi'.split()}) 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')) 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(): for x in 'created modified'.split():
x = cp.makeelement('{%s}%s' % (namespaces['dcterms'], x), **{'{%s}type' % namespaces['xsi']:'dcterms:W3CDTF'}) x = cp.makeelement('{%s}%s' % (namespaces['dcterms'], x), **{'{%s}type' % namespaces['xsi']:'dcterms:W3CDTF'})
x.text = ts x.text = ts

10
src/calibre/ebooks/docx/writer/from_html.py
View File

@ -101,7 +101,7 @@ class TextRun(object):
for text, preserve_whitespace, bookmark in self.texts: for text, preserve_whitespace, bookmark in self.texts:
if bookmark is not None: if bookmark is not None:
bid = links_manager.bookmark_id 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: if text is None:
makeelement(r, 'w:br', w_clear=preserve_whitespace) makeelement(r, 'w:br', w_clear=preserve_whitespace)
elif hasattr(text, 'xpath'): elif hasattr(text, 'xpath'):
@ -112,7 +112,7 @@ class TextRun(object):
if preserve_whitespace: if preserve_whitespace:
t.set('{http://www.w3.org/XML/1998/namespace}space', 'preserve') t.set('{http://www.w3.org/XML/1998/namespace}space', 'preserve')
if bookmark is not None: 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): def __repr__(self):
return repr(self.texts) return repr(self.texts)
@ -207,7 +207,7 @@ class Block(object):
p = makeelement(body, 'w:p') p = makeelement(body, 'w:p')
end_bookmarks = [] end_bookmarks = []
for bmark in self.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) makeelement(p, 'w:bookmarkStart', w_id=end_bookmarks[-1], w_name=bmark)
if self.block_lang: if self.block_lang:
rpr = makeelement(p, 'w:rPr') rpr = makeelement(p, 'w:rPr')
@ -220,8 +220,8 @@ class Block(object):
self.float_spec.serialize(self, ppr) self.float_spec.serialize(self, ppr)
if self.numbering_id is not None: if self.numbering_id is not None:
numpr = makeelement(ppr, 'w:numPr') numpr = makeelement(ppr, 'w:numPr')
makeelement(numpr, 'w:ilvl', w_val=str(self.numbering_id[1])) makeelement(numpr, 'w:ilvl', w_val=unicode_type(self.numbering_id[1]))
makeelement(numpr, 'w:numId', w_val=str(self.numbering_id[0])) makeelement(numpr, 'w:numId', w_val=unicode_type(self.numbering_id[0]))
if self.linked_style is not None: if self.linked_style is not None:
makeelement(ppr, 'w:pStyle', w_val=self.linked_style.id) makeelement(ppr, 'w:pStyle', w_val=self.linked_style.id)
elif self.style.id: elif self.style.id:

5
src/calibre/ebooks/docx/writer/links.py
View File

@ -9,6 +9,7 @@ import posixpath, re
from uuid import uuid4 from uuid import uuid4
from calibre.utils.filenames import ascii_text from calibre.utils.filenames import ascii_text
from polyglot.builtins import unicode_type
from polyglot.urllib import urlparse from polyglot.urllib import urlparse
@ -35,7 +36,7 @@ class TOCItem(object):
p = makeelement(body, 'w:p', append=False) p = makeelement(body, 'w:p', append=False)
ppr = makeelement(p, 'w:pPr') ppr = makeelement(p, 'w:pPr')
makeelement(ppr, 'w:pStyle', w_val="Normal") 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: if self.is_first:
makeelement(ppr, 'w:pageBreakBefore', w_val='off') makeelement(ppr, 'w:pageBreakBefore', w_val='off')
r = makeelement(p, 'w:r') r = makeelement(p, 'w:r')
@ -69,7 +70,7 @@ class LinksManager(object):
self.namespace = namespace self.namespace = namespace
self.log = log self.log = log
self.document_relationships = document_relationships self.document_relationships = document_relationships
self.top_anchor = type('')(uuid4().hex) self.top_anchor = uuid4().hex
self.anchor_map = {} self.anchor_map = {}
self.used_bookmark_names = set() self.used_bookmark_names = set()
self.bmark_id = 0 self.bmark_id = 0

14
src/calibre/ebooks/docx/writer/lists.py
View File

@ -8,7 +8,7 @@ __copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
from collections import defaultdict from collections import defaultdict
from operator import attrgetter from operator import attrgetter
from polyglot.builtins import iteritems, itervalues from polyglot.builtins import iteritems, itervalues, unicode_type
LIST_STYLES = frozenset( LIST_STYLES = frozenset(
'disc circle square decimal decimal-leading-zero lower-roman upper-roman' 'disc circle square decimal decimal-leading-zero lower-roman upper-roman'
@ -83,7 +83,7 @@ class NumberingDefinition(object):
def serialize(self, parent): def serialize(self, parent):
makeelement = self.namespace.makeelement 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:multiLevelType', w_val='hybridMultilevel')
makeelement(an, 'w:name', w_val='List %d' % (self.num_id + 1)) makeelement(an, 'w:name', w_val='List %d' % (self.num_id + 1))
for level in self.levels: for level in self.levels:
@ -114,12 +114,12 @@ class Level(object):
return hash((self.start, self.num_fmt, self.lvl_text)) return hash((self.start, self.num_fmt, self.lvl_text))
def serialize(self, parent, makeelement): def serialize(self, parent, makeelement):
lvl = makeelement(parent, 'w:lvl', w_ilvl=str(self.ilvl)) lvl = makeelement(parent, 'w:lvl', w_ilvl=unicode_type(self.ilvl))
makeelement(lvl, 'w:start', w_val=str(self.start)) makeelement(lvl, 'w:start', w_val=unicode_type(self.start))
makeelement(lvl, 'w:numFmt', w_val=self.num_fmt) makeelement(lvl, 'w:numFmt', w_val=self.num_fmt)
makeelement(lvl, 'w:lvlText', w_val=self.lvl_text) makeelement(lvl, 'w:lvlText', w_val=self.lvl_text)
makeelement(lvl, 'w:lvlJc', w_val='left') 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': if self.num_fmt == 'bullet':
ff = {'\uf0b7':'Symbol', '\uf0a7':'Wingdings'}.get(self.lvl_text, 'Courier New') 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") 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) defn.serialize(parent)
makeelement = self.namespace.makeelement makeelement = self.namespace.makeelement
for defn in self.definitions: for defn in self.definitions:
n = makeelement(parent, 'w:num', w_numId=str(defn.num_id + 1)) n = makeelement(parent, 'w:num', w_numId=unicode_type(defn.num_id + 1))
makeelement(n, 'w:abstractNumId', w_val=str(defn.num_id)) makeelement(n, 'w:abstractNumId', w_val=unicode_type(defn.num_id))

