diff --git a/src/calibre/devices/usbms/driver.py b/src/calibre/devices/usbms/driver.py
index 604cd9002b..cadc61e584 100644
--- a/src/calibre/devices/usbms/driver.py
+++ b/src/calibre/devices/usbms/driver.py
@@ -10,6 +10,7 @@ import os, fnmatch, shutil
from itertools import cycle
from calibre.ebooks.metadata.meta import metadata_from_formats, path_to_ext
+from calibre.ebooks.metadata import authors_to_string
from calibre.devices.usbms.device import Device
from calibre.devices.usbms.books import BookList, Book
from calibre.devices.errors import FreeSpaceError, PathError
@@ -221,12 +222,7 @@ class USBMS(Device):
mi = metadata_from_formats([path])
mime = MIME_MAP[fileext] if fileext in MIME_MAP.keys() else 'Unknown'
- authors = 'Unknown'
- for author in mi.authors:
- if authors == 'Unknown':
- authors = author
- else:
- authors += ', %s' % author
+ authors = authors_to_string(mi.authors)
return Book(path, mi.title, authors, mime)
diff --git a/src/calibre/ebooks/epub/from_html.py b/src/calibre/ebooks/epub/from_html.py
index d61dc0051a..722b6cd4e3 100644
--- a/src/calibre/ebooks/epub/from_html.py
+++ b/src/calibre/ebooks/epub/from_html.py
@@ -153,11 +153,27 @@ class HTMLProcessor(Processor, Rationalizer):
Perform various markup transforms to get the output to render correctly
in the quirky ADE.
'''
- # Replace
that are children of with
+ # Replace
that are children of as ADE doesn't handle them
if hasattr(self.body, 'xpath'):
for br in self.body.xpath('./br'):
+ if br.getparent() is None:
+ continue
+ try:
+ sibling = br.itersiblings().next()
+ except:
+ sibling = None
br.tag = 'p'
br.text = u'\u00a0'
+ if (br.tail and br.tail.strip()) or sibling is None or \
+ getattr(sibling, 'tag', '') != 'br':
+ br.set('style', br.get('style', '')+'; margin: 0pt; border:0pt; height:0pt')
+ else:
+ sibling.getparent().remove(sibling)
+ if sibling.tail:
+ if not br.tail:
+ br.tail = ''
+ br.tail += sibling.tail
+
if self.opts.profile.remove_object_tags:
for tag in self.root.xpath('//embed'):
@@ -166,6 +182,14 @@ class HTMLProcessor(Processor, Rationalizer):
if tag.get('type', '').lower().strip() in ('image/svg+xml',):
continue
tag.getparent().remove(tag)
+
+
+ for tag in self.root.xpath('//title|//style'):
+ if not tag.text:
+ tag.getparent().remove(tag)
+ for tag in self.root.xpath('//script'):
+ if not tag.text and not tag.get('src', False):
+ tag.getparent().remove(tag)
def save(self):
for meta in list(self.root.xpath('//meta')):
diff --git a/src/calibre/ebooks/lrf/html/convert_from.py b/src/calibre/ebooks/lrf/html/convert_from.py
index e884ea7213..673c92ebb9 100644
--- a/src/calibre/ebooks/lrf/html/convert_from.py
+++ b/src/calibre/ebooks/lrf/html/convert_from.py
@@ -1720,7 +1720,7 @@ class HTMLConverter(object, LoggingInterface):
self.previous_text = '\n'
elif tagname in ['hr', 'tr']: # tr needed for nested tables
self.end_current_block()
- if tagname == 'hr':
+ if tagname == 'hr' and not tag_css.get('width', '').strip().startswith('0'):
self.current_page.RuledLine(linelength=int(self.current_page.pageStyle.attrs['textwidth']))
self.previous_text = '\n'
self.process_children(tag, tag_css, tag_pseudo_css)
diff --git a/src/calibre/ebooks/mobi/from_comic.py b/src/calibre/ebooks/mobi/from_comic.py
new file mode 100644
index 0000000000..87d63ea15f
--- /dev/null
+++ b/src/calibre/ebooks/mobi/from_comic.py
@@ -0,0 +1,44 @@
+#!/usr/bin/env python
+__license__ = 'GPL v3'
+__copyright__ = '2009, Kovid Goyal kovid@kovidgoyal.net'
+__docformat__ = 'restructuredtext en'
+
+'''
+'''
+import sys, os
+from calibre.ebooks.lrf.comic.convert_from import do_convert, option_parser, \
+ ProgressBar, terminal_controller
+from calibre.ebooks.mobi.from_any import config, any2mobi
+from calibre.ptempfile import PersistentTemporaryFile
+
+
+def convert(path_to_file, opts, notification=lambda m, p: p):
+ pt = PersistentTemporaryFile('_comic2mobi.epub')
+ pt.close()
+ orig_output = opts.output
+ opts.output = pt.name
