Sync to trunk.

Changelog.yaml

@@ -19,6 +19,94 @@
 #  new recipes:
 #    - title: 
 
+- version: 0.8.22
+  date: 2011-10-14
+
+  new features:
+    - title: "Input plugin for OCR-ed DJVU files (i.e. .djvu files that contain text. Only the text is converted)"
+      type: major
+
+    - title: "Driver for the SONY PRS T1"
+
+    - title: "Add a 'Back' button to the metadata download dialog while downloading covers, so that you can go back and select a different match if you dont lke the covers, instead of having to re-do the entire download."
+      tickets: [855055]
+
+    - title: "Add an option in Preferences->Saving to disk to not show files in file browser after saving to disk"
+
+    - title: "Get Books: Add the amazon.fr store. Remove leading 'by' from author names. Fix encoding issues with non English titles/names"
+
+    - title: "Driver for Onyx BOOX A61S/X61S"
+      tickets: [872741] 
+
+    - title: "Kobo: Add support for uploading new covers to the device without converting the ePub. You can just resend the book to have the cover updated"
+
+    - title: "Make it a little harder to ignore the fact that there are multiple toolbars when customizing toolbars"
+      tickets: [864589]
+  
+  bug fixes:
+    - title:   "MOBI Input: Remove invalid tags of the form <xyz: >"
+      tickets: [872883]
+
+    - title: "calibredb add_format does not refresh running calibre instance"
+      tickets: [872961] 
+
+    - title: "Conversion pipeline: Translate <font face> to CSS font-family"
+      tickets: [871388]
+
+    - title: "When sending email add a Date: header so that amavis does not consider the emails to be spam"
+
+    - title: "Fix for the problem where setting the restriction to an empty current search clears the restriction box but does not clear the restriction." 
+      tickets: [871921]
+
+    - title: "Fix generation of column coloring rules for date/time columns"
+    
+    - title: "Fix plugboard problem where customizations to formats accepted by a device were ignored."
+    
+    - title: "Enable adding of various actions to the toolbar when device is connected (they had been erroneously marked as being non-addable)"
+
+    - title: "Fixable content in library check is not hidden after repair"
+      tickets: [864096]
+
+    - title: "Catalog generation: Handle a corrupted thumbnail cache."
+
+    - title: "Do not error out when user clicks stop selected job with no job selected."
+      tickets: [863766]
+
+  improved recipes:
+    - automatiseringgids 
+    - CNET
+    - Geek and Poke
+    - Gosc Niedzielny
+    - Dilbert
+    - Economist
+    - Ming Pao
+    - Metro UK
+    - Heise Online
+    - FAZ.net
+    - Houston Chronicle
+    - Slate
+    - Descopera
+
+  new recipes:
+    - title: WoW Insider 
+      author: Krittika Goyal
+
+    - title: Merco Press and Penguin news
+      author: Russell Phillips
+
+    - title: Defense News
+      author: Darko Miletic
+
+    - title: Revista Piaui 
+      author: Eduardo Simoes
+
+    - title: Dark Horizons
+      author: Jaded
+
+    - title: Various polish news sources
+      author: fenuks
+
+
 - version: 0.8.21
   date: 2011-09-30
 

recipes/automatiseringgids.recipe

@@ -10,27 +10,15 @@ class autogids(BasicNewsRecipe):
     publisher              = 'AutomatiseringGids'
     category               = 'Nieuws, IT, Nederlandstalig'
     simultaneous_downloads = 5
-    #delay          = 1
-    timefmt        = ' [%A, %d %B, %Y]'
-    #timefmt        = ''
+    timefmt        = ' [%a, %d %B, %Y]'
     no_stylesheets = True
     remove_javascript = True
     remove_empty_feeds = True
     publication_type = 'newspaper'
     encoding              = 'utf-8'
-    cover_url    = 'http://www.automatiseringgids.nl/siteimg/header_logo.gif'
-    keep_only_tags = [dict(id=['content'])]
-    extra_css = '.artikelheader {font-size:0.8em; color: #666;} .artikelintro {font-weight:bold} div.imgArticle {float: right; margin: 0 0em 1em 1em; display: block; position: relative; } \
-        h2 { margin: 0 0 0.5em; min-height: 30px; font-size: 1.5em; letter-spacing: -0.2px; margin: 0 0 0.5em; color: black; font-weight: bold; line-height: 1.2em; padding: 4px 3px 0; }'
+    cover_url    = 'http://www.automatiseringgids.nl/binaries/content/gallery/ag/marketing/ag-avatar-100x50.jpg'
+    keep_only_tags = [dict(name='div', attrs={'class':['content']})]
 
-
-
-    remove_tags = [dict(name='div', attrs={'id':['loginbox','reactiecollapsible','reactiebox']}),
-        dict(name='div', attrs={'class':['column_a','column_c','bannerfullsize','reactieheader','reactiecollapsible','formulier','artikel_headeroptions']}),
-        dict(name='ul', attrs={'class':['highlightlist']}),
-        dict(name='input', attrs={'type':['button']}),
-        dict(name='div', attrs={'style':['display:block; width:428px; height:30px; float:left;']}),
-    ]
     preprocess_regexps = [
         (re.compile(r'(<h3>Reacties</h3>|<h2>Zie ook:</h2>|<div style=".*</div>|<a[^>]*>|</a>)', re.DOTALL|re.IGNORECASE),
         lambda match: ''),

recipes/brand_eins.recipe

@@ -110,8 +110,10 @@ class BrandEins(BasicNewsRecipe):
     selected_issue = issue_map[selected_issue_key]
     url = selected_issue.get('href', False)
     # Get the title for the magazin - build it out of the title of the cover - take the issue and year;
-    self.title = "brand eins " + selected_issue_key[4:] + "/" + selected_issue_key[0:4]
+    # self.title = "brand eins " + selected_issue_key[4:] + "/" + selected_issue_key[0:4]
+    # Get the alternative title for the magazin - build it out of the title of the cover - without the issue and year;
     url = 'http://brandeins.de/'+url
+    self.timefmt = ' ' + selected_issue_key[4:] + '/' + selected_issue_key[:4]
 