58
src/calibre/ebooks/docx/writer/styles.py
View File

@ -14,7 +14,7 @@ from lxml import etree
from calibre.ebooks import parse_css_length from calibre.ebooks import parse_css_length
from calibre.ebooks.docx.writer.utils import convert_color, int_or_zero from calibre.ebooks.docx.writer.utils import convert_color, int_or_zero
from calibre.utils.localization import lang_as_iso639_1 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 from tinycss.css21 import CSS21Parser
css_parser = CSS21Parser() css_parser = CSS21Parser()
@ -76,7 +76,7 @@ class CombinedStyle(object):
pPr = makeelement(block, 'w:pPr') pPr = makeelement(block, 'w:pPr')
self.bs.serialize_properties(pPr, normal_style.bs) self.bs.serialize_properties(pPr, normal_style.bs)
if self.outline_level is not None: 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') rPr = makeelement(block, 'w:rPr')
self.rs.serialize_properties(rPr, normal_style.rs) self.rs.serialize_properties(rPr, normal_style.rs)
@ -109,16 +109,16 @@ class FloatSpec(object):
def serialize(self, block, parent): def serialize(self, block, parent):
if self.is_dropcaps: 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: else:
attrs = dict( attrs = dict(
w_wrap='around', w_vAnchor='text', w_hAnchor='text', w_xAlign=self.x_align, w_y='1', 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: 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: 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) self.makeelement(parent, 'w:framePr', **attrs)
# Margins are already applied by the frame style, so override them to # Margins are already applied by the frame style, so override them to
# be zero on individual blocks # be zero on individual blocks
@ -137,7 +137,7 @@ class FloatSpec(object):
padding = getattr(self, 'padding_' + edge) padding = getattr(self, 'padding_' + edge)
width = getattr(self, 'border_%s_width' % edge) width = getattr(self, 'border_%s_width' % edge)
bstyle = getattr(self, 'border_%s_style' % 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): class DOCXStyle(object):
@ -233,7 +233,7 @@ class TextStyle(DOCXStyle):
self.spacing = None self.spacing = None
va = css.first_vertical_align va = css.first_vertical_align
if isinstance(va, numbers.Number): if isinstance(va, numbers.Number):
self.vertical_align = str(int(va * 2)) self.vertical_align = unicode_type(int(va * 2))
else: else:
val = { val = {
'top':'superscript', 'text-top':'superscript', 'sup':'superscript', 'super':'superscript', 'top':'superscript', 'text-top':'superscript', 'sup':'superscript', 'super':'superscript',
@ -289,9 +289,9 @@ class TextStyle(DOCXStyle):
w = self.w w = self.w
is_normal_style = self is normal_style is_normal_style = self is normal_style
if is_normal_style or self.padding != normal_style.padding: 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: 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: if is_normal_style or self.border_style != normal_style.border_style:
bdr.set(w('val'), self.border_style) bdr.set(w('val'), self.border_style)
if is_normal_style or self.border_color != normal_style.border_color: if is_normal_style or self.border_color != normal_style.border_color:
@ -341,7 +341,7 @@ class TextStyle(DOCXStyle):
if check_attr('shadow'): if check_attr('shadow'):
rPr.append(makeelement(rPr, 'shadow', val=bmap(self.shadow))) rPr.append(makeelement(rPr, 'shadow', val=bmap(self.shadow)))
if check_attr('spacing'): 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: if is_normal_style:
rPr.append(makeelement(rPr, 'vertAlign', val=self.vertical_align if self.vertical_align in {'superscript', 'subscript'} else 'baseline')) 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: 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')): for name, attr in (('sz', 'font_size'), ('b', 'bold'), ('i', 'italic')):
pval, cval = vals(attr) pval, cval = vals(attr)
if pval != cval: 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'): for suffix in ('', 'Cs'):
add(name + suffix, val=val) add(name + suffix, val=val)
@ -400,7 +400,7 @@ class DescendantTextStyle(object):
if check('shadow'): if check('shadow'):
add('shadow', val='on') # toggle property add('shadow', val='on') # toggle property
if check('spacing'): 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'): if check('vertical_align'):
val = child_style.vertical_align val = child_style.vertical_align
if val in {'superscript', 'subscript', 'baseline'}: if val in {'superscript', 'subscript', 'baseline'}:
@ -410,9 +410,9 @@ class DescendantTextStyle(object):
bdr = {} bdr = {}
if check('padding'): if check('padding'):
bdr['space'] = str(child_style.padding) bdr['space'] = unicode_type(child_style.padding)
if check('border_width'): if check('border_width'):
bdr['sz'] = str(child_style.border_width) bdr['sz'] = unicode_type(child_style.border_width)
if check('border_style'): if check('border_style'):
bdr['val'] = child_style.border_style bdr['val'] = child_style.border_style
if check('border_color'): if check('border_color'):
@ -536,14 +536,14 @@ class BlockStyle(DOCXStyle):
e = bdr.makeelement(w(edge)) e = bdr.makeelement(w(edge))
padding = getattr(self, 'padding_' + edge) padding = getattr(self, 'padding_' + edge)
if (self is normal_style and padding > 0) or (padding != getattr(normal_style, '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) width = getattr(self, 'border_%s_width' % edge)
bstyle = getattr(self, 'border_%s_style' % edge) bstyle = getattr(self, 'border_%s_style' % edge)
if (self is normal_style and width > 0 and bstyle != 'none' if (self is normal_style and width > 0 and bstyle != 'none'
) or width != getattr(normal_style, 'border_%s_width' % edge ) or width != getattr(normal_style, 'border_%s_width' % edge
) or bstyle != getattr(normal_style, 'border_%s_style' % edge): ) or bstyle != getattr(normal_style, 'border_%s_style' % edge):
e.set(w('val'), bstyle) 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)) e.set(w('color'), getattr(self, 'border_%s_color' % edge))
if e.attrib: if e.attrib:
bdr.append(e) bdr.append(e)
@ -567,15 +567,15 @@ class BlockStyle(DOCXStyle):
if css_unit in ('em', 'ex'): if css_unit in ('em', 'ex'):
lines = max(0, int(css_val * (50 if css_unit == 'ex' else 100))) 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): 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: else:
getter = attrgetter('margin_' + edge) getter = attrgetter('margin_' + edge)
val = getter(self) val = getter(self)
if (self is normal_style and val > 0) or val != getter(normal_style): 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: 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') spacing.set(w('lineRule'), 'atLeast')
if spacing.attrib: if spacing.attrib:
@ -588,31 +588,31 @@ class BlockStyle(DOCXStyle):
if css_unit in ('em', 'ex'): if css_unit in ('em', 'ex'):
chars = max(0, int(css_val * (50 if css_unit == 'ex' else 100))) 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): 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: else:
getter = attrgetter('margin_' + edge) getter = attrgetter('margin_' + edge)
val = getter(self) val = getter(self)
if (self is normal_style and val > 0) or val != getter(normal_style): 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 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) css_val, css_unit = parse_css_length(self.css_text_indent)
if css_unit in ('em', 'ex'): if css_unit in ('em', 'ex'):
chars = int(css_val * (50 if css_unit == 'ex' else 100)) chars = int(css_val * (50 if css_unit == 'ex' else 100))
if css_val >= 0: if css_val >= 0:
if (self is normal_style and chars > 0) or self.css_text_indent != normal_style.css_text_indent: 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: else:
if (self is normal_style and chars < 0) or self.css_text_indent != normal_style.css_text_indent: 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: else:
val = self.text_indent val = self.text_indent
if val >= 0: if val >= 0:
if (self is normal_style and val > 0) or self.text_indent != normal_style.text_indent: 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 ind.set(w('firstLineChars'), '0') # This is needed to override any declaration in the parent style
else: else:
if (self is normal_style and val < 0) or self.text_indent != normal_style.text_indent: 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') ind.set(w('hangingChars'), '0')
if ind.attrib: if ind.attrib:
pPr.append(ind) pPr.append(ind)
@ -686,7 +686,7 @@ class StylesManager(object):
pure_block_styles.add(bs) pure_block_styles.add(bs)
self.pure_block_styles = sorted(pure_block_styles, key=block_counts.__getitem__) 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): for i, bs in enumerate(self.pure_block_styles):
bs.id = bs.name = '%0{}d Block'.format(bnum) % i bs.id = bs.name = '%0{}d Block'.format(bnum) % i
bs.seq = i bs.seq = i
@ -706,7 +706,7 @@ class StylesManager(object):
heading_style = styles[-1] heading_style = styles[-1]
heading_style.outline_level = i heading_style.outline_level = i
snum = len(str(max(1, len(counts) - 1))) snum = len(unicode_type(max(1, len(counts) - 1)))
heading_styles = [] heading_styles = []
for i, (style, count) in enumerate(counts.most_common()): for i, (style, count) in enumerate(counts.most_common()):
if i == 0: if i == 0:
@ -734,7 +734,7 @@ class StylesManager(object):
if run.descendant_style is None: if run.descendant_style is None:
run.descendant_style = descendant_style_map[ds] = ds run.descendant_style = descendant_style_map[ds] = ds
ds_counts[run.descendant_style] += run.style_weight 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()): for i, (text_style, count) in enumerate(ds_counts.most_common()):
text_style.id = 'Text%d' % i text_style.id = 'Text%d' % i
text_style.name = '%0{}d Text'.format(rnum) % i text_style.name = '%0{}d Text'.format(rnum) % i