+ do_convert(path_to_file, opts, notification=notification, output_format='epub')
+ opts = config('').parse()
+ if orig_output is None:
+ orig_output = os.path.splitext(path_to_file)[0]+'.mobi'
+ opts.output = orig_output
+ any2mobi(opts, pt.name)
+
+def main(args=sys.argv):
+ parser = option_parser()
+ opts, args = parser.parse_args(args)
+ if len(args) < 2:
+ parser.print_help()
+ print '\nYou must specify a file to convert'
+ return 1
+
+ pb = ProgressBar(terminal_controller, _('Rendering comic pages...'),
+ no_progress_bar=opts.no_progress_bar or getattr(opts, 'no_process', False))
+ notification = pb.update
+
+ source = os.path.abspath(args[1])
+ convert(source, opts, notification=notification)
+ return 0
+
+if __name__ == '__main__':
+ sys.exit(main())
\ No newline at end of file
diff --git a/src/calibre/ebooks/mobi/writer.py b/src/calibre/ebooks/mobi/writer.py
index fdafd2e08b..39c77eace5 100644
--- a/src/calibre/ebooks/mobi/writer.py
+++ b/src/calibre/ebooks/mobi/writer.py
@@ -452,6 +452,13 @@ class MobiWriter(object):
code = EXTH_CODES[term]
for item in oeb.metadata[term]:
data = self.COLLAPSE_RE.sub(' ', unicode(item))
+ if term == 'identifier':
+ if data.lower().startswith('urn:isbn:'):
+ data = data[9:]
+ elif item.get('scheme', '').lower() == 'isbn':
+ pass
+ else:
+ continue
data = data.encode('utf-8')
exth.write(pack('>II', code, len(data) + 8))
exth.write(data)
@@ -468,7 +475,7 @@ class MobiWriter(object):
nrecs += 3
exth = exth.getvalue()
trail = len(exth) % 4
- pad = '' if not trail else '\0' * (4 - trail)
+ pad = '\0' * (4 - trail) # Always pad w/ at least 1 byte
exth = ['EXTH', pack('>II', len(exth) + 12, nrecs), exth, pad]
return ''.join(exth)
diff --git a/src/calibre/ebooks/oeb/base.py b/src/calibre/ebooks/oeb/base.py
index c2d30eb2c3..3336391a38 100644
--- a/src/calibre/ebooks/oeb/base.py
+++ b/src/calibre/ebooks/oeb/base.py
@@ -21,6 +21,7 @@ from lxml import etree
from lxml import html
from calibre import LoggingInterface
from calibre.translations.dynamic import translate
+from calibre.startup import get_lang
XML_PARSER = etree.XMLParser(recover=True)
XML_NS = 'http://www.w3.org/XML/1998/namespace'
@@ -30,6 +31,7 @@ OPF2_NS = 'http://www.idpf.org/2007/opf'
DC09_NS = 'http://purl.org/metadata/dublin_core'
DC10_NS = 'http://purl.org/dc/elements/1.0/'
DC11_NS = 'http://purl.org/dc/elements/1.1/'
+DC_NSES = set([DC09_NS, DC10_NS, DC11_NS])
XSI_NS = 'http://www.w3.org/2001/XMLSchema-instance'
DCTERMS_NS = 'http://purl.org/dc/terms/'
NCX_NS = 'http://www.daisy.org/z3986/2005/ncx/'
@@ -194,15 +196,19 @@ class Metadata(object):
if term == OPF('meta') and not value:
term = self.fq_attrib.pop('name')
value = self.fq_attrib.pop('content')
- elif term in Metadata.TERMS and not namespace(term):
- term = DC(term)
+ elif barename(term).lower() in Metadata.TERMS and \
+ (not namespace(term) or namespace(term) in DC_NSES):
+ # Anything looking like Dublin Core is coerced
+ term = DC(barename(term).lower())
+ elif namespace(term) == OPF2_NS:
+ term = barename(term)
self.term = term
self.value = value
self.attrib = attrib = {}
for fq_attr in fq_attrib:
if fq_attr in Metadata.ATTRS:
attr = fq_attr
- fq_attr = OPF2(fq_attr)
+ fq_attr = OPF(fq_attr)
fq_attrib[fq_attr] = fq_attrib.pop(attr)
else:
attr = barename(fq_attr)
@@ -216,7 +222,16 @@ class Metadata(object):
raise AttributeError(
'%r object has no attribute %r' \
% (self.__class__.__name__, name))
-
+
+ def __getitem__(self, key):
+ return self.attrib[key]
+
+ def __contains__(self, key):
+ return key in self.attrib
+
+ def get(self, key, default=None):
+ return self.attrib.get(key, default)
+
def __repr__(self):
return 'Item(term=%r, value=%r, attrib=%r)' \
% (barename(self.term), self.value, self.attrib)
@@ -814,13 +829,13 @@ class OEBBook(object):
break
if not metadata.language:
self.logger.warn(u'Language not specified.')
- metadata.add('language', 'en')
+ metadata.add('language', get_lang())
if not metadata.creator:
self.logger.warn(u'Creator not specified.')