     # url = "http://www.brandeins.de/archiv/magazin/tierisch.html"
     titles_and_articles = self.brand_eins_parse_issue(url)
@@ -163,4 +165,3 @@ class BrandEins(BasicNewsRecipe):
           current_articles.append({'title': title, 'url': url, 'description': description, 'date':''})
     titles_and_articles.append([chapter_title, current_articles])
     return titles_and_articles
-

recipes/cnetnews.recipe

@@ -5,8 +5,8 @@ __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
 Changelog:
 2011-09-24
 Changed cover (drMerry)
-'''
-'''
+2011-10-13
+Updated Cover (drMerry)
 news.cnet.com
 '''
 
@@ -24,7 +24,7 @@ class CnetNews(BasicNewsRecipe):
     encoding              = 'cp1252'
     use_embedded_content  = False
     language              = 'en'
-
+    cover_url = 'http://reviews.cnet.com/i/ff/wp/logo_cnet.gif'
     conversion_options = {
                           'comment'   : description
                         , 'tags'      : category

recipes/dallas.recipe

@@ -8,11 +8,7 @@ class DallasNews(BasicNewsRecipe):
 
     no_stylesheets = True
     use_embedded_content = False
-    remove_tags_before = dict(name='h1')
-    keep_only_tags = {'class':lambda x: x and 'article' in x}
-    remove_tags = [
-            {'class':['DMNSocialTools', 'article ', 'article first ', 'article premium']},
-    ]
+    auto_cleanup = True
 
     feeds          = [
                       ('Local News',

recipes/ftd.recipe

@@ -16,7 +16,7 @@ class FTDe(BasicNewsRecipe):
     use_embedded_content   = False
     timefmt = ' [%d %b %Y]'
     language = 'de'
-    max_articles_per_feed = 40
+    max_articles_per_feed = 30
     no_stylesheets = True
 
     remove_tags = [dict(id='navi_top'),
@@ -84,19 +84,19 @@ class FTDe(BasicNewsRecipe):
 		   dict(name='div', attrs={'class':'artikelsplitfaq'})]
     #remove_tags_after = [dict(name='a', attrs={'class':'more'})]
 
-    feeds =  [ ('Finanzen', 'http://www.ftd.de/rss2/finanzen/maerkte'),
-	       ('Meinungshungrige', 'http://www.ftd.de/rss2/meinungshungrige'),
-	       ('Unternehmen', 'http://www.ftd.de/rss2/unternehmen'),
-	       ('Politik', 'http://www.ftd.de/rss2/politik'),
-	       ('Karriere_Management', 'http://www.ftd.de/rss2/karriere-management'),
-	       ('IT_Medien', 'http://www.ftd.de/rss2/it-medien'),
-	       ('Wissen', 'http://www.ftd.de/rss2/wissen'),
-	       ('Sport', 'http://www.ftd.de/rss2/sport'),
-	       ('Auto', 'http://www.ftd.de/rss2/auto'),
-	       ('Lifestyle', 'http://www.ftd.de/rss2/lifestyle')
-
-	     ]
+    feeds =  [
+	         ('Unternehmen', 'http://www.ftd.de/rss2/unternehmen'),
+	         ('Finanzen', 'http://www.ftd.de/rss2/finanzen/maerkte'),
+	         ('Meinungen', 'http://www.ftd.de/rss2/meinungshungrige'),
+	         ('Politik', 'http://www.ftd.de/rss2/politik'),
+	         ('Management & Karriere', 'http://www.ftd.de/rss2/karriere-management'),
+	         ('IT & Medien', 'http://www.ftd.de/rss2/it-medien'),
+	         ('Wissen', 'http://www.ftd.de/rss2/wissen'),
+	         ('Sport', 'http://www.ftd.de/rss2/sport'),
+	         ('Auto', 'http://www.ftd.de/rss2/auto'),
+	         ('Lifestyle', 'http://www.ftd.de/rss2/lifestyle')
+	       ]
 
 
     def print_version(self, url):
-        return url.replace('.html', '.html?mode=print')
+        return url.replace('.html', '.html?mode=print')

recipes/geek_poke.recipe

@@ -1,6 +1,6 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 import re
-from calibre.utils.magick import Image
+from calibre.utils.magick import Image, create_canvas
 
 class AdvancedUserRecipe1307556816(BasicNewsRecipe):
     title          = u'Geek and Poke'
@@ -11,7 +11,7 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe):
     oldest_article = 31
     max_articles_per_feed = 100
     language       = u'en'
-    simultaneous_downloads = 5
+    simultaneous_downloads = 1
     #delay          = 1
     timefmt        = ' [%a, %d %B, %Y]'
     summary_length = -1
@@ -22,6 +22,7 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe):
     remove_javascript = True
     remove_empty_feeds = True
     publication_type = 'blog'
+    masthead_url = None
     conversion_options = {
                             'comments'         : ''
                             ,'tags'            : category
@@ -44,28 +45,38 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe):
                         (r'yimg\.com'),
                         (r'scorecardresearch\.com')]
 