7
src/calibre/ebooks/epub/__init__.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
@ -18,7 +19,7 @@ def rules(stylesheets):
def simple_container_xml(opf_path, extra_entries=''): def simple_container_xml(opf_path, extra_entries=''):
return u'''\ return '''\
<?xml version="1.0"?> <?xml version="1.0"?>
<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container"> <container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
<rootfiles> <rootfiles>
@ -36,7 +37,7 @@ def initialize_container(path_to_container, opf_name='metadata.opf',
''' '''
rootfiles = '' rootfiles = ''
for path, mimetype, _ in extra_entries: for path, mimetype, _ in extra_entries:
rootfiles += u'<rootfile full-path="{0}" media-type="{1}"/>'.format( rootfiles += '<rootfile full-path="{0}" media-type="{1}"/>'.format(
path, mimetype) path, mimetype)
CONTAINER = simple_container_xml(opf_name, rootfiles).encode('utf-8') CONTAINER = simple_container_xml(opf_name, rootfiles).encode('utf-8')
zf = ZipFile(path_to_container, 'w') zf = ZipFile(path_to_container, 'w')

5
src/calibre/ebooks/epub/pages.py
View File

@ -2,7 +2,7 @@
Add page mapping information to an EPUB book. 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' __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>' __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
@ -13,6 +13,7 @@ from itertools import count
from calibre.ebooks.oeb.base import XHTML_NS from calibre.ebooks.oeb.base import XHTML_NS
from calibre.ebooks.oeb.base import OEBBook from calibre.ebooks.oeb.base import OEBBook
from lxml.etree import XPath from lxml.etree import XPath
from polyglot.builtins import unicode_type
NSMAP = {'h': XHTML_NS, 'html': XHTML_NS, 'xhtml': XHTML_NS} NSMAP = {'h': XHTML_NS, 'html': XHTML_NS, 'xhtml': XHTML_NS}
PAGE_RE = re.compile(r'page', re.IGNORECASE) PAGE_RE = re.compile(r'page', re.IGNORECASE)
@ -32,7 +33,7 @@ def filter_name(name):
def build_name_for(expr): def build_name_for(expr):
if not expr: if not expr:
counter = count(1) counter = count(1)
return lambda elem: str(next(counter)) return lambda elem: unicode_type(next(counter))
selector = XPath(expr, namespaces=NSMAP) selector = XPath(expr, namespaces=NSMAP)
def name_for(elem): def name_for(elem):

19
src/calibre/ebooks/epub/periodical.py
View File

@ -1,5 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # 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' __license__ = 'GPL v3'
__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
@ -13,7 +14,7 @@ from calibre import strftime, prepare_string_for_xml as xml
from calibre.utils.date import parse_date from calibre.utils.date import parse_date
from polyglot.builtins import unicode_type, filter from polyglot.builtins import unicode_type, filter
SONY_METADATA = u'''\ SONY_METADATA = '''\
<?xml version="1.0" encoding="utf-8"?> <?xml version="1.0" encoding="utf-8"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dcterms="http://purl.org/dc/terms/"
@ -32,7 +33,7 @@ SONY_METADATA = u'''\
</rdf:RDF> </rdf:RDF>
''' '''
SONY_ATOM = u'''\ SONY_ATOM = '''\
<?xml version="1.0" encoding="utf-8" ?> <?xml version="1.0" encoding="utf-8" ?>
<feed xmlns="http://www.w3.org/2005/Atom" <feed xmlns="http://www.w3.org/2005/Atom"
xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dc="http://purl.org/dc/elements/1.1/"
@ -49,7 +50,7 @@ SONY_ATOM = u'''\
</feed> </feed>
''' '''
SONY_ATOM_SECTION = u'''\ SONY_ATOM_SECTION = '''\
<entry rdf:ID="{title}"> <entry rdf:ID="{title}">
<title>{title}</title> <title>{title}</title>
<link href="{href}"/> <link href="{href}"/>
@ -63,7 +64,7 @@ SONY_ATOM_SECTION = u'''\
</entry> </entry>
''' '''
SONY_ATOM_ENTRY = u'''\ SONY_ATOM_ENTRY = '''\
<entry> <entry>
<title>{title}</title> <title>{title}</title>
<author><name>{author}</name></author> <author><name>{author}</name></author>
@ -86,7 +87,7 @@ def sony_metadata(oeb):
publisher = __appname__ + ' ' + __version__ publisher = __appname__ + ' ' + __version__
try: try:
pt = unicode_type(oeb.metadata.publication_type[0]) pt = unicode_type(oeb.metadata.publication_type[0])
short_title = u':'.join(pt.split(':')[2:]) short_title = ':'.join(pt.split(':')[2:])
except: except:
pass pass
@ -116,7 +117,7 @@ def sony_metadata(oeb):
try: try:
base_id = unicode_type(list(filter(cal_id, m.identifier))[0]) base_id = unicode_type(list(filter(cal_id, m.identifier))[0])
except: except:
base_id = str(uuid4()) base_id = unicode_type(uuid4())
toc = oeb.toc toc = oeb.toc
@ -144,7 +145,7 @@ def sony_metadata(oeb):
d = 1 d = 1
bsectitle = sectitle bsectitle = sectitle
while sectitle in seen_titles: while sectitle in seen_titles:
sectitle = bsectitle + ' ' + str(d) sectitle = bsectitle + ' ' + unicode_type(d)
d += 1 d += 1
seen_titles.add(sectitle) seen_titles.add(sectitle)
sectitle = xml(sectitle, True) sectitle = xml(sectitle, True)
@ -163,7 +164,7 @@ def sony_metadata(oeb):
btitle = atitle btitle = atitle
d = 1 d = 1
while atitle in seen_titles: while atitle in seen_titles:
atitle = btitle + ' ' + str(d) atitle = btitle + ' ' + unicode_type(d)
d += 1 d += 1
auth = article.author if article.author else '' auth = article.author if article.author else ''
@ -180,7 +181,7 @@ def sony_metadata(oeb):
short_title=short_title, short_title=short_title,
section_title=sectitle, section_title=sectitle,
href=article.href, href=article.href,
word_count=str(1), word_count=unicode_type(1),
id=xml(base_id)+'/'+secid+'/'+aid id=xml(base_id)+'/'+secid+'/'+aid
)) ))

