Merge from trunk

Changelog.yaml

@@ -4,6 +4,100 @@
 # for important features/bug fixes.
 # Also, each release can have new and improved recipes.
 
+- version: 0.7.28
+  date: 2010-11-12
+
+  new features:
+    - title: "Update the version of the grahical toolkit (Qt 4.7.1) used in the calibre binary builds on windows and linux. This should result in a significant speed up for the calibre ebook viewer"
+
+    - title: "Driver for Nook Color, Eken M001"
+
+    - title: "Add a tweak to turn off double clicking to open viewer"
+
+    - title: "Catalog generation: Add indication when a book has no formats"
+      tickets: [7376]
+
+    - title: "Advanced search dialog: Add a tab to allow searching particular metadata fields easily"
+
+    - title: "Conversion pipeline: When using the Level x Table of Contents expressions, if a tag is empty but has a non-empty title attribute, use that instead of ignoring the tag"
+
+  bug fixes:
+    - title: "Comic metadata reader: Sort filenames aplhabetically when choosing an image for the cover"
+      tickets: [7488]
+
+    - title: "Bulk convert dialog: Hide useless restore defaults button."
+      tickets: [7471]
+
+    - title: "Conversion pipeline: Handle input documents that encode null bytes as HTML entities correctly"
+      tickets: [7355]
+
+    - title: "Fix some SONY readers not being detected on windows"
+      tickets: [7413]
+
+    - title: "MOBI Input: Fix images missing when converting MOBI news downloads created with Mobipocket reader"
+      tickets: [7455]
+
+    - title: "ODT Input: Handle hyperlinks to headings that have truncated destination specifiers correctly"
+      tickets: [7506]
+
+    - title: "Sony driver: Ignore invalid strings when updating XML database"
+
+    - title: "Content Server: Add day to displayed date in /mobile book listing"
+
+    - title: "MOBI Input: Do not generate filenames with only extensions if the MOBI file has no internal name"
+      tickets: [7481]
+
+    - title: "MOBI Input: Handle files that has the record sizes set incorrectly to a long integer"
+      tickets: [7472]
+
+    - title: "Fix not enough vertical space for text in the preferences dialog category listing"
+
+    - title: "Remove 'sort' from Search and replace destination fields and add it to source fields. S&R is no longer marked experimental"
+
+    - title: "Edit metadata dialog: Save dialog geometry on reject as well as on accept"
+
+    - title: "E-book viewer: Fix clicking entries in TOC that point to the currently loaded flow not scrolling view to the top of the document"
+
+    - title: "Fix bug in regex used to extract charset from <meta> tags"
+
+    - title: "MOBI Output: Add support for the <q> tag"
+
+  improved recipes:
+    - Zeit Online
+    - Gamespot Review
+    - Ploitika
+    - Pagina12
+    - Irish Times
+    - elektrolese
+
+  new recipes:
+    - title: "Handelsblatt and European Voice"
+      author: "malfi"
+      
+    - title: "Polityka and Newsweek"
+      author: "Mateusz Kielar"
+
+    - title: "MarcTV"
+      author: "Marc Toensings"
+
+    - title: "Rolling Stone"
+      author: "Darko Miletic"
+
+    - title: "Vedomosti"
+      author: "Nikolai Kotchetkov"
+
+    - title: "Hola.com"
+      author: "bmsleight"
+
+    - title: "Dnevnik, Siol.net, MMC-RTV and Avto-magazon"
+      author: "BlonG"
+
+    - title: "SC Print Magazine"
+      author: "Tony Maro"
+
+    - title: "Diario Sport"
+      author: "Jefferson Frantz"
+
 - version: 0.7.27
   date: 2010-11-05
 
@@ -44,6 +138,7 @@
       tickets: [7356]
 
     - title: "News download: Workaround lack of thread safety in python mechanize, causing corrupted network packets (degrading network performance) on Ubuntu Maverick 64bit kernels"
+      tickets: [7321]
 
     - title: "Convert comments to HTML for book details panel in separate thread to make scrolling through the book list faster when large comments are present"
 

resources/catalog/stylesheet.css

@@ -81,6 +81,14 @@ p.unread_book {
 	text-indent: -2em;
 }
 
+p.missing_book {
+	text-align:left;
+	margin-top:0px;
+	margin-bottom:0px;
+	margin-left:2em;
+	text-indent:-2em;
+	}
+
 p.date_read {
 	text-align: left;
 	margin-top: 0px;

resources/recipes/avto-magazin.recipe

@@ -0,0 +1,46 @@
+__license__ = 'GPL v3'
+__copyright__ = '2010, BlonG'
+'''
+avto-magazin.si
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+class Dnevnik(BasicNewsRecipe):
+  title = u'Avto Magazin'
+  __author__ = u'BlonG'
+  description = u'Za avtomobilisti\xc4\x8dne frike, poznavalce in nedeljske \xc5\xa1oferje.'
+  oldest_article = 7
+  max_articles_per_feed = 20
+  labguage = 'sl'
+  no_stylesheets = True
+  use_embedded_content = False
+
+  conversion_options = {'linearize_tables' : True}
+
+
+  cover_url = 'https://sites.google.com/site/javno2010/home/avto_magazin_cover.jpg'
+
+  extra_css = '''
+	h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+	h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+	p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+	body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+	'''
+
+  keep_only_tags = [
+	dict(name='div', attrs={'id':'_iprom_inStream'}),
+#	dict(name='div', attrs={'class':'entry-content'}),
+	]
+
+  remove_tags = [
+	dict(name='div', attrs={'id':'voteConfirmation'}),
+	dict(name='div', attrs={'id':'InsideVote'}),
+	dict(name='div', attrs={'class':'Zone234'}),
+	dict(name='div', attrs={'class':'Comments'}),
+	dict(name='div', attrs={'class':'sorodneNovice'}),
+	dict(name='div', attrs={'id':'footer'}),
+	]
+
+
+  feeds = [
+	(u'Novice', u'http://www.avto-magazin.si/rss/')
+	]

resources/recipes/danas.recipe

@@ -25,7 +25,7 @@ class Danas(BasicNewsRecipe):
     remove_empty_feeds    = True
     extra_css             = """ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
                                 @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
-                                .article_description,body,.lokacija{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif}
+                                .article,.articledescription,body,.lokacija,.feed{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif}
                                 .nadNaslov,h1,.preamble{font-family: Georgia,"Times New Roman",Times,serif1,serif}
                                 .antrfileText{border-left: 2px solid #999999; 
                                               margin-left: 0.8em; 
@@ -66,7 +66,7 @@ class Danas(BasicNewsRecipe):
 
     keep_only_tags     = [dict(name='div', attrs={'id':'left'})]
     remove_tags = [
-                     dict(name='div', attrs={'class':['width_1_4','metaClanka','baner']})
+                     dict(name='div', attrs={'class':['width_1_4','metaClanka','baner','listaVesti','article_nav']})
                     ,dict(name='div', attrs={'id':'comments'})
                     ,dict(name=['object','link','iframe','meta'])
                   ]

resources/recipes/deredactie.recipe

@@ -0,0 +1,61 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class deredactie(BasicNewsRecipe):
+    title          = u'Deredactie.be'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://www.deredactie.be/polopoly_fs/1.510827!image/2710428628.gif'
+    language = 'de'
+    keep_only_tags = []
+    __author__ = 'malfi'
+    keep_only_tags.append(dict(name = 'div', attrs = {'id': 'articlehead'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'id': 'articlebody'}))
+    remove_tags = []
+    remove_tags.append(dict(name = 'div', attrs = {'id': 'story'}))
+    remove_tags.append(dict(name = 'div', attrs = {'id': 'useractions'}))
+    remove_tags.append(dict(name = 'hr'))
+
+    extra_css = '''
+     h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+     h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+     p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+     body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+     '''
+    def parse_index(self):
+        categories = []
+        catnames = {}
+        soup = self.index_to_soup('http://www.deredactie.be/cm/vrtnieuws.deutsch')
+        for elem in soup.findAll('li', attrs={'id' : re.compile("^navItem[2-9]") }):
+              a = elem.find('a', href=True)
+              m = re.search('(?<=/)[^/]*$', a['href'])
+              cat = str(m.group(0))
+              categories.append(cat)
+              catnames[cat] = a['title']
+              self.log("found cat %s\n" % catnames[cat])
+
+        feeds = []
+
+        for cat in categories:
+            articles = []
+            soup = self.index_to_soup('http://www.deredactie.be/cm/vrtnieuws.deutsch/'+cat)
+            for a in soup.findAll('a',attrs={'href' : re.compile("deutsch.*/[0-9][0-9][0-9][0-9][0-9][0-9]_")}):
+                skip_this_article = False
+                url = a['href'].strip()
+                if url.startswith('/'):
+                    url = 'http://www.deredactie.be' + url
+                myarticle=({'title':self.tag_to_string(a), 'url':url, 'description':'', 'date':''})
+                for article in articles :
+                    if article['url'] == url :
+                        skip_this_article = True
+                        self.log("SKIPPING DUP %s" % url)
+                        break
+                if skip_this_article :
+                        continue;
+                articles.append(myarticle)
+                self.log("Adding URL %s\n" %url)
+            if articles:
+                feeds.append((catnames[cat], articles))
+        return feeds
+

resources/recipes/dnevnik.recipe

@@ -0,0 +1,63 @@
+__license__ = 'GPL v3'
+__copyright__ = '2010, BlonG'
+'''
+dnevnik.si
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+class Dnevnik(BasicNewsRecipe):
+  title = u'Dnevnik.si'
+  __author__ = u'BlonG'
+  description = u'''Dnevnik je \u010dasnik z ve\u010d kot polstoletno zgodovino.
+  Pod sloganom \xbb\u017divljenje ima besedo\xab na svojih straneh prina\u0161a
+  bralcem bogastvo informacij, komentarjev in kolumen in raznovrstnost
+  pogledov, zaznamovanih z odgovornostjo do posameznika in \u0161ir\u0161e
+  dru\u017ebe.'''
+  oldest_article = 3
+  max_articles_per_feed = 20
+  language = 'sl'
+  no_stylesheets = True
+  use_embedded_content = False
+
+  cover_url = 'https://sites.google.com/site/javno2010/home/dnevnik_cover.jpg'
+
+  extra_css = '''
+	h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+	h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+	p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+	body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+	'''
+
+  keep_only_tags = [
+	dict(name='div', attrs={'id':'_iprom_inStream'}),
+	dict(name='div', attrs={'class':'entry-content'}),
+	]
+
+  remove_tags = [
+	dict(name='div', attrs={'class':'fb_article_top'}),
+	dict(name='div', attrs={'class':'related'}),
+	dict(name='div', attrs={'class':'fb_article_foot'}),
+	dict(name='div', attrs={'class':'spreading'}),
+	dict(name='dl', attrs={'class':'ad'}),
+	dict(name='p', attrs={'class':'report'}),
+	dict(name='div', attrs={'class':'hfeed comments'}),
+	dict(name='dl', attrs={'id':'entryPanel'}),
+	dict(name='dl', attrs={'class':'infopush ip_wide'}),
+	dict(name='div', attrs={'class':'sidebar'}),
+	dict(name='dl', attrs={'class':'bottom'}),
+	dict(name='div', attrs={'id':'footer'}),
+	]
+
+
+  feeds = [
+	(u'Slovenija', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=13')
+	,(u'Svet', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=14')
+	,(u'EU', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=116')
+	,(u'Poslovni dnevnik', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=5')
+	,(u'Kronika', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=15')
+	,(u'Kultura', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=17')
+	,(u'Zdravje', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=18')
+	,(u'Znanost in IT', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=19')
+	,(u'(Ne)verjetno', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=20')
+	,(u'E-strada', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=21')
+	,(u'Svet vozil', u'http://www.dnevnik.si/rss/?articleType=1&articleSection=22')
+	]

resources/recipes/european_voice.recipe

@@ -0,0 +1,51 @@
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class EuropeanVoice(BasicNewsRecipe):
+    title          = u'European Voice'
+    __author__     = 'malfi'
+    oldest_article = 14
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://www.europeanvoice.com/Css/images/logo.gif'
+    language = 'en'
+    keep_only_tags    = [dict(name='div', attrs={'id':'articleLeftColumn'})]
+    remove_tags    = [dict(name='div', attrs={'id':'BreadCrump'})]
+    feeds          = [
+                        (u'Whole site ',u'http://www.europeanvoice.com/Rss/2.xml'),
+                          (u'News and analysis',u'http://www.europeanvoice.com/Rss/6.xml'),
+                          (u'Comment',u'http://www.europeanvoice.com/Rss/7.xml'),
+                          (u'Special reports',u'http://www.europeanvoice.com/Rss/5.xml'),
+                          (u'People',u'http://www.europeanvoice.com/Rss/8.xml'),
+                          (u'Career',u'http://www.europeanvoice.com/Rss/11.xml'),
+                          (u'Policies',u'http://www.europeanvoice.com/Rss/4.xml'),
+                          (u'EVents',u'http://www.europeanvoice.com/Rss/10.xml'),
+                          (u'Policies - Economics',u'http://www.europeanvoice.com/Rss/31.xml'),
+                          (u'Policies - Business',u'http://www.europeanvoice.com/Rss/19.xml'),
+                          (u'Policies - Trade',u'http://www.europeanvoice.com/Rss/25.xml'),
+                          (u'Policies - Information society',u'http://www.europeanvoice.com/Rss/20.xml'),
+                          (u'Policies - Energy',u'http://www.europeanvoice.com/Rss/15.xml'),
+                          (u'Policies - Transport',u'http://www.europeanvoice.com/Rss/18.xml'),
+                          (u'Policies - Climate change',u'http://www.europeanvoice.com/Rss/16.xml'),
+                          (u'Policies - Environment',u'http://www.europeanvoice.com/Rss/17.xml'),
+                          (u'Policies - Farming & food',u'http://www.europeanvoice.com/Rss/23.xml'),
+                          (u'Policies - Health & society',u'http://www.europeanvoice.com/Rss/24.xml'),
+                          (u'Policies - Justice',u'http://www.europeanvoice.com/Rss/29.xml'),
+                          (u'Policies - Foreign affairs',u'http://www.europeanvoice.com/Rss/27.xml')
+                     ]
+    extra_css = '''
+        h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+        h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+        p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+        body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+        '''
+
+    def print_version(self, url):
+          return url + '?bPrint=1'
+
+    def preprocess_html(self, soup):
+           denied = soup.findAll(True,text='Subscribers')
+           if denied:
+                raise Exception('Article skipped, because content can only be seen with subscription')
+           return soup
+