-    preprocess_regexps = [(re.compile(r'(<p>(&nbsp;|\s)*</p>|<a[^>]*>Tweet</a>|<a[^>]*>|</a>)', re.DOTALL|re.IGNORECASE),lambda match: ''),
+    preprocess_regexps = [(re.compile(r'(<p>(&nbsp;|\s)*</p>|<a[^>]*>Tweet</a>|<a[^>]*>|</a>|<!--.*?-->|<h2[^>]*>[^<]*</h2>[^<]*)', re.DOTALL|re.IGNORECASE),lambda match: ''),
                         (re.compile(r'(&nbsp;|\s\s)+\s*', re.DOTALL|re.IGNORECASE),lambda match: ' '),
-                        (re.compile(r'<h2[^>]*>([^<]*)</h2>[^>]*(<div[^>]*>)', re.DOTALL|re.IGNORECASE), lambda match: match.group(2) + '<div id="MERRYdate">' + match.group(1) + '</div>'),
                         (re.compile(r'(<h3[^>]*>)<a[^>]>((?!</a)*)</a></h3>', re.DOTALL|re.IGNORECASE),lambda match: match.group(1) + match.group(2) + '</h3>'),
-                        (re.compile(r'(<img[^>]*alt="([^"]*)"[^>]*>)', re.DOTALL|re.IGNORECASE),lambda match: match.group(1) + '<br><cite>' + match.group(2) + '</cite>'),
+                        (re.compile(r'(<img[^>]*alt="([^"]*)"[^>]*>)', re.DOTALL|re.IGNORECASE),lambda match: '<div id="merryImage"><cite>' + match.group(2) + '</cite><br>' + match.group(1) + '</div>'),
                         (re.compile(r'<br( /)?>(<br( /)?>)+', re.DOTALL|re.IGNORECASE),lambda match: '<br>'),
-                        (re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')
                         ]
 
-    extra_css = 'body, h3, p, #MERRYdate, h1, div, span{margin:0px; padding:0px} h3.entry-header{font-size: 0.8em} div.entry-body{font-size: 0.7em} #MERRYdate {font-size: 0.5em}'
+    extra_css = 'body, h3, p, div, span{margin:0px; padding:0px} h3.entry-header{font-size: 0.8em} div.entry-body{font-size: 0.7em}'
 
     def postprocess_html(self, soup, first):
         for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
             iurl = tag['src']
             img = Image()
             img.open(iurl)
-            width, height = img.size
-            #print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
+            #width, height = img.size
+            #print '***img is: ', iurl, '\n****width is: ', width, 'height is: ', height
             img.trim(0)
-            img.save(iurl)
+            #width, height = img.size
+            #print '***TRIMMED img width is: ', width, 'height is: ', height
+            left=0
+            top=0
+            border_color='#ffffff'
             width, height = img.size
-            #print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
+            #print '***retrieved img width is: ', width, 'height is: ', height
+            height_correction = 1.17
+            canvas = create_canvas(width, height*height_correction,border_color)
+            canvas.compose(img, left, top)
+            #img = canvas
+            #img.save(iurl)
+            canvas.save(iurl)
+            #width, height = canvas.size
+            #print '***NEW img width is: ', width, 'height is: ', height
         return soup
 
     feeds          = ['http://feeds.feedburner.com/GeekAndPoke?format=xml']

recipes/gosc_niedzielny.recipe

@@ -19,6 +19,7 @@ class GN(BasicNewsRecipe):
         language = 'pl'
         remove_javascript = True
         temp_files = []
+        simultaneous_downloads = 1
 
         articles_are_obfuscated = True
 
@@ -94,16 +95,16 @@ class GN(BasicNewsRecipe):
 
         def find_articles(self, main_block):
                 for a in main_block.findAll('div', attrs={'class':'prev_doc2'}):
-                        art = a.find('a')
-                        yield {
+						art = a.find('a')
+						yield {
                                 'title' : self.tag_to_string(art),
                                 'url'   : 'http://www.gosc.pl' + art['href'].replace('/doc/','/doc_pr/'),
                                 'date'  : '',
                                 'description' : ''
                                 }
                 for a in main_block.findAll('div', attrs={'class':'sr-document'}):
-                        art = a.find('a')
-                        yield {
+						art = a.find('a')
+						yield {
                                 'title' : self.tag_to_string(art),
                                 'url'   : 'http://www.gosc.pl' + art['href'].replace('/doc/','/doc_pr/'),
                                 'date'  : '',

recipes/helsingin_sanomat.recipe

@@ -3,7 +3,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class AdvancedUserRecipe1298137661(BasicNewsRecipe):
   title          = u'Helsingin Sanomat'
   __author__ = 'oneillpt'
-  language = 'fi'
+  language              = 'fi'
   oldest_article = 7
   max_articles_per_feed = 100
   no_stylesheets = True
@@ -11,21 +11,12 @@ class AdvancedUserRecipe1298137661(BasicNewsRecipe):
   conversion_options = {
                          'linearize_tables' : True
                        }
-  remove_tags = [
-                  dict(name='a', attrs={'id':'articleCommentUrl'}),
-                  dict(name='p', attrs={'class':'newsSummary'}),
-                  dict(name='div', attrs={'class':'headerTools'})
-                ]
+  keep_only_tags = [dict(name='div', attrs={'id':'main-content'}),
+              dict(name='div', attrs={'class':'contentNewsArticle'})]
 
-  feeds          = [(u'Uutiset - HS.fi', u'http://www.hs.fi/uutiset/rss/'), (u'Politiikka - HS.fi', u'http://www.hs.fi/politiikka/rss/'),
+  feeds          = [(u'Uutiset - HS.fi', u'http://www.hs.fi/uutiset/rss/')
+, (u'Politiikka - HS.fi', u'http://www.hs.fi/politiikka/rss/'),
                      (u'Ulkomaat - HS.fi', u'http://www.hs.fi/ulkomaat/rss/'), (u'Kulttuuri - HS.fi', u'http://www.hs.fi/kulttuuri/rss/'),
                      (u'Kirjat - HS.fi', u'http://www.hs.fi/kulttuuri/kirjat/rss/'), (u'Elokuvat - HS.fi', u'http://www.hs.fi/kulttuuri/elokuvat/rss/')
                      ]
 
-  def print_version(self, url):
-    j = url.rfind("/")
-    s = url[j:]
-    i = s.rfind("?ref=rss")
-    if i > 0:
-      s = s[:i]
-    return "http://www.hs.fi/tulosta" + s

recipes/la_republica.recipe

@@ -1,51 +1,55 @@
-#!/usr/bin/env  python
 __license__   = 'GPL v3'
 __author__    = 'Lorenzo Vigentini, based on Darko Miletic, Gabriele Marini'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>'
+__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>'
 description   = 'Italian daily newspaper - v1.01 (04, January 2010); 16.05.2010 new version'
 
 '''
 http://www.repubblica.it/
 '''
 