35
src/calibre/ebooks/fb2/fb2ml.py
View File

@ -1,4 +1,5 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>' __copyright__ = '2009, John Schember <john@nachtimwald.com>'
@ -62,12 +63,12 @@ class FB2MLizer(object):
output.append(self.get_text()) output.append(self.get_text())
output.append(self.fb2mlize_images()) output.append(self.fb2mlize_images())
output.append(self.fb2_footer()) output.append(self.fb2_footer())
output = self.clean_text(u''.join(output)) output = self.clean_text(''.join(output))
if self.opts.pretty_print: if self.opts.pretty_print:
return u'<?xml version="1.0" encoding="UTF-8"?>\n%s' % etree.tostring(etree.fromstring(output), encoding='unicode', pretty_print=True) return '<?xml version="1.0" encoding="UTF-8"?>\n%s' % etree.tostring(etree.fromstring(output), encoding='unicode', pretty_print=True)
else: else:
return u'<?xml version="1.0" encoding="UTF-8"?>' + output return '<?xml version="1.0" encoding="UTF-8"?>' + output
def clean_text(self, text): def clean_text(self, text):
# Condense empty paragraphs into a line break. # Condense empty paragraphs into a line break.
@ -116,11 +117,11 @@ class FB2MLizer(object):
metadata['cover'] = self.get_cover() metadata['cover'] = self.get_cover()
metadata['genre'] = self.opts.fb2_genre metadata['genre'] = self.opts.fb2_genre
metadata['author'] = u'' metadata['author'] = ''
for auth in self.oeb_book.metadata.creator: for auth in self.oeb_book.metadata.creator:
author_first = u'' author_first = ''
author_middle = u'' author_middle = ''
author_last = u'' author_last = ''
author_parts = auth.value.split(' ') author_parts = auth.value.split(' ')
if len(author_parts) == 1: if len(author_parts) == 1:
author_last = author_parts[0] author_last = author_parts[0]
@ -138,22 +139,22 @@ class FB2MLizer(object):
metadata['author'] += '<last-name>%s</last-name>' % prepare_string_for_xml(author_last) metadata['author'] += '<last-name>%s</last-name>' % prepare_string_for_xml(author_last)
metadata['author'] += '</author>' metadata['author'] += '</author>'
if not metadata['author']: if not metadata['author']:
metadata['author'] = u'<author><first-name></first-name><last-name></last-name></author>' metadata['author'] = '<author><first-name></first-name><last-name></last-name></author>'
metadata['keywords'] = u'' metadata['keywords'] = ''
tags = list(map(unicode_type, self.oeb_book.metadata.subject)) tags = list(map(unicode_type, self.oeb_book.metadata.subject))
if tags: if tags:
tags = ', '.join(prepare_string_for_xml(x) for x in tags) tags = ', '.join(prepare_string_for_xml(x) for x in tags)
metadata['keywords'] = '<keywords>%s</keywords>'%tags metadata['keywords'] = '<keywords>%s</keywords>'%tags
metadata['sequence'] = u'' metadata['sequence'] = ''
if self.oeb_book.metadata.series: if self.oeb_book.metadata.series:
index = '1' index = '1'
if self.oeb_book.metadata.series_index: if self.oeb_book.metadata.series_index:
index = self.oeb_book.metadata.series_index[0] index = self.oeb_book.metadata.series_index[0]
metadata['sequence'] = u'<sequence name="%s" number="%s" />' % (prepare_string_for_xml(u'%s' % self.oeb_book.metadata.series[0]), index) metadata['sequence'] = '<sequence name="%s" number="%s" />' % (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'] identifiers = self.oeb_book.metadata['identifier']
for x in identifiers: for x in identifiers:
if x.get(OPF('scheme'), None).lower() == 'uuid' or unicode_type(x).startswith('urn:uuid:'): if x.get(OPF('scheme'), None).lower() == 'uuid' or unicode_type(x).startswith('urn:uuid:'):
@ -161,7 +162,7 @@ class FB2MLizer(object):
break break
if metadata['id'] is None: if metadata['id'] is None:
self.log.warn('No UUID identifier found') self.log.warn('No UUID identifier found')
metadata['id'] = str(uuid.uuid4()) metadata['id'] = unicode_type(uuid.uuid4())
try: try:
date = self.oeb_book.metadata['date'][0] date = self.oeb_book.metadata['date'][0]
@ -194,7 +195,7 @@ class FB2MLizer(object):
from calibre.utils.html2text import html2text from calibre.utils.html2text import html2text
metadata['comments'] = '<annotation>{}</annotation>'.format(prepare_string_for_xml(html2text(comments.value.strip()))) metadata['comments'] = '<annotation>{}</annotation>'.format(prepare_string_for_xml(html2text(comments.value.strip())))
return textwrap.dedent(u''' return textwrap.dedent('''
<FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:xlink="http://www.w3.org/1999/xlink"> <FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:xlink="http://www.w3.org/1999/xlink">
<description> <description>
<title-info> <title-info>
@ -222,7 +223,7 @@ class FB2MLizer(object):
</description>\n''') % metadata </description>\n''') % metadata
def fb2_footer(self): def fb2_footer(self):
return u'\n</FictionBook>' return '\n</FictionBook>'
def get_cover(self): def get_cover(self):
from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES 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 in self.oeb_book.manifest.hrefs.keys():
if cover_href not in self.image_hrefs.keys(): if cover_href not in self.image_hrefs.keys():
self.image_hrefs[cover_href] = '_%s.jpg' % len(self.image_hrefs.keys()) self.image_hrefs[cover_href] = '_%s.jpg' % len(self.image_hrefs.keys())
return u'<coverpage><image xlink:href="#%s" /></coverpage>' % self.image_hrefs[cover_href] return '<coverpage><image xlink:href="#%s" /></coverpage>' % self.image_hrefs[cover_href]
return u'' return ''
def get_text(self): def get_text(self):
from calibre.ebooks.oeb.base import XHTML from calibre.ebooks.oeb.base import XHTML