resources/recipes/gamespot.recipe

@@ -1,5 +1,5 @@
 __license__   = 'GPL v3'
-__author__ = u'Marc T\xf6nsing'
+__author__    = u'Marc Toensing'
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
@@ -17,6 +17,7 @@ class GamespotCom(BasicNewsRecipe):
     no_javascript = True
 
     feeds =  [
+               ('All Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5'),
                ('PC Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=5'),
                ('XBOX 360 Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1029'),
                ('Wii Reviews', 'http://www.gamespot.com/rss/game_updates.php?type=5&platform=1031'),
@@ -37,5 +38,3 @@ class GamespotCom(BasicNewsRecipe):
 
     def get_article_url(self, article):
         return article.get('link') + '?print=1'
-
-

resources/recipes/handelsblatt.recipe

@@ -0,0 +1,41 @@
+import re
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Handelsblatt(BasicNewsRecipe):
+    title          = u'Handelsblatt'
+    __author__ = 'malfi'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://www.handelsblatt.com/images/logo/logo_handelsblatt.com.png'
+    language = 'de'
+    keep_only_tags = []
+    keep_only_tags.append(dict(name = 'div', attrs = {'class': 'structOneCol'}))
+    keep_only_tags.append(dict(name = 'div', attrs = {'id': 'fullText'}))
+    remove_tags    = [dict(name='img', attrs = {'src': 'http://www.handelsblatt.com/images/icon/loading.gif'})]
+
+    feeds          = [
+                        (u'Handelsblatt Exklusiv',u'http://www.handelsblatt.com/rss/exklusiv'),
+                        (u'Handelsblatt Top-Themen',u'http://www.handelsblatt.com/rss/top-themen'),
+                        (u'Handelsblatt Schlagzeilen',u'http://www.handelsblatt.com/rss/ticker/'),
+                        (u'Handelsblatt Finanzen',u'http://www.handelsblatt.com/rss/finanzen/'),
+                        (u'Handelsblatt Unternehmen',u'http://www.handelsblatt.com/rss/unternehmen/'),
+                        (u'Handelsblatt Politik',u'http://www.handelsblatt.com/rss/politik/'),
+                        (u'Handelsblatt Technologie',u'http://www.handelsblatt.com/rss/technologie/'),
+                        (u'Handelsblatt Meinung',u'http://www.handelsblatt.com/rss/meinung'),
+                        (u'Handelsblatt Magazin',u'http://www.handelsblatt.com/rss/magazin/'),
+                        (u'Handelsblatt Weblogs',u'http://www.handelsblatt.com/rss/blogs')
+                     ]
+    extra_css = '''
+        h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+        h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+        p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+        body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+        '''
+
+    def print_version(self, url):
+         m = re.search('(?<=;)[0-9]*', url)
+         return u'http://www.handelsblatt.com/_b=' + str(m.group(0)) + ',_p=21,_t=ftprint,doc_page=0;printpage'
+
+

resources/recipes/hola.recipe

@@ -0,0 +1,38 @@
+#!/usr/bin/env  python
+__license__   = 'GPL v3'
+__copyright__ = '2010, Brendan Sleight <bms.calibre at barwap.com>'
+'''
+hola.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Hackaday(BasicNewsRecipe):
+    title                 = u'Hola'
+    __author__            = 'bmsleight'
+    description           = 'diario de actualidad, moda y belleza.'
+    oldest_article        = 10
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    language              = 'es'
+
+    use_embedded_content  = False
+
+    keep_only_tags      = [
+                           dict(name='div', attrs={'id':'cuerpo'})
+                          ]
+
+    feeds               = [
+                         (u'Famosos'        , u'http://www.hola.com/famosos/rss.xml'           ),
+                         (u'Realeza'        , u'http://www.hola.com/realeza/rss.xml'           ),
+                         (u'Cine'           , u'http://www.hola.com/cine/rss.xml'              ),
+                         (u'Música'         , u'http://www.hola.com/musica/rss.xml'            ),
+                         (u'Moda y modelos' , u'http://www.hola.com/moda/portada/rss.xml'      ),
+                         (u'Belleza y salud', u'http://www.hola.com/belleza/portada/rss.xml'   ),
+                         (u'Niños'          , u'http://www.hola.com/ninos/rss.xml'             ),
+                         (u'Todas las noticias', u'http://int2.hola.com/app/feeds/rss_hola.php'),
+                         ]
+
+    def get_article_url(self, article):
+        url = article.get('guid', None)
+        return url

resources/recipes/irish_times.recipe

@@ -33,13 +33,14 @@ class IrishTimes(BasicNewsRecipe):
                       ('Letters', 'http://www.irishtimes.com/feeds/rss/newspaper/letters.rss'),
                     ]
 
-
     def print_version(self, url):
-        if url.count('rss.feedsportal.com'):
+         if url.count('rss.feedsportal.com'):
-            u = url.replace('0Bhtml/story01.htm','_pf0Bhtml/story01.htm')
+             u = 'http://www.irishtimes.com' + \
-        else:
+ (((url[69:].replace('0C','/')).replace('0A','0'))).replace('0Bhtml/story01..htm','_pf.html')
-            u = url.replace('.html','_pf.html')
+         else:
-        return u
+             u = url.replace('.html','_pf.html')
+         return u
+
 
     def get_article_url(self, article):
         return article.link

resources/recipes/la_jornada.recipe

@@ -54,10 +54,7 @@ class LaJornada_mx(BasicNewsRecipe):
     preprocess_regexps = [
                           (re.compile(  r'<div class="inicial">(.*)</div><p class="s-s">'
                                        ,re.DOTALL|re.IGNORECASE)
-                                       ,lambda match: '<p class="inicial">' + match.group(1) + '</p><p class="s-s">'),
+                                       ,lambda match: '<p class="inicial">' + match.group(1) + '</p><p class="s-s">')
-                          (re.compile(  r'<q>(.*?)</q>'
-                                       ,re.DOTALL|re.IGNORECASE)
-                                       ,lambda match: '"' + match.group(1) + '"')
                          ]
                         
     keep_only_tags = [

resources/recipes/marctv.recipe

@@ -0,0 +1,35 @@
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+
+'''
+Fetch MarcTV.
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class MarcTVde(BasicNewsRecipe):
+
+    title = 'Marc Toensings Visionen'
+
+    description = 'Marc Toensings Visionen'
+
+    language = 'de'
+
+    __author__ = 'Marc Toensing'
+
+    max_articles_per_feed = 40
+
+    oldest_article = 665
+
+    use_embedded_content = False
+
+    remove_tags = []
+
+    keep_only_tags = dict(name='div', attrs={'class':["content"]})
+
+    feeds          = [(u'Spiele', u'http://feeds.feedburner.com/marctv/spiele'), (u'Leben', u'http://feeds.feedburner.com/marctv/leben'), (u'Medien', u'http://feeds.feedburner.com/marctv/medien')]
+
+    extra_css = '.#wrapper .entry p img{width:620px; height: 270px;}'
+
+    def get_cover_url(self):
+            return 'http://marctv.de/marctv.png'

resources/recipes/mmc_rtv.recipe

@@ -0,0 +1,57 @@
+__license__ = 'GPL v3'
+__copyright__ = '2010, BlonG'
+'''
+www.rtvslo.si
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class MMCRTV(BasicNewsRecipe):
+    title = u'MMC RTV Slovenija'
+    __author__ = u'BlonG'
+    description = u"Prvi interaktivni multimedijski portal, MMC RTV Slovenija"
+    oldest_article = 3
+    max_articles_per_feed = 20
+    language = 'sl'
+    no_stylesheets = True
+    use_embedded_content = False
+
+    cover_url = 'https://sites.google.com/site/javno2010/home/rtv_slo_cover.jpg'
+
+    extra_css = '''
+            h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+            h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+            p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+            body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+            '''
+
+    def print_version(self, url):
+            split_url = url.split("/")
+            print_url = 'http://www.rtvslo.si/index.php?c_mod=news&op=print&id=' + split_url[-1]
+            return print_url
+
+    keep_only_tags = [
+            dict(name='div', attrs={'class':'title'}),
+            dict(name='div', attrs={'id':'newsbody'}),
+            dict(name='div', attrs={'id':'newsblocks'}),
+            ]
+#    remove_tags=[
+# 40            dict(name='div', attrs={'id':'newsblocks'}),
+#            ]
+
+    feeds = [
+            (u'Slovenija', u'http://www.rtvslo.si/feeds/01.xml'),
+            (u'Svet', u'http://www.rtvslo.si/feeds/02.xml'),
+            (u'Evropska unija', u'http://www.rtvslo.si/feeds/16.xml'),
+            (u'Gospodarstvo', u'http://www.rtvslo.si/feeds/04.xml'),
+            (u'\u010crna kronika', u'http://www.rtvslo.si/feeds/08.xml'),
+            (u'Okolje', u'http://www.rtvslo.si/feeds/12.xml'),
+            (u'Znanost in tehnologija', u'http://www.rtvslo.si/feeds/09.xml'),
+            (u'Zabava', u'http://www.rtvslo.si/feeds/06.xml'),
+            (u'Ture avanture', u'http://www.rtvslo.si/feeds/28.xml'),
+            ]
+
+#    def preprocess_html(self, soup):
+#            newsblocks = soup.find('div',attrs = ['id':'newsblocks'])
+#            soup.find('div', attrs = {'id':'newsbody'}).insert(-1, newsblocks)
+#            return soup
+

resources/recipes/newsweek_polska.recipe

@@ -0,0 +1,68 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Mateusz Kielar, matek09@gmail.com'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Newsweek(BasicNewsRecipe):
+	EDITION = 0
+
+	title = u'Newsweek Polska'
+	__author__ = 'Mateusz Kielar'
+	description = 'Weekly magazine'
+	encoding = 'utf-8'
+	no_stylesheets = True
+	language = 'en'
+	remove_javascript = True
+
+	keep_only_tags =[]
+	keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'article'}))
+
+	remove_tags =[]
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'copy'}))
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'url'}))
+
+	extra_css = '''
+					.body {font-size: small}
+					.author {font-size: x-small}
+					.lead {font-size: x-small}
+					.title{font-size: x-large; font-weight: bold}
+					'''
+
+	def print_version(self, url):
+		return url.replace("http://www.newsweek.pl/artykuly/wydanie/" + str(self.EDITION), "http://www.newsweek.pl/artykuly") + '/print'
+
+	def find_last_full_issue(self):
+		page = self.index_to_soup('http://www.newsweek.pl/Frames/IssueCover.aspx')
+		issue = 'http://www.newsweek.pl/Frames/' + page.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
+		page = self.index_to_soup(issue)
+		issue = 'http://www.newsweek.pl/Frames/' + page.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
+		page = self.index_to_soup(issue)
+		self.EDITION = page.find('a', attrs={'target' : '_parent'})['href'].replace('/wydania/','')
+
+	def parse_index(self):
+		self.find_last_full_issue()
+		soup = self.index_to_soup('http://www.newsweek.pl/wydania/' + str(self.EDITION))
+		img = soup.find('img', id="ctl00_C1_PaperIsssueView_IssueImage", src=True)
+		self.cover_url = img['src']
+		feeds = []
+		parent = soup.find(id='content-left-big')
+		for txt in parent.findAll(attrs={'class':'txt_normal_red strong'}):
+			section = self.tag_to_string(txt).capitalize()
+			articles = list(self.find_articles(txt))
+			feeds.append((section, articles))
+		return feeds
+
+	def find_articles(self, txt):
+		for a in txt.findAllNext( attrs={'class':['strong','hr']}):
+			if a.name in "div":
+				break
+			yield {
+				'title' : self.tag_to_string(a),
+				'url'   : 'http://www.newsweek.pl'+a['href'],
+				'date'  : '',
+				'description' : ''
+				}
+
+

resources/recipes/pagina12.recipe

@@ -21,8 +21,16 @@ class Pagina12(BasicNewsRecipe):
     use_embedded_content  = False
     language              = 'es'
     remove_empty_feeds    = True
+    publication_type      = 'newspaper'
     masthead_url          = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif'
-    extra_css             = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} #autor{font-weight: bold} #fecha,#epigrafe{font-size: 0.9em; margin: 5px} #imagen{border: 1px solid black; margin: 0 0 1.25em 1.25em; width: 232px }  '
+    extra_css             = """ 
+                               body{font-family: Arial,Helvetica,sans-serif } 
+                               img{margin-bottom: 0.4em; display:block}
+                               #autor{font-weight: bold} 
+                               #fecha,#epigrafe{font-size: 0.9em; margin: 5px} 
+                               #imagen{border: 1px solid black; margin: 0 0 1.25em 1.25em; width: 232px }
+                               .fgprincipal{font-size: large; font-weight: bold}
+                            """
 
     conversion_options = {
                           'comment'   : description
@@ -31,7 +39,11 @@ class Pagina12(BasicNewsRecipe):
                         , 'language'  : language
                         }
 