+import re
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class LaRepubblica(BasicNewsRecipe):
-    __author__        = 'Lorenzo Vigentini, Gabriele Marini'
-    description   = 'Italian daily newspaper'
-
-    cover_url      = 'http://www.repubblica.it/images/homepage/la_repubblica_logo.gif'
-    title          = u'La Repubblica'
-    publisher      = 'Gruppo editoriale L\'Espresso'
-    category       = 'News, politics, culture, economy, general interest'
-
-    language       = 'it'
-    timefmt        = '[%a, %d %b, %Y]'
-
-    oldest_article = 5
-    max_articles_per_feed = 100
-    use_embedded_content  = False
-    recursion             = 10
-
-    remove_javascript = True
-    no_stylesheets    = True
+    title                = 'La Repubblica'
+    __author__           = 'Lorenzo Vigentini, Gabriele Marini, Darko Miletic'
+    description          = 'il quotidiano online con tutte le notizie in tempo reale. News e ultime notizie. Tutti i settori: politica, cronaca, economia, sport, esteri, scienza, tecnologia, internet, spettacoli, musica, cultura, arte, mostre, libri, dvd, vhs, concerti, cinema, attori, attrici, recensioni, chat, cucina, mappe. Le citta di Repubblica: Roma, Milano, Bologna, Firenze, Palermo, Napoli, Bari, Torino.'
+    masthead_url         = 'http://www.repubblica.it/static/images/homepage/2010/la-repubblica-logo-home-payoff.png'
+    publisher            = 'Gruppo editoriale L\'Espresso'
+    category             = 'News, politics, culture, economy, general interest'
+    language             = 'it'
+    timefmt              = '[%a, %d %b, %Y]'
+    oldest_article       = 5
+    encoding             = 'utf8'
+    use_embedded_content = False
+    #recursion           = 10
+    no_stylesheets       = True
+    extra_css            = """
+                              img{display: block}
+                           """
 
+    preprocess_regexps = [
+        (re.compile(r'.*?<head>', re.DOTALL|re.IGNORECASE), lambda match: '<head>'),
+        (re.compile(r'<head>.*?<title>', re.DOTALL|re.IGNORECASE), lambda match: '<head><title>'),
+        (re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE), lambda match: '</title></head>')
+    ]
+    
     def get_article_url(self, article):
         link = article.get('id', article.get('guid', None))
         if link is None:
             return article
         return link
-
-    keep_only_tags     = [dict(name='div', attrs={'class':'articolo'}),
-                          dict(name='div', attrs={'class':'body-text'}),
-#                          dict(name='div', attrs={'class':'page-content'}),
+    
+    keep_only_tags     = [
+                          dict(attrs={'class':'articolo'}),
+                          dict(attrs={'class':'body-text'}),
                           dict(name='p', attrs={'class':'disclaimer clearfix'}),
-                          dict(name='div', attrs={'id':'contA'})
+                          dict(attrs={'id':'contA'})
                          ]
 
 
     remove_tags        = [
-                            dict(name=['object','link']),
+                            dict(name=['object','link','meta']),
                             dict(name='span',attrs={'class':'linkindice'}),
                             dict(name='div', attrs={'class':'bottom-mobile'}),
                             dict(name='div', attrs={'id':['rssdiv','blocco']}),

recipes/sueddeutsche.recipe

@@ -10,7 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class Sueddeutsche(BasicNewsRecipe):
 
-    title = u'Süddeutsche'
+    title = u'sueddeutsche.de'
     description = 'News from Germany'
     __author__ = 'Oliver Niesner and Armin Geller'
     use_embedded_content   = False
@@ -62,7 +62,7 @@ class Sueddeutsche(BasicNewsRecipe):
               (u'Sport', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5ESport%24?output=rss'),
               (u'Leben', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5ELeben%24?output=rss'),
               (u'Karriere', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EKarriere%24?output=rss'),
-              (u'München&Region', u'http://www.sueddeutsche.de/app/service/rss/ressort/muenchen/rss.xml'),
+              (u'München & Region', u'http://www.sueddeutsche.de/app/service/rss/ressort/muenchen/rss.xml'),
               (u'Bayern', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EBayern%24?output=rss'),
               (u'Medien', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EMedien%24?output=rss'),
               (u'Digital', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EDigital%24?output=rss'),
@@ -75,7 +75,7 @@ class Sueddeutsche(BasicNewsRecipe):
               (u'Job', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EJob%24?output=rss'),         # sometimes only
               (u'Service', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EService%24?output=rss'), # sometimes only
               (u'Verlag', u'http://suche.sueddeutsche.de/query/%23/sort/-docdatetime/drilldown/%C2%A7ressort%3A%5EVerlag%24?output=rss'),   # sometimes only
-             ]
+            ]
 
     def print_version(self, url):
         main, sep, id = url.rpartition('/')

recipes/telepolis.recipe

@@ -3,7 +3,7 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class TelepolisNews(BasicNewsRecipe):
-    title          = u'Telepolis (News+Artikel)'
+    title          = u'Telepolis'
     __author__ = 'syntaxis'
     publisher = 'Heise Zeitschriften Verlag GmbH & Co KG'
     description = 'News from Telepolis'
@@ -15,11 +15,8 @@ class TelepolisNews(BasicNewsRecipe):
     encoding = "utf-8"
     language = 'de'
 
-
     remove_empty_feeds = True
 
-
-
     keep_only_tags = [dict(name = 'div',attrs={'class':'head'}),dict(name = 'div',attrs={'class':'leftbox'}),dict(name='td',attrs={'class':'strict'})]
     remove_tags = [ dict(name='td',attrs={'class':'blogbottom'}),
             dict(name='div',attrs={'class':'forum'}), dict(name='div',attrs={'class':'social'}),dict(name='div',attrs={'class':'blog-letter p-news'}),
@@ -28,7 +25,6 @@ class TelepolisNews(BasicNewsRecipe):
 
     remove_tags_after  = [dict(name='span', attrs={'class':['breadcrumb']})]
 