26
src/calibre/ebooks/html/__init__.py
View File

@ -1,31 +1,7 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # 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' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __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 = '<?xml version="1.0" encoding="utf-8" ?>\n'+ans
return ans

12
src/calibre/ebooks/html/input.py
View File

@ -1,7 +1,6 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # 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
from __future__ import print_function
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
@ -18,7 +17,7 @@ from calibre.ebooks.oeb.base import urlunquote
from calibre.ebooks.chardet import detect_xml_encoding from calibre.ebooks.chardet import detect_xml_encoding
from calibre.constants import iswindows from calibre.constants import iswindows
from calibre import unicode_path, as_unicode, replace_entities 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 from polyglot.urllib import urlparse, urlunparse
@ -68,6 +67,9 @@ class Link(object):
def __str__(self): def __str__(self):
return u'Link: %s --> %s'%(self.url, self.path) return u'Link: %s --> %s'%(self.url, self.path)
if not is_py3:
__unicode__ = __str__
class IgnoreFile(Exception): class IgnoreFile(Exception):
@ -149,10 +151,10 @@ class HTMLFile(object):
return hash(self.path) return hash(self.path)
def __str__(self): 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): def __repr__(self):
return str(self) return unicode_type(self)
def find_links(self, src): def find_links(self, src):
for match in self.LINK_PAT.finditer(src): for match in self.LINK_PAT.finditer(src):

3
src/calibre/ebooks/html/meta.py
View File

@ -1,4 +1,5 @@
from __future__ import with_statement from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL 3' __license__ = 'GPL 3'
__copyright__ = '2010, Fabian Grassl <fg@jusmeum.de>' __copyright__ = '2010, Fabian Grassl <fg@jusmeum.de>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'

4
src/calibre/ebooks/iterator/__init__.py
View File

@ -1,9 +1,7 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # 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' __license__ = 'GPL v3'
__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'

2
src/calibre/ebooks/lit/__init__.py
View File

@ -1,3 +1,5 @@
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>' __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'

3
src/calibre/ebooks/lit/lzx.py
View File

@ -1,7 +1,8 @@
from __future__ import absolute_import, division, print_function, unicode_literals
''' '''
LZX compression/decompression wrapper. LZX compression/decompression wrapper.
''' '''
from __future__ import with_statement
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>' __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'

2
src/calibre/ebooks/lit/maps/__init__.py
View File

@ -1,3 +1,5 @@
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>' __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'

2
src/calibre/ebooks/lit/maps/html.py
View File

@ -1,3 +1,5 @@
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>' __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'

2
src/calibre/ebooks/lit/maps/opf.py
View File

@ -1,3 +1,5 @@
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>' __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'

2
src/calibre/ebooks/lrf/fonts.py
View File

@ -1,3 +1,5 @@
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'

56
src/calibre/ebooks/lrf/lrfparser.py
View File

@ -1,3 +1,5 @@
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''''' ''''''
@ -79,47 +81,49 @@ class LRFDocument(LRFMetaFile):
def write_files(self): def write_files(self):
for obj in chain(itervalues(self.image_map), itervalues(self.font_map)): 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): def to_xml(self, write_files=True):
bookinfo = u'<BookInformation>\n<Info version="1.1">\n<BookInfo>\n' bookinfo = '<BookInformation>\n<Info version="1.1">\n<BookInfo>\n'
bookinfo += u'<Title reading="%s">%s</Title>\n'%(self.metadata.title_reading, self.metadata.title) bookinfo += '<Title reading="%s">%s</Title>\n'%(self.metadata.title_reading, self.metadata.title)
bookinfo += u'<Author reading="%s">%s</Author>\n'%(self.metadata.author_reading, self.metadata.author) bookinfo += '<Author reading="%s">%s</Author>\n'%(self.metadata.author_reading, self.metadata.author)
bookinfo += u'<BookID>%s</BookID>\n'%(self.metadata.book_id,) bookinfo += '<BookID>%s</BookID>\n'%(self.metadata.book_id,)
bookinfo += u'<Publisher reading="">%s</Publisher>\n'%(self.metadata.publisher,) bookinfo += '<Publisher reading="">%s</Publisher>\n'%(self.metadata.publisher,)
bookinfo += u'<Label reading="">%s</Label>\n'%(self.metadata.label,) bookinfo += '<Label reading="">%s</Label>\n'%(self.metadata.label,)
bookinfo += u'<Category reading="">%s</Category>\n'%(self.metadata.category,) bookinfo += '<Category reading="">%s</Category>\n'%(self.metadata.category,)
bookinfo += u'<Classification reading="">%s</Classification>\n'%(self.metadata.classification,) bookinfo += '<Classification reading="">%s</Classification>\n'%(self.metadata.classification,)
bookinfo += u'<FreeText reading="">%s</FreeText>\n</BookInfo>\n<DocInfo>\n'%(self.metadata.free_text,) bookinfo += '<FreeText reading="">%s</FreeText>\n</BookInfo>\n<DocInfo>\n'%(self.metadata.free_text,)
th = self.doc_info.thumbnail th = self.doc_info.thumbnail
if th: if th:
prefix = ascii_filename(self.metadata.title) prefix = ascii_filename(self.metadata.title)
bookinfo += u'<CThumbnail file="%s" />\n'%(prefix+'_thumbnail.'+self.doc_info.thumbnail_extension,) bookinfo += '<CThumbnail file="%s" />\n'%(prefix+'_thumbnail.'+self.doc_info.thumbnail_extension,)
if write_files: if write_files:
open(prefix+'_thumbnail.'+self.doc_info.thumbnail_extension, 'wb').write(th) with open(prefix+'_thumbnail.'+self.doc_info.thumbnail_extension, 'wb') as f:
bookinfo += u'<Language reading="">%s</Language>\n'%(self.doc_info.language,) f.write(th)
bookinfo += u'<Creator reading="">%s</Creator>\n'%(self.doc_info.creator,) bookinfo += '<Language reading="">%s</Language>\n'%(self.doc_info.language,)
bookinfo += u'<Producer reading="">%s</Producer>\n'%(self.doc_info.producer,) bookinfo += '<Creator reading="">%s</Creator>\n'%(self.doc_info.creator,)
bookinfo += u'<SumPage>%s</SumPage>\n</DocInfo>\n</Info>\n%s</BookInformation>\n'%(self.doc_info.page,self.toc) bookinfo += '<Producer reading="">%s</Producer>\n'%(self.doc_info.producer,)
pages = u'' bookinfo += '<SumPage>%s</SumPage>\n</DocInfo>\n</Info>\n%s</BookInformation>\n'%(self.doc_info.page,self.toc)
pages = ''
done_main = False done_main = False
pt_id = -1 pt_id = -1
for page_tree in self: for page_tree in self:
if not done_main: if not done_main:
done_main = True done_main = True
pages += u'<Main>\n' pages += '<Main>\n'
close = u'</Main>\n' close = '</Main>\n'
pt_id = page_tree.id pt_id = page_tree.id
else: else:
pages += u'<PageTree objid="%d">\n'%(page_tree.id,) pages += '<PageTree objid="%d">\n'%(page_tree.id,)
close = u'</PageTree>\n' close = '</PageTree>\n'
for page in page_tree: for page in page_tree:
pages += unicode_type(page) pages += unicode_type(page)
pages += close pages += close
traversed_objects = [int(i) for i in re.findall(r'objid="(\w+)"', pages)] + [pt_id] traversed_objects = [int(i) for i in re.findall(r'objid="(\w+)"', pages)] + [pt_id]
objects = u'\n<Objects>\n' objects = '\n<Objects>\n'
styles = u'\n<Style>\n' styles = '\n<Style>\n'
for obj in self.objects: for obj in self.objects:
obj = self.objects[obj] obj = self.objects[obj]
if obj.id in traversed_objects: if obj.id in traversed_objects:
@ -159,13 +163,13 @@ def main(args=sys.argv, logger=None):
return 1 return 1
if opts.out is None: if opts.out is None:
opts.out = os.path.join(os.path.dirname(args[1]), os.path.splitext(os.path.basename(args[1]))[0]+".lrs") opts.out = os.path.join(os.path.dirname(args[1]), os.path.splitext(os.path.basename(args[1]))[0]+".lrs")
o = codecs.open(os.path.abspath(os.path.expanduser(opts.out)), 'wb', 'utf-8')
o.write(u'<?xml version="1.0" encoding="UTF-8"?>\n')
logger.info(_('Parsing LRF...')) logger.info(_('Parsing LRF...'))
d = LRFDocument(open(args[1], 'rb')) d = LRFDocument(open(args[1], 'rb'))
d.parse() d.parse()
logger.info(_('Creating XML...')) logger.info(_('Creating XML...'))
o.write(d.to_xml(write_files=opts.output_resources)) with codecs.open(os.path.abspath(os.path.expanduser(opts.out)), 'wb', 'utf-8') as f:
f.write('<?xml version="1.0" encoding="UTF-8"?>\n')
f.write(d.to_xml(write_files=opts.output_resources))
logger.info(_('LRS written to ')+opts.out) logger.info(_('LRS written to ')+opts.out)
return 0 return 0