-    remove_tags = [dict(name='div', attrs={'id':['volver','logo','logo_suple','fin','permalink']})]
+    remove_tags = [
+                     dict(name=['meta','link'])
+                    ,dict(name='div', attrs={'id':['volver','logo','logo_suple','fin','permalink']})
+                  ]
+    remove_attributes=['lang']
 
 
     feeds = [
@@ -65,4 +77,13 @@ class Pagina12(BasicNewsRecipe):
     def preprocess_html(self, soup):
         for item in soup.findAll(style=True):
             del item['style']
+        for item in soup.findAll('span', attrs={'id':'seccion'}):
+            it = item.a
+            it.name='span'
+            del it['href']
+            del it['title']
+        for item in soup.findAll('p'):
+            it = item.find('h3')            
+            if it:
+               it.name='span'
         return soup

resources/recipes/politika.recipe

@@ -1,13 +1,10 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
 '''
 politika.rs
 '''
 import re
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
 
 class Politika(BasicNewsRecipe):
     title                 = 'Politika Online'
@@ -19,53 +16,51 @@ class Politika(BasicNewsRecipe):
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
-    remove_javascript     = True
     encoding              = 'utf8'
-    language = 'sr'
+    delay                 = 1
-
+    language              = 'sr'
-    lang                 = 'sr-Latn-RS'
+    publication_type      = 'newspaper'    
-    direction            = 'ltr'
+    masthead_url          = 'http://static.politika.co.rs/images_new/politika.gif'    
-    extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: sans1, sans-serif}'
+    extra_css             = """ 
+                               @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} 
+                               @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} 
+                               body{font-family: Arial,Helvetica,sans1,sans-serif}
+                               h1{font-family: "Times New Roman",Times,serif1,serif}
+                               .articledescription{font-family: sans1, sans-serif}
+                            """
 
     conversion_options = {
-                          'comment'          : description
+                          'comment'   : description
-                        , 'tags'             : category
+                        , 'tags'      : category
-                        , 'publisher'        : publisher
+                        , 'publisher' : publisher
-                        , 'language'         : lang
+                        , 'language'  : language
-                        , 'pretty_print'     : True
                         }
 
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
-    keep_only_tags     = [dict(name='div', attrs={'class':'content_center_border'})]
+    keep_only_tags     = [dict(name='div', attrs={'class':'big_article_home item_details'})]
-
+    remove_tags_after  = dict(attrs={'class':'online_date'})
-    remove_tags = [
+    remove_tags        = [dict(name=['link','meta','iframe','embed','object'])]
-                    dict(name='div', attrs={'class':['send_print','txt-komentar']})
+    
-                   ,dict(name=['object','link','a'])
-                   ,dict(name='h1', attrs={'class':'box_header-tags'})
-                  ]
-
-
     feeds          = [
-                         (u'Politika'             , u'http://www.politika.rs/rubrike/Politika/index.1.lt.xml'             )
+                         (u'Politika'         , u'http://www.politika.rs/rubrike/Politika/index.1.lt.xml'         )
-                        ,(u'Svet'                 , u'http://www.politika.rs/rubrike/Svet/index.1.lt.xml'                 )
+                        ,(u'Svet'             , u'http://www.politika.rs/rubrike/Svet/index.1.lt.xml'             )
-                        ,(u'Redakcijski komentari', u'http://www.politika.rs/rubrike/redakcijski-komentari/index.1.lt.xml')
+                        ,(u'Ostali komentari' , u'http://www.politika.rs/rubrike/ostali-komentari/index.1.lt.xml' )
-                        ,(u'Pogledi'              , u'http://www.politika.rs/pogledi/index.lt.xml'                        )
+                        ,(u'Pogledi'          , u'http://www.politika.rs/pogledi/index.lt.xml'                    )
-                        ,(u'Pogledi sa strane'    , u'http://www.politika.rs/rubrike/Pogledi-sa-strane/index.1.lt.xml'    )
+                        ,(u'Pogledi sa strane', u'http://www.politika.rs/rubrike/Pogledi-sa-strane/index.1.lt.xml')
-                        ,(u'Tema dana'            , u'http://www.politika.rs/rubrike/tema-dana/index.1.lt.xml'            )
+                        ,(u'Tema dana'        , u'http://www.politika.rs/rubrike/tema-dana/index.1.lt.xml'        )
-                        ,(u'Kultura'              , u'http://www.politika.rs/rubrike/Kultura/index.1.lt.xml'              )
+                        ,(u'Kultura'          , u'http://www.politika.rs/rubrike/Kultura/index.1.lt.xml'          )
-                        ,(u'Zivot i stil'         , u'http://www.politika.rs/rubrike/zivot-i-stil/index.1.lt.xml'         )
+                        ,(u'Spektar'          , u'http://www.politika.rs/rubrike/zivot-i-stil/index.1.lt.xml'     )
                      ]
 
     def preprocess_html(self, soup):
-        soup.html['lang'] = self.lang
-        soup.html['dir' ] = self.direction
-        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        soup.head.insert(0,mlang)
         for item in soup.findAll(style=True):
             del item['style']
-        ftag = soup.find('div',attrs={'class':'content_center_border'})
+        for item in soup.findAll('a', attrs={'class':'category'}):
-        if ftag.has_key('align'):
+            item.name='span'
-           del ftag['align']
+            if item.has_key('href'):            
-        return self.adeify_images(soup)
+               del item['href']
+            if item.has_key('title'):            
+               del item['title']
+        return soup

resources/recipes/polityka.recipe

@@ -0,0 +1,68 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Mateusz Kielar, matek09@gmail.com'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Polityka(BasicNewsRecipe):
+
+	title = u'Polityka'
+	__author__ = 'Mateusz Kielar'
+	description = 'Weekly magazine. Last archive issue'
+	encoding = 'utf-8'
+	no_stylesheets = True
+	language = 'en'
+	remove_javascript = True
+
+	remove_tags_before = dict(dict(name = 'h2', attrs = {'class' : 'box_nag'}))
+	remove_tags_after = dict(dict(name = 'div', attrs = {'class' : 'box_footer'}))
+
+	remove_tags =[]
+	remove_tags.append(dict(name = 'h2', attrs = {'class' : 'box_nag'}))
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'box_footer'}))
+
+
+	extra_css = '''
+					h1 {font-size: x-large; font-weight: bold}
+					'''
+
+	def parse_index(self):
+		soup = self.index_to_soup('http://archiwum.polityka.pl/')
+		box_img3 = soup.findAll(attrs={'class' : 'box_img3'})
+		feeds = []
+		last = 0
+		self.cover_url = 'http://archiwum.polityka.pl' + box_img3[-1].find('img')['src']
+		last_edition = 'http://archiwum.polityka.pl' + box_img3[-1].find('a')['href']
+
+		while True:
+			index = self.index_to_soup(last_edition)
+
+
+			box_list = index.findAll('div', attrs={'class' : 'box_list'})
+			if len(box_list) == 0:
+				break
+
+			articles = {}
+			for box in box_list:
+				for div in box.findAll('div', attrs={'class': 'list_tresc'}):
+					article_page = self.index_to_soup('http://archiwum.polityka.pl' + div.a['href'],)
+					section = self.tag_to_string(article_page.find('h2', attrs = {'class' : 'box_nag'})).split('/')[0].lstrip().rstrip()
+					print section
+					if not articles.has_key(section):
+						articles[section] = []
+					articles[section].append( {
+						'title' : self.tag_to_string(div.a),
+						'url'   : 'http://archiwum.polityka.pl' + div.a['href'],
+						'date'  : '',
+						'description' : ''
+						})
+
+			for section in articles:
+				feeds.append((section, articles[section]))
+
+			last_edition = last_edition.replace('http://archiwum.polityka.pl/wydanie/' + str(last), 'http://archiwum.polityka.pl/wydanie/' + str(last + 1))
+			last = last + 1
+
+		return feeds
+

resources/recipes/rollingstone.recipe

@@ -0,0 +1,69 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
+'''
+rollingstone.com
+'''
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class RollingStone(BasicNewsRecipe):
+    title                 = 'Rolling Stone Magazine - free content'
+    __author__            = 'Darko Miletic'
+    description           = 'Rolling Stone Magazine features music, album and artist news, movie reviews, political, economic and pop culture commentary, videos, photos, and more.'
+    publisher             = 'Werner Media inc.'
+    category              = 'news, music, USA, world'
+    oldest_article        = 15
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    use_embedded_content  = False
+    language              = 'en'
+    remove_empty_feeds    = True
+    publication_type      = 'magazine'
+    masthead_url          = 'http://www.rollingstone.com/templates/rolling-stone-templates/theme/rstheme/images/rsLogo.png'
+    extra_css             = """
+                               body{font-family: Georgia,Times,serif }
+                               img{margin-bottom: 0.4em; display:block}
+                            """
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    preprocess_regexps = [
+                          (re.compile(r'xml:lang="en">.*?<head>', re.DOTALL|re.IGNORECASE),lambda match: 'xml:lang="en">\n<head>\n')
+                         ,(re.compile(r'</title>.*?</head>'     , re.DOTALL|re.IGNORECASE),lambda match: '</title>\n</head>\n'     )
+                         ]
+
+    keep_only_tags=[
+                     dict(attrs={'class':['headerImgHolder','headerContent']})
+                    ,dict(name='div',attrs={'id':['teaser','storyTextContainer']})
+                    ,dict(name='div',attrs={'class':'blogDetailModule clearfix'})
+                   ]
+
+    remove_tags = [
+                      dict(name=['meta','iframe','object','embed'])
+                     ,dict(attrs={'id':'mpStoryHeader'})
+                     ,dict(attrs={'class':'relatedTopics'})
+                  ]
+    remove_attributes=['lang','onclick','width','height','name']
+    remove_tags_before=dict(attrs={'class':'bloggerInfo'})
+    remove_tags_after=dict(attrs={'class':'relatedTopics'})
+
+
+    feeds = [
+              (u'All News'      , u'http://www.rollingstone.com/siteServices/rss/allNews'      )
+             ,(u'All Blogs'     , u'http://www.rollingstone.com/siteServices/rss/allBlogs'     )
+             ,(u'Movie Reviews' , u'http://www.rollingstone.com/siteServices/rss/movieReviews' )
+             ,(u'Album Reviews' , u'http://www.rollingstone.com/siteServices/rss/albumReviews' )
+             ,(u'Song Reviews'  , u'http://www.rollingstone.com/siteServices/rss/songReviews'  )
+            ]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

resources/recipes/scprint.recipe

@@ -1,4 +1,4 @@
-from calibre.web.feeds.recipes import BasicNewsRecipe, LoginFailed
+from calibre.web.feeds.news import BasicNewsRecipe, LoginFailed
 
 class SCPrintMagazine(BasicNewsRecipe):
     title          = u'SC Print Magazine'

resources/recipes/siol.recipe

@@ -5,18 +5,17 @@ __copyright__ = '2010, BlonG'
 www.siol.si
 '''
 from calibre.web.feeds.news import BasicNewsRecipe
-
 class Siol(BasicNewsRecipe):
     title = u'Siol.net'
     __author__ = u'BlonG'
     description = "Multimedijski portal z aktualnimi vsebinami, intervjuji, komentarji iz Slovenije in sveta, sportal, trendi, avtomoto, blogos"
     oldest_article = 3
+    language = 'sl'
     max_articles_per_feed = 20
     no_stylesheets = True
     use_embedded_content = False
-    language = 'sl'
 
-    cover_url = 'http://farm4.static.flickr.com/3540/3401820496_c771550fe6.jpg'
+    cover_url = 'https://sites.google.com/site/javno2010/home/siol_cover.jpg'
 
     extra_css = '''
                     h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
@@ -25,6 +24,8 @@ class Siol(BasicNewsRecipe):
                     body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
 	'''
 