-
     feeds          = [(u'News', u'http://www.heise.de/tp/news-atom.xml')]
 
     html2lrf_options = [
@@ -39,8 +35,7 @@ class TelepolisNews(BasicNewsRecipe):
 
     html2epub_options  = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
 
-
     def preprocess_html(self, soup):
         mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
         soup.head.insert(0,mtag)
-        return soup
+        return soup

src/calibre/constants.py

@@ -4,7 +4,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = u'calibre'
-numeric_version = (0, 8, 21)
+numeric_version = (0, 8, 22)
 __version__   = u'.'.join(map(unicode, numeric_version))
 __author__    = u"Kovid Goyal <kovid@kovidgoyal.net>"
 

src/calibre/devices/android/driver.py

@@ -62,7 +62,8 @@ class ANDROID(USBMS):
                 0x4e11 : [0x0100, 0x226, 0x227],
                 0x4e12 : [0x0100, 0x226, 0x227],
                 0x4e21 : [0x0100, 0x226, 0x227],
-                0xb058 : [0x0222, 0x226, 0x227]
+                0xb058 : [0x0222, 0x226, 0x227],
+                0x0ff9 : [0x0226],
             },
 
             # Samsung

src/calibre/devices/hanlin/driver.py

@@ -116,6 +116,7 @@ class BOOX(HANLINV3):
     supported_platforms = ['windows', 'osx', 'linux']
     METADATA_CACHE = '.metadata.calibre'
     DRIVEINFO = '.driveinfo.calibre'
+    icon           = I('devices/boox.jpg')
 
     # Ordered list of supported formats
     FORMATS     = ['epub', 'fb2', 'djvu', 'pdf', 'html', 'txt', 'rtf', 'mobi',
@@ -123,7 +124,7 @@ class BOOX(HANLINV3):
 
     VENDOR_ID   = [0x0525]
     PRODUCT_ID  = [0xa4a5]
-    BCD         = [0x322]
+    BCD         = [0x322, 0x323]
 
     MAIN_MEMORY_VOLUME_LABEL  = 'BOOX Internal Memory'
     STORAGE_CARD_VOLUME_LABEL = 'BOOX Storage Card'

src/calibre/devices/interface.py

@@ -464,6 +464,13 @@ class DevicePlugin(Plugin):
         '''
         pass
 
+    def prepare_addable_books(self, paths):
+        '''
+        Given a list of paths, returns another list of paths. These paths
+        point to addable versions of the books.
+        '''
+        return paths
+
 class BookList(list):
     '''
     A list of books. Each Book object must have the fields
@@ -518,9 +525,3 @@ class BookList(list):
         '''
         raise NotImplementedError()
 
-    def prepare_addable_books(self, paths):
-        '''
-        Given a list of paths, returns another list of paths. These paths
-        point to addable versions of the books.
-        '''
-        return paths

src/calibre/devices/misc.py

@@ -84,7 +84,7 @@ class PDNOVEL(USBMS):
     FORMATS = ['epub', 'pdf']
 
     VENDOR_ID   = [0x18d1]
-    PRODUCT_ID  = [0xb004]
+    PRODUCT_ID  = [0xb004, 0xa004]
     BCD         = [0x224]
 
     VENDOR_NAME = 'ANDROID'

src/calibre/ebooks/mobi/reader.py

@@ -325,6 +325,10 @@ class MobiReader(object):
         self.processed_html = self.processed_html.replace('</</', '</')
         self.processed_html = re.sub(r'</([a-zA-Z]+)<', r'</\1><',
                 self.processed_html)
+        # Remove tags of the form <xyz: ...> as they can cause issues further
+        # along the pipeline
+        self.processed_html = re.sub(r'</{0,1}[a-zA-Z]+:\s+[^>]*>', '',
+                self.processed_html)
 
         for pat in ENCODING_PATS:
             self.processed_html = pat.sub('', self.processed_html)

src/calibre/gui2/book_details.py

@@ -204,6 +204,7 @@ def render_data(mi, use_roman_numbers=True, all_fields=False):
 class CoverView(QWidget): # {{{
 
     cover_changed = pyqtSignal(object, object)
+    cover_removed = pyqtSignal(object)
 
     def __init__(self, vertical, parent=None):
         QWidget.__init__(self, parent)
@@ -289,10 +290,12 @@ class CoverView(QWidget): # {{{
         cm = QMenu(self)
         paste = cm.addAction(_('Paste Cover'))
         copy = cm.addAction(_('Copy Cover'))
+        remove = cm.addAction(_('Remove Cover'))
         if not QApplication.instance().clipboard().mimeData().hasImage():
             paste.setEnabled(False)
         copy.triggered.connect(self.copy_to_clipboard)
         paste.triggered.connect(self.paste_from_clipboard)
+        remove.triggered.connect(self.remove_cover)
         cm.exec_(ev.globalPos())
 
     def copy_to_clipboard(self):
@@ -315,6 +318,13 @@ class CoverView(QWidget): # {{{
                 self.cover_changed.emit(id_,
                     pixmap_to_data(pmap))
 
+    def remove_cover(self):
+        id_ = self.data.get('id', None)
+        self.pixmap = self.default_pixmap
+        self.do_layout()
+        self.update()
+        if id_ is not None:
+            self.cover_removed.emit(id_)
 
     # }}}
 
@@ -457,6 +467,7 @@ class BookDetails(QWidget): # {{{
     remote_file_dropped = pyqtSignal(object, object)
     files_dropped = pyqtSignal(object, object)
     cover_changed = pyqtSignal(object, object)
+    cover_removed = pyqtSignal(object)
 
