Sync to trunk.

recipes/arcamax.recipe

@@ -6,12 +6,13 @@ __copyright__ = 'Copyright 2010 Starson17'
 www.arcamax.com
 '''
 from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag
 
 class Arcamax(BasicNewsRecipe):
     title               = 'Arcamax'
     __author__          = 'Starson17'
-    __version__         = '1.03'
+    __version__         = '1.04'
-    __date__            = '25 November 2010'
+    __date__            = '18 April 2011'
     description         = u'Family Friendly Comics - Customize for more days/comics: Defaults to 7 days, 25 comics - 20 general, 5 editorial.'
     category            = 'news, comics'
     language            = 'en'
@@ -30,8 +31,15 @@ class Arcamax(BasicNewsRecipe):
                         , 'language'          : language
                         }
 
-    keep_only_tags     = [dict(name='div', attrs={'class':['toon']}),
+    keep_only_tags     = [dict(name='div', attrs={'class':['comics-header']}),
-                          ]
+                                        dict(name='b', attrs={'class':['current']}),
+                                        dict(name='article', attrs={'class':['comic']}),
+                                        ]
+
+    remove_tags = [dict(name='div', attrs={'id':['comicfull' ]}),
+                               dict(name='div', attrs={'class':['calendar' ]}),
+                               dict(name='nav', attrs={'class':['calendar-nav' ]}),
+                               ]
 
     def parse_index(self):
         feeds = []
@@ -71,7 +79,6 @@ class Arcamax(BasicNewsRecipe):
                             #(u"Rugrats", u"http://www.arcamax.com/rugrats"),
                             (u"Speed Bump", u"http://www.arcamax.com/speedbump"),
                             (u"Wizard of Id", u"http://www.arcamax.com/wizardofid"),
-                            (u"Dilbert", u"http://www.arcamax.com/dilbert"),
                             (u"Zits", u"http://www.arcamax.com/zits"),
                              ]:
             articles = self.make_links(url)
@@ -86,24 +93,37 @@ class Arcamax(BasicNewsRecipe):
         for page in pages:
             page_soup = self.index_to_soup(url)
             if page_soup:
-                title = page_soup.find(name='div', attrs={'class':'toon'}).p.img['alt']
+                title = page_soup.find(name='div', attrs={'class':'comics-header'}).h1.contents[0]
                 page_url = url
-                prev_page_url = 'http://www.arcamax.com' + page_soup.find('a', attrs={'class':'next'}, text='Previous').parent['href']
+                # orig prev_page_url = 'http://www.arcamax.com' + page_soup.find('a', attrs={'class':'prev'}, text='Previous').parent['href']
-            current_articles.append({'title': title, 'url': page_url, 'description':'', 'date':''})
+                prev_page_url = 'http://www.arcamax.com' + page_soup.find('span', text='Previous').parent.parent['href']
+                date = self.tag_to_string(page_soup.find(name='b', attrs={'class':['current']}))
+            current_articles.append({'title': title, 'url': page_url, 'description':'', 'date': date})
             url = prev_page_url
         current_articles.reverse()
         return current_articles
 
     def preprocess_html(self, soup):
-        main_comic = soup.find('p',attrs={'class':'m0'})
+        for img_tag in soup.findAll('img'):
-        if main_comic.a['target'] == '_blank':
+            parent_tag = img_tag.parent
-            main_comic.a.img['id'] = 'main_comic'
+            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
 
     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;}
-                    img#main_comic {max-width:100%; min-width:100%;}
+                    img {max-width:100%; min-width:100%;}
                     p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                     body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
 		'''

recipes/babyonline.recipe

@@ -0,0 +1,59 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+babyonline.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class BabyOnline(BasicNewsRecipe):
+    title                 = u'Baby Online'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'De la p\u0103rinte la p\u0103rinte'
+    publisher             = u'Baby Online'
+    oldest_article        = 50
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,Copii,Mame'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.babyonline.ro/images/default/logo.gif'
+
+    conversion_options = {
+                                 'comments'   : description
+                                ,'tags'       : category
+                                ,'language'   : language
+                                ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                        dict(name='div', attrs={'id':'article_container'})
+                     ]
+
+    remove_tags = [
+						dict(name='div', attrs={'id':'bar_nav'}),
+						dict(name='div', attrs={'id':'service_send'}),
+						dict(name='div', attrs={'id':'other_videos'}),
+						dict(name='div', attrs={'class':'dot_line_yellow'}),
+						dict(name='a', attrs={'class':'print'}),
+						dict(name='a', attrs={'class':'email'}),
+						dict(name='a', attrs={'class':'YM'}),
+						dict(name='a', attrs={'class':'comment'}),
+						dict(name='div', attrs={'class':'tombstone_cross'}),
+						dict(name='span', attrs={'class':'liketext'})
+                  ]
+
+    remove_tags_after = [
+						dict(name='div', attrs={'id':'service_send'})
+                        ]
+
+    feeds          = [
+                        (u'Feeds', u'http://www.babyonline.ro/rss_homepage.xml')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

recipes/daily_telegraph.recipe

@@ -61,6 +61,12 @@ class DailyTelegraph(BasicNewsRecipe):
                       (u'Entertainment News', u'http://feeds.news.com.au/public/rss/2.0/dtele_entertainment_news_201.xml'),
                       (u'Lifestyle News', u'http://feeds.news.com.au/public/rss/2.0/dtele_lifestyle_227.xml'),
                       (u'Music', u'http://feeds.news.com.au/public/rss/2.0/dtele_music_441.xml'),
+                      (u'Sport',
+                          u'http://feeds.news.com.au/public/rss/2.0/dtele_sport_203.xml'),
+                      (u'Soccer',
+                          u'http://feeds.news.com.au/public/rss/2.0/dtele_sports_soccer_344.xml'),
+                      (u'Rugby Union',
+                          u'http://feeds.news.com.au/public/rss/2.0/dtele_sports_rugby_union_342.xml'),
                       (u'Property Confidential', u'http://feeds.news.com.au/public/rss/2.0/dtele_property_confidential_463.xml'),
                       (u'Property - Your Space', u'http://feeds.news.com.au/public/rss/2.0/dtele_property_yourspace_462.xml'),
                       (u'Confidential News', u'http://feeds.news.com.au/public/rss/2.0/dtele_entertainment_confidential_252.xml'),