+    html2lrf_options = ['--base-font-size', '10']
+
     keep_only_tags = [
 	dict(name='div', attrs={'id':'idContent'}),
 	]
@@ -52,4 +53,3 @@ class Siol(BasicNewsRecipe):
 	,(u'Tehnologija', u'http://www.siol.net/rss.aspx?path=Tehnologija')
 	,(u'TV / Film', u'http://www.siol.net/rss.aspx?path=TV')
 	]
-

resources/recipes/vedomosti.recipe

@@ -0,0 +1,195 @@
+#!/usr/bin/env  python
+
+u'''
+Ведомости
+'''
+
+from calibre.web.feeds.feedparser import parse
+from calibre.ebooks.BeautifulSoup import Tag
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class VedomostiRecipe(BasicNewsRecipe):
+    title = u'Ведомости'
+    __author__ = 'Nikolai Kotchetkov'
+    publisher = 'vedomosti.ru'
+    category = 'press, Russia'
+    description = u'Ежедневная деловая газета'
+    oldest_article = 3
+    max_articles_per_feed = 100
+
+    masthead_url = u'http://motorro.com/imgdir/logos/ved_logo_black2_cropped.gif'
+    cover_url = u'http://motorro.com/imgdir/logos/ved_logo_black2_cropped.gif'
+
+    #Add feed names if you want them to be sorted (feeds of this list appear first)
+    sortOrder = [u'_default', u'Первая полоса', u'Власть и деньги']
+
+    encoding = 'cp1251'
+    language = 'ru'
+    no_stylesheets = True
+    remove_javascript = True
+    recursions = 0
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+
+    keep_only_tags = [dict(name='td', attrs={'class' : ['second_content']})]
+
+    remove_tags_after = [dict(name='div', attrs={'class' : 'article_text'})]
+
+    remove_tags = [dict(name='div', attrs={'class' : ['sep', 'choice', 'articleRightTbl']})]
+
+    feeds = [u'http://www.vedomosti.ru/newspaper/out/rss.xml']
+
+    #base URL for relative links
+    base_url = u'http://www.vedomosti.ru'
+
+    extra_css = 'h1 {font-size: 1.5em; margin: 0em 0em 0em 0em; text-align: center;}'\
+                'h2 {font-size: 1.0em; margin: 0em 0em 0em 0em;}'\
+                'h3 {font-size: 0.8em; margin: 0em 0em 0em 0em;}'\
+                '.article_date {font-size: 0.5em; color: gray; font-family: monospace; text-align:right;}'\
+                '.article_authors {font-size: 0.5em; color: gray; font-family: monospace; text-align:right;}'\
+                '.article_img {width:100%; text-align: center; padding: 3px 3px 3px 3px;}'\
+                '.article_img_desc {width:100%; text-align: center; font-size: 0.5em; color: gray; font-family: monospace;}'\
+                '.article_desc {font-size: 1em; font-style:italic;}'
+
+    def parse_index(self):
+        try:
+            feedData = parse(self.feeds[0])
+            if not feedData:
+                raise NotImplementedError
+            self.log("parse_index: Feed loaded successfully.")
+            if feedData.feed.has_key('title'):
+                self.title = feedData.feed.title
+                self.log("parse_index: Title updated to: ", self.title)
+            if feedData.feed.has_key('description'):
+                self.description = feedData.feed.description
+                self.log("parse_index: Description updated to: ", self.description)
+
+            def get_virtual_feed_articles(feed):
+                if feeds.has_key(feed):
+                    return feeds[feed][1]
+                self.log("Adding new feed: ", feed)
+                articles = []
+                feeds[feed] = (feed, articles)
+                return articles
+
+            feeds = {}
+
+            #Iterate feed items and distribute articles using tags
+            for item in feedData.entries:
+                link = item.get('link', '');
+                title = item.get('title', '');
+                if '' == link or '' == title:
+                    continue
+                article = {'title':title, 'url':link, 'description':item.get('description', ''), 'date':item.get('date', ''), 'content':''};
+                if not item.has_key('tags'):
+                    get_virtual_feed_articles('_default').append(article)
+                    continue
+                for tag in item.tags:
+                    addedToDefault = False
+                    term = tag.get('term', '')
+                    if '' == term:
+                        if (not addedToDefault):
+                            get_virtual_feed_articles('_default').append(article)
+                        continue
+                    get_virtual_feed_articles(term).append(article)
+
+            #Get feed list
+            #Select sorted feeds first of all
+            result = []
+            for feedName in self.sortOrder:
+                if (not feeds.has_key(feedName)): continue
+                result.append(feeds[feedName])
+                del feeds[feedName]
+            result = result + feeds.values()
+
+            return result
+
+        except Exception, err:
+            self.log(err)
+            raise NotImplementedError
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+
+    def postprocess_html(self, soup, first_fetch):
+        #self.log('Original: ', soup.prettify())
+
+        #Find article
+        contents = soup.find('div', {'class':['article_text']})
+        if not contents:
+            self.log('postprocess_html: article div not found!')
+            return soup
+        contents.extract()
+
+        #Find title
+        title = soup.find('h1')
+        if title:
+            contents.insert(0, title)
+
+        #Find article image
+        newstop = soup.find('div', {'class':['newstop']})
+        if newstop:
+            img = newstop.find('img')
+            if img:
+                imgDiv = Tag(soup, 'div')
+                imgDiv['class'] = 'article_img'
+
+                if img.has_key('width'):
+                    del(img['width'])
+                if img.has_key('height'):
+                    del(img['height'])
+
+                #find description
+                element = img.parent.nextSibling
+
+                img.extract()
+                imgDiv.insert(0, img)
+
+                while element:
+                    if not isinstance(element, Tag):
+                        continue
+                    nextElement = element.nextSibling
+                    if 'p' == element.name:
+                        element.extract()
+                        element['class'] = 'article_img_desc'
+                        imgDiv.insert(len(imgDiv.contents), element)
+                    element = nextElement
+
+                contents.insert(1, imgDiv)
+
+        #find article abstract
+        abstract = soup.find('p', {'class':['subhead']})
+        if abstract:
+            abstract['class'] = 'article_desc'
+            contents.insert(2, abstract)
+
+        #Find article authors
+        authorsDiv = soup.find('div', {'class':['autors']})
+        if authorsDiv:
+            authorsP = authorsDiv.find('p')
+            if authorsP:
+                authorsP['class'] = 'article_authors'
+                contents.insert(len(contents.contents), authorsP)
+
+        #Fix urls that use relative path
+        urls = contents.findAll('a');
+        if urls:
+            for url in urls:
+                if not url.has_key('href'):
+                    continue
+                if '/' == url['href'][0]:
+                    url['href'] = self.base_url + url['href']
+
+        body = soup.find('td', {'class':['second_content']})
+        if body:
+            body.replaceWith(contents)
+
+        self.log('Result: ', soup.prettify())
+        return soup
+

resources/recipes/zeitde.recipe

@@ -43,7 +43,7 @@ class ZeitDe(BasicNewsRecipe):
                ('Sport', 'http://newsfeed.zeit.de/sport/index'),
              ]
 
-    extra_css = '.reaktion,.taglist,.comments,.reponse,.responsetitle,.responsebody,.reponse,.inline,.date{display:none;}li.date{display:block}'
+    extra_css = '.excerpt{font-size:1em}.reaktion,.taglist,.comments,.reponse,.responsetitle,.responsebody,.reponse,.inline,.date{display:none;}li.date{display:block}'
 
     #filter_regexps = [r'ad.de.doubleclick.net/']
 
@@ -55,6 +55,16 @@ class ZeitDe(BasicNewsRecipe):
               ans = None
         return ans
 
+    def preprocess_html(self, soup):
+        for tag in soup.findAll(name=['ul','li']):
+            tag.name = 'div'
+        
+        soup.html['xml:lang'] = self.lang
+        soup.html['lang']     = self.lang
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
+        soup.head.insert(0,mtag)
+        return soup
+
     def get_cover_url(self):
         try:
             inhalt = self.index_to_soup('http://www.zeit.de/inhalt')

setup/extensions.py

@@ -348,8 +348,12 @@ class Build(Command):
                 VERSION  = 1.0.0
                 CONFIG   += %s
             ''')%(ext.name, ' '.join(ext.headers), ' '.join(ext.sources), archs)
+            pro = pro.replace('\\', '\\\\')
             open(ext.name+'.pro', 'wb').write(pro)
-            subprocess.check_call([QMAKE, '-o', 'Makefile', ext.name+'.pro'])
+            qmc = [QMAKE, '-o', 'Makefile']
+            if iswindows:
+                qmc += ['-spec', 'win32-msvc2008']
+            subprocess.check_call(qmc + [ext.name+'.pro'])
             subprocess.check_call([make, '-f', 'Makefile'])
             objects = glob.glob(obj_pat)
         return list(map(self.a, objects))

setup/installer/windows/freeze.py

@@ -13,7 +13,7 @@ from setup import Command, modules, functions, basenames, __version__, \
 from setup.build_environment import msvc, MT, RC
 from setup.installer.windows.wix import WixMixIn
 
-QT_DIR = 'C:\\Qt\\4.6.3'
+QT_DIR = 'Q:\\Qt\\4.7.1'
 QT_DLLS = ['Core', 'Gui', 'Network', 'Svg', 'WebKit', 'Xml', 'XmlPatterns']
 LIBUSB_DIR       = 'C:\\libusb'
 LIBUNRAR         = 'C:\\Program Files\\UnrarDLL\\unrar.dll'

setup/installer/windows/notes.rst

@@ -37,8 +37,7 @@ Qt
 
 Extract Qt sourcecode to C:\Qt\4.x.x. Run configure and make::
 
-    configure -opensource -qt-zlib -qt-gif -qt-libmng -qt-libpng -qt-libtiff -qt-libjpeg -release -platform win32-msvc -no-qt3support -webkit -xmlpatterns -no-phonon
+    configure -opensource -release -qt-zlib -qt-gif -qt-libmng -qt-libpng -qt-libtiff -qt-libjpeg -release -platform win32-msvc2008 -no-qt3support -webkit -xmlpatterns -no-phonon -no-style-plastique -no-style-cleanlooks -no-style-motif -no-style-cde -no-declarative -no-scripttools -no-audio-backend -no-multimedia -no-dbus -no-openvg -no-opengl -no-qt3support -confirm-license && nmake
-    nmake
 
 SIP
 -----

src/calibre/__init__.py

@@ -444,6 +444,9 @@ xml_entity_to_unicode = partial(entity_to_unicode, result_exceptions = {
 def replace_entities(raw):
     return _ent_pat.sub(entity_to_unicode, raw)
 
+def xml_replace_entities(raw):
+    return _ent_pat.sub(xml_entity_to_unicode, raw)
+
 def prepare_string_for_xml(raw, attribute=False):
     raw = _ent_pat.sub(entity_to_unicode, raw)
     raw = raw.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;')

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.7.27'
+__version__   = '0.7.28'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 
 import re

src/calibre/customize/builtins.py

@@ -2,9 +2,7 @@ import os.path
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 
-import textwrap
+import textwrap, os, glob, functools
-import os
-import glob
 from calibre.customize import FileTypePlugin, MetadataReaderPlugin, \
     MetadataWriterPlugin, PreferencesPlugin, InterfaceActionBase
 from calibre.constants import numeric_version
@@ -95,10 +93,12 @@ class ComicMetadataReader(MetadataReaderPlugin):
 
     def get_metadata(self, stream, ftype):
         if ftype == 'cbr':
-            from calibre.libunrar import extract_member as extract_first
+            from calibre.libunrar import extract_first_alphabetically as extract_first
             extract_first
         else:
-            from calibre.libunzip import extract_member as extract_first
+            from calibre.libunzip import extract_member
+            extract_first = functools.partial(extract_member,
+                    sort_alphabetically=True)
         from calibre.ebooks.metadata import MetaInformation
         ret = extract_first(stream)
         mi = MetaInformation(None, None)
@@ -462,7 +462,7 @@ from calibre.devices.iliad.driver import ILIAD
 from calibre.devices.irexdr.driver import IREXDR1000, IREXDR800
 from calibre.devices.jetbook.driver import JETBOOK, MIBUK, JETBOOK_MINI
 from calibre.devices.kindle.driver import KINDLE, KINDLE2, KINDLE_DX
-from calibre.devices.nook.driver import NOOK
+from calibre.devices.nook.driver import NOOK, NOOK_COLOR
 from calibre.devices.prs505.driver import PRS505
 from calibre.devices.android.driver import ANDROID, S60
 from calibre.devices.nokia.driver import N770, N810, E71X, E52
@@ -548,6 +548,7 @@ plugins += [
     KINDLE2,
     KINDLE_DX,
     NOOK,
+    NOOK_COLOR,
     PRS505,
     ANDROID,
     S60,

src/calibre/customize/profiles.py

@@ -250,8 +250,11 @@ class OutputProfile(Plugin):
     #: If True, the date is appended to the title of downloaded news
     periodical_date_in_title = True
 
-    #: The character used to represent a star in ratings
+    #: Characters used in jackets and catalogs
+	missing_char = u'x'
     ratings_char = u'*'
+    empty_ratings_char = u' '
+    read_char = u'+'
 
     #: Unsupported unicode characters to be replaced during preprocessing
     unsupported_unicode_chars = []
@@ -287,7 +290,12 @@ class iPadOutput(OutputProfile):
             'macros': {'border-width': '{length}|medium|thick|thin'}
         }
     ]
-    ratings_char = u'\u2605'
+
+	missing_char = u'\u2715\u200a'		# stylized 'x' plus hair space
+    ratings_char = u'\u2605'			# filled star
+	empty_ratings_char = u'\u2606'		# hollow star
+    read_char = u'\u2713'				# check mark
+
     touchscreen = True
     # touchscreen_news_css {{{
     touchscreen_news_css = u'''
@@ -498,7 +506,6 @@ class SonyReaderLandscapeOutput(SonyReaderOutput):
     screen_size               = (784, 1012)
     comic_screen_size         = (784, 1012)
 
-
 class MSReaderOutput(OutputProfile):
 
     name        = 'Microsoft Reader'
@@ -582,7 +589,12 @@ class KindleOutput(OutputProfile):
     fsizes                    = [12, 12, 14, 16, 18, 20, 22, 24]
     supports_mobi_indexing = True
     periodical_date_in_title = False
+
+	missing_char = u'x\u2009'
+	empty_ratings_char = u'\u2606'
     ratings_char = u'\u2605'
+    read_char = u'\u2713'
+
     mobi_ems_per_blockquote = 2.0
 