- metadata.add('creator', 'Unknown')
+ metadata.add('creator', _('Unknown'))
if not metadata.title:
self.logger.warn(u'Title not specified.')
- metadata.add('title', 'Unknown')
+ metadata.add('title', _('Unknown'))
def _manifest_from_opf(self, opf):
self.manifest = manifest = Manifest(self)
@@ -857,6 +872,8 @@ class OEBBook(object):
extras.sort()
for item in extras:
spine.add(item, False)
+ if len(spine) == 0:
+ raise OEBError("Spine is empty")
def _guide_from_opf(self, opf):
self.guide = guide = Guide(self)
@@ -886,8 +903,11 @@ class OEBBook(object):
if len(result) != 1:
return False
id = result[0]
- ncx = self.manifest[id].data
- self.manifest.remove(id)
+ if id not in self.manifest.ids:
+ return False
+ item = self.manifest.ids[id]
+ ncx = item.data
+ self.manifest.remove(item)
title = xpath(ncx, 'ncx:docTitle/ncx:text/text()')[0]
self.toc = toc = TOC(title)
navmaps = xpath(ncx, 'ncx:navMap')
diff --git a/src/calibre/gui2/images/news/freakonomics.png b/src/calibre/gui2/images/news/freakonomics.png
new file mode 100644
index 0000000000..7cb9e79916
Binary files /dev/null and b/src/calibre/gui2/images/news/freakonomics.png differ
diff --git a/src/calibre/gui2/main.ui b/src/calibre/gui2/main.ui
index 2733a61be3..2b243ba2b9 100644
--- a/src/calibre/gui2/main.ui
+++ b/src/calibre/gui2/main.ui
@@ -119,7 +119,11 @@
-
-
+
+
+ Set the output format that is used when converting ebooks and downloading news
+
+
diff --git a/src/calibre/linux.py b/src/calibre/linux.py
index a05a7ea7a8..93571cce4f 100644
--- a/src/calibre/linux.py
+++ b/src/calibre/linux.py
@@ -63,6 +63,7 @@ entry_points = {
'oeb2lit = calibre.ebooks.lit.writer:main',
'comic2lrf = calibre.ebooks.lrf.comic.convert_from:main',
'comic2epub = calibre.ebooks.epub.from_comic:main',
+ 'comic2mobi = calibre.ebooks.mobi.from_comic:main',
'comic2pdf = calibre.ebooks.pdf.from_comic:main',
'calibre-debug = calibre.debug:main',
'calibredb = calibre.library.cli:main',
@@ -239,6 +240,7 @@ def setup_completion(fatal_errors):
f.write(opts_and_exts('lit2oeb', lit2oeb, ['lit']))
f.write(opts_and_exts('comic2lrf', comicop, ['cbz', 'cbr']))
f.write(opts_and_exts('comic2epub', comic2epub, ['cbz', 'cbr']))
+ f.write(opts_and_exts('comic2mobi', comic2epub, ['cbz', 'cbr']))
f.write(opts_and_exts('comic2pdf', comic2epub, ['cbz', 'cbr']))
f.write(opts_and_words('feeds2disk', feeds2disk, feed_titles))
f.write(opts_and_words('feeds2lrf', feeds2lrf, feed_titles))
diff --git a/src/calibre/web/feeds/recipes/__init__.py b/src/calibre/web/feeds/recipes/__init__.py
index 71c4b71483..f2ed6d2d24 100644
--- a/src/calibre/web/feeds/recipes/__init__.py
+++ b/src/calibre/web/feeds/recipes/__init__.py
@@ -23,7 +23,7 @@ recipe_modules = ['recipe_' + r for r in (
'spiegel_int', 'themarketticker', 'tomshardware', 'xkcd', 'ftd', 'zdnet',
'joelonsoftware', 'telepolis', 'common_dreams', 'nin', 'tomshardware_de',
'pagina12', 'infobae', 'ambito', 'elargentino', 'sueddeutsche', 'the_age',
- 'laprensa', 'amspec',
+ 'laprensa', 'amspec', 'freakonomics',
)]
import re, imp, inspect, time, os
diff --git a/src/calibre/web/feeds/recipes/recipe_freakonomics.py b/src/calibre/web/feeds/recipes/recipe_freakonomics.py
new file mode 100644
index 0000000000..704f7f727d
--- /dev/null
+++ b/src/calibre/web/feeds/recipes/recipe_freakonomics.py
@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+__license__ = 'GPL v3'
+__copyright__ = '2009, Kovid Goyal kovid@kovidgoyal.net'
+__docformat__ = 'restructuredtext en'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Freakonomics(BasicNewsRecipe):
+
+ title = 'Freakonomics Blog'
+ description = 'The Hidden side of everything'
+ __author__ = 'Kovid Goyal'
+
+ feeds = [('Blog', 'http://freakonomics.blogs.nytimes.com/feed/atom/')]
+
+ def get_article_url(self, article):
+ return article.get('feedburner_origlink', None)
+
+ def print_version(self, url):
+ return url + '?pagemode=print'
\ No newline at end of file