0.8.6

Changelog.yaml

@@ -19,6 +19,69 @@
 #  new recipes:
 #    - title: 
 
+- version: 0.8.6
+  date: 2011-06-17
+
+  new features:
+    - title: "Builtin support for downloading and installing/updating calibre plugins. Go to Preferences->Plugins and click 'Get new plugins'"
+      description: "When updates for installed plugins are available, calibre will automatically (unobtrusively) notify you"
+      type: major
+
+    - title: "Metadata download configuration: Allow defining a set of 'default' fields for metadata download and quichly switching to/from them"
+
+    - title: "Allow clicking on the news category in the Tag Browser to display all downloaded periodicals"
+
+    - title: "Driver for the Libre Air"
+
+    - title: "Email sending: Allow user to stop email jobs (note that stopping may not actually prevent the email from being sent, depending on when the stop happens). Also automatically abort email sending if it takes longer than 15mins."
+      tickets: [795960]
+  
+  bug fixes:
+    - title: "MOBI Output: Allow setting of background color on tables also set the border attribute on the table if the table has any border related css defined."
+      tickets: [797580]
+
+    - title: "Nook TSR: Put news sent to the device in My Files/Newspapers instaed of My Files/Books."
+      tickets: [796674]
+
+    - title: "MOBI Output: Fix a bug where linking to the very first element in an HTML file could sometimes result in the link pointing to the last element in the previous file."
+      tickets: [797214]
+
+    - title: "CSV catalog: Convert HTML comments to plain text"
+
+    - title: "HTML Input: Ignore links to text files."
+      tickets: [791568]
+
+    - title: "EPUB Output: Change orphaned <td> tags to <div> as they cause ADE to crash."
+
+    - title: "Fix 'Stop selected jobs' button trying to stop the same job multiple times"
+
+    - title: "Database: Explicitly test for case sensitivity on OS X instead of assuming a case insensitive filesystem."
+      tickets: [796258]
+
+    - title: "Get Books: More fixes to the Amazon store plugin"
+
+    - title: "FB2 Input: Do not specify font families/background colors"
+
+
+  improved recipes:
+    - Philadelphia Inquirer
+    - Macleans Magazone
+    - Metro UK
+
+  new recipes:
+    - title: "Christian Post, Down To Earth and Words Without Borders"
+      author: sexymax15
+
+    - title: "Noticias R7"
+      author: Diniz Bortolotto
+
+    - title: "UK Daily Mirror"
+      author: Dave Asbury
+
+    - title: "New Musical Express Magazine"
+      author: scissors
+
+
 - version: 0.8.5
   date: 2011-06-10
 

recipes/christian_post.recipe

@@ -0,0 +1,37 @@
+#created by sexymax15 ....sexymax15@gmail.com
+#christian post recipe
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ChristianPost(BasicNewsRecipe):
+
+    title = 'The Christian Post'
+    __author__ = 'sexymax15'
+    description = 'Homepage'
+    language = 'en'
+    no_stylesheets = True
+    use_embedded_content	= False
+    oldest_article	= 30
+    max_articles_per_feed = 15
+
+    remove_empty_feeds = True
+    no_stylesheets = True
+    remove_javascript = True
+
+    extra_css = '''
+              h1 {color:#008852;font-family:Arial,Helvetica,sans-serif; font-size:20px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:18px;}
+              h2 {color:#4D4D4D;font-family:Arial,Helvetica,sans-serif; font-size:16px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:16px; } '''
+
+
+    feeds =  [
+             ('Homepage', 'http://www.christianpost.com/services/rss/feed/'),
+             ('Most Popular', 'http://www.christianpost.com/services/rss/feed/most-popular'),
+             ('Entertainment', 'http://www.christianpost.com/services/rss/feed/entertainment/'),
+             ('Politics', 'http://www.christianpost.com/services/rss/feed/politics/'),
+             ('Living', 'http://www.christianpost.com/services/rss/feed/living/'),
+             ('Business', 'http://www.christianpost.com/services/rss/feed/business/'),
+             ('Opinion', 'http://www.christianpost.com/services/rss/feed/opinion/')
+             ]
+
+    def print_version(self, url):
+        return url +'print.html'
+