     @classmethod
@@ -603,6 +615,8 @@ class KindleDXOutput(OutputProfile):
     #comic_screen_size         = (741, 1022)
     supports_mobi_indexing = True
     periodical_date_in_title = False
+    ratings_char = u'\u2605'
+    read_char = u'\u2713'
     mobi_ems_per_blockquote = 2.0
 
     @classmethod

src/calibre/devices/android/driver.py

@@ -23,6 +23,9 @@ class ANDROID(USBMS):
                 : [0x0100, 0x0227, 0x0226], 0x0c87: [0x0100, 0x0227, 0x0226],
                 0xc92 : [0x100]},
 
+            # Eken
+            0x040d : { 0x8510 : [0x0001] },
+
             # Motorola
             0x22b8 : { 0x41d9 : [0x216], 0x2d67 : [0x100], 0x41db : [0x216],
                 0x4285 : [0x216]},

src/calibre/devices/blackberry/driver.py

@@ -19,7 +19,7 @@ class BLACKBERRY(USBMS):
 
     VENDOR_ID   = [0x0fca]
     PRODUCT_ID  = [0x8004, 0x0004]
-    BCD         = [0x0200, 0x0107, 0x0210, 0x0201]
+    BCD         = [0x0200, 0x0107, 0x0210, 0x0201, 0x0211]
 
     VENDOR_NAME = 'RIM'
     WINDOWS_MAIN_MEM = 'BLACKBERRY_SD'

src/calibre/devices/interface.py

@@ -74,9 +74,9 @@ class DevicePlugin(Plugin):
         if bcd is None or len(bcd) == 0:
             return True
         for c in bcd:
-            # Bug in winutil.get_usb_devices converts a to :
+            rev = 'rev_%4.4x'%c
-            rev = ('rev_%4.4x'%c).replace('a', ':')
+            # Bug in winutil.get_usb_devices sometimes converts a to :
-            if rev in device_id:
+            if rev in device_id or rev.replace('a', ':') in device_id:
                 return True
         return False
 

src/calibre/devices/nook/driver.py

@@ -80,3 +80,14 @@ class NOOK(USBMS):
 
     def sanitize_path_components(self, components):
         return [x.replace('#', '_') for x in components]
+
+class NOOK_COLOR(NOOK):
+    gui_name       = _('Nook Color')
+    description    = _('Communicate with the Nook Color eBook reader.')
+
+    PRODUCT_ID  = [0x002]
+    BCD         = [0x216]
+    WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'EBOOK_DISK'
+
+    EBOOK_DIR_MAIN = 'My Files/Books'
+

src/calibre/devices/prs505/sony_cache.py

@@ -619,6 +619,13 @@ class XMLCache(object):
             x.replace(u'\0', '')
             return x
 
+        def record_set(k, v):
+            try:
+                record.set(k, clean(v))
+            except:
+                # v is not suitable for XML, ignore
+                pass
+
         if not getattr(book, '_new_book', False): # book is not new
                 if record.get('tz', None) is not None:
                     use_tz_var = True
@@ -641,20 +648,20 @@ class XMLCache(object):
             record.set('date', clean(date))
         record.set('size', clean(str(os.stat(path).st_size)))
         title = book.title if book.title else _('Unknown')
-        record.set('title', clean(title))
+        record_set('title', title)
         ts = book.title_sort
         if not ts:
             ts = title_sort(title)
-        record.set('titleSorter', clean(ts))
+        record_set('titleSorter', ts)
         if self.use_author_sort:
             if book.author_sort:
                 aus = book.author_sort
             else:
                 debug_print('Author_sort is None for book', book.lpath)
                 aus = authors_to_sort_string(book.authors)
-            record.set('author', clean(aus))
+            record_set('author', aus)
         else:
-            record.set('author', clean(authors_to_string(book.authors)))
+            record_set('author', authors_to_string(book.authors))
         ext = os.path.splitext(path)[1]
         if ext:
             ext = ext[1:].lower()

src/calibre/ebooks/metadata/epub.py

@@ -109,9 +109,11 @@ class OCFZipReader(OCFReader):
             raise EPubException("not a ZIP .epub OCF container")
         self.root = root
         if self.root is None:
-            self.root = os.getcwdu()
+            name = getattr(stream, 'name', False)
-            if hasattr(stream, 'name'):
+            if name:
-                self.root = os.path.abspath(os.path.dirname(stream.name))
+                self.root = os.path.abspath(os.path.dirname(name))
+            else:
+                self.root = os.getcwdu()
         super(OCFZipReader, self).__init__()
 
     def open(self, name, mode='r'):

src/calibre/ebooks/mobi/reader.py

@@ -221,7 +221,10 @@ class MetadataHeader(BookHeader):
         else:
             end = self.section_offset(number + 1)
         self.stream.seek(start)
-        return self.stream.read(end - start)
+        try:
+            return self.stream.read(end - start)
+        except OverflowError:
+            return self.stream.read(os.stat(self.stream.name).st_size - start)
 
 
 class MobiReader(object):
@@ -398,6 +401,8 @@ class MobiReader(object):
             elem.getparent().remove(elem)
         fname = self.name.encode('ascii', 'replace')
         fname = re.sub(r'[\x08\x15\0]+', '', fname)
+        if not fname:
+            fname = 'dummy'
         htmlfile = os.path.join(output_dir,
             ascii_filename(fname) + '.html')
         try:
@@ -564,6 +569,10 @@ class MobiReader(object):
                 for attr in self.IMAGE_ATTRS:
                     recindex = attrib.pop(attr, None) or recindex
                 if recindex is not None:
+                    try:
+                        recindex = '%05d'%int(recindex)
+                    except:
+                        pass
                     attrib['src'] = 'images/%s.jpg' % recindex
                 for attr in ('width', 'height'):
                     if attr in attrib:

src/calibre/ebooks/oeb/base.py

@@ -787,6 +787,8 @@ class Manifest(object):
             # Convert to Unicode and normalize line endings
             data = self.oeb.decode(data)
             data = self.oeb.html_preprocessor(data)
+            # There could be null bytes in data if it had � entities in it
+            data = data.replace('\0', '')
 
             # Remove DOCTYPE declaration as it messes up parsing
             # In particular, it causes tostring to insert xmlns

src/calibre/gui2/book_details.py

@@ -213,11 +213,13 @@ class BookInfo(QWebView):
         f = QFontInfo(QApplication.font(self.parent())).pixelSize()
         p = unicode(QApplication.palette().color(QPalette.Normal,
             QPalette.Base).name())
+        c = unicode(QApplication.palette().color(QPalette.Normal,
+                        QPalette.Text).name())
         templ = u'''\
         <html>
             <head>
             <style type="text/css">
-                body, td {background-color: %s; font-size: %dpx}
+                body, td {background-color: %s; font-size: %dpx; color: %s }
                 a { text-decoration: none; color: blue }
             </style>
             </head>
@@ -225,7 +227,7 @@ class BookInfo(QWebView):
             %%s
             </body>
         <html>
-        '''%(p, f)
+        '''%(p, f, c)
         if self.vertical:
             if comments:
                 rows += u'<tr><td colspan="2">%s</td></tr>'%comments

src/calibre/gui2/convert/bulk.py

@@ -47,6 +47,8 @@ class BulkConfig(Config):
                 self.show_pane)
         self.connect(self.groups, SIGNAL('entered(QModelIndex)'),
                 self.show_group_help)
+        rb = self.buttonBox.button(self.buttonBox.RestoreDefaults)
+        rb.setVisible(False)
         self.groups.setMouseTracking(True)
 
 

src/calibre/gui2/device.py

@@ -1014,7 +1014,13 @@ class DeviceMixin(object): # {{{
             self.status_bar.show_message(_('Sent by email:') + ', '.join(good),
                     5000)
             if remove:
-                self.library_view.model().delete_books_by_id(remove)
+                try:
+                    self.library_view.model().delete_books_by_id(remove)
+                except:
+                    # Probably the user deleted the files, in any case, failing
+                    # to delete the book is not catastrophic
+                    traceback.print_exc()
+
 
     def cover_to_thumbnail(self, data):
         ht = self.device_manager.device.THUMBNAIL_HEIGHT \

src/calibre/gui2/dialogs/metadata_bulk.py

@@ -240,13 +240,13 @@ class MetadataBulkDialog(QDialog, Ui_MetadataBulkDialog):
         self.writable_fields = ['']
         fm = self.db.field_metadata
         for f in fm:
-            if (f in ['author_sort'] or (
+            if (f in ['author_sort'] or
-                fm[f]['datatype'] in ['text', 'series'])
+                    (fm[f]['datatype'] in ['text', 'series']
-                    and fm[f].get('search_terms', None)
+                     and fm[f].get('search_terms', None)
-                    and f not in ['formats', 'ondevice']):
+                     and f not in ['formats', 'ondevice', 'sort'])):
                 self.all_fields.append(f)
                 self.writable_fields.append(f)
-            if fm[f]['datatype'] == 'composite':
+            if f in ['sort'] or fm[f]['datatype'] == 'composite':
                 self.all_fields.append(f)
         self.all_fields.sort()
         self.writable_fields.sort()
@@ -274,7 +274,6 @@ class MetadataBulkDialog(QDialog, Ui_MetadataBulkDialog):
         self.main_heading = _(
                  '<b>You can destroy your library using this feature.</b> '
                  'Changes are permanent. There is no undo function. '
-                 ' This feature is experimental, and there may be bugs. '
                  'You are strongly encouraged to back up your library '
                  'before proceeding.<p>'
                  'Search and replace in text fields using character matching '
@@ -338,7 +337,10 @@ class MetadataBulkDialog(QDialog, Ui_MetadataBulkDialog):
     def s_r_get_field(self, mi, field):
         if field:
             fm = self.db.metadata_for_field(field)
-            val = mi.get(field, None)
+            if field == 'sort':
+                val = mi.get('title_sort', None)
+            else:
+                val = mi.get(field, None)
             if val is None:
                 val = []
             elif not fm['is_multiple']:

src/calibre/gui2/dialogs/metadata_bulk.ui

@@ -400,7 +400,7 @@ Future conversion of these books will use the default settings.</string>
        </widget>
        <widget class="QWidget" name="tabWidgetPage3">
         <attribute name="title">
-         <string>&amp;Search and replace (experimental)</string>
+         <string>&amp;Search and replace</string>
         </attribute>
         <layout class="QGridLayout" name="vargrid">
          <property name="sizeConstraint">

src/calibre/gui2/dialogs/search.py

@@ -1,17 +1,75 @@
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
-import re
+
-from PyQt4.QtGui import QDialog
+import re, copy
+
+from PyQt4.QtGui import QDialog, QDialogButtonBox
 
 from calibre.gui2.dialogs.search_ui import Ui_Dialog
 from calibre.library.caches import CONTAINS_MATCH, EQUALS_MATCH
+from calibre.gui2 import gprefs
+
+box_values = {}
 
 class SearchDialog(QDialog, Ui_Dialog):
 
-    def __init__(self, *args):
+    def __init__(self, parent, db):
-        QDialog.__init__(self, *args)
+        QDialog.__init__(self, parent)
         self.setupUi(self)
         self.mc = ''
+        searchables = sorted(db.field_metadata.searchable_fields(),
+                             lambda x, y: cmp(x if x[0] != '#' else x[1:],
+                                              y if y[0] != '#' else y[1:]))
+        self.general_combo.addItems(searchables)
+
+        self.box_last_values = copy.deepcopy(box_values)
+        if self.box_last_values:
+            for k,v in self.box_last_values.items():
+                if k == 'general_index':
+                    continue
+                getattr(self, k).setText(v)
+            self.general_combo.setCurrentIndex(
+                    self.general_combo.findText(self.box_last_values['general_index']))
+
+        self.buttonBox.accepted.connect(self.advanced_search_button_pushed)
+        self.tab_2_button_box.accepted.connect(self.accept)
+        self.tab_2_button_box.rejected.connect(self.reject)
+        self.clear_button.clicked.connect(self.clear_button_pushed)
+        self.adv_search_used = False
+
+        current_tab = gprefs.get('advanced search dialog current tab', 0)
+        self.tabWidget.setCurrentIndex(current_tab)
+        self.tabWidget.currentChanged[int].connect(self.tab_changed)
+        self.tab_changed(current_tab)
+
+    def save_state(self):
+        gprefs['advanced search dialog current tab'] = \
+            self.tabWidget.currentIndex()
+
+    def accept(self):
+        self.save_state()
+        return QDialog.accept(self)
+
+    def reject(self):
+        self.save_state()
+        return QDialog.reject(self)
+
+    def tab_changed(self, idx):
+        if idx == 1:
+            self.tab_2_button_box.button(QDialogButtonBox.Ok).setDefault(True)
+        else:
+            self.buttonBox.button(QDialogButtonBox.Ok).setDefault(True)
+
+    def advanced_search_button_pushed(self):
+        self.adv_search_used = True
+        self.accept()
+
+    def clear_button_pushed(self):
+        self.title_box.setText('')
+        self.authors_box.setText('')
+        self.series_box.setText('')
+        self.tags_box.setText('')
+        self.general_box.setText('')
 
     def tokens(self, raw):
         phrases = re.findall(r'\s*".*?"\s*', raw)
@@ -21,6 +79,12 @@ class SearchDialog(QDialog, Ui_Dialog):
         return ['"' + self.mc + t + '"' for t in phrases + [r.strip() for r in raw.split()]]
 
     def search_string(self):
+        if self.adv_search_used:
+            return self.adv_search_string()
+        else:
+            return self.box_search_string()
+
+    def adv_search_string(self):
         mk = self.matchkind.currentIndex()
         if mk == CONTAINS_MATCH:
             self.mc = ''
@@ -56,3 +120,36 @@ class SearchDialog(QDialog, Ui_Dialog):
                 tok = '"%s"'%tok
             return tok
 