40
src/calibre/ebooks/lrf/meta.py
View File

@ -1,4 +1,5 @@
from __future__ import print_function from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
@ -9,7 +10,7 @@ Just create an L{LRFMetaFile} object and use its properties
to get and set meta information. For example: to get and set meta information. For example:
>>> lrf = LRFMetaFile("mybook.lrf") >>> lrf = LRFMetaFile("mybook.lrf")
>>> print lrf.title, lrf.author >>> print(lrf.title, lrf.author)
>>> lrf.category = "History" >>> lrf.category = "History"
""" """
@ -50,8 +51,8 @@ class field(object):
def __repr__(self): def __repr__(self):
typ = {DWORD: 'unsigned int', 'QWORD': 'unsigned long long', BYTE: 'unsigned char', WORD: 'unsigned short'}.get(self._fmt, '') typ = {DWORD: 'unsigned int', 'QWORD': 'unsigned long long', BYTE: 'unsigned char', WORD: 'unsigned short'}.get(self._fmt, '')
return "An " + typ + " stored in " + \ return "An " + typ + " stored in " + \
str(struct.calcsize(self._fmt)) + \ unicode_type(struct.calcsize(self._fmt)) + \
" bytes starting at byte " + str(self._start) " bytes starting at byte " + unicode_type(self._start)
class versioned_field(field): class versioned_field(field):
@ -92,20 +93,20 @@ class fixed_stringfield(object):
self._start = start self._start = start
def __get__(self, obj, typ=None): def __get__(self, obj, typ=None):
length = str(self._length) length = unicode_type(self._length)
return obj.unpack(start=self._start, fmt="<"+length+"s")[0] return obj.unpack(start=self._start, fmt="<"+length+"s")[0]
def __set__(self, obj, val): def __set__(self, obj, val):
if val.__class__.__name__ != 'str': if not isinstance(val, unicode_type):
val = str(val) val = unicode_type(val)
if len(val) != self._length: if len(val) != self._length:
raise LRFException("Trying to set fixed_stringfield with a " + raise LRFException("Trying to set fixed_stringfield with a " +
"string of incorrect length") "string of incorrect length")
obj.pack(val, start=self._start, fmt="<"+str(len(val))+"s") obj.pack(val, start=self._start, fmt="<"+unicode_type(len(val))+"s")
def __repr__(self): def __repr__(self):
return "A string of length " + str(self._length) + \ return "A string of length " + unicode_type(self._length) + \
" starting at byte " + str(self._start) " starting at byte " + unicode_type(self._start)
class xml_attr_field(object): class xml_attr_field(object):
@ -191,7 +192,7 @@ class xml_field(object):
return elem return elem
if not val: if not val:
val = u'' val = ''
if not isinstance(val, unicode_type): if not isinstance(val, unicode_type):
val = val.decode('utf-8') val = val.decode('utf-8')
@ -703,9 +704,8 @@ def main(args=sys.argv):
lrf.producer = options.producer lrf.producer = options.producer
if options.thumbnail: if options.thumbnail:
path = os.path.expanduser(os.path.expandvars(options.thumbnail)) path = os.path.expanduser(os.path.expandvars(options.thumbnail))
f = open(path, "rb") with open(path, "rb") as f:
lrf.thumbnail = f.read() lrf.thumbnail = f.read()
f.close()
if options.book_id is not None: if options.book_id is not None:
lrf.book_id = options.book_id lrf.book_id = options.book_id
if options.comment: if options.comment:
@ -716,15 +716,14 @@ def main(args=sys.argv):
td = "None" td = "None"
if t and len(t) > 0: if t and len(t) > 0:
td = os.path.basename(args[1])+"_thumbnail."+lrf.thumbail_extension() td = os.path.basename(args[1])+"_thumbnail."+lrf.thumbail_extension()
f = open(td, "w") with open(td, "wb") as f:
f.write(t) f.write(t)
f.close()
fields = LRFMetaFile.__dict__.items() fields = LRFMetaFile.__dict__.items()
fields.sort() fields.sort()
for f in fields: for f in fields:
if "XML" in str(f): if "XML" in unicode_type(f):
print(str(f[1]) + ":", lrf.__getattribute__(f[0]).encode('utf-8')) print(unicode_type(f[1]) + ":", lrf.__getattribute__(f[0]).encode('utf-8'))
if options.get_thumbnail: if options.get_thumbnail:
print("Thumbnail:", td) print("Thumbnail:", td)
if options.get_cover: if options.get_cover:
@ -734,7 +733,8 @@ def main(args=sys.argv):
ext, data = None, None ext, data = None, None
if data: if data:
cover = os.path.splitext(os.path.basename(args[1]))[0]+"_cover."+ext cover = os.path.splitext(os.path.basename(args[1]))[0]+"_cover."+ext
open(cover, 'wb').write(data) with open(cover, 'wb') as f:
f.write(data)
print('Cover:', cover) print('Cover:', cover)
else: else:
print('Could not find cover in the LRF file') print('Could not find cover in the LRF file')