     # Drag 'n drop {{{
     DROPABBLE_EXTENSIONS = IMAGE_EXTENSIONS+BOOK_EXTENSIONS
@@ -514,6 +525,7 @@ class BookDetails(QWidget): # {{{
 
         self.cover_view = CoverView(vertical, self)
         self.cover_view.cover_changed.connect(self.cover_changed.emit)
+        self.cover_view.cover_removed.connect(self.cover_removed.emit)
         self._layout.addWidget(self.cover_view)
         self.book_info = BookInfo(vertical, self)
         self._layout.addWidget(self.book_info)

src/calibre/gui2/init.py

@@ -261,6 +261,8 @@ class LayoutMixin(object): # {{{
         self.book_details.files_dropped.connect(self.iactions['Add Books'].files_dropped_on_book)
         self.book_details.cover_changed.connect(self.bd_cover_changed,
                 type=Qt.QueuedConnection)
+        self.book_details.cover_removed.connect(self.bd_cover_removed,
+                type=Qt.QueuedConnection)
         self.book_details.remote_file_dropped.connect(
                 self.iactions['Add Books'].remote_file_dropped_on_book,
                 type=Qt.QueuedConnection)
@@ -279,6 +281,12 @@ class LayoutMixin(object): # {{{
         if self.cover_flow:
             self.cover_flow.dataChanged()
 
+    def bd_cover_removed(self, id_):
+        self.library_view.model().db.remove_cover(id_, commit=True,
+                notify=False)
+        if self.cover_flow:
+            self.cover_flow.dataChanged()
+
     def save_layout_state(self):
         for x in ('library', 'memory', 'card_a', 'card_b'):
             getattr(self, x+'_view').save_state()

src/calibre/gui2/jobs.py

@@ -500,7 +500,8 @@ class JobsDialog(QDialog, Ui_JobsDialog):
     def kill_job(self, *args):
         rows = [index.row() for index in
                 self.jobs_view.selectionModel().selectedRows()]
-        return error_dialog(self, _('No job'),
+        if not rows:
+            return error_dialog(self, _('No job'),
                 _('No job selected'), show=True)
         if question_dialog(self, _('Are you sure?'),
                 ngettext('Do you really want to stop the selected job?',

src/calibre/gui2/preferences/create_custom_column.py

@@ -127,7 +127,7 @@ class CreateCustomColumn(QDialog, Ui_QCreateCustomColumn):
             self.composite_sort_by.setCurrentIndex(sb)
             self.composite_make_category.setChecked(
                                 c['display'].get('make_category', False))
-            self.composite_make_category.setChecked(
+            self.composite_contains_html.setChecked(
                                 c['display'].get('contains_html', False))
         elif ct == 'enumeration':
             self.enum_box.setText(','.join(c['display'].get('enum_values', [])))

src/calibre/library/cli.py

@@ -368,6 +368,7 @@ def command_remove(args, dbpath):
 
 def do_add_format(db, id, fmt, path):
     db.add_format_with_hooks(id, fmt.upper(), path, index_is_id=True)
+    send_message()
 
 def add_format_option_parser():
     return get_parser(_(
@@ -396,6 +397,7 @@ def command_add_format(args, dbpath):
 
 def do_remove_format(db, id, fmt):
     db.remove_format(id, fmt, index_is_id=True)
+    send_message()
 
 def remove_format_option_parser():
     return get_parser(_(

src/calibre/manual/faq.rst

@@ -20,7 +20,7 @@ What formats does |app| support conversion to/from?
 |app| supports the conversion of many input formats to many output formats.
 It can convert every input format in the following list, to every output format.
 
-*Input Formats:* CBZ, CBR, CBC, CHM, EPUB, FB2, HTML, HTMLZ, LIT, LRF, MOBI, ODT, PDF, PRC, PDB, PML, RB, RTF, SNB, TCR, TXT, TXTZ
+*Input Formats:* CBZ, CBR, CBC, CHM, DJVU, EPUB, FB2, HTML, HTMLZ, LIT, LRF, MOBI, ODT, PDF, PRC, PDB, PML, RB, RTF, SNB, TCR, TXT, TXTZ
 
 *Output Formats:* EPUB, FB2, OEB, LIT, LRF, MOBI, HTMLZ, PDB, PML, RB, PDF, RTF, SNB, TCR, TXT, TXTZ
 
@@ -28,6 +28,7 @@ It can convert every input format in the following list, to every output format.
 
     PRC is a generic format, |app| supports PRC files with TextRead and MOBIBook headers.
     PDB is also a generic format. |app| supports eReder, Plucker, PML and zTxt PDB files.
+    DJVU support is only for converting DJVU files that contain embedded text. These are typically generated by OCR software.
 
 .. _best-source-formats:
 

src/calibre/manual/template_lang.rst

@@ -268,6 +268,7 @@ The following functions are available in addition to those described in single-f
     * ``list_difference(list1, list2, separator)`` -- return a list made by removing from `list1` any item found in `list2`, using a case-insensitive compare. The items in `list1` and `list2` are separated by separator, as are the items in the returned list.
     * ``list_equals(list1, sep1, list2, sep2, yes_val, no_val)`` -- return `yes_val` if `list1` and `list2` contain the same items, otherwise return `no_val`. The items are determined by splitting each list using the appropriate separator character (`sep1` or `sep2`). The order of items in the lists is not relevant. The compare is case insensitive.
     * ``list_intersection(list1, list2, separator)`` -- return a list made by removing from `list1` any item not found in `list2`, using a case-insensitive compare. The items in `list1` and `list2` are separated by separator, as are the items in the returned list.
+    * ``list_re(src_list, separator, search_re, opt_replace)`` -- Construct a list by first separating `src_list` into items using the `separator` character. For each item in the list, check if it matches `search_re`. If it does, then add it to the list to be returned. If `opt_replace` is not the empty string, then apply the replacement before adding the item to the returned list.
     * ``list_sort(list, direction, separator)`` -- return list sorted using a case-insensitive sort. If `direction` is zero, the list is sorted ascending, otherwise descending. The list items are separated by separator, as are the items in the returned list.
     * ``list_union(list1, list2, separator)`` -- return a list made by merging the items in list1 and list2, removing duplicate items using a case-insensitive compare. If items differ in case, the one in list1 is used. The items in list1 and list2 are separated by separator, as are the items in the returned list.
     * ``multiply(x, y)`` -- returns x * y. Throws an exception if either x or y are not numbers.