+    def box_search_string(self):
+        ans = []
+        self.box_last_values = {}
+        title = unicode(self.title_box.text()).strip()
+        self.box_last_values['title_box'] = title
+        if title:
+            ans.append('title:"' + title + '"')
+        author = unicode(self.authors_box.text()).strip()
+        self.box_last_values['authors_box'] = author
+        if author:
+            ans.append('author:"' + author + '"')
+        series = unicode(self.series_box.text()).strip()
+        self.box_last_values['series_box'] = series
+        if series:
+            ans.append('series:"' + series + '"')
+        self.mc = '='
+        tags = unicode(self.tags_box.text())
+        self.box_last_values['tags_box'] = tags
+        tags = self.tokens(tags)
+        if tags:
+            tags = ['tags:' + t for t in tags]
+            ans.append('(' + ' or '.join(tags) + ')')
+        general = unicode(self.general_box.text())
+        self.box_last_values['general_box'] = general
+        general_index = unicode(self.general_combo.currentText())
+        self.box_last_values['general_index'] = general_index
+        global box_values
+        box_values = copy.deepcopy(self.box_last_values)
+        if general:
+            ans.append(unicode(self.general_combo.currentText()) + ':"' + general + '"')
+        if ans:
+            return ' and '.join(ans)
+        return ''

src/calibre/gui2/dialogs/search.ui

@@ -1,195 +1,370 @@
-<ui version="4.0" >
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
  <class>Dialog</class>
- <widget class="QDialog" name="Dialog" >
+ <widget class="QDialog" name="Dialog">
-  <property name="geometry" >
+  <property name="geometry">
    <rect>
     <x>0</x>
     <y>0</y>
-    <width>667</width>
+    <width>731</width>
-    <height>391</height>
+    <height>411</height>
    </rect>
   </property>
-  <property name="windowTitle" >
+  <property name="windowTitle">
    <string>Advanced Search</string>
   </property>
-  <property name="windowIcon" >
+  <property name="windowIcon">
-   <iconset resource="../../../../resources/images.qrc" >
+   <iconset resource="../../../../resources/images.qrc">
     <normaloff>:/images/search.png</normaloff>:/images/search.png</iconset>
   </property>
-  <layout class="QVBoxLayout" name="verticalLayout_3" >
+  <layout class="QGridLayout" name="gridLayout_2">
-   <item>
+   <item row="0" column="0">
-    <widget class="QGroupBox" name="groupBox" >
+    <widget class="QLabel" name="label_5">
-     <property name="title" >
+     <property name="text">
-      <string>Find entries that have...</string>
+      <string>What kind of match to use:</string>
+     </property>
+     <property name="buddy">
+      <cstring>matchkind</cstring>
      </property>
-     <layout class="QVBoxLayout" name="verticalLayout" >
-      <item>
-       <layout class="QHBoxLayout" name="horizontalLayout" >
-        <item>
-         <widget class="QLabel" name="label" >
-          <property name="text" >
-           <string>&amp;All these words:</string>
-          </property>
-          <property name="buddy" >
-           <cstring>all</cstring>
-          </property>
-         </widget>
-        </item>
-        <item>
-         <widget class="QLineEdit" name="all" />
-        </item>
-       </layout>
-      </item>
-      <item>
-       <layout class="QHBoxLayout" name="horizontalLayout_2" >
-        <item>
-         <widget class="QLabel" name="label_2" >
-          <property name="text" >
-           <string>This exact &amp;phrase:</string>
-          </property>
-          <property name="buddy" >
-           <cstring>all</cstring>
-          </property>
-         </widget>
-        </item>
-        <item>
-         <widget class="QLineEdit" name="phrase" />
-        </item>
-       </layout>
-      </item>
-      <item>
-       <layout class="QHBoxLayout" name="horizontalLayout_3" >
-        <item>
-         <widget class="QLabel" name="label_3" >
-          <property name="text" >
-           <string>&amp;One or more of these words:</string>
-          </property>
-          <property name="buddy" >
-           <cstring>all</cstring>
-          </property>
-         </widget>
-        </item>
-        <item>
-         <widget class="QLineEdit" name="any" />
-        </item>
-       </layout>
-      </item>
-     </layout>
     </widget>
    </item>
-   <item>
+   <item row="0" column="1">
-    <widget class="QGroupBox" name="groupBox_2" >
+    <widget class="QComboBox" name="matchkind">
-     <property name="title" >
+     <item>
-      <string>But dont show entries that have...</string>
+      <property name="text">
-     </property>
+       <string>Contains: the word or phrase matches anywhere in the metadata field</string>
-     <layout class="QVBoxLayout" name="verticalLayout_2" >
+      </property>
-      <item>
+     </item>
-       <layout class="QHBoxLayout" name="horizontalLayout_4" >
+     <item>
-        <item>
+      <property name="text">
-         <widget class="QLabel" name="label_4" >
+       <string>Equals: the word or phrase must match the entire metadata field</string>
-          <property name="text" >
+      </property>
-           <string>Any of these &amp;unwanted words:</string>
+     </item>
-          </property>
+     <item>
-          <property name="buddy" >
+      <property name="text">
-           <cstring>all</cstring>
+       <string>Regular expression: the expression must match anywhere in the metadata field</string>
-          </property>
+      </property>
-         </widget>
+     </item>
-        </item>
-        <item>
-         <widget class="QLineEdit" name="none" />
-        </item>
-       </layout>
-      </item>
-     </layout>
     </widget>
    </item>
-   <item>
+   <item row="2" column="0" colspan="2">
-    <widget class="QGroupBox" name="groupBox" >
+    <widget class="QTabWidget" name="tabWidget">
-     <property name="maximumSize" >
+     <property name="currentIndex">
+      <number>0</number>
+     </property>
+     <widget class="QWidget" name="tab">
+      <attribute name="title">
+       <string>A&amp;dvanced Search</string>
+      </attribute>
+      <layout class="QGridLayout" name="gridLayout_3">
+       <item row="0" column="0">
+        <widget class="QGroupBox" name="groupBox">
+         <property name="title">
+          <string>Find entries that have...</string>
+         </property>
+         <layout class="QVBoxLayout" name="verticalLayout">
+          <item>
+           <layout class="QHBoxLayout" name="horizontalLayout">
+            <item>
+             <widget class="QLabel" name="label">
+              <property name="text">
+               <string>&amp;All these words:</string>
+              </property>
+              <property name="buddy">
+               <cstring>all</cstring>
+              </property>
+             </widget>
+            </item>
+            <item>
+             <widget class="QLineEdit" name="all"/>
+            </item>
+           </layout>
+          </item>
+          <item>
+           <layout class="QHBoxLayout" name="horizontalLayout_2">
+            <item>
+             <widget class="QLabel" name="label_2">
+              <property name="text">
+               <string>This exact &amp;phrase:</string>
+              </property>
+              <property name="buddy">
+               <cstring>all</cstring>
+              </property>
+             </widget>
+            </item>
+            <item>
+             <widget class="QLineEdit" name="phrase"/>
+            </item>
+           </layout>
+          </item>
+          <item>
+           <layout class="QHBoxLayout" name="horizontalLayout_3">
+            <item>
+             <widget class="QLabel" name="label_3">
+              <property name="text">
+               <string>&amp;One or more of these words:</string>
+              </property>
+              <property name="buddy">
+               <cstring>all</cstring>
+              </property>
+             </widget>
+            </item>
+            <item>
+             <widget class="QLineEdit" name="any"/>
+            </item>
+           </layout>
+          </item>
+         </layout>
+        </widget>
+       </item>
+       <item row="1" column="0">
+        <widget class="QGroupBox" name="groupBox_2">
+         <property name="title">
+          <string>But dont show entries that have...</string>
+         </property>
+         <layout class="QVBoxLayout" name="verticalLayout_2">
+          <item>
+           <layout class="QHBoxLayout" name="horizontalLayout_4">
+            <item>
+             <widget class="QLabel" name="label_4">
+              <property name="text">
+               <string>Any of these &amp;unwanted words:</string>
+              </property>
+              <property name="buddy">
+               <cstring>all</cstring>
+              </property>
+             </widget>
+            </item>
+            <item>
+             <widget class="QLineEdit" name="none"/>
+            </item>
+           </layout>
+          </item>
+          <item>
+           <widget class="QGroupBox" name="groupBox">
+            <property name="maximumSize">
+             <size>
+              <width>16777215</width>
+              <height>60</height>
+             </size>
+            </property>
+            <layout class="QHBoxLayout" name="horizontalLayout_5">
+             <item>
+              <widget class="QLabel" name="label_51">
+               <property name="sizePolicy">
+                <sizepolicy hsizetype="Preferred" vsizetype="Preferred">
+                 <horstretch>40</horstretch>
+                 <verstretch>0</verstretch>
+                </sizepolicy>
+               </property>
+               <property name="text">
+                <string/>
+               </property>
+               <property name="buddy">
+                <cstring>matchkind</cstring>
+               </property>
+              </widget>
+             </item>
+            </layout>
+           </widget>
+          </item>
+          <item>
+           <widget class="QLabel" name="label_6">
+            <property name="maximumSize">
+             <size>
+              <width>16777215</width>
+              <height>30</height>
+             </size>
+            </property>
+            <property name="text">
+             <string>See the &lt;a href=&quot;http://calibre-ebook.com/user_manual/gui.html#the-search-interface&quot;&gt;User Manual&lt;/a&gt; for more help</string>
+            </property>
+            <property name="openExternalLinks">
+             <bool>true</bool>
+            </property>
+           </widget>
+          </item>
+         </layout>
+        </widget>
+       </item>
+       <item row="2" column="0">
+        <spacer name="verticalSpacer_2">
+         <property name="orientation">
+          <enum>Qt::Vertical</enum>
+         </property>
+         <property name="sizeHint" stdset="0">
+          <size>
+           <width>20</width>
+           <height>40</height>
+          </size>
+         </property>
+        </spacer>
+       </item>
+       <item row="3" column="0">
+        <widget class="QDialogButtonBox" name="buttonBox">
+         <property name="orientation">
+          <enum>Qt::Horizontal</enum>
+         </property>
+         <property name="standardButtons">
+          <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
+         </property>
+        </widget>
+       </item>
+      </layout>
+     </widget>
+     <widget class="QWidget" name="tab_2">
+      <attribute name="title">
+       <string>Titl&amp;e/Author/Series ...</string>
+      </attribute>
+      <layout class="QGridLayout" name="gridLayout">
+       <item row="1" column="0">
+        <widget class="QLabel" name="label_7">
+         <property name="text">
+          <string>&amp;Title:</string>
+         </property>
+         <property name="buddy">
+          <cstring>title_box</cstring>
+         </property>
+        </widget>
+       </item>
+       <item row="1" column="1">
+        <widget class="QLineEdit" name="title_box">
+         <property name="toolTip">
+          <string>Enter the title.</string>
+         </property>
+        </widget>
+       </item>
+       <item row="2" column="0">
+        <widget class="QLabel" name="label_8">
+         <property name="text">
+          <string>&amp;Author:</string>
+         </property>
+         <property name="buddy">
+          <cstring>authors_box</cstring>
+         </property>
+        </widget>
+       </item>
+       <item row="3" column="0">
+        <widget class="QLabel" name="label_9">
+         <property name="text">
+          <string>&amp;Series:</string>
+         </property>
+         <property name="buddy">
+          <cstring>series_box</cstring>
+         </property>
+        </widget>
+       </item>
+       <item row="4" column="0">
+        <widget class="QLabel" name="label_10">
+         <property name="text">
+          <string>Ta&amp;gs:</string>
+         </property>
+         <property name="buddy">
+          <cstring>tags_box</cstring>
+         </property>
+        </widget>
+       </item>
+       <item row="2" column="1">
+        <widget class="QLineEdit" name="authors_box">
+         <property name="toolTip">
+          <string>Enter an author's name. Only one author can be used.</string>
+         </property>
+        </widget>
+       </item>
+       <item row="3" column="1">
+        <widget class="QLineEdit" name="series_box">
+         <property name="toolTip">
+          <string>Enter a series name, without an index. Only one series name can be used.</string>
+         </property>
+        </widget>
+       </item>
+       <item row="4" column="1">
+        <widget class="QLineEdit" name="tags_box">
+         <property name="toolTip">
+          <string>Enter tags separated by spaces</string>
+         </property>
+        </widget>
+       </item>
+       <item row="6" column="1">
+        <widget class="QLineEdit" name="general_box"/>
+       </item>
+       <item row="6" column="0">
+        <widget class="QComboBox" name="general_combo"/>
+       </item>
+       <item row="8" column="0" colspan="2">
+        <layout class="QHBoxLayout" name="horizontalLayout_6">
+         <item>
+          <widget class="QPushButton" name="clear_button">
+           <property name="text">
+            <string>&amp;Clear</string>
+           </property>
+          </widget>
+         </item>
+         <item>
+          <widget class="QDialogButtonBox" name="tab_2_button_box">
+           <property name="standardButtons">
+            <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
+           </property>
+          </widget>
+         </item>
+        </layout>
+       </item>
+       <item row="7" column="1">
+        <spacer name="verticalSpacer">
+         <property name="orientation">
+          <enum>Qt::Vertical</enum>
+         </property>
+         <property name="sizeHint" stdset="0">
+          <size>
+           <width>20</width>
+           <height>40</height>
+          </size>
+         </property>
+        </spacer>
+       </item>
+       <item row="0" column="0" colspan="2">
+        <widget class="QLabel" name="label_11">
+         <property name="text">
+          <string>Search only in specific fields:</string>
+         </property>
+        </widget>
+       </item>
+      </layout>
+     </widget>
+    </widget>
+   </item>
+   <item row="1" column="1">
+    <spacer name="verticalSpacer_3">
+     <property name="orientation">
+      <enum>Qt::Vertical</enum>
+     </property>
+     <property name="sizeHint" stdset="0">
       <size>
-       <width>16777215</width>
+       <width>20</width>
-       <height>60</height>
+       <height>40</height>
       </size>
      </property>
-     <layout class="QHBoxLayout" name="horizontalLayout_5" >
+    </spacer>
-      <item>
-       <widget class="QLabel" name="label_5" >
-        <property name="text" >
-         <string>What kind of match to use:</string>
-        </property>
-        <property name="buddy" >
-         <cstring>matchkind</cstring>
-        </property>
-       </widget>
-      </item>
-      <item>
-       <widget class="QComboBox" name="matchkind">
-        <item>
-         <property name="text">
-          <string>Contains: the word or phrase matches anywhere in the metadata</string>
-         </property>
-        </item>
-        <item>
-         <property name="text">
-          <string>Equals: the word or phrase must match an entire metadata field</string>
-         </property>
-        </item>
-        <item>
-         <property name="text">
-          <string>Regular expression: the expression must match anywhere in the metadata</string>
-         </property>
-        </item>
-       </widget>
-      </item>
-      <item>
-       <widget class="QLabel" name="label_51" >
-        <property name="sizePolicy">
-         <sizepolicy hsizetype="Preferred" vsizetype="Preferred">
-          <horstretch>40</horstretch>
-          <verstretch>0</verstretch>
-         </sizepolicy>
-        </property>
-        <property name="text" >
-         <string> </string>
-        </property>
-        <property name="buddy" >
-         <cstring>matchkind</cstring>
-        </property>
-       </widget>
-      </item>
-     </layout>
-    </widget>
-   </item>
-   <item>
-    <widget class="QLabel" name="label_6" >
-     <property name="maximumSize" >
-      <size>
-       <width>16777215</width>
-       <height>30</height>
-      </size>
-     </property>
-     <property name="text" >
-      <string>See the &lt;a href="http://calibre-ebook.com/user_manual/gui.html#the-search-interface">User Manual&lt;/a> for more help</string>
-     </property>
-     <property name="openExternalLinks" >
-      <bool>true</bool>
-     </property>
-    </widget>
-   </item>
-   <item>
-    <widget class="QDialogButtonBox" name="buttonBox" >
-     <property name="orientation" >
-      <enum>Qt::Horizontal</enum>
-     </property>
-     <property name="standardButtons" >
-      <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
-     </property>
-    </widget>
    </item>
   </layout>
  </widget>
+ <tabstops>
+  <tabstop>all</tabstop>
+  <tabstop>phrase</tabstop>
+  <tabstop>any</tabstop>
+  <tabstop>none</tabstop>
+  <tabstop>buttonBox</tabstop>
+  <tabstop>title_box</tabstop>
+  <tabstop>authors_box</tabstop>
+  <tabstop>series_box</tabstop>
+  <tabstop>tags_box</tabstop>
+  <tabstop>general_combo</tabstop>
+  <tabstop>general_box</tabstop>
+  <tabstop>clear_button</tabstop>
+  <tabstop>tab_2_button_box</tabstop>
+ </tabstops>
  <resources>
-  <include location="../../../../resources/images.qrc" />
+  <include location="../../../../resources/images.qrc"/>
  </resources>
  <connections>
   <connection>
@@ -198,11 +373,11 @@
    <receiver>Dialog</receiver>
    <slot>accept()</slot>
    <hints>
-    <hint type="sourcelabel" >
+    <hint type="sourcelabel">
      <x>248</x>
      <y>254</y>
     </hint>
-    <hint type="destinationlabel" >
+    <hint type="destinationlabel">
      <x>157</x>
      <y>274</y>
     </hint>
@@ -214,11 +389,11 @@
    <receiver>Dialog</receiver>
    <slot>reject()</slot>
    <hints>
-    <hint type="sourcelabel" >
+    <hint type="sourcelabel">
      <x>316</x>
      <y>260</y>
     </hint>
-    <hint type="destinationlabel" >
+    <hint type="destinationlabel">
      <x>286</x>
      <y>274</y>
     </hint>