73
src/calibre/ebooks/lrf/objects.py
View File

@ -1,4 +1,5 @@
from __future__ import print_function from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
import struct, array, zlib, io, collections, re import struct, array, zlib, io, collections, re
@ -127,7 +128,7 @@ class LRFContentObject(LRFObject):
func, args = action[0], (action[1],) func, args = action[0], (action[1],)
getattr(self, func)(tag, *args) getattr(self, func)(tag, *args)
else: else:
raise LRFParseError("Unknown tag in %s: %s" % (self.__class__.__name__, str(tag))) raise LRFParseError("Unknown tag in %s: %s" % (self.__class__.__name__, unicode_type(tag)))
def __iter__(self): def __iter__(self):
for i in self._contents: for i in self._contents:
@ -195,17 +196,17 @@ class PageTree(LRFObject):
class StyleObject(object): class StyleObject(object):
def _tags_to_xml(self): def _tags_to_xml(self):
s = u'' s = ''
for h in self.tag_map.values(): for h in self.tag_map.values():
attr = h[0] attr = h[0]
if hasattr(self, attr): if hasattr(self, attr):
s += u'%s="%s" '%(attr, getattr(self, attr)) s += '%s="%s" '%(attr, getattr(self, attr))
return s return s
def __str__(self): def __str__(self):
s = u'<%s objid="%s" stylelabel="%s" '%(self.__class__.__name__.replace('Attr', 'Style'), self.id, self.id) s = '<%s objid="%s" stylelabel="%s" '%(self.__class__.__name__.replace('Attr', 'Style'), self.id, self.id)
s += self._tags_to_xml() s += self._tags_to_xml()
s += u'/>\n' s += '/>\n'
return s return s
if not ispy3: if not ispy3:
@ -254,7 +255,7 @@ class Color(object):
self.a, self.r, self.g, self.b = val & 0xFF, (val>>8)&0xFF, (val>>16)&0xFF, (val>>24)&0xFF self.a, self.r, self.g, self.b = val & 0xFF, (val>>8)&0xFF, (val>>16)&0xFF, (val>>24)&0xFF
def __str__(self): def __str__(self):
return u'0x%02x%02x%02x%02x'%(self.a, self.r, self.g, self.b) return '0x%02x%02x%02x%02x'%(self.a, self.r, self.g, self.b)
if not ispy3: if not ispy3:
__unicode__ = __str__ __unicode__ = __str__
@ -286,7 +287,7 @@ class PageDiv(EmptyPageElement):
self.linecolor = Color(linecolor) self.linecolor = Color(linecolor)
def __str__(self): def __str__(self):
return u'\n<PageDiv pain="%s" spacesize="%s" linewidth="%s" linecolor="%s" />\n'%\ return '\n<PageDiv pain="%s" spacesize="%s" linewidth="%s" linecolor="%s" />\n'%\
(self.pain, self.spacesize, self.linewidth, self.color) (self.pain, self.spacesize, self.linewidth, self.color)
if not ispy3: if not ispy3:
@ -304,7 +305,7 @@ class RuledLine(EmptyPageElement):
self.id = -1 self.id = -1
def __str__(self): def __str__(self):
return u'\n<RuledLine linelength="%s" linetype="%s" linewidth="%s" linecolor="%s" />\n'%\ return '\n<RuledLine linelength="%s" linetype="%s" linewidth="%s" linecolor="%s" />\n'%\
(self.linelength, self.linetype, self.linewidth, self.linecolor) (self.linelength, self.linetype, self.linewidth, self.linecolor)
if not ispy3: if not ispy3:
@ -317,7 +318,7 @@ class Wait(EmptyPageElement):
self.time = time self.time = time
def __str__(self): def __str__(self):
return u'\n<Wait time="%d" />\n'%(self.time) return '\n<Wait time="%d" />\n'%(self.time)
if not ispy3: if not ispy3:
__unicode__ = __str__ __unicode__ = __str__
@ -331,7 +332,7 @@ class Locate(EmptyPageElement):
self.pos = self.pos_map[pos] self.pos = self.pos_map[pos]
def __str__(self): def __str__(self):
return u'\n<Locate pos="%s" />\n'%(self.pos) return '\n<Locate pos="%s" />\n'%(self.pos)
if not ispy3: if not ispy3:
__unicode__ = __str__ __unicode__ = __str__
@ -343,7 +344,7 @@ class BlockSpace(EmptyPageElement):
self.xspace, self.yspace = xspace, yspace self.xspace, self.yspace = xspace, yspace
def __str__(self): def __str__(self):
return u'\n<BlockSpace xspace="%d" yspace="%d" />\n'%\ return '\n<BlockSpace xspace="%d" yspace="%d" />\n'%\
(self.xspace, self.yspace) (self.xspace, self.yspace)
if not ispy3: if not ispy3:
@ -444,7 +445,7 @@ class Page(LRFStream):
yield i yield i
def __str__(self): def __str__(self):
s = u'\n<Page pagestyle="%d" objid="%d">\n'%(self.style_id, self.id) s = '\n<Page pagestyle="%d" objid="%d">\n'%(self.style_id, self.id)
for i in self: for i in self:
s += unicode_type(i) s += unicode_type(i)
s += '\n</Page>\n' s += '\n</Page>\n'
@ -454,7 +455,7 @@ class Page(LRFStream):
__unicode__ = __str__ __unicode__ = __str__
def to_html(self): def to_html(self):
s = u'' s = ''
for i in self: for i in self:
s += i.to_html() s += i.to_html()
return s return s
@ -629,7 +630,7 @@ class Block(LRFStream, TextCSS):
self.attrs[attr] = getattr(self, attr) self.attrs[attr] = getattr(self, attr)
def __str__(self): def __str__(self):
s = u'\n<%s objid="%d" blockstyle="%d" '%(self.name, self.id, self.style_id) s = '\n<%s objid="%d" blockstyle="%d" '%(self.name, self.id, self.style_id)
if hasattr(self, 'textstyle_id'): if hasattr(self, 'textstyle_id'):
s += 'textstyle="%d" '%(self.textstyle_id,) s += 'textstyle="%d" '%(self.textstyle_id,)
for attr in self.attrs: for attr in self.attrs:
@ -646,8 +647,8 @@ class Block(LRFStream, TextCSS):
def to_html(self): def to_html(self):
if self.name == 'TextBlock': if self.name == 'TextBlock':
return u'<div class="block%s text%s">%s</div>'%(self.style_id, self.textstyle_id, self.content.to_html()) return '<div class="block%s text%s">%s</div>'%(self.style_id, self.textstyle_id, self.content.to_html())
return u'' return ''
class MiniPage(LRFStream): class MiniPage(LRFStream):
@ -668,7 +669,7 @@ class Text(LRFStream):
style = property(fget=lambda self : self._document.objects[self.style_id]) style = property(fget=lambda self : self._document.objects[self.style_id])
text_map = {0x22: u'"', 0x26: u'&amp;', 0x27: u'\'', 0x3c: u'&lt;', 0x3e: u'&gt;'} text_map = {0x22: '"', 0x26: '&amp;', 0x27: '\'', 0x3c: '&lt;', 0x3e: '&gt;'}
entity_pattern = re.compile(r'&amp;(\S+?);') entity_pattern = re.compile(r'&amp;(\S+?);')
text_tags = { text_tags = {
@ -717,20 +718,20 @@ class Text(LRFStream):