src/calibre/utils/formatter_functions.py

@@ -133,7 +133,7 @@ class BuiltinCmp(BuiltinFormatterFunction):
 class BuiltinStrcat(BuiltinFormatterFunction):
     name = 'strcat'
     arg_count = -1
-    category = 'String Manipulation'
+    category = 'String manipulation'
     __doc__ = doc = _('strcat(a, b, ...) -- can take any number of arguments. Returns a '
             'string formed by concatenating all the arguments')
 
@@ -147,7 +147,7 @@ class BuiltinStrcat(BuiltinFormatterFunction):
 class BuiltinStrlen(BuiltinFormatterFunction):
     name = 'strlen'
     arg_count = 1
-    category = 'String Manipulation'
+    category = 'String manipulation'
     __doc__ = doc = _('strlen(a) -- Returns the length of the string passed as '
             'the argument')
 
@@ -277,7 +277,7 @@ class BuiltinRawField(BuiltinFormatterFunction):
 class BuiltinSubstr(BuiltinFormatterFunction):
     name = 'substr'
     arg_count = 3
-    category = 'String Manipulation'
+    category = 'String manipulation'
     __doc__ = doc = _('substr(str, start, end) -- returns the start\'th through the end\'th '
             'characters of str. The first character in str is the zero\'th '
             'character. If end is negative, then it indicates that many '
@@ -369,7 +369,7 @@ class BuiltinSwitch(BuiltinFormatterFunction):
 class BuiltinStrcatMax(BuiltinFormatterFunction):
     name = 'strcat_max'
     arg_count = -1
-    category = 'String Manipulation'
+    category = 'String manipulation'
     __doc__ = doc = _('strcat_max(max, string1, prefix2, string2, ...) -- '
             'Returns a string formed by concatenating the arguments. The '
             'returned value is initialized to string1. `Prefix, string` '
@@ -403,7 +403,7 @@ class BuiltinStrcatMax(BuiltinFormatterFunction):
 class BuiltinInList(BuiltinFormatterFunction):
     name = 'in_list'
     arg_count = 5
-    category = 'List Lookup'
+    category = 'List lookup'
     __doc__ = doc = _('in_list(val, separator, pattern, found_val, not_found_val) -- '
             'treat val as a list of items separated by separator, '
             'comparing the pattern against each value in the list. If the '
@@ -468,7 +468,7 @@ class BuiltinIdentifierInList(BuiltinFormatterFunction):
 class BuiltinRe(BuiltinFormatterFunction):
     name = 're'
     arg_count = 3
-    category = 'String Manipulation'
+    category = 'String manipulation'
     __doc__ = doc = _('re(val, pattern, replacement) -- return the field after applying '
             'the regular expression. All instances of `pattern` are replaced '
             'with `replacement`. As in all of calibre, these are '
@@ -480,7 +480,7 @@ class BuiltinRe(BuiltinFormatterFunction):
 class BuiltinSwapAroundComma(BuiltinFormatterFunction):
     name = 'swap_around_comma'
     arg_count = 1
-    category = 'String Manipulation'
+    category = 'String manipulation'
     __doc__ = doc = _('swap_around_comma(val) -- given a value of the form '
             '"B, A", return "A B". This is most useful for converting names '
             'in LN, FN format to FN LN. If there is no comma, the function '
@@ -505,7 +505,7 @@ class BuiltinIfempty(BuiltinFormatterFunction):
 class BuiltinShorten(BuiltinFormatterFunction):
     name = 'shorten'
     arg_count = 4
-    category = 'String Manipulation'
+    category = 'String manipulation'
     __doc__ = doc = _('shorten(val, left chars, middle text, right chars) -- Return a '
             'shortened version of the field, consisting of `left chars` '
             'characters from the beginning of the field, followed by '
@@ -531,7 +531,7 @@ class BuiltinShorten(BuiltinFormatterFunction):
 class BuiltinCount(BuiltinFormatterFunction):
     name = 'count'
     arg_count = 2
-    category = 'List Manipulation'
+    category = 'List manipulation'
     __doc__ = doc = _('count(val, separator) -- interprets the value as a list of items '
             'separated by `separator`, returning the number of items in the '
             'list. Most lists use a comma as the separator, but authors '
@@ -543,7 +543,7 @@ class BuiltinCount(BuiltinFormatterFunction):
 class BuiltinListitem(BuiltinFormatterFunction):
     name = 'list_item'
     arg_count = 3
-    category = 'List Lookup'
+    category = 'List lookup'
     __doc__ = doc = _('list_item(val, index, separator) -- interpret the value as a list of '
             'items separated by `separator`, returning the `index`th item. '
             'The first item is number zero. The last item can be returned '
@@ -564,7 +564,7 @@ class BuiltinListitem(BuiltinFormatterFunction):
 class BuiltinSelect(BuiltinFormatterFunction):
     name = 'select'
     arg_count = 2
-    category = 'List Lookup'
+    category = 'List lookup'
     __doc__ = doc = _('select(val, key) -- interpret the value as a comma-separated list '
             'of items, with the items being "id:value". Find the pair with the '
             'id equal to key, and return the corresponding value.'
@@ -656,7 +656,7 @@ class BuiltinFormatNumber(BuiltinFormatterFunction):
 class BuiltinSublist(BuiltinFormatterFunction):
     name = 'sublist'
     arg_count = 4
-    category = 'List Manipulation'
+    category = 'List manipulation'
     __doc__ = doc = _('sublist(val, start_index, end_index, separator) -- interpret the '
             'value as a list of items separated by `separator`, returning a '
             'new list made from the `start_index` to the `end_index` item. '
@@ -677,6 +677,9 @@ class BuiltinSublist(BuiltinFormatterFunction):
         ei = int(end_index)
         # allow empty list items so counts are what the user expects
         val = [v.strip() for v in val.split(sep)]
+
+        if sep == ',':
+            sep = ', '
         try:
             if ei == 0:
                 return sep.join(val[si:])
@@ -688,7 +691,7 @@ class BuiltinSublist(BuiltinFormatterFunction):
 class BuiltinSubitems(BuiltinFormatterFunction):
     name = 'subitems'
     arg_count = 3
-    category = 'List Manipulation'
+    category = 'List manipulation'
     __doc__ = doc = _('subitems(val, start_index, end_index) -- This function is used to '
             'break apart lists of items such as genres. It interprets the value '
             'as a comma-separated list of items, where each item is a period-'
@@ -892,7 +895,7 @@ class BuiltinNot(BuiltinFormatterFunction):
 class BuiltinListUnion(BuiltinFormatterFunction):
     name = 'list_union'
     arg_count = 3
-    category = 'List Manipulation'
+    category = 'List manipulation'
     __doc__ = doc = _('list_union(list1, list2, separator) -- '
             'return a list made by merging the items in list1 and list2, '
             'removing duplicate items using a case-insensitive compare. If '
@@ -912,12 +915,14 @@ class BuiltinListUnion(BuiltinFormatterFunction):
         for i in l2:
             if icu_lower(i) not in lcl1:
                 res.append(i)
-        return ', '.join(res)
+        if separator == ',':
+            return ', '.join(res)
+        return separator.join(res)
 