recipes/down_to_earth.recipe

@@ -0,0 +1,18 @@
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class AdvancedUserRecipe1307834113(BasicNewsRecipe):
+
+    title          = u'Down To Earth'
+    oldest_article = 300
+    __author__ = 'sexymax15'
+    max_articles_per_feed = 30
+    no_stylesheets = True
+    remove_javascript     = True
+    remove_attributes = ['width','height']
+    use_embedded_content  = False
+    language              = 'en_IN'
+    remove_empty_feeds    = True
+    remove_tags_before = dict(name='div', id='PageContent')
+    remove_tags_after = [dict(name='div'),{'class':'box'}]
+    remove_tags =[{'class':'box'}]
+    feeds          = [(u'editor', u'http://www.downtoearth.org.in/taxonomy/term/20348/0/feed'), (u'cover story', u'http://www.downtoearth.org.in/taxonomy/term/20345/0/feed'), (u'special report', u'http://www.downtoearth.org.in/taxonomy/term/20384/0/feed'), (u'features', u'http://www.downtoearth.org.in/taxonomy/term/20350/0/feed'), (u'news', u'http://www.downtoearth.org.in/taxonomy/term/20366/0/feed'), (u'debate', u'http://www.downtoearth.org.in/taxonomy/term/20347/0/feed'), (u'natural disasters', u'http://www.downtoearth.org.in/taxonomy/term/20822/0/feed')]

recipes/macleans.recipe

@@ -1,239 +1,28 @@
 #!/usr/bin/env  python
+from calibre.web.feeds.news import BasicNewsRecipe
 
-__license__   = 'GPL v3'
-
-'''
-macleans.ca
-'''
-from calibre.web.feeds.recipes import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import Tag
-from datetime import timedelta, date
-
-class Macleans(BasicNewsRecipe):
+class AdvancedUserRecipe1308306308(BasicNewsRecipe):
     title          = u'Macleans Magazine'
-    __author__     = 'Nick Redding'
     language = 'en_CA'
-    description = ('Macleans Magazine')
+    __author__ = 'sexymax15'
+    oldest_article = 30
+    max_articles_per_feed = 12
 
+    use_embedded_content = False
+
+    remove_empty_feeds = True
     no_stylesheets = True
-    timefmt = ' [%b %d]'
+    remove_javascript = True
+    remove_tags = [dict(name ='img'),dict (id='header'),{'class':'postmetadata'}]
+    remove_tags_after = {'class':'postmetadata'}
 
-    # customization notes: delete sections you are not interested in
-    # set oldest_article to the maximum number of days back from today to include articles
-    sectionlist = [
-                        ['http://www2.macleans.ca/','Front Page'],
-                        ['http://www2.macleans.ca/category/canada/','Canada'],
-                        ['http://www2.macleans.ca/category/world-from-the-magazine/','World'],
-                        ['http://www2.macleans.ca/category/business','Business'],
-                        ['http://www2.macleans.ca/category/arts-culture/','Culture'],
-                        ['http://www2.macleans.ca/category/opinion','Opinion'],
-                        ['http://www2.macleans.ca/category/health-from-the-magazine/','Health'],
-                        ['http://www2.macleans.ca/category/environment-from-the-magazine/','Environment'],
-                        ['http://www2.macleans.ca/category/education/','On Campus'],
-                        ['http://www2.macleans.ca/category/travel-from-the-magazine/','Travel']
-                    ]
-    oldest_article = 7
-
-    # formatting for print version of articles
-    extra_css   =   '''h2{font-family:Times,serif; font-size:large;}
-                        small {font-family:Times,serif; font-size:xx-small; list-style-type: none;}
-                    '''
-
-    # tag handling for print version of articles
-    keep_only_tags = [dict(id='tw-print')]
-    remove_tags =   [dict({'class':'postmetadata'})]
-
-
-    def preprocess_html(self,soup):
-        for img_tag in soup.findAll('img'):
-            parent_tag = img_tag.parent
-            if parent_tag.name == 'a':
-                new_tag = Tag(soup,'p')
-                new_tag.insert(0,img_tag)
-                parent_tag.replaceWith(new_tag)
-            elif parent_tag.name == 'p':
-                if not self.tag_to_string(parent_tag) == '':
-                    new_div = Tag(soup,'div')
-                    new_tag = Tag(soup,'p')
-                    new_tag.insert(0,img_tag)
-                    parent_tag.replaceWith(new_div)
-                    new_div.insert(0,new_tag)
-                    new_div.insert(1,parent_tag)
-        return soup
-
-    def parse_index(self):
-
-
-
-        articles = {}
-        key = None
-        ans = []
-
-        def parse_index_page(page_url,page_title):
-
-            def decode_date(datestr):
-                dmysplit = datestr.strip().lower().split(',')
-                mdsplit = dmysplit[1].split()
-                m = ['january','february','march','april','may','june','july','august','september','october','november','december'].index(mdsplit[0])+1
-                d = int(mdsplit[1])
-                y = int(dmysplit[2].split()[0])
-                return date(y,m,d)
-
-            def article_title(tag):
-                atag = tag.find('a',href=True)
-                if not atag:
-                    return ''
-                return self.tag_to_string(atag)
-
-            def article_url(tag):
-                atag = tag.find('a',href=True)
-                if not atag:
-                    return ''
-                return atag['href']+'print/'
-
-            def article_description(tag):
-                for p_tag in tag.findAll('p'):
-                    d = self.tag_to_string(p_tag,False)
-                    if not d == '':
-                        return d
-                return ''
-
-            def compound_h4_h3_title(tag):
-                if tag.h4:
-                    if tag.h3:
-                        return self.tag_to_string(tag.h4,False)+u'\u2014'+self.tag_to_string(tag.h3,False)
-                    else:
-                        return self.tag_to_string(tag.h4,False)
-                elif tag.h3:
-                    return self.tag_to_string(tag.h3,False)
-                else:
-                    return ''
-
-            def compound_h2_h4_title(tag):
-                if tag.h2:
-                    if tag.h4:
-                        return self.tag_to_string(tag.h2,False)+u'\u2014'+self.tag_to_string(tag.h4,False)
-                    else:
-                        return self.tag_to_string(tag.h2,False)
-                elif tag.h4:
-                    return self.tag_to_string(tag.h4,False)
-                else:
-                    return ''
-
-
-            def handle_article(header_tag, outer_tag):
-                if header_tag:
-                    url = article_url(header_tag)
-                    title = article_title(header_tag)
-                    author_date_tag = outer_tag.h4
-                    if author_date_tag:
-                        author_date = self.tag_to_string(author_date_tag,False).split(' - ')
-                        author = author_date[0].strip()
-                        article_date = decode_date(author_date[1])
-                        earliest_date = date.today() - timedelta(days=self.oldest_article)
-                        if article_date < earliest_date:
-                            self.log("Skipping article dated %s" % author_date[1])
-                        else:
-                            excerpt_div = outer_tag.find('div','excerpt')
-                            if excerpt_div:
-                                description = article_description(excerpt_div)
-                            else:
-                                description = ''
-                            if not articles.has_key(page_title):
-                                articles[page_title] = []
-                            articles[page_title].append(dict(title=title,url=url,date=author_date[1],description=description,author=author,content=''))
-
-            def handle_category_article(cat, header_tag, outer_tag):
-                url = article_url(header_tag)
-                title = article_title(header_tag)
-                if not title == '':
-                    title = cat+u'\u2014'+title
-                a_tag = outer_tag.find('span','authorLink')
-                if a_tag:
-                    author = self.tag_to_string(a_tag,False)
-                    a_tag.parent.extract()
-                else:
-                    author = ''
-                description = article_description(outer_tag)
-                if not articles.has_key(page_title):
-                    articles[page_title] = []
-                articles[page_title].append(dict(title=title,url=url,date='',description=description,author=author,content=''))
-
-
-            soup = self.index_to_soup(page_url)
-
-            if page_title == 'Front Page':
-                # special processing for the front page
-                top_stories = soup.find('div',{ "id" : "macleansFeatured" })
-                if top_stories:
-                    for div_slide in top_stories.findAll('div','slide'):
-                        url = article_url(div_slide)
-                        div_title = div_slide.find('div','header')
-                        if div_title:
-                            title = self.tag_to_string(div_title,False)
-                        else:
-                            title = ''
-                        description = article_description(div_slide)
-                        if not articles.has_key(page_title):
-                             articles[page_title] = []
-                        articles[page_title].append(dict(title=title,url=url,date='',description=description,author='',content=''))
-
-                from_macleans = soup.find('div',{ "id" : "fromMacleans" })
-                if from_macleans:
-                    for li_tag in from_macleans.findAll('li','fromMacleansArticle'):
-                        title = compound_h4_h3_title(li_tag)
-                        url = article_url(li_tag)
-                        description = article_description(li_tag)
-                        if not articles.has_key(page_title):
-                            articles[page_title] = []
-                        articles[page_title].append(dict(title=title,url=url,date='',description=description,author='',content=''))
-
-                blog_central = soup.find('div',{ "id" : "bloglist" })
-                if blog_central:
-                    for li_tag in blog_central.findAll('li'):
-                        title = compound_h2_h4_title(li_tag)
-                        if li_tag.h4:
-                            url = article_url(li_tag.h4)
-                            if not articles.has_key(page_title):
-                                articles[page_title] = []
-                            articles[page_title].append(dict(title=title,url=url,date='',description='',author='',content=''))
-
-#                need_to_know = soup.find('div',{ "id" : "needToKnow" })
-#                if need_to_know:
-#                    for div_tag in need_to_know('div',attrs={'class' : re.compile("^needToKnowArticle")}):
-#                        title = compound_h4_h3_title(div_tag)
-#                        url = article_url(div_tag)
-#                        description = article_description(div_tag)
-#                        if not articles.has_key(page_title):
-#                            articles[page_title] = []
-#                        articles[page_title].append(dict(title=title,url=url,date='',description=description,author='',content=''))
-
-                for news_category in soup.findAll('div','newsCategory'):
-                    news_cat = self.tag_to_string(news_category.h4,False)
-                    handle_category_article(news_cat, news_category.find('h2'), news_category.find('div'))
-                    for news_item in news_category.findAll('li'):
-                        handle_category_article(news_cat,news_item.h3,news_item)
-
-                return
-
-            # find the div containing the highlight article
-            div_post = soup.find('div','post')
-            if div_post:
-                h1_tag = div_post.h1
-                handle_article(h1_tag,div_post)
-
-            # find the divs containing the rest of the articles
-            div_other = div_post.find('div', { "id" : "categoryOtherPosts" })
-            if div_other:
-                for div_entry in div_other.findAll('div','entry'):
-                    h2_tag = div_entry.h2
-                    handle_article(h2_tag,div_entry)
-
-
-
-        for page_name,page_title in self.sectionlist:
-            parse_index_page(page_name,page_title)
-            ans.append(page_title)
-
-        ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
-        return ans
+    feeds          = [(u'Blog Central', u'http://www2.macleans.ca/category/blog-central/feed/'),
+ (u'Canada', u'http://www2.macleans.ca/category/canada/feed/'),
+(u'World', u'http://www2.macleans.ca/category/world-from-the-magazine/feed/'),
+(u'Business', u'http://www2.macleans.ca/category/business/feed/'),
+(u'Arts & Culture', u'http://www2.macleans.ca/category/arts-culture/feed/'),
+(u'Opinion', u'http://www2.macleans.ca/category/opinion/feed/'),
+(u'Health', u'http://www2.macleans.ca/category/health-from-the-magazine/feed/'),
+ (u'Environment', u'http://www2.macleans.ca/category/environment-from-the-magazine/feed/')]
+    def print_version(self, url):
+        return url + 'print/'