self.self_closing = self_closing self.self_closing = self_closing
def __str__(self): def __str__(self):
s = u'<%s '%(self.name,) s = '<%s '%(self.name,)
for name, val in self.attrs.items(): for name, val in self.attrs.items():
s += '%s="%s" '%(name, val) s += '%s="%s" '%(name, val)
return s.rstrip() + (u' />' if self.self_closing else u'>') return s.rstrip() + (' />' if self.self_closing else '>')
if not ispy3: if not ispy3:
__unicode__ = __str__ __unicode__ = __str__
def to_html(self): def to_html(self):
s = u'' s = ''
return s return s
def close_html(self): def close_html(self):
return u'' return ''
class Span(TextTag): class Span(TextTag):
pass pass
@ -901,7 +902,7 @@ class Text(LRFStream):
self.stream = None self.stream = None
def __str__(self): def __str__(self):
s = u'' s = ''
open_containers = collections.deque() open_containers = collections.deque()
for c in self.content: for c in self.content:
if isinstance(c, string_or_bytes): if isinstance(c, string_or_bytes):
@ -909,7 +910,7 @@ class Text(LRFStream):
elif c is None: elif c is None:
if open_containers: if open_containers:
p = open_containers.pop() p = open_containers.pop()
s += u'</%s>'%(p.name,) s += '</%s>'%(p.name,)
else: else:
s += unicode_type(c) s += unicode_type(c)
if not c.self_closing: if not c.self_closing:
@ -917,7 +918,7 @@ class Text(LRFStream):
if len(open_containers) > 0: if len(open_containers) > 0:
if len(open_containers) == 1: if len(open_containers) == 1:
s += u'</%s>'%(open_containers[0].name,) s += '</%s>'%(open_containers[0].name,)
else: else:
raise LRFParseError('Malformed text stream %s'%([i.name for i in open_containers if isinstance(i, Text.TextTag)],)) raise LRFParseError('Malformed text stream %s'%([i.name for i in open_containers if isinstance(i, Text.TextTag)],))
return s return s
@ -926,7 +927,7 @@ class Text(LRFStream):
__unicode__ = __str__ __unicode__ = __str__
def to_html(self): def to_html(self):
s = u'' s = ''
open_containers = collections.deque() open_containers = collections.deque()
in_p = False in_p = False
for c in self.content: for c in self.content:
@ -970,7 +971,7 @@ class Image(LRFObject):
data = property(fget=lambda self : self._document.objects[self.refstream].stream) data = property(fget=lambda self : self._document.objects[self.refstream].stream)
def __str__(self): def __str__(self):
return u'<Image objid="%s" x0="%d" y0="%d" x1="%d" y1="%d" xsize="%d" ysize="%d" refstream="%d" />\n'%\ return '<Image objid="%s" x0="%d" y0="%d" x1="%d" y1="%d" xsize="%d" ysize="%d" refstream="%d" />\n'%\
(self.id, self.x0, self.y0, self.x1, self.y1, self.xsize, self.ysize, self.refstream) (self.id, self.x0, self.y0, self.x1, self.y1, self.xsize, self.ysize, self.refstream)
if not ispy3: if not ispy3:
@ -984,7 +985,7 @@ class PutObj(EmptyPageElement):
self.object = objects[refobj] self.object = objects[refobj]
def __str__(self): def __str__(self):
return u'<PutObj x1="%d" y1="%d" refobj="%d" />'%(self.x1, self.y1, self.refobj) return '<PutObj x1="%d" y1="%d" refobj="%d" />'%(self.x1, self.y1, self.refobj)
if not ispy3: if not ispy3:
__unicode__ = __str__ __unicode__ = __str__
@ -1069,12 +1070,12 @@ class ImageStream(LRFStream):
def end_stream(self, *args): def end_stream(self, *args):
LRFStream.end_stream(self, *args) LRFStream.end_stream(self, *args)
self.file = str(self.id) + '.' + self.encoding.lower() self.file = unicode_type(self.id) + '.' + self.encoding.lower()
if self._document is not None: if self._document is not None:
self._document.image_map[self.id] = self self._document.image_map[self.id] = self
def __str__(self): def __str__(self):
return u'<ImageStream objid="%s" encoding="%s" file="%s" />\n'%\ return '<ImageStream objid="%s" encoding="%s" file="%s" />\n'%\
(self.id, self.encoding, self.file) (self.id, self.encoding, self.file)
if not ispy3: if not ispy3:
@ -1156,7 +1157,7 @@ class Button(LRFObject):
return (None, None) return (None, None)
def __str__(self): def __str__(self):
s = u'<Button objid="%s">\n'%(self.id,) s = '<Button objid="%s">\n'%(self.id,)
if self.button_flags & 0x10 != 0: if self.button_flags & 0x10 != 0:
s += '<PushButton ' s += '<PushButton '
if 2 in self.refimage: if 2 in self.refimage:
@ -1233,10 +1234,10 @@ class BookAttr(StyleObject, LRFObject):
self.font_link_list.append(tag.dword) self.font_link_list.append(tag.dword)
def __str__(self): def __str__(self):
s = u'<BookStyle objid="%s" stylelabel="%s">\n'%(self.id, self.id) s = '<BookStyle objid="%s" stylelabel="%s">\n'%(self.id, self.id)
s += u'<SetDefault %s />\n'%(self._tags_to_xml(),) s += '<SetDefault %s />\n'%(self._tags_to_xml(),)
doc = self._document doc = self._document
s += u'<BookSetting bindingdirection="%s" dpi="%s" screenwidth="%s" screenheight="%s" colordepth="%s" />\n'%\ s += '<BookSetting bindingdirection="%s" dpi="%s" screenwidth="%s" screenheight="%s" colordepth="%s" />\n'%\
(self.binding_map[doc.binding], doc.dpi, doc.width, doc.height, doc.color_depth) (self.binding_map[doc.binding], doc.dpi, doc.width, doc.height, doc.color_depth)
for font in self._document.font_map.values(): for font in self._document.font_map.values():
s += unicode_type(font) s += unicode_type(font)
@ -1257,7 +1258,7 @@ class TocLabel(object):
self.refpage, self.refobject, self.label = refpage, refobject, label self.refpage, self.refobject, self.label = refpage, refobject, label
def __str__(self): def __str__(self):
return u'<TocLabel refpage="%s" refobj="%s">%s</TocLabel>\n'%(self.refpage, self.refobject, self.label) return '<TocLabel refpage="%s" refobj="%s">%s</TocLabel>\n'%(self.refpage, self.refobject, self.label)
if not ispy3: if not ispy3:
__unicode__ = __str__ __unicode__ = __str__
@ -1284,7 +1285,7 @@ class TOCObject(LRFStream):
yield i yield i
def __str__(self): def __str__(self):
s = u'<TOC>\n' s = '<TOC>\n'
for i in self: for i in self:
s += unicode_type(i) s += unicode_type(i)
return s + '</TOC>\n' return s + '</TOC>\n'