 class BuiltinListDifference(BuiltinFormatterFunction):
     name = 'list_difference'
     arg_count = 3
-    category = 'List Manipulation'
+    category = 'List manipulation'
     __doc__ = doc = _('list_difference(list1, list2, separator) -- '
             'return a list made by removing from list1 any item found in list2, '
             'using a case-insensitive compare. The items in list1 and list2 '
@@ -931,12 +936,14 @@ class BuiltinListDifference(BuiltinFormatterFunction):
         for i in l1:
             if icu_lower(i) not in l2:
                 res.append(i)
-        return ', '.join(res)
+        if separator == ',':
+            return ', '.join(res)
+        return separator.join(res)
 
 class BuiltinListIntersection(BuiltinFormatterFunction):
     name = 'list_intersection'
     arg_count = 3
-    category = 'List Manipulation'
+    category = 'List manipulation'
     __doc__ = doc = _('list_intersection(list1, list2, separator) -- '
             'return a list made by removing from list1 any item not found in list2, '
             'using a case-insensitive compare. The items in list1 and list2 '
@@ -950,12 +957,14 @@ class BuiltinListIntersection(BuiltinFormatterFunction):
         for i in l1:
             if icu_lower(i) in l2:
                 res.append(i)
-        return ', '.join(res)
+        if separator == ',':
+            return ', '.join(res)
+        return separator.join(res)
 
 class BuiltinListSort(BuiltinFormatterFunction):
     name = 'list_sort'
     arg_count = 3
-    category = 'List Manipulation'
+    category = 'List manipulation'
     __doc__ = doc = _('list_sort(list, direction, separator) -- '
             'return list sorted using a case-insensitive sort. If direction is '
             'zero, the list is sorted ascending, otherwise descending. The list items '
@@ -963,12 +972,14 @@ class BuiltinListSort(BuiltinFormatterFunction):
 
     def evaluate(self, formatter, kwargs, mi, locals, list1, direction, separator):
         res = [l.strip() for l in list1.split(separator) if l.strip()]
-        return ', '.join(sorted(res, key=sort_key, reverse=direction != "0"))
+        if separator == ',':
+            return ', '.join(sorted(res, key=sort_key, reverse=direction != "0"))
+        return separator.join(sorted(res, key=sort_key, reverse=direction != "0"))
 
 class BuiltinListEquals(BuiltinFormatterFunction):
     name = 'list_equals'
     arg_count = 6
-    category = 'List Manipulation'
+    category = 'List manipulation'
     __doc__ = doc = _('list_equals(list1, sep1, list2, sep2, yes_val, no_val) -- '
             'return yes_val if list1 and list2 contain the same items, '
             'otherwise return no_val. The items are determined by splitting '
@@ -983,6 +994,29 @@ class BuiltinListEquals(BuiltinFormatterFunction):
             return yes_val
         return no_val
 
+class BuiltinListRe(BuiltinFormatterFunction):
+    name = 'list_re'
+    arg_count = 4
+    category = 'List manipulation'
+    __doc__ = doc = _('list_re(src_list, separator, search_re, opt_replace) -- '
+            'Construct a list by first separating src_list into items using '
+            'the separator character. For each item in the list, check if it '
+            'matches search_re. If it does, then add it to the list to be '
+            'returned. If opt_replace is not the empty string, then apply the '
+            'replacement before adding the item to the returned list.')
+
+    def evaluate(self, formatter, kwargs, mi, locals, src_list, separator, search_re, opt_replace):
+        l = [l.strip() for l in src_list.split(separator) if l.strip()]
+        res = []
+        for item in l:
+            if re.search(search_re, item, flags=re.I) is not None:
+                if opt_replace:
+                    item = re.sub(search_re, opt_replace, item)
+                res.append(item)
+        if separator == ',':
+            return ', '.join(res)
+        return separator.join(res)
+
 class BuiltinToday(BuiltinFormatterFunction):
     name = 'today'
     arg_count = 0
@@ -1064,8 +1098,8 @@ _formatter_builtins = [
     BuiltinHasCover(), BuiltinHumanReadable(), BuiltinIdentifierInList(),
     BuiltinIfempty(), BuiltinLanguageCodes(), BuiltinLanguageStrings(),
     BuiltinInList(), BuiltinListDifference(), BuiltinListEquals(),
-    BuiltinListIntersection(), BuiltinListitem(), BuiltinListSort(),
-    BuiltinListUnion(), BuiltinLookup(),
+    BuiltinListIntersection(), BuiltinListitem(), BuiltinListRe(),
+    BuiltinListSort(), BuiltinListUnion(), BuiltinLookup(),
     BuiltinLowercase(), BuiltinMultiply(), BuiltinNot(),
     BuiltinOndevice(), BuiltinOr(), BuiltinPrint(), BuiltinRawField(),
     BuiltinRe(), BuiltinSelect(), BuiltinShorten(), BuiltinStrcat(),