recipes/mail_and_guardian.recipe

@@ -3,7 +3,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class AdvancedUserRecipe1295081935(BasicNewsRecipe):
      title          = u'Mail & Guardian ZA News'
      __author__     = '77ja65'
-     language = 'en'
+     language = 'en_ZA'
      oldest_article = 7
      max_articles_per_feed = 30
      no_stylesheets = True

recipes/philly.recipe

@@ -1,85 +1,45 @@
 #!/usr/bin/env  python
-__license__   = 'GPL v3'
-'''
-philly.com/inquirer/
-'''
-from calibre.web.feeds.recipes import BasicNewsRecipe
+from calibre.web.feeds.news import BasicNewsRecipe
 
-class Philly(BasicNewsRecipe):
-
-    title       = 'Philadelphia Inquirer'
-    __author__  = 'RadikalDissent and Sujata Raman'
+class AdvancedUserRecipe1308312288(BasicNewsRecipe):
+    title          = u'Philadelphia Inquirer'
+    __author__ = 'sexymax15'
     language = 'en'
     description = 'Daily news from the Philadelphia Inquirer'
-    no_stylesheets        = True
+    oldest_article = 15
+    max_articles_per_feed = 20
     use_embedded_content = False
-    oldest_article = 1
-    max_articles_per_feed = 25
+    remove_empty_feeds = True
+    no_stylesheets = True
+    remove_javascript = True
 
-    extra_css = '''
-        h1{font-family:verdana,arial,helvetica,sans-serif; font-size: large;}
-        h2{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
-        .body-content{font-family:verdana,arial,helvetica,sans-serif; font-size: small;}
-        .byline {font-size: small; color: #666666; font-style:italic; }
-        .lastline {font-size: small; color: #666666; font-style:italic;}
-        .contact {font-size: small; color: #666666;}
-        .contact p {font-size: small; color: #666666;}
-        #photoCaption { font-family:verdana,arial,helvetica,sans-serif; font-size:x-small;}
-        .photoCaption { font-family:verdana,arial,helvetica,sans-serif; font-size:x-small;}
-        #photoCredit{ font-family:verdana,arial,helvetica,sans-serif; font-size:x-small; color:#666666;}
-        .photoCredit{ font-family:verdana,arial,helvetica,sans-serif; font-size:x-small; color:#666666;}
-        .article_timestamp{font-size:x-small; color:#666666;}
-        a {font-family:verdana,arial,helvetica,sans-serif; font-size: x-small;}
-                '''
+   # remove_tags_before = {'class':'article_timestamp'}
+    #remove_tags_after = {'class':'graylabel'}
+    keep_only_tags= [dict(name=['h1','p'])]
+    remove_tags = [dict(name=['hr','dl','dt','img','meta','iframe','link','script','form','input','label']),
+dict(id=['toggleConfirmEmailDiv','toggleTOS','toggleUsernameMsgDiv','toggleConfirmYear','navT1_philly','secondaryNav','navPlacement','globalPrimaryNav'
+,'ugc-footer-philly','bv_footer_include','footer','header',
+'container_rag_bottom','section_rectangle','contentrightside'])
+,{'class':['megamenu3 megamenu','container misc','container_inner misc_inner'
+,'misccontainer_left_32','headlineonly','misccontainer_middle_32'
+,'misccontainer_right_32','headline formBegin',
+'post_balloon','relatedlist','linkssubhead','b_sq','dotted-rule-above'
+,'container','headlines-digest','graylabel','container_inner'
+,'rlinks_colorbar1','rlinks_colorbar2','supercontainer','container_5col_left','container_image_left',
+'digest-headline2','digest-lead','container_5col_leftmiddle',
+'container_5col_middlemiddle','container_5col_rightmiddle'
+,'container_5col_right','divclear','supercontainer_outer force-width',
+'supercontainer','containertitle  kicker-title',
+'pollquestion','pollchoice','photomore','pollbutton','container rssbox','containertitle video ',
+'containertitle_image ','container_tabtwo','selected'
+,'shadetabs','selected','tabcontentstyle','tabcontent','inner_container'
+,'arrow','container_ad','containertitlespacer','adUnit','tracking','sitemsg_911 clearfix']}]
 
-    keep_only_tags = [
-               dict(name='div', attrs={'class':'story-content'}),
-               dict(name='div', attrs={'id': 'contentinside'})
-                    ]
+    extra_css             = """
+                               h1{font-family: Georgia,serif; font-size: xx-large}
 
-    remove_tags = [
-         dict(name='div', attrs={'class':['linkssubhead','post_balloon','relatedlist','pollquestion','b_sq']}),
-         dict(name='dl', attrs={'class':'relatedlist'}),
-        dict(name='div', attrs={'id':['photoNav','sidebar_adholder']}),
-        dict(name='a', attrs={'class': ['headlineonly','bl']}),
-         dict(name='img', attrs={'class':'img_noborder'})
-    ]
-   # def print_version(self, url):
-   #     return url + '?viewAll=y'
+                            """
 
 
-    feeds = [
-        ('Front Page', 'http://www.philly.com/inquirer_front_page.rss'),
-        ('Business', 'http://www.philly.com/inq_business.rss'),
-        #('News', 'http://www.philly.com/inquirer/news/index.rss'),
-        ('Nation', 'http://www.philly.com/inq_news_world_us.rss'),
-        ('Local', 'http://www.philly.com/inquirer_local.rss'),
-        ('Health', 'http://www.philly.com/inquirer_health_science.rss'),
-        ('Education', 'http://www.philly.com/inquirer_education.rss'),
-        ('Editorial and opinion', 'http://www.philly.com/inq_news_editorial.rss'),
-        ('Sports', 'http://www.philly.com/inquirer_sports.rss')
-        ]
+    feeds          = [(u'News', u'http://www.philly.com/philly_news.rss')]
 
-    def get_article_url(self, article):
-        ans = article.link
-
-        try:
-            self.log('Looking for full story link in', ans)
-            soup = self.index_to_soup(ans)
-            x = soup.find(text="View All")
-
-            if x is not None:
-                ans = ans + '?viewAll=y'
-                self.log('Found full story link', ans)
-        except:
-            pass
-        return ans
-
-    def postprocess_html(self, soup,first):
-
-         for tag in soup.findAll(name='div',attrs={'class':"container_ate_qandatitle"}):
-                tag.extract()
-         for tag in soup.findAll(name='br'):
-                tag.extract()
-
-         return soup

recipes/words_without_borders.recipe

@@ -0,0 +1,25 @@
+#recipe created by sexymax15.....sexymax15@gmail.com
+#Words without Borders recipe
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1308302002(BasicNewsRecipe):
+    title          = u'Words Without Borders'
+    language = 'en'
+    __author__ = 'sexymax15'
+    oldest_article = 90
+    max_articles_per_feed = 30
+    use_embedded_content = False
+
+    remove_empty_feeds = True
+    no_stylesheets = True
+    remove_javascript = True
+    keep_only_tags = {'class':'span-14 article'}
+    remove_tags_after = [{'class':'addthis_toolbox addthis_default_style no_print'}]
+    remove_tags = [{'class':['posterous_quote_citation','button']}]
+    extra_css             = """
+                               h1{font-family: Georgia,serif; font-size: large}h2{font-family: Georgia,serif; font-size: large} """
+
+
+
+    feeds          = [(u'wwb', u'http://feeds.feedburner.com/wwborders?format=xml')]

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, 5)
+numeric_version = (0, 8, 6)
 __version__   = u'.'.join(map(unicode, numeric_version))
 __author__    = u"Kovid Goyal <kovid@kovidgoyal.net>"
 

src/calibre/customize/builtins.py

@@ -867,11 +867,11 @@ class ActionStore(InterfaceActionBase):
         from calibre.gui2.store.config.store import save_settings as save
         save(config_widget)
 
-class ActionPluginUpdates(InterfaceActionBase):
-    name = 'Plugin Updates'
+class ActionPluginUpdater(InterfaceActionBase):
+    name = 'Plugin Updater'
     author = 'Grant Drake'
     description = 'Queries the MobileRead forums for updates to plugins to install'
-    actual_plugin = 'calibre.gui2.actions.plugin_updates:PluginUpdatesAction'
+    actual_plugin = 'calibre.gui2.actions.plugin_updates:PluginUpdaterAction'
 
 plugins += [ActionAdd, ActionFetchAnnotations, ActionGenerateCatalog,
         ActionConvert, ActionDelete, ActionEditMetadata, ActionView,
@@ -880,7 +880,7 @@ plugins += [ActionAdd, ActionFetchAnnotations, ActionGenerateCatalog,
         ActionSendToDevice, ActionHelp, ActionPreferences, ActionSimilarBooks,
         ActionAddToLibrary, ActionEditCollections, ActionChooseLibrary,
         ActionCopyToLibrary, ActionTweakEpub, ActionNextMatch, ActionStore,
-        ActionPluginUpdates]
+        ActionPluginUpdater]
 
 # }}}
 

src/calibre/ebooks/metadata/sources/base.py

@@ -21,6 +21,7 @@ from calibre.ebooks.metadata import check_isbn
 msprefs = JSONConfig('metadata_sources/global.json')
 msprefs.defaults['txt_comments'] = False
 msprefs.defaults['ignore_fields'] = []
+msprefs.defaults['user_default_ignore_fields'] = []
 msprefs.defaults['max_tags'] = 20
 msprefs.defaults['wait_after_first_identify_result'] = 30 # seconds
 msprefs.defaults['wait_after_first_cover_result'] = 60 # seconds

src/calibre/ebooks/metadata/sources/identify.py

@@ -85,6 +85,10 @@ class ISBNMerge(object):
                 isbns, min_year = xisbn.get_isbn_pool(isbn)
                 if not isbns:
                     isbns = frozenset([isbn])
+                if isbns in self.pools:
+                    # xISBN had a brain fart
+                    pool = self.pools[isbns]
+                else:
                     self.pools[isbns] = pool = (min_year, [])
 
             if not self.pool_has_result_from_same_source(pool, result):

src/calibre/ebooks/metadata/xisbn.py

@@ -45,6 +45,11 @@ class xISBN(object):
                 ans.append(rec)
         return ans
 
+    def isbns_in_data(self, data):
+        for rec in data:
+            for i in rec.get('isbn', []):
+                yield i
+
     def get_data(self, isbn):
         isbn = self.purify(isbn)
         with self.lock:
@@ -57,8 +62,7 @@ class xISBN(object):
                     data = []
                 id_ = len(self._data)
                 self._data.append(data)
-                for rec in data:
-                    for i in rec.get('isbn', []):
+                for i in self.isbns_in_data(data):
                     self._map[i] = id_
                 self._map[isbn] = id_
             return self._data[self._map[isbn]]

src/calibre/ebooks/mobi/mobiml.py

@@ -443,11 +443,15 @@ class MobiMLizer(object):
             tag = 'span' if tag == 'td' else 'div'
 
         if tag == 'table':
+            col = style.backgroundColor
+            if col:
+                elem.set('bgcolor', col)
             css = style.cssdict()
             if 'border' in css or 'border-width' in css:
                 elem.set('border', '1')
         if tag in TABLE_TAGS:
-            for attr in ('rowspan', 'colspan', 'width', 'border', 'scope'):
+            for attr in ('rowspan', 'colspan', 'width', 'border', 'scope',
+                    'bgcolor'):
                 if attr in elem.attrib:
                     istate.attrib[attr] = elem.attrib[attr]
         if tag == 'q':

src/calibre/ebooks/oeb/stylizer.py

@@ -11,7 +11,6 @@ __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
 import os, itertools, re, logging, copy, unicodedata
 from weakref import WeakKeyDictionary
 from xml.dom import SyntaxErr as CSSSyntaxError
-import cssutils
 from cssutils.css import (CSSStyleRule, CSSPageRule, CSSStyleDeclaration,
     CSSFontFaceRule, cssproperties)
 try:
@@ -20,7 +19,8 @@ try:
 except ImportError:
     # cssutils >= 0.9.8
     from cssutils.css import PropertyValue as CSSValueList
-from cssutils import profile as cssprofiles
+from cssutils import (profile as cssprofiles, parseString, parseStyle, log as
+        cssutils_log, CSSParser, profiles)
 from lxml import etree
 from lxml.cssselect import css_to_xpath, ExpressionError, SelectorSyntaxError
 from calibre import force_unicode
@@ -28,7 +28,7 @@ from calibre.ebooks import unit_convert
 from calibre.ebooks.oeb.base import XHTML, XHTML_NS, CSS_MIME, OEB_STYLES
 from calibre.ebooks.oeb.base import XPNSMAP, xpath, urlnormalize
 
-cssutils.log.setLevel(logging.WARN)
+cssutils_log.setLevel(logging.WARN)
 
 _html_css_stylesheet = None
 
@@ -36,7 +36,7 @@ def html_css_stylesheet():
     global _html_css_stylesheet
     if _html_css_stylesheet is None:
         html_css = open(P('templates/html.css'), 'rb').read()
-        _html_css_stylesheet = cssutils.parseString(html_css)
+        _html_css_stylesheet = parseString(html_css)
         _html_css_stylesheet.namespaces['h'] = XHTML_NS
     return _html_css_stylesheet
 
@@ -157,11 +157,11 @@ class Stylizer(object):
 
         # Add cssutils parsing profiles from output_profile
         for profile in self.opts.output_profile.extra_css_modules:
-            cssutils.profile.addProfile(profile['name'],
+            cssprofiles.addProfile(profile['name'],
                                         profile['props'],
                                         profile['macros'])
 
-        parser = cssutils.CSSParser(fetcher=self._fetch_css_file,
+        parser = CSSParser(fetcher=self._fetch_css_file,
                 log=logging.getLogger('calibre.css'))
         self.font_face_rules = []
         for elem in head:
@@ -473,6 +473,7 @@ class Style(object):
         self._width = None
         self._height = None
         self._lineHeight = None
+        self._bgcolor = None
         stylizer._styles[element] = self
 
     def set(self, prop, val):
@@ -533,6 +534,48 @@ class Style(object):
     def pt_to_px(self, value):
         return (self._profile.dpi / 72.0) * value
 
+    @property
+    def backgroundColor(self):
+        '''
+        Return the background color by parsing both the background-color and
+        background shortcut properties. Note that inheritance/default values
+        are not used. None is returned if no background color is set.
+        '''
+
+        def validate_color(col):
+            return cssprofiles.validateWithProfile('color',
+                        col,
+                        profiles=[profiles.Profiles.CSS_LEVEL_2])[1]
+
+        if self._bgcolor is None:
+            col = None
+            val = self._style.get('background-color', None)
+            if val and validate_color(val):
+                col = val
+            else:
+                val = self._style.get('background', None)
+                if val is not None:
+                    try:
+                        style = parseStyle('background: '+val)
+                        val = style.getProperty('background').cssValue
+                        try:
+                            val = list(val)
+                        except:
+                            # val is CSSPrimitiveValue
+                            val = [val]
+                        for c in val:
+                            c = c.cssText
+                            if validate_color(c):
+                                col = c
+                                break
+                    except:
+                        pass
+            if col is None:
+                self._bgcolor = False
+            else:
+                self._bgcolor = col
+        return self._bgcolor if self._bgcolor else None
+
     @property
     def fontSize(self):
         def normalize_fontsize(value, base):

src/calibre/gui2/actions/choose_library.py

@@ -287,6 +287,18 @@ class ChooseLibraryAction(InterfaceAction):
               'rate of approximately 1 book every three seconds.'), show=True)
 
     def restore_database(self):
+        m = self.gui.library_view.model()
+        db = m.db
+        if (iswindows and len(db.library_path) >
+                LibraryDatabase2.WINDOWS_LIBRARY_PATH_LIMIT):
+            return error_dialog(self.gui, _('Too long'),
+                    _('Path to library too long. Must be less than'
+                    ' %d characters. Move your library to a location with'
+                    ' a shorter path using Windows Explorer, then point'
+                    ' calibre to the new location and try again.')%
+                    LibraryDatabase2.WINDOWS_LIBRARY_PATH_LIMIT,
+                    show=True)
+
         from calibre.gui2.dialogs.restore_library import restore_database
         m = self.gui.library_view.model()
         m.stop_metadata_backup()

src/calibre/gui2/actions/plugin_updates.py

@@ -12,10 +12,10 @@ from calibre.gui2.actions import InterfaceAction
 from calibre.gui2.dialogs.plugin_updater import (PluginUpdaterDialog,
                                                  FILTER_ALL, FILTER_UPDATE_AVAILABLE)
 
-class PluginUpdatesAction(InterfaceAction):
+class PluginUpdaterAction(InterfaceAction):
 
-    name = 'Plugin Updates'
-    action_spec = (_('Plugin Updates'), None, None, None)
+    name = 'Plugin Updater'
+    action_spec = (_('Plugin Updater'), None, None, None)
     action_type = 'current'
 
     def genesis(self):

src/calibre/gui2/metadata/single.py

@@ -388,6 +388,10 @@ class MetadataSingleDialogBase(ResizableDialog):
 
     def apply_changes(self):
         self.changed.add(self.book_id)
+        if self.db is None:
+            # break_cycles has already been called, don't know why this should
+            # happen but a user reported it
+            return True
         for widget in self.basic_metadata_widgets:
             try:
                 if not widget.commit(self.db, self.book_id):

src/calibre/gui2/preferences/metadata_sources.py

@@ -224,6 +224,20 @@ class FieldsModel(QAbstractListModel): # {{{
             Qt.Unchecked])
         msprefs['ignore_fields'] = list(ignored_fields.union(changed))
 
+    def user_default_state(self, field):
+        return (Qt.Unchecked if field in msprefs.get('user_default_ignore_fields',[])
+                    else Qt.Checked)
+
+    def select_user_defaults(self):
+        self.overrides = dict([(f, self.user_default_state(f)) for f in self.fields])
+        self.reset()
+
+    def commit_user_defaults(self):
+        default_ignored_fields = set([x for x in msprefs['user_default_ignore_fields'] if x not in
+            self.overrides])
+        changed = set([k for k, v in self.overrides.iteritems() if v ==
+            Qt.Unchecked])
+        msprefs['user_default_ignore_fields'] = list(default_ignored_fields.union(changed))
 
 # }}}
 
@@ -286,6 +300,9 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
         self.select_all_button.clicked.connect(self.changed_signal)
         self.clear_all_button.clicked.connect(self.fields_model.clear_all)
         self.clear_all_button.clicked.connect(self.changed_signal)
+        self.select_default_button.clicked.connect(self.fields_model.select_user_defaults)
+        self.select_default_button.clicked.connect(self.changed_signal)
+        self.set_as_default_button.clicked.connect(self.fields_model.commit_user_defaults)
 
     def configure_plugin(self):
         for index in self.sources_view.selectionModel().selectedRows():

src/calibre/gui2/preferences/metadata_sources.ui

@@ -102,6 +102,26 @@
             </property>
            </widget>
           </item>
+          <item row="2" column="0">
+           <widget class="QPushButton" name="select_default_button">
+            <property name="text">
+             <string>&amp;Select default</string>
+            </property>
+             <property name="toolTip">
+             <string>Restore your own subset of checked fields that you define using the 'Set as default' button</string>
+            </property>
+           </widget>
+          </item>
+          <item row="2" column="1">
+           <widget class="QPushButton" name="set_as_default_button">
+            <property name="text">
+             <string>&amp;Set as default</string>
+            </property>
+             <property name="toolTip">
+             <string>Store the currently checked fields as a default you can restore using the 'Select default' button</string>
+            </property>
+           </widget>
+          </item>
          </layout>
         </widget>
        </item>

src/calibre/utils/localization.py

@@ -121,6 +121,7 @@ _extra_lang_codes = {
         'en_YE' : _('English (Yemen)'),
         'en_IE' : _('English (Ireland)'),
         'en_CN' : _('English (China)'),
+        'en_ZA' : _('English (South Africa)'),
         'es_PY' : _('Spanish (Paraguay)'),
         'es_UY' : _('Spanish (Uruguay)'),
         'es_AR' : _('Spanish (Argentina)'),

src/calibre/web/feeds/recipes/collection.py

@@ -21,8 +21,8 @@ NS = 'http://calibre-ebook.com/recipe_collection'
 E = ElementMaker(namespace=NS, nsmap={None:NS})
 
 def iterate_over_builtin_recipe_files():
-    exclude = ['craigslist', 'iht', 'outlook_india', 'toronto_sun',
-            'indian_express', 'india_today', 'livemint']
+    exclude = ['craigslist', 'iht', 'toronto_sun',
+            'india_today', 'livemint']
     d = os.path.dirname
     base = os.path.join(d(d(d(d(d(d(os.path.abspath(__file__))))))), 'recipes')
     for f in os.listdir(base):