src/calibre/gui2/layout.py

@@ -167,6 +167,7 @@ class SearchBar(QWidget): # {{{
         x.setSizePolicy(QSizePolicy.Minimum, QSizePolicy.Minimum)
 
         parent.advanced_search_button = x = QToolButton(self)
+        parent.advanced_search_button.setShortcut(_("Shift+Ctrl+F"))
         x.setIcon(QIcon(I('search.png')))
         l.addWidget(x)
         x.setToolTip(_("Advanced search"))

src/calibre/gui2/library/views.py

@@ -50,10 +50,11 @@ class BooksView(QTableView): # {{{
     def __init__(self, parent, modelcls=BooksModel):
         QTableView.__init__(self, parent)
 
-        self.setEditTriggers(self.SelectedClicked|self.EditKeyPressed)
+        self.setEditTriggers(self.EditKeyPressed)
         if tweaks['doubleclick_on_library_view'] == 'edit_cell':
             self.setEditTriggers(self.DoubleClicked|self.editTriggers())
         elif tweaks['doubleclick_on_library_view'] == 'open_viewer':
+            self.setEditTriggers(self.SelectedClicked|self.editTriggers())
             self.doubleClicked.connect(parent.iactions['View'].view_triggered)
 
         self.drag_allowed = True

src/calibre/gui2/preferences/main.py

@@ -101,9 +101,9 @@ class Category(QWidget): # {{{
             ac.setStatusTip(p.description)
             self.actions.append(ac)
             w = self.bar.widgetForAction(ac)
-            w.setStyleSheet('QToolButton { margin-right: 20px; min-width: 100px }')
             w.setCursor(Qt.PointingHandCursor)
             w.setAutoRaise(True)
+            w.setMinimumWidth(100)
 
     def triggered(self, plugin, *args):
         self.plugin_activated.emit(plugin)

src/calibre/gui2/search_box.py

@@ -392,7 +392,7 @@ class SearchBoxMixin(object):
         self.tags_view.clear()
 
     def do_advanced_search(self, *args):
-        d = SearchDialog(self)
+        d = SearchDialog(self, self.library_view.model().db)
         if d.exec_() == QDialog.Accepted:
             self.search.set_search_string(d.search_string())
 

src/calibre/gui2/tools.py

@@ -299,7 +299,7 @@ def generate_catalog(parent, dbspec, ids, device_manager):
         ]
     out.close()
 
-    # This returns to gui2.ui:generate_catalog()
+    # This returns to gui2.actions.catalog:generate_catalog()
     # Which then calls gui2.convert.gui_conversion:gui_catalog() with the args inline
     return 'gui_catalog', args, _('Generate catalog'), out.name, d.catalog_sync, \
             d.catalog_title

src/calibre/library/caches.py

@@ -625,7 +625,11 @@ class ResultCache(SearchQueryParser): # {{{
     # }}}
 
     def remove(self, id):
-        self._data[id] = None
+        try:
+            self._data[id] = None
+        except IndexError:
+            # id is out of bounds, no point setting it to None anyway
+            pass
         try:
             self._map.remove(id)
         except ValueError:

src/calibre/library/catalog.py

@@ -832,6 +832,9 @@ class EPUB_MOBI(CatalogPlugin):
             '[<source>] : Source of content (e.g., Amazon, Project Gutenberg).  Do not create genre
 
         - Program flow
+            gui2.actions.catalog:generate_catalog()
+            gui2.tools:generate_catalog() or library.cli:command_catalog()
+            called from gui2.convert.gui_conversion:gui_catalog()
             catalog = Catalog(notification=Reporter())
             catalog.createDirectoryStructure()
             catalog.copyResources()
@@ -883,6 +886,7 @@ class EPUB_MOBI(CatalogPlugin):
             self.__htmlFileList = []
             self.__markerTags = self.getMarkerTags()
             self.__ncxSoup = None
+            self.__output_profile = None
             self.__playOrder = 1
             self.__plugin = plugin
             self.__progressInt = 0.0
@@ -897,6 +901,12 @@ class EPUB_MOBI(CatalogPlugin):
             self.__useSeriesPrefixInTitlesSection = False
             self.__verbose = opts.verbose
 
+            from calibre.customize.ui import output_profiles
+            for profile in output_profiles():
+                if profile.short_name == self.opts.output_profile:
+                    self.__output_profile = profile
+                    break
+
             # Tweak build steps based on optional sections:  1 call for HTML, 1 for NCX
             if self.opts.generate_titles:
                 self.__totalSteps += 2
@@ -1168,10 +1178,14 @@ class EPUB_MOBI(CatalogPlugin):
                 return property(fget=fget, fset=fset)
 
             @dynamic_property
+            def MISSING_SYMBOL(self):
+                def fget(self):
+                    return self.__output_profile.missing_char
+                return property(fget=fget)
+            @dynamic_property
             def NOT_READ_SYMBOL(self):
                 def fget(self):
-                    return '<span style="color:white">&#x2713;</span>' if self.generateForKindle else \
+                    return '<span style="color:white">%s</span>' % self.__output_profile.read_char
-                           '<span style="color:white">%s</span>' % self.opts.read_tag
                 return property(fget=fget)
             @dynamic_property
             def READING_SYMBOL(self):
@@ -1182,18 +1196,17 @@ class EPUB_MOBI(CatalogPlugin):
             @dynamic_property
             def READ_SYMBOL(self):
                 def fget(self):
-                    return '<span style="color:black">&#x2713;</span>' if self.generateForKindle else \
+                    return self.__output_profile.read_char
-                           '<span style="color:black">%s</span>' % self.opts.read_tag
                 return property(fget=fget)
             @dynamic_property
             def FULL_RATING_SYMBOL(self):
                 def fget(self):
-                    return "&#9733;" if self.generateForKindle else "*"
+                    return self.__output_profile.ratings_char
                 return property(fget=fget)
             @dynamic_property
             def EMPTY_RATING_SYMBOL(self):
                 def fget(self):
-                    return "&#9734;" if self.generateForKindle else ' '
+                    return self.__output_profile.empty_ratings_char
                 return property(fget=fget)
             @dynamic_property
             def READ_PROGRESS_SYMBOL(self):
@@ -1626,13 +1639,16 @@ class EPUB_MOBI(CatalogPlugin):
                                                 self.generateAuthorAnchor(title['author']))
                 aTag.insert(0, title['author'])
 
-                # Prefix author with read/reading/none symbol
+                # Prefix author with read|reading|none symbol or missing symbol
-                if title['read']:
+                if 'formats' in title and title['formats']:
-                    authorTag.insert(0, NavigableString(self.READ_SYMBOL + "by "))
+                    if title['read']:
-                elif self.opts.connected_kindle and title['id'] in self.bookmarked_books:
+                        authorTag.insert(0, NavigableString(self.READ_SYMBOL + " by "))
-                    authorTag.insert(0, NavigableString(self.READING_SYMBOL + " by "))
+                    elif self.opts.connected_kindle and title['id'] in self.bookmarked_books:
+                        authorTag.insert(0, NavigableString(self.READING_SYMBOL + " by "))
+                    else:
+                        authorTag.insert(0, NavigableString(self.NOT_READ_SYMBOL + " by "))
                 else:
-                    authorTag.insert(0, NavigableString(self.NOT_READ_SYMBOL + "by "))
+                    authorTag.insert(0, NavigableString(self.MISSING_SYMBOL + " by "))
                 authorTag.insert(1, aTag)
 
                 '''
@@ -1666,7 +1682,7 @@ class EPUB_MOBI(CatalogPlugin):
                     fontTag['style'] = 'color:white;font-size:large'
                     if self.opts.fmt == 'epub':
                         fontTag['style'] += ';opacity: 0.0'
-                    fontTag.insert(0, NavigableString("by "))
+                    fontTag.insert(0, NavigableString(" by "))
                     tagsTag.insert(ttc, fontTag)
                     ttc += 1
 
@@ -1819,21 +1835,27 @@ class EPUB_MOBI(CatalogPlugin):
                 pBookTag = Tag(soup, "p")
                 ptc = 0
 
-                #  book with read/reading/unread symbol
+                #  book with read|reading|unread symbol or missing symbol
-                if book['read']:
+                if 'formats' in book and book['formats']:
-                    # check mark
+                    if book['read']:
-                    pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
+                        # check mark
-                    pBookTag['class'] = "read_book"
+                        pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
-                    ptc += 1
+                        pBookTag['class'] = "read_book"
-                elif book['id'] in self.bookmarked_books:
+                        ptc += 1
-                    pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
+                    elif book['id'] in self.bookmarked_books:
-                    pBookTag['class'] = "read_book"
+                        pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
-                    ptc += 1
+                        pBookTag['class'] = "read_book"
+                        ptc += 1
+                    else:
+                        # hidden check mark
+                        pBookTag['class'] = "unread_book"
+                        pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                        ptc += 1
                 else:
-                    # hidden check mark
+                        # missing formats
-                    pBookTag['class'] = "unread_book"
+                        pBookTag['class'] = "missing_book"
-                    pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                        pBookTag.insert(ptc,NavigableString(self.MISSING_SYMBOL))
-                    ptc += 1
+                        ptc += 1
 
                 # Link to book
                 aTag = Tag(soup, "a")
@@ -1988,20 +2010,26 @@ class EPUB_MOBI(CatalogPlugin):
                 pBookTag = Tag(soup, "p")
                 ptc = 0
 
-                #  book with read/reading/unread symbol
+                #  book with read|reading|unread symbol or missing symbol
-                if book['read']:
+                if 'formats' in book and book['formats']:
-                    # check mark
+                    if book['read']:
-                    pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
+                        # check mark
-                    pBookTag['class'] = "read_book"
+                        pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
-                    ptc += 1
+                        pBookTag['class'] = "read_book"
-                elif book['id'] in self.bookmarked_books:
+                        ptc += 1
-                    pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
+                    elif book['id'] in self.bookmarked_books:
-                    pBookTag['class'] = "read_book"
+                        pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
-                    ptc += 1
+                        pBookTag['class'] = "read_book"
+                        ptc += 1
+                    else:
+                        # hidden check mark
+                        pBookTag['class'] = "unread_book"
+                        pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                        ptc += 1
                 else:
-                    # hidden check mark
+                    # missing book
-                    pBookTag['class'] = "unread_book"
+                    pBookTag['class'] = "missing_book"
-                    pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                    pBookTag.insert(ptc,NavigableString(self.MISSING_SYMBOL))
                     ptc += 1
 
                 aTag = Tag(soup, "a")
@@ -2116,20 +2144,26 @@ class EPUB_MOBI(CatalogPlugin):
                         pBookTag = Tag(soup, "p")
                         ptc = 0
 
-                        #  book with read/reading/unread symbol
+                        #  book with read|reading|unread symbol or missing symbol
-                        if new_entry['read']:
+                        if 'formats' in new_entry and new_entry['formats']:
-                            # check mark
+                            if new_entry['read']:
-                            pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
+                                # check mark
-                            pBookTag['class'] = "read_book"
+                                pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
-                            ptc += 1
+                                pBookTag['class'] = "read_book"
-                        elif new_entry['id'] in self.bookmarked_books:
+                                ptc += 1
-                            pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
+                            elif new_entry['id'] in self.bookmarked_books:
-                            pBookTag['class'] = "read_book"
+                                pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
-                            ptc += 1
+                                pBookTag['class'] = "read_book"
+                                ptc += 1
+                            else:
+                                # hidden check mark
+                                pBookTag['class'] = "unread_book"
+                                pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                                ptc += 1
                         else:
-                            # hidden check mark
+                            # missing book
-                            pBookTag['class'] = "unread_book"
+                            pBookTag['class'] = "missing_book"
-                            pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                            pBookTag.insert(ptc,NavigableString(self.MISSING_SYMBOL))
                             ptc += 1
 
                         aTag = Tag(soup, "a")
@@ -2162,20 +2196,26 @@ class EPUB_MOBI(CatalogPlugin):
                         pBookTag = Tag(soup, "p")
                         ptc = 0
 
-                        #  book with read/reading/unread symbol
+                        #  book with read|reading|unread symbol or missing symbol
-                        if new_entry['read']:
+                        if 'formats' in new_entry and new_entry['formats']:
-                            # check mark
+                            if new_entry['read']:
-                            pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
+                                # check mark
-                            pBookTag['class'] = "read_book"
+                                pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
-                            ptc += 1
+                                pBookTag['class'] = "read_book"
-                        elif new_entry['id'] in self.bookmarked_books:
+                                ptc += 1
-                            pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
+                            elif new_entry['id'] in self.bookmarked_books:
-                            pBookTag['class'] = "read_book"
+                                pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
-                            ptc += 1
+                                pBookTag['class'] = "read_book"
+                                ptc += 1
+                            else:
+                                # hidden check mark
+                                pBookTag['class'] = "unread_book"
+                                pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                                ptc += 1
                         else:
-                            # hidden check mark
+                            # missing book
-                            pBookTag['class'] = "unread_book"
+                            pBookTag['class'] = "missing_book"
-                            pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                            pBookTag.insert(ptc,NavigableString(self.MISSING_SYMBOL))
                             ptc += 1
 
                         aTag = Tag(soup, "a")
@@ -2611,19 +2651,26 @@ class EPUB_MOBI(CatalogPlugin):
                 else:
                     book['read'] = False
 
-                if book['read']:
+                #  book with read|reading|unread symbol or missing symbol
-                    # check mark
+                if 'formats' in book and book['formats']:
-                    pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
+                    if book['read']:
-                    pBookTag['class'] = "read_book"
+                        # check mark
-                    ptc += 1
+                        pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
-                elif book['id'] in self.bookmarked_books:
+                        pBookTag['class'] = "read_book"
-                    pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
+                        ptc += 1
-                    pBookTag['class'] = "read_book"
+                    elif book['id'] in self.bookmarked_books:
-                    ptc += 1
+                        pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
+                        pBookTag['class'] = "read_book"
+                        ptc += 1
+                    else:
+                        # hidden check mark
+                        pBookTag['class'] = "unread_book"
+                        pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                        ptc += 1
                 else:
-                    # hidden check mark
+                    # missing book
-                    pBookTag['class'] = "unread_book"
+                    pBookTag['class'] = "missing_book"
-                    pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                    pBookTag.insert(ptc,NavigableString(self.MISSING_SYMBOL))
                     ptc += 1
 
                 aTag = Tag(soup, "a")
@@ -2702,6 +2749,8 @@ class EPUB_MOBI(CatalogPlugin):
                         this_book['title'] = book['title']
                         this_book['author_sort'] = book['author_sort'].capitalize()
                         this_book['read'] = book['read']
+                        if 'formats' in book:
+                            this_book['formats'] = book['formats']
                         this_book['id'] = book['id']
                         this_book['series'] = book['series']
                         normalized_tag = self.genre_tags_dict[friendly_tag]
@@ -4103,20 +4152,26 @@ class EPUB_MOBI(CatalogPlugin):
                 pBookTag = Tag(soup, "p")
                 ptc = 0
 
-                #  book with read/reading/unread symbol
+                #  book with read|reading|unread symbol or missing symbol
-                if book['read']:
+                if 'formats' in book and book['formats']:
-                    # check mark
+                    if book['read']:
-                    pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
+                        # check mark
-                    pBookTag['class'] = "read_book"
+                        pBookTag.insert(ptc,NavigableString(self.READ_SYMBOL))
-                    ptc += 1
+                        pBookTag['class'] = "read_book"
-                elif book['id'] in self.bookmarked_books:
+                        ptc += 1
-                    pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
+                    elif book['id'] in self.bookmarked_books:
-                    pBookTag['class'] = "read_book"
+                        pBookTag.insert(ptc,NavigableString(self.READING_SYMBOL))
-                    ptc += 1
+                        pBookTag['class'] = "read_book"
+                        ptc += 1
+                    else:
+                        # hidden check mark
+                        pBookTag['class'] = "unread_book"
+                        pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                        ptc += 1
                 else:
-                    # hidden check mark
+                    # missing book
-                    pBookTag['class'] = "unread_book"
+                    pBookTag['class'] = "missing_book"
-                    pBookTag.insert(ptc,NavigableString(self.NOT_READ_SYMBOL))
+                    pBookTag.insert(ptc,NavigableString(self.MISSING_SYMBOL))
                     ptc += 1
 
                 # Add the book title
@@ -4575,7 +4630,8 @@ class EPUB_MOBI(CatalogPlugin):
 
         if opts.connected_device['name'] and 'kindle' in opts.connected_device['name'].lower():
             opts.connected_kindle = True
-            if opts.connected_device['serial'] and opts.connected_device['serial'][:4] in ['B004','B005']:
+            if opts.connected_device['serial'] and \
+               opts.connected_device['serial'][:4] in ['B004','B005']:
                 op = "kindle_dx"
             else:
                 op = "kindle"
@@ -4638,7 +4694,8 @@ class EPUB_MOBI(CatalogPlugin):
         build_log.append(" opts:")
         for key in keys:
             if key in ['catalog_title','authorClip','connected_kindle','descriptionClip',
-                       'exclude_genre','exclude_tags','note_tag','numbers_as_text','read_tag',
+                       'exclude_genre','exclude_tags','note_tag','numbers_as_text',
+                       'output_profile','read_tag',
                        'search_text','sort_by','sort_descriptions_by_author','sync']:
                 build_log.append("  %s: %s" % (key, opts_dict[key]))
 

src/calibre/library/server/mobile.py

@@ -235,7 +235,7 @@ class MobileServer(object):
                                              no_tag_count=True)
             book['title'] = record[FM['title']]
             for x in ('timestamp', 'pubdate'):
-                book[x] = strftime('%b, %Y', record[FM[x]])
+                book[x] = strftime('%d %b, %Y', record[FM[x]])
             book['id'] = record[FM['id']]
             books.append(book)
             for key in CKEYS:

src/calibre/libunrar.py

@@ -269,3 +269,16 @@ def extract_member(path, match=re.compile(r'\.(jpg|jpeg|gif|png)\s*$', re.I),
                 path = _extract_member(path, match, name)
                 return path, open(path, 'rb').read()
 
+def extract_first_alphabetically(path):
+    if hasattr(path, 'read'):
+        data = path.read()
+        f = NamedTemporaryFile(suffix='.rar')
+        f.write(data)
+        f.flush()
+        path = f.name
+
+    names_ = [x for x in names(path) if os.path.splitext(x)[1][1:].lower() in
+            ('png', 'jpg', 'jpeg', 'gif')]
+    names_.sort()
+    return extract_member(path, name=names_[0], match=None)
+

src/calibre/libunzip.py

@@ -43,9 +43,12 @@ def extract(filename, dir):
     zf = zipfile.ZipFile( filename )
     zf.extractall(dir)
 
-def extract_member(filename, match=re.compile(r'\.(jpg|jpeg|gif|png)\s*$', re.I)):
+def extract_member(filename, match=re.compile(r'\.(jpg|jpeg|gif|png)\s*$',
+    re.I), sort_alphabetically=False):
     zf = zipfile.ZipFile(filename)
-    names = zf.namelist()
+    names = list(zf.namelist())
+    if sort_alphabetically:
+        names.sort()
     for name in names:
         if match.search(name):
             return name, zf.read(name)

src/calibre/manual/gui.rst

@@ -380,6 +380,8 @@ Calibre has several keyboard shortcuts to save you time and mouse movement. Thes
       - Show books in the same series as current book
     * - :kbd:`/, Ctrl+F` 
       - Focus the search bar
+    * - :kbd:`Shift+Ctrl+F`
+      - Open the advanced search dialog
     * - :kbd:`Ctrl+D` 
       - Download metadata and shortcuts
     * - :kbd:`Ctrl+R` 

src/odf/odf2xhtml.py

@@ -21,15 +21,14 @@
 #import pdb
 #pdb.set_trace()
 import zipfile
-import xml.sax
 from xml.sax import handler, expatreader
 from xml.sax.xmlreader import InputSource
 from xml.sax.saxutils import escape, quoteattr
 from cStringIO import StringIO
 
-from namespaces import ANIMNS, CHARTNS, CONFIGNS, DCNS, DR3DNS, DRAWNS, FONS, \
+from namespaces import DCNS, DRAWNS, FONS, \
-  FORMNS, MATHNS, METANS, NUMBERNS, OFFICENS, PRESENTATIONNS, SCRIPTNS, \
+  METANS, NUMBERNS, OFFICENS, PRESENTATIONNS, \
-  SMILNS, STYLENS, SVGNS, TABLENS, TEXTNS, XLINKNS
+  STYLENS, SVGNS, TABLENS, TEXTNS, XLINKNS
 
 # Handling of styles
 #
@@ -526,7 +525,8 @@ class ODF2XHTML(handler.ContentHandler):
 
     def get_anchor(self, name):
         if not self.anchors.has_key(name):
-            self.anchors[name] = "anchor%03d" % (len(self.anchors) + 1)
+            # Changed by Kovid
+            self.anchors[name] = "anchor%d" % (len(self.anchors) + 1)
         return self.anchors.get(name)
 
 
@@ -1025,9 +1025,13 @@ class ODF2XHTML(handler.ContentHandler):
         if level < 1: level = 1
         lev = self.headinglevels[1:level+1]
         outline = '.'.join(map(str,lev) )
-        anchor = self.get_anchor("%s.%s" % ( outline, ''.join(self.data)))
+        tail = ''.join(self.data)
+        anchor = self.get_anchor("%s.%s" % ( outline, tail))
+        anchor2 = self.get_anchor(tail) # Added by kovid to fix #7506
         self.opentag('a', {'id': anchor} )
         self.closetag('a', False)
+        self.opentag('a', {'id': anchor2} )
+        self.closetag('a', False)
         self.closetag('h%s' % level)
         self.purgedata()