recipes/der_spiegel.recipe

@@ -0,0 +1,83 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2011, Nikolas Mangold <nmangold at gmail.com>'
+'''
+spiegel.de
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre import strftime
+from calibre import re
+
+class DerSpiegel(BasicNewsRecipe):
+    title                  = 'Der Spiegel'
+    __author__             = 'Nikolas Mangold'
+    description            = 'Der Spiegel, Printed Edition. Access to paid content.'
+    publisher              = 'SPIEGEL-VERLAG RUDOLF AUGSTEIN GMBH & CO. KG'
+    category               = 'news, politics, Germany'
+    no_stylesheets         = True
+    encoding               = 'cp1252'
+    needs_subscription     = True
+    remove_empty_feeds     = True
+    delay                  = 1
+    PREFIX                 = 'http://m.spiegel.de'
+    INDEX                  = PREFIX + '/spiegel/print/epaper/index-heftaktuell.html'
+    use_embedded_content   = False
+    masthead_url = 'http://upload.wikimedia.org/wikipedia/en/thumb/1/17/Der_Spiegel_logo.svg/200px-Der_Spiegel_logo.svg.png'
+    language               = 'de'
+    publication_type       = 'magazine'
+    extra_css              = ' body{font-family: Arial,Helvetica,sans-serif} '
+    timefmt = '[%W/%Y]'
+    empty_articles = ['Titelbild']
+    preprocess_regexps = [
+        (re.compile(r'<p>&#9670;</p>', re.DOTALL|re.IGNORECASE), lambda match: '<hr>'),
+        ]
+
+    def get_browser(self):
+        def has_login_name(form):
+            try:
+                form.find_control(name="f.loginName")
+            except:
+                return False
+            else:
+                return True
+
+        br = BasicNewsRecipe.get_browser()
+        if self.username is not None and self.password is not None:
+            br.open(self.PREFIX + '/meinspiegel/login.html')
+            br.select_form(predicate=has_login_name)
+            br['f.loginName'    ] = self.username
+            br['f.password'] = self.password
+            br.submit()
+        return br
+
+    remove_tags_before =  dict(attrs={'class':'spArticleContent'})
+    remove_tags_after  =  dict(attrs={'class':'spArticleCredit'})
+
+    def parse_index(self):
+        soup = self.index_to_soup(self.INDEX)
+
+        cover = soup.find('img', width=248)
+        if cover is not None:
+            self.cover_url = cover['src']
+
+        index = soup.find('dl')
+
+        feeds = []
+        for section in index.findAll('dt'):
+            section_title = self.tag_to_string(section).strip()
+            self.log('Found section ', section_title)
+
+            articles = []
+            for article in section.findNextSiblings(['dd','dt']):
+                if article.name == 'dt':
+                    break
+                link = article.find('a')
+                title = self.tag_to_string(link).strip()
+                if title in self.empty_articles:
+                    continue
+                self.log('Found article ', title)
+                url = self.PREFIX + link['href']
+                articles.append({'title' : title, 'date' : strftime(self.timefmt), 'url' : url})
+            feeds.append((section_title,articles))
+        return feeds;

recipes/ecuisine.recipe

@@ -14,14 +14,14 @@ class EcuisineRo(BasicNewsRecipe):
     __author__            = u'Silviu Cotoar\u0103'
     description           = u'Reinventeaz\u0103 pl\u0103cerea de a g\u0103ti'
     publisher             = 'eCuisine'
-    oldest_article        = 5
+    oldest_article        = 50
     language              = 'ro'
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
     category              = 'Ziare,Retete,Bucatarie'
     encoding              = 'utf-8'
-    cover_url             = ''
+    cover_url             = 'http://www.ecuisine.ro/sites/all/themes/ecuisine/images/logo.gif'
 
     conversion_options = {
                              'comments'   : description
@@ -31,8 +31,8 @@ class EcuisineRo(BasicNewsRecipe):
                          }
 
     keep_only_tags = [
-            dict(name='div', attrs={'class':'page-title'})
+            dict(name='h1', attrs={'id':'page-title'})
-            , dict(name='div', attrs={'class':'content clearfix'})
+            , dict(name='div', attrs={'class':'field-item even'})
                      ]
 
     remove_tags = [

recipes/egirl.recipe

@@ -31,8 +31,8 @@ class EgirlRo(BasicNewsRecipe):
                          }
 
     keep_only_tags = [
-                          dict(name='div', attrs={'id':'title_art'})
+                          dict(name='div', attrs={'id':'content_art'})
-                        , dict(name='div', attrs={'class':'content_style'})
+                        , dict(name='div', attrs={'class':'content_articol'})
                      ]
 
     feeds          = [

recipes/handelsblatt.recipe

@@ -1,4 +1,3 @@
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Handelsblatt(BasicNewsRecipe):
@@ -7,14 +6,11 @@ class Handelsblatt(BasicNewsRecipe):
     oldest_article = 7
     max_articles_per_feed = 100
     no_stylesheets = True
-    cover_url = 'http://www.handelsblatt.com/images/logo/logo_handelsblatt.com.png'
+#    cover_url = 'http://www.handelsblatt.com/images/logo/logo_handelsblatt.com.png'
     language = 'de'
-  #  keep_only_tags = []
+
-    keep_only_tags = (dict(name = 'div', attrs = {'class': ['hcf-detail-abstract hcf-teaser ajaxify','hcf-detail','hcf-author-wrapper']}))
+    remove_tags_before =  dict(attrs={'class':'hcf-overline'})
-   # keep_only_tags.append(dict(name = 'div', attrs = {'id': 'fullText'}))
+    remove_tags_after  =  dict(attrs={'class':'hcf-footer'})
-    remove_tags    = [dict(name='img', attrs = {'src': 'http://www.handelsblatt.com/images/icon/loading.gif'})
-                      ,dict(name='ul' , attrs={'class':['hcf-detail-tools']})
-    									]
 
     feeds          = [
                         (u'Handelsblatt Exklusiv',u'http://www.handelsblatt.com/rss/exklusiv'),
@@ -28,17 +24,16 @@ class Handelsblatt(BasicNewsRecipe):
                         (u'Handelsblatt Magazin',u'http://www.handelsblatt.com/rss/magazin/'),
                         (u'Handelsblatt Weblogs',u'http://www.handelsblatt.com/rss/blogs')
                      ]
+
     extra_css = '''
-        .hcf-headline {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:x-large;}
+        h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
-        .hcf-overline {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:x-large;}
+        h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
-        .hcf-exclusive {font-family:Arial,Helvetica,sans-serif; font-style:italic;font-weight:bold; margin-right:5pt;}
+        p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
-        p{font-family:Arial,Helvetica,sans-serif;}
+        body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
-        .hcf-location-mark{font-weight:bold; margin-right:5pt;}
-        .MsoNormal{font-family:Helvetica,Arial,sans-serif;}
-        .hcf-author-wrapper{font-style:italic;}
-        .hcf-article-date{font-size:x-small;}
-        .hcf-caption {font-style:italic;font-size:small;}
-        img {align:left;}
         '''
 
-
+    def print_version(self, url):
+        url = url.split('/')
+        url[-1] = 'v_detail_tab_print,'+url[-1]
+        url = '/'.join(url)
+        return url

recipes/ilsole24ore.recipe

@@ -1,71 +1,65 @@
-#!/usr/bin/env  python
+__author__    = 'Marco Saraceno'
-__license__   = 'GPL v3'
+__copyright__ = '2010, Marco Saraceno <marcosaraceno at gmail.com>'
-__author__    = 'Lorenzo Vigentini & Edwin van Maastrigt'
+description   = 'Italian daily newspaper - v 1.1 (Mar14,2011)'
-__copyright__ = '2009, Lorenzo Vigentini <l.vigentini at gmail.com> and Edwin van Maastrigt <evanmaastrigt at gmail.com>'
-__description__ = 'Financial news daily paper - v1.02 (30, January 2010)'
 
 '''
-http://www.ilsole24ore.com/
+http://www.ilsole24ore.com
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
+class IlSole24Ore(BasicNewsRecipe):
+    __author__        = 'Marco Saraceno'
+    description   = 'Italian financial daily newspaper'
 
-class ilsole24Ore(BasicNewsRecipe):
+    cover_url      = 'http://www.shopping24.ilsole24ore.com/ProductRelated/rds/img/logo_sole.gif'
-    author        = 'Lorenzo Vigentini & Edwin van Maastrigt'
+    title          = u'Il Sole 24 Ore'
-    description   = 'Financial news daily paper'
+    publisher      = 'Gruppo editoriale GRUPPO 24ORE'
-
+    category       = 'News, politics, culture, economy, financial, Italian'
-    cover_url      = 'http://www.ilsole24ore.com/img2007/print_header.gif'
-
-    title          = u'il Sole 24 Ore New'
-    publisher      = 'italiaNews'
-    category       = 'News, finance, economy, politics'
 
     language       = 'it'
     timefmt        = '[%a, %d %b, %Y]'
 
     oldest_article = 2
-    max_articles_per_feed = 50
+    max_articles_per_feed = 100
     use_embedded_content  = False
+    extra_css      = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt  }'
+
+
+    remove_tags = [
+                            dict(name='div', attrs={'class':['header','titolo']}),
+                            dict(name='table', attrs={'class':['footer1024','footerdown']}),
+                            ]
 
-    remove_javascript     = True
-    no_stylesheets        = True
 
     def get_article_url(self, article):
-        return article.get('id', article.get('guid', None))
+       link = article.get('link', None)
+       if link is None:
+           return article
+       if link.split('/')[-1]=="story01.htm":
+           link=link.split('/')[-2]
+           a=['0B','0C','0D','0E','0F','0G','0N'  ,'0L0S','0A']
+           b=['.' ,'/' ,'?' ,'-' ,'=' ,'&' ,'.com','www.','0']
+           for i in range(0,len(a)):
+              link=link.replace(a[i],b[i])
+           link="http://"+link
+       return link
+
+    feeds = [
+                  (u'Notizie Italia', u'http://www.ilsole24ore.com/rss/notizie/italia.xml'),
+                  (u'Notizie Europa', u'http://www.ilsole24ore.com/rss/notizie/europa.xml'),
+                  (u'Notizie USA', u'http://www.ilsole24ore.com/rss/notizie/usa.xml'),
+                  (u'Notizie Americhe', u'http://www.ilsole24ore.com/rss/notizie/americhe.xml'),
+                  (u'Notizie Medio Oriente e Africa', u'http://www.ilsole24ore.com/rss/notizie/medio-oriente-e-africa.xml'),
+                  (u'Notizie Asia e Oceania', u'http://www.ilsole24ore.com/rss/notizie/asia-e-oceania.xml'),
+                  (u'Commenti', u'http://www.ilsole24ore.com/rss/commenti-e-idee.xml'),
+                  (u'Norme e tributi', u'http://www.ilsole24ore.com/rss/norme-e-tributi.xml'),
+                  (u'Finanza', u'http://www.ilsole24ore.com/rss/finanza-e-mercati.xml'),
+                  (u'Economia', u'http://www.ilsole24ore.com/rss/economia.xml'),
+                  (u'Tecnologia', u'http://www.ilsole24ore.com/rss/tecnologie.xml'),
+                  (u'Cultura', u'http://www.ilsole24ore.com/rss/cultura.xml'),
+                  ]
 
     def print_version(self, url):
-        link, sep, params = url.rpartition('?')
+          return url.replace('.shtml', '_PRN.shtml')
-        if link  is None:
-           return link.replace('_1.php', '_php')
-        return link.replace('.shtml', '_PRN.shtml')
-
-    keep_only_tags     = [
-                            dict(name='div', attrs={'class':'txt'})
-                        ]
-#    remove_tags = [dict(name='br')]
-
-    feeds          = [
-                       (u'Prima pagina', u'http://www.ilsole24ore.com/rss/primapagina.xml'),
-                       (u'Norme e tributi', u'http://www.ilsole24ore.com/rss/norme-tributi.xml'),
-                       (u'Finanza e mercati', u'http://www.ilsole24ore.com/rss/finanza-mercati.xml'),
-                       (u'Economia e lavoro', u'http://www.ilsole24ore.com/rss/economia-lavoro.xml'),
-                       (u'Italia', u'http://www.ilsole24ore.com/rss/italia.xml'),
-                       (u'Mondo', u'http://www.ilsole24ore.com/rss/mondo.xml'),
-                       (u'Tecnologia e business', u'http://www.ilsole24ore.com/rss/tecnologia-business.xml'),
-                       (u'Cultura e tempo libero', u'http://www.ilsole24ore.com/rss/tempolibero-cultura.xml'),
-                       (u'Sport', u'http://www.ilsole24ore.com/rss/sport.xml'),
-                       (u'Professionisti 24', u'http://www.ilsole24ore.com/rss/prof_home.xml'),
-                       (u'Ambiente e Sicurezza',u'http://www.ilsole24ore.com/rss/prof_as.xml')
-                     ]
-
-    extra_css = '''
-                html, body, table, tr, td, h1, h2, h3, h4, h5, h6, p, a, span, br, img {margin:0;padding:0;border:0;font-size:12px;font-family:"Georgia","Times New Roman";}
-                .linkHighlight {color:#0292c6;}
-                .txt {border-bottom:1px solid #7c7c7c;padding-bottom:20px};text-align:justify;font-family:"serif"}
-                .txt p {line-height:18px;}
-                .txt span {line-height:22px;}
-                .title h3 {color:#7b7b7b;}
-                .title h4 {color:#08526e;font-size:26px;font-family:"Times New Roman";font-weight:normal;}
-                '''
 

recipes/newsweek.recipe

@@ -1,4 +1,3 @@
-import string
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Newsweek(BasicNewsRecipe):
@@ -11,7 +10,6 @@ class Newsweek(BasicNewsRecipe):
     no_stylesheets = True
 
     BASE_URL = 'http://www.newsweek.com'
-    INDEX = BASE_URL+'/topics.html'
 
     keep_only_tags = dict(name='article', attrs={'class':'article-text'})
     remove_tags = [dict(attrs={'data-dartad':True})]
@@ -23,11 +21,14 @@ class Newsweek(BasicNewsRecipe):
         return soup
 
     def newsweek_sections(self):
-        soup = self.index_to_soup(self.INDEX)
+        return [
-        for a in soup.findAll('a', title='Primary tag', href=True):
+                ('Nation', 'http://www.newsweek.com/tag/nation.html'),
-            yield (string.capitalize(self.tag_to_string(a)),
+                ('Society', 'http://www.newsweek.com/tag/society.html'),
-                    self.BASE_URL+a['href'])
+                ('Culture', 'http://www.newsweek.com/tag/culture.html'),
-
+                ('World', 'http://www.newsweek.com/tag/world.html'),
+                ('Politics', 'http://www.newsweek.com/tag/politics.html'),
+                ('Business', 'http://www.newsweek.com/tag/business.html'),
+        ]
 
     def newsweek_parse_section_page(self, soup):
         for article in soup.findAll('article', about=True,

recipes/slashdot.recipe

@@ -8,23 +8,36 @@ __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net> edited by Huan T'
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Slashdot(BasicNewsRecipe):
-             title          = u'Slashdot.org'
+    title          = u'Slashdot.org'
-             description    = '''Tech news. WARNING: This recipe downloads a lot
+    description    = '''Tech news. WARNING: This recipe downloads a lot
-             of content and may result in your IP being banned from slashdot.org'''
+    of content and may result in your IP being banned from slashdot.org'''
-             oldest_article = 7
+    oldest_article = 7
-             simultaneous_downloads = 1
+    simultaneous_downloads = 1
-             delay = 3
+    delay = 3
-             max_articles_per_feed = 100
+    max_articles_per_feed = 100
-             language = 'en'
+    language = 'en'
 
-             __author__ = 'floweros edited by Huan T'
+    __author__ = 'floweros edited by Huan T'
-             no_stylesheets = True
+    no_stylesheets = True
-#             keep_only_tags = [
+    keep_only_tags = [
-#                 dict(name='div',attrs={'class':'article'}),
+        dict(name='div',attrs={'id':'article'}),
-#                 dict(name='div',attrs={'class':'commentTop'}),
+        dict(name='div',attrs={'class':['postBody' 'details']}),
-#                 ]
+        dict(name='footer',attrs={'class':['clearfix meta article-foot']}),
+        dict(name='article',attrs={'class':['fhitem fhitem-story article usermode thumbs grid_24']}),
+        dict(name='dl',attrs={'class':'relatedPosts'}),
+        dict(name='h2',attrs={'class':'story'}),
+        dict(name='span',attrs={'class':'comments'}),
+        ]
 
-             feeds          = [
+
+    remove_tags    = [
+        dict(name='aside',attrs={'id':'slashboxes'}),
+        dict(name='div',attrs={'class':'paginate'}),
+        dict(name='section',attrs={'id':'comments'}),
+        dict(name='span',attrs={'class':'topic'}),
+        ]
+
+    feeds          = [
                  (u'Slashdot',
  u'http://rss.slashdot.org/Slashdot/slashdot'),
                  (u'/. IT',
@@ -37,5 +50,3 @@ class Slashdot(BasicNewsRecipe):
  u'http://rss.slashdot.org/Slashdot/slashdotYourRightsOnline')
                  ]
 
-             def get_article_url(self, article):
-                          return article.get('feedburner_origlink', None)

recipes/tabu.recipe

@@ -37,10 +37,12 @@ class TabuRo(BasicNewsRecipe):
                      ]
 
     remove_tags = [
-            dict(name='div', attrs={'class':'asemanatoare'})
+            dict(name='div', attrs={'class':'asemanatoare'}),
+			 dict(name='div', attrs={'class':'social'})
                            ]
 
     remove_tags_after = [
+					  dict(name='div', attrs={'class':'social'}),
                       dict(name='div', attrs={'id':'comments'}),
                       dict(name='div', attrs={'class':'asemanatoare'})
                         ]

recipes/the_journal.recipe

@@ -0,0 +1,26 @@
+__license__   = 'GPL v3'
+__copyright__ = '2011 Phil Burns'
+'''
+TheJournal.ie
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class TheJournal(BasicNewsRecipe):
+
+    __author_              = 'Phil Burns'
+    title                  = u'TheJournal.ie'
+    oldest_article         = 1
+    max_articles_per_feed  = 100
+    encoding               = 'utf8'
+    language               = 'en_IE'
+    timefmt                = ' (%A, %B %d, %Y)'
+
+    no_stylesheets         = True
+    remove_tags            = [dict(name='div', attrs={'class':'footer'}),
+                           dict(name=['script', 'noscript'])]
+
+    extra_css              = 'p, div { margin: 0pt; border: 0pt; text-indent: 0.5em }'
+
+    feeds                  = [
+                          (u'Latest News', u'http://www.thejournal.ie/feed/')]

resources/default_tweaks.py

@@ -48,7 +48,7 @@ authors_completer_append_separator = False
 # When this tweak is changed, the author_sort values stored with each author
 # must be recomputed by right-clicking on an author in the left-hand tags pane,
 # selecting 'manage authors', and pressing 'Recalculate all author sort values'.
-author_sort_copy_method = 'invert'
+author_sort_copy_method = 'comma'
 
 #: Use author sort in Tag Browser
 # Set which author field to display in the tags pane (the list of authors,

resources/template-functions.json

@@ -5,6 +5,7 @@
     "strcat": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n    i = 0\n    res = ''\n    for i in range(0, len(args)):\n        res += args[i]\n    return res\n", 
     "substr": "def evaluate(self, formatter, kwargs, mi, locals, str_, start_, end_):\n    return str_[int(start_): len(str_) if int(end_) == 0 else int(end_)]\n", 
     "ifempty": "def evaluate(self, formatter, kwargs, mi, locals, val, value_if_empty):\n    if val:\n        return val\n    else:\n        return value_if_empty\n", 
+    "booksize": "def evaluate(self, formatter, kwargs, mi, locals):\n    if mi.book_size is not None:\n        try:\n            return str(mi.book_size)\n        except:\n            pass\n    return ''\n", 
     "select": "def evaluate(self, formatter, kwargs, mi, locals, val, key):\n    if not val:\n        return ''\n    vals = [v.strip() for v in val.split(',')]\n    for v in vals:\n        if v.startswith(key+':'):\n            return v[len(key)+1:]\n    return ''\n", 
     "field": "def evaluate(self, formatter, kwargs, mi, locals, name):\n    return formatter.get_value(name, [], kwargs)\n", 
     "subtract": "def evaluate(self, formatter, kwargs, mi, locals, x, y):\n    x = float(x if x else 0)\n    y = float(y if y else 0)\n    return unicode(x - y)\n", 
@@ -25,9 +26,9 @@
     "capitalize": "def evaluate(self, formatter, kwargs, mi, locals, val):\n    return capitalize(val)\n", 
     "count": "def evaluate(self, formatter, kwargs, mi, locals, val, sep):\n    return unicode(len(val.split(sep)))\n", 
     "lowercase": "def evaluate(self, formatter, kwargs, mi, locals, val):\n    return val.lower()\n", 
-    "assign": "def evaluate(self, formatter, kwargs, mi, locals, target, value):\n    locals[target] = value\n    return value\n", 
-    "switch": "def evaluate(self, formatter, kwargs, mi, locals, val, *args):\n    if (len(args) % 2) != 1:\n        raise ValueError(_('switch requires an odd number of arguments'))\n    i = 0\n    while i < len(args):\n        if i + 1 >= len(args):\n            return args[i]\n        if re.search(args[i], val):\n            return args[i+1]\n        i += 2\n", 
     "strcmp": "def evaluate(self, formatter, kwargs, mi, locals, x, y, lt, eq, gt):\n    v = strcmp(x, y)\n    if v < 0:\n        return lt\n    if v == 0:\n        return eq\n    return gt\n", 
+    "switch": "def evaluate(self, formatter, kwargs, mi, locals, val, *args):\n    if (len(args) % 2) != 1:\n        raise ValueError(_('switch requires an odd number of arguments'))\n    i = 0\n    while i < len(args):\n        if i + 1 >= len(args):\n            return args[i]\n        if re.search(args[i], val):\n            return args[i+1]\n        i += 2\n", 
+    "assign": "def evaluate(self, formatter, kwargs, mi, locals, target, value):\n    locals[target] = value\n    return value\n", 
     "raw_field": "def evaluate(self, formatter, kwargs, mi, locals, name):\n    return unicode(getattr(mi, name, None))\n", 
     "cmp": "def evaluate(self, formatter, kwargs, mi, locals, x, y, lt, eq, gt):\n    x = float(x if x else 0)\n    y = float(y if y else 0)\n    if x < y:\n        return lt\n    if x == y:\n        return eq\n    return gt\n"
 }

setup.py

@@ -15,9 +15,9 @@ from setup import prints, get_warnings
 
 def check_version_info():
     vi = sys.version_info
-    if vi[0] == 2 and vi[1] > 5:
+    if vi[0] == 2 and vi[1] > 6:
         return None
-    return 'calibre requires python >= 2.6'
+    return 'calibre requires python >= 2.7 and < 3'
 
 def option_parser():
     parser = optparse.OptionParser()

setup/__init__.py

@@ -24,8 +24,10 @@ def initialize_constants():
     global __version__, __appname__, modules, functions, basenames, scripts
 
     src = open('src/calibre/constants.py', 'rb').read()
-    __version__ = re.search(r'__version__\s+=\s+[\'"]([^\'"]+)[\'"]', src).group(1)
+    nv = re.search(r'numeric_version\s+=\s+\((\d+), (\d+), (\d+)\)', src)
-    __appname__ = re.search(r'__appname__\s+=\s+[\'"]([^\'"]+)[\'"]', src).group(1)
+    __version__ = '%s.%s.%s'%(nv.group(1), nv.group(2), nv.group(3))
+    __appname__ = re.search(r'__appname__\s+=\s+(u{0,1})[\'"]([^\'"]+)[\'"]',
+            src).group(2)
     epsrc = re.compile(r'entry_points = (\{.*?\})', re.DOTALL).\
             search(open('src/calibre/linux.py', 'rb').read()).group(1)
     entry_points = eval(epsrc, {'__appname__': __appname__})

setup/installer/windows/freeze.py

@@ -13,7 +13,8 @@ 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 = 'Q:\\Qt\\4.7.1'
+OPENSSL_DIR = r'Q:\openssl'
+QT_DIR = 'Q:\\Qt\\4.7.2'
 QT_DLLS = ['Core', 'Gui', 'Network', 'Svg', 'WebKit', 'Xml', 'XmlPatterns']
 LIBUSB_DIR       = 'C:\\libusb'
 LIBUNRAR         = 'C:\\Program Files\\UnrarDLL\\unrar.dll'
@@ -108,6 +109,8 @@ class Win32Freeze(Command, WixMixIn):
         self.dll_dir = self.j(self.base, 'DLLs')
         shutil.copytree(r'C:\Python%s\DLLs'%self.py_ver, self.dll_dir,
                 ignore=shutil.ignore_patterns('msvc*.dll', 'Microsoft.*'))
+        for x in glob.glob(self.j(OPENSSL_DIR, 'bin', '*.dll')):
+            shutil.copy2(x, self.dll_dir)
         for x in QT_DLLS:
             x += '4.dll'
             if not x.startswith('phonon'): x = 'Qt'+x

setup/installer/windows/notes.rst

@@ -53,12 +53,25 @@ SQLite
 
 Put sqlite3*.h from the sqlite windows amlgamation in ~/sw/include
 
+OpenSSL
+--------
+
+First install ActiveState Perl if you dont already have perl in windows
+Download and untar the openssl tarball, follow the instructions in INSTALL.W32 (use no-asm)
+to install use prefix q:\openssl
+
+perl Configure VC-WIN32 no-asm enable-static-engine --prefix=Q:/openssl
+ms\do_ms.bat
+nmake -f ms\ntdll.mak
+nmake -f ms\ntdll.mak test
+nmake -f ms\ntdll.mak install
+
 Qt
 --------
 
 Extract Qt sourcecode to C:\Qt\4.x.x. Run configure and make::
 
-    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 -nomake examples -nomake demos -nomake docs && nmake
+    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 -nomake examples -nomake demos -nomake docs -openssl -I Q:\openssl\include -L Q:\openssl\lib && nmake
 
 SIP
 -----

src/calibre/__init__.py

@@ -3,11 +3,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
-import uuid, sys, os, re, logging, time, random, \
+import sys, os, re, time, random, __builtin__, warnings
-       __builtin__, warnings, multiprocessing
-from contextlib import closing
-from urllib import getproxies
-from urllib2 import unquote as urllib2_unquote
 __builtin__.__dict__['dynamic_property'] = lambda(func): func(None)
 from htmlentitydefs import name2codepoint
 from math import floor
@@ -16,25 +12,51 @@ from functools import partial
 warnings.simplefilter('ignore', DeprecationWarning)
 
 
-from calibre.constants import iswindows, isosx, islinux, isfreebsd, isfrozen, \
+from calibre.constants import (iswindows, isosx, islinux, isfreebsd, isfrozen,
-                              terminal_controller, preferred_encoding, \
+                              preferred_encoding, __appname__, __version__, __author__,
-                              __appname__, __version__, __author__, \
+                              win32event, win32api, winerror, fcntl,
-                              win32event, win32api, winerror, fcntl, \
+                              filesystem_encoding, plugins, config_dir)
-                              filesystem_encoding, plugins, config_dir
+from calibre.startup import winutil, winutilerror
-from calibre.startup import winutil, winutilerror, guess_type
 
-if islinux and not getattr(sys, 'frozen', False):
+if False and islinux and not getattr(sys, 'frozen', False):
-    # Imported before PyQt4 to workaround PyQt4 util-linux conflict on gentoo
+    # Imported before PyQt4 to workaround PyQt4 util-linux conflict discovered on gentoo
+    # See http://bugs.gentoo.org/show_bug.cgi?id=317557
+    # Importing uuid is slow so get rid of this at some point, maybe in a few
+    # years when even Debian has caught up
+    # Also remember to remove it from site.py in the binary builds
+    import uuid
     uuid.uuid4()
 
 if False:
     # Prevent pyflakes from complaining
     winutil, winutilerror, __appname__, islinux, __version__
-    fcntl, win32event, isfrozen, __author__, terminal_controller
+    fcntl, win32event, isfrozen, __author__
-    winerror, win32api, isfreebsd, guess_type
+    winerror, win32api, isfreebsd
 
-import cssutils
+_mt_inited = False
-cssutils.log.setLevel(logging.WARN)
+def _init_mimetypes():
+    global _mt_inited
+    import mimetypes
+    mimetypes.init([P('mime.types')])
+    _mt_inited = True
+
+def guess_type(*args, **kwargs):
+    import mimetypes
+    if not _mt_inited:
+        _init_mimetypes()
+    return mimetypes.guess_type(*args, **kwargs)
+
+def guess_all_extensions(*args, **kwargs):
+    import mimetypes
+    if not _mt_inited:
+        _init_mimetypes()
+    return mimetypes.guess_all_extensions(*args, **kwargs)
+
+def get_types_map():
+    import mimetypes
+    if not _mt_inited:
+        _init_mimetypes()
+    return mimetypes.types_map
 
 def to_unicode(raw, encoding='utf-8', errors='strict'):
     if isinstance(raw, unicode):
@@ -182,6 +204,7 @@ class CommandLineError(Exception):
     pass
 
 def setup_cli_handlers(logger, level):
+    import logging
     if os.environ.get('CALIBRE_WORKER', None) is not None and logger.handlers:
         return
     logger.setLevel(level)
@@ -243,6 +266,7 @@ def extract(path, dir):
     extractor(path, dir)
 
 def get_proxies(debug=True):
+    from urllib import getproxies
     proxies = getproxies()
     for key, proxy in list(proxies.items()):
         if not proxy or '..' in proxy:
@@ -386,6 +410,7 @@ class StreamReadWrapper(object):
 
 def detect_ncpus():
     """Detects the number of effective CPUs in the system"""
+    import multiprocessing
     ans = -1
     try:
         ans = multiprocessing.cpu_count()
@@ -550,6 +575,9 @@ def get_download_filename(url, cookie_file=None):
     '''
     Get a local filename for a URL using the content disposition header
     '''
+    from contextlib import closing
+    from urllib2 import unquote as urllib2_unquote
+
     filename = ''
 
     br = browser()
@@ -679,4 +707,3 @@ main()
     ipshell()
     sys.argv = old_argv
 
-

src/calibre/constants.py

@@ -1,28 +1,32 @@
+from future_builtins import map
+
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
-__appname__   = 'calibre'
+__appname__   = u'calibre'
-__version__   = '0.7.56'
+numeric_version = (0, 7, 56)
-__author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
+__version__   = u'.'.join(map(unicode, numeric_version))
-
+__author__    = u"Kovid Goyal <kovid@kovidgoyal.net>"
-import re, importlib
-_ver = __version__.split('.')
-_ver = [int(re.search(r'(\d+)', x).group(1)) for x in _ver]
-numeric_version = tuple(_ver)
 
 '''
 Various run time constants.
 '''
 
-import sys, locale, codecs, os
+import sys, locale, codecs, os, importlib, collections
-from calibre.utils.terminfo import TerminalController
 
-terminal_controller = TerminalController(sys.stdout)
+_tc = None
+def terminal_controller():
+    global _tc
+    if _tc is None:
+        from calibre.utils.terminfo import TerminalController
+        _tc = TerminalController(sys.stdout)
+    return _tc
 
-iswindows = 'win32' in sys.platform.lower() or 'win64' in sys.platform.lower()
+_plat = sys.platform.lower()
-isosx     = 'darwin' in sys.platform.lower()
+iswindows = 'win32' in _plat or 'win64' in _plat
-isnewosx = isosx and getattr(sys, 'new_app_bundle', False)
+isosx     = 'darwin' in _plat
-isfreebsd = 'freebsd' in sys.platform.lower()
+isnewosx  = isosx and getattr(sys, 'new_app_bundle', False)
+isfreebsd = 'freebsd' in _plat
 islinux   = not(iswindows or isosx or isfreebsd)
 isfrozen  = hasattr(sys, 'frozen')
 isunix = isosx or islinux
@@ -41,6 +45,7 @@ fcntl      = None if iswindows else importlib.import_module('fcntl')
 filesystem_encoding = sys.getfilesystemencoding()
 if filesystem_encoding is None: filesystem_encoding = 'utf-8'
 
+
 DEBUG = False
 
 def debug():
@@ -48,15 +53,12 @@ def debug():
     DEBUG = True
 
 # plugins {{{
-plugins = None
-if plugins is None:
-    # Load plugins
-    def load_plugins():
-        plugins = {}
-        plugin_path = sys.extensions_location
-        sys.path.insert(0, plugin_path)
 
-        for plugin in [
+class Plugins(collections.Mapping):
+
+    def __init__(self):
+        self._plugins = {}
+        plugins = [
                 'pictureflow',
                 'lzx',
                 'msdes',
@@ -70,19 +72,44 @@ if plugins is None:
                 'chm_extra',
                 'icu',
                 'speedup',
-            ] + \
+            ]
-                    (['winutil'] if iswindows else []) + \
+        if iswindows:
-                    (['usbobserver'] if isosx else []):
+            plugins.append('winutil')
-            try:
+        if isosx:
-                p, err = importlib.import_module(plugin), ''
+            plugins.append('usbobserver')
-            except Exception as err:
+        self.plugins = frozenset(plugins)
-                p = None
-                err = str(err)
-            plugins[plugin] = (p, err)
-        sys.path.remove(plugin_path)
-        return plugins
 
-    plugins = load_plugins()
+    def load_plugin(self, name):
+        if name in self._plugins:
+            return
+        sys.path.insert(0, sys.extensions_location)
+        try:
+            p, err = importlib.import_module(name), ''
+        except Exception as err:
+            p = None
+            err = str(err)
+        self._plugins[name] = (p, err)
+        sys.path.remove(sys.extensions_location)
+
+    def __iter__(self):
+        return iter(self.plugins)
+
+    def __len__(self):
+        return len(self.plugins)
+
+    def __contains__(self, name):
+        return name in self.plugins
+
+    def __getitem__(self, name):
+        if name not in self.plugins:
+            raise KeyError('No plugin named %r'%name)
+        self.load_plugin(name)
+        return self._plugins[name]
+
+
+plugins = None
+if plugins is None:
+    plugins = Plugins()
 # }}}
 
 # config_dir {{{

src/calibre/customize/builtins.py

@@ -9,7 +9,6 @@ from calibre.customize import FileTypePlugin, MetadataReaderPlugin, \
 from calibre.constants import numeric_version
 from calibre.ebooks.metadata.archive import ArchiveExtract, get_cbz_metadata
 from calibre.ebooks.metadata.opf2 import metadata_to_opf
-from calibre.ebooks.oeb.base import OEB_IMAGES
 from calibre.utils.config import test_eight_code
 
 # To archive plugins {{{
@@ -98,6 +97,8 @@ class TXT2TXTZ(FileTypePlugin):
     on_import = True
 
     def _get_image_references(self, txt, base_dir):
+        from calibre.ebooks.oeb.base import OEB_IMAGES
+
         images = []
 
         # Textile
@@ -626,8 +627,9 @@ if test_eight_code:
     from calibre.ebooks.metadata.sources.amazon import Amazon
     from calibre.ebooks.metadata.sources.openlibrary import OpenLibrary
     from calibre.ebooks.metadata.sources.isbndb import ISBNDB
+    from calibre.ebooks.metadata.sources.overdrive import OverDrive
 
-    plugins += [GoogleBooks, Amazon, OpenLibrary, ISBNDB]
+    plugins += [GoogleBooks, Amazon, OpenLibrary, ISBNDB, OverDrive]
 
 # }}}
 else:

src/calibre/customize/ui.py

@@ -22,6 +22,11 @@ from calibre.utils.config import make_config_dir, Config, ConfigProxy, \
 from calibre.ebooks.epub.fix import ePubFixer
 from calibre.ebooks.metadata.sources.base import Source
 
+builtin_names = frozenset([p.name for p in builtin_plugins])
+
+class NameConflict(ValueError):
+    pass
+
 def _config():
     c = Config('customize')
     c.add_opt('plugins', default={}, help=_('Installed plugins'))
@@ -355,6 +360,9 @@ def set_file_type_metadata(stream, mi, ftype):
 def add_plugin(path_to_zip_file):
     make_config_dir()
     plugin = load_plugin(path_to_zip_file)
+    if plugin.name in builtin_names:
+        raise NameConflict(
+            'A builtin plugin with the name %r already exists' % plugin.name)
     plugin = initialize_plugin(plugin, path_to_zip_file)
     plugins = config['plugins']
     zfp = os.path.join(plugin_dir, plugin.name+'.zip')
@@ -506,7 +514,11 @@ def initialize_plugin(plugin, path_to_zip_file):
 def initialize_plugins():
     global _initialized_plugins
     _initialized_plugins = []
-    for zfp in list(config['plugins'].values()) + builtin_plugins:
+    conflicts = [name for name in config['plugins'] if name in
+            builtin_names]
+    for p in conflicts:
+        remove_plugin(p)
+    for zfp in list(config['plugins'].itervalues()) + builtin_plugins:
         try:
             try:
                 plugin = load_plugin(zfp) if not isinstance(zfp, type) else zfp

src/calibre/debug.py

@@ -106,7 +106,7 @@ def migrate(old, new):
     from calibre.library.database import LibraryDatabase
     from calibre.library.database2 import LibraryDatabase2
     from calibre.utils.terminfo import ProgressBar
-    from calibre import terminal_controller
+    from calibre.constants import terminal_controller
     class Dummy(ProgressBar):
         def setLabelText(self, x): pass
         def setAutoReset(self, y): pass
@@ -119,7 +119,7 @@ def migrate(old, new):
 
     db = LibraryDatabase(old)
     db2 = LibraryDatabase2(new)
-    db2.migrate_old(db, Dummy(terminal_controller, 'Migrating database...'))
+    db2.migrate_old(db, Dummy(terminal_controller(), 'Migrating database...'))
     prefs['library_path'] = os.path.abspath(new)
     print 'Database migrated to', os.path.abspath(new)
 

src/calibre/devices/android/driver.py

@@ -108,10 +108,10 @@ class ANDROID(USBMS):
             'SGH-T849', '_MB300', 'A70S', 'S_ANDROID', 'A101IT', 'A70H',
             'IDEOS_TABLET', 'MYTOUCH_4G', 'UMS_COMPOSITE', 'SCH-I800_CARD',
             '7', 'A956', 'A955', 'A43', 'ANDROID_PLATFORM', 'TEGRA_2',
-            'MB860', 'MULTI-CARD', 'MID7015A']
+            'MB860', 'MULTI-CARD', 'MID7015A', 'INCREDIBLE']
     WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
             'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
-            'A70S', 'A101IT', '7']
+            'A70S', 'A101IT', '7', 'INCREDIBLE']
 
     OSX_MAIN_MEM = 'Android Device Main Memory'
 

src/calibre/devices/scanner.py

@@ -8,7 +8,7 @@ manner.
 import sys, os, re
 from threading import RLock
 
-from calibre import iswindows, isosx, plugins, islinux
+from calibre.constants import iswindows, isosx, plugins, islinux
 
 osx_scanner = win_scanner = linux_scanner = None
 

src/calibre/ebooks/__init__.py

@@ -7,7 +7,7 @@ Code for the conversion of ebook formats and the reading of metadata
 from various formats.
 '''
 
-import traceback, os
+import traceback, os, re
 from calibre import CurrentDir
 
 class ConversionError(Exception):
@@ -169,3 +169,42 @@ def calibre_cover(title, author_string, series_string=None,
         lines.append(TextLine(series_string, author_size))
     return create_cover_page(lines, I('library.png'), output_format='jpg')
 
+UNIT_RE = re.compile(r'^(-*[0-9]*[.]?[0-9]*)\s*(%|em|ex|en|px|mm|cm|in|pt|pc)$')
+
+def unit_convert(value, base, font, dpi):
+    ' Return value in pts'
+    if isinstance(value, (int, long, float)):
+        return value
+    try:
+        return float(value) * 72.0 / dpi
+    except:
+        pass
+    result = value
+    m = UNIT_RE.match(value)
+    if m is not None and m.group(1):
+        value = float(m.group(1))
+        unit = m.group(2)
+        if unit == '%':
+            result = (value / 100.0) * base
+        elif unit == 'px':
+            result = value * 72.0 / dpi
+        elif unit == 'in':
+            result = value * 72.0
+        elif unit == 'pt':
+            result = value
+        elif unit == 'em':
+            result = value * font
+        elif unit in ('ex', 'en'):
+            # This is a hack for ex since we have no way to know
+            # the x-height of the font
+            font = font
+            result = value * font * 0.5
+        elif unit == 'pc':
+            result = value * 12.0
+        elif unit == 'mm':
+            result = value * 0.04
+        elif unit == 'cm':
+            result = value * 0.40
+    return result
+
+

src/calibre/ebooks/chm/reader.py

@@ -5,8 +5,8 @@ __copyright__  = '2008, Kovid Goyal <kovid at kovidgoyal.net>,' \
                  ' and Alex Bramley <a.bramley at gmail.com>.'
 
 import os, re
-from mimetypes import guess_type as guess_mimetype
 
+from calibre import guess_type as guess_mimetype
 from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString
 from calibre.constants import iswindows, filesystem_encoding
 from calibre.utils.chm.chm import CHMFile

src/calibre/ebooks/conversion/plumber.py

@@ -14,7 +14,8 @@ from calibre.ebooks.conversion.preprocess import HTMLPreProcessor
 from calibre.ptempfile import PersistentTemporaryDirectory
 from calibre.utils.date import parse_date
 from calibre.utils.zipfile import ZipFile
-from calibre import extract, walk, isbytestring, filesystem_encoding
+from calibre import (extract, walk, isbytestring, filesystem_encoding,
+        get_types_map)
 from calibre.constants import __version__
 
 DEBUG_README=u'''
@@ -875,6 +876,9 @@ OptionRecommendation(name='sr3_replace',
         if self.opts.verbose:
             self.log.filter_level = self.log.DEBUG
         self.flush()
+        import cssutils, logging
+        cssutils.log.setLevel(logging.WARN)
+        get_types_map() # Ensure the mimetypes module is intialized
 
         if self.opts.debug_pipeline is not None:
             self.opts.verbose = max(self.opts.verbose, 4)

src/calibre/ebooks/conversion/preprocess.py

@@ -399,7 +399,7 @@ class HTMLPreProcessor(object):
                   (re.compile(u'˙\s*(<br.*?>)*\s*Z', re.UNICODE), lambda match: u'Ż'),
 
                   # If pdf printed from a browser then the header/footer has a reliable pattern
-                  (re.compile(r'((?<=</a>)\s*file:////?[A-Z].*<br>|file:////?[A-Z].*<br>(?=\s*<hr>))', re.IGNORECASE), lambda match: ''),
+                  (re.compile(r'((?<=</a>)\s*file:/{2,4}[A-Z].*<br>|file:////?[A-Z].*<br>(?=\s*<hr>))', re.IGNORECASE), lambda match: ''),
 
                   # Center separator lines
                   (re.compile(u'<br>\s*(?P<break>([*#•✦=]+\s*)+)\s*<br>'), lambda match: '<p>\n<p style="text-align:center">' + match.group(1) + '</p>'),

src/calibre/ebooks/conversion/utils.py

@@ -764,6 +764,7 @@ class HeuristicProcessor(object):
         # Multiple sequential blank paragraphs are merged with appropriate margins
         # If non-blank scene breaks exist they are center aligned and styled with appropriate margins.
         if getattr(self.extra_opts, 'format_scene_breaks', False):
+            html = re.sub('(?i)<div[^>]*>\s*<br(\s?/)?>\s*</div>', '<p></p>', html)
             html = self.detect_whitespace(html)
             html = self.detect_soft_breaks(html)
             blanks_count = len(self.any_multi_blank.findall(html))

src/calibre/ebooks/fb2/fb2ml.py

@@ -10,7 +10,6 @@ Transform OEB content into FB2 markup
 
 from base64 import b64encode
 from datetime import datetime
-from mimetypes import types_map
 import re
 import uuid
 
@@ -18,9 +17,6 @@ from lxml import etree
 
 from calibre import prepare_string_for_xml
 from calibre.constants import __appname__, __version__
-from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
-from calibre.ebooks.oeb.stylizer import Stylizer
-from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES, OPF
 from calibre.utils.magick import Image
 
 class FB2MLizer(object):
@@ -100,6 +96,7 @@ class FB2MLizer(object):
         return text
 
     def fb2_header(self):
+        from calibre.ebooks.oeb.base import OPF
         metadata = {}
         metadata['title'] = self.oeb_book.metadata.title[0].value
         metadata['appname'] = __appname__
@@ -180,6 +177,8 @@ class FB2MLizer(object):
         return u'</FictionBook>'
 
     def get_cover(self):
+        from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
+
         cover_href = None
 
         # Get the raster cover if it's available.
@@ -213,6 +212,8 @@ class FB2MLizer(object):
         return u''
 
     def get_text(self):
+        from calibre.ebooks.oeb.base import XHTML
+        from calibre.ebooks.oeb.stylizer import Stylizer
         text = ['<body>']
 
         # Create main section if there are no others to create
@@ -248,6 +249,8 @@ class FB2MLizer(object):
         '''
         This function uses the self.image_hrefs dictionary mapping. It is populated by the dump_text function.
         '''
+        from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
+
         images = []
         for item in self.oeb_book.manifest:
             # Don't write the image if it's not referenced in the document's text.
@@ -255,7 +258,7 @@ class FB2MLizer(object):
                 continue
             if item.media_type in OEB_RASTER_IMAGES:
                 try:
-                    if not item.media_type == types_map['.jpeg'] or not item.media_type == types_map['.jpg']:
+                    if item.media_type != 'image/jpeg':
                         im = Image()
                         im.load(item.data)
                         im.set_compression_quality(70)
@@ -344,6 +347,8 @@ class FB2MLizer(object):
 
         @return: List of string representing the XHTML converted to FB2 markup.
         '''
+        from calibre.ebooks.oeb.base import XHTML_NS, barename, namespace
+
         # Ensure what we are converting is not a string and that the fist tag is part of the XHTML namespace.
         if not isinstance(elem_tree.tag, basestring) or namespace(elem_tree.tag) != XHTML_NS:
             return []

src/calibre/ebooks/html/input.py

@@ -315,7 +315,8 @@ class HTMLInput(InputFormatPlugin):
         from calibre import guess_type
         from calibre.ebooks.oeb.transforms.metadata import \
             meta_info_to_oeb_metadata
-        import cssutils
+        import cssutils, logging
+        cssutils.log.setLevel(logging.WARN)
         self.OEB_STYLES = OEB_STYLES
         oeb = create_oebbook(log, None, opts, self,
                 encoding=opts.input_encoding, populate=False)

src/calibre/ebooks/html/meta.py

@@ -4,7 +4,6 @@ __copyright__ = '2010, Fabian Grassl <fg@jusmeum.de>'
 __docformat__ = 'restructuredtext en'
 
 
-from calibre.ebooks.oeb.base import namespace, barename, DC11_NS
 
 class EasyMeta(object):
 
@@ -12,6 +11,7 @@ class EasyMeta(object):
         self.meta = meta
 
     def __iter__(self):
+        from calibre.ebooks.oeb.base import namespace, barename, DC11_NS
         meta = self.meta
         for item_name in meta.items:
             for item in meta[item_name]:

src/calibre/ebooks/html/output.py

@@ -12,7 +12,6 @@ from os.path import dirname, abspath, relpath, exists, basename
 from lxml import etree
 from templite import Templite
 
-from calibre.ebooks.oeb.base import element
 from calibre.customize.conversion import OutputFormatPlugin, OptionRecommendation
 from calibre import CurrentDir
 from calibre.ptempfile import PersistentTemporaryDirectory
@@ -51,6 +50,7 @@ class HTMLOutput(OutputFormatPlugin):
         '''
         Generate table of contents
         '''
+        from calibre.ebooks.oeb.base import element
         with CurrentDir(output_dir):
             def build_node(current_node, parent=None):
                 if parent is None:

src/calibre/ebooks/htmlz/output.py

@@ -12,7 +12,6 @@ from lxml import etree
 
 from calibre.customize.conversion import OutputFormatPlugin, \
     OptionRecommendation
-from calibre.ebooks.oeb.base import OEB_IMAGES, SVG_MIME
 from calibre.ptempfile import TemporaryDirectory
 from calibre.utils.zipfile import ZipFile
 
@@ -42,6 +41,8 @@ class HTMLZOutput(OutputFormatPlugin):
     ])
 
     def convert(self, oeb_book, output_path, input_plugin, opts, log):
+        from calibre.ebooks.oeb.base import OEB_IMAGES, SVG_MIME
+
         # HTML
         if opts.htmlz_css_type == 'inline':
             from calibre.ebooks.htmlz.oeb2html import OEB2HTMLInlineCSSizer

src/calibre/ebooks/metadata/__init__.py

@@ -6,11 +6,11 @@ __docformat__ = 'restructuredtext en'
 """
 Provides abstraction for metadata reading.writing from a variety of ebook formats.
 """
-import os, mimetypes, sys, re
+import os, sys, re
 from urllib import unquote, quote
 from urlparse import urlparse
 
-from calibre import relpath
+from calibre import relpath, guess_type
 
 from calibre.utils.config import tweaks
 
@@ -118,7 +118,7 @@ class Resource(object):
         self.path = None
         self.fragment = ''
         try:
-            self.mime_type = mimetypes.guess_type(href_or_path)[0]
+            self.mime_type = guess_type(href_or_path)[0]
         except:
             self.mime_type = None
         if self.mime_type is None:

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

@@ -592,7 +592,7 @@ class Metadata(object):
             elif datatype == 'bool':
                 res = _('Yes') if res else _('No')
             elif datatype == 'rating':
-                res = res/2
+                res = res/2.0
             return (name, unicode(res), orig_res, cmeta)
 
         # convert top-level ids into their value
@@ -625,6 +625,8 @@ class Metadata(object):
                 res = res + ' [%s]'%self.format_series_index()
             elif datatype == 'datetime':
                 res = format_date(res, fmeta['display'].get('date_format','dd MMM yyyy'))
+            elif datatype == 'rating':
+                res = res/2.0
             return (name, unicode(res), orig_res, fmeta)
 
         return (None, None, None, None)

src/calibre/ebooks/metadata/fb2.py

@@ -5,11 +5,12 @@ __copyright__ = '2008, Anatoly Shipitsin <norguhtar at gmail.com>'
 
 '''Read meta information from fb2 files'''
 
-import mimetypes, os
+import os
 from base64 import b64decode
 from lxml import etree
 from calibre.ebooks.metadata import MetaInformation
 from calibre.ebooks.chardet import xml_to_unicode
+from calibre import guess_all_extensions
 
 XLINK_NS     = 'http://www.w3.org/1999/xlink'
 def XLINK(name):
@@ -71,7 +72,7 @@ def get_metadata(stream):
             binary = XPath('//fb2:binary[@id="%s"]'%id)(root)
             if binary:
                 mt = binary[0].get('content-type', 'image/jpeg')
-                exts = mimetypes.guess_all_extensions(mt)
+                exts = guess_all_extensions(mt)
                 if not exts:
                     exts = ['.jpg']
                 cdata = (exts[0][1:], b64decode(tostring(binary[0])))

src/calibre/ebooks/metadata/opf2.py

@@ -7,7 +7,7 @@ __docformat__ = 'restructuredtext en'
 lxml based OPF parser.
 '''
 
-import re, sys, unittest, functools, os, mimetypes, uuid, glob, cStringIO, json
+import re, sys, unittest, functools, os, uuid, glob, cStringIO, json
 from urllib import unquote
 from urlparse import urlparse
 
@@ -20,7 +20,7 @@ from calibre.ebooks.metadata import string_to_authors, MetaInformation, check_is
 from calibre.ebooks.metadata.book.base import Metadata
 from calibre.utils.date import parse_date, isoformat
 from calibre.utils.localization import get_lang
-from calibre import prints
+from calibre import prints, guess_type
 from calibre.utils.cleantext import clean_ascii_chars
 
 class Resource(object): # {{{
@@ -42,7 +42,7 @@ class Resource(object): # {{{
         self.path = None
         self.fragment = ''
         try:
-            self.mime_type = mimetypes.guess_type(href_or_path)[0]
+            self.mime_type = guess_type(href_or_path)[0]
         except:
             self.mime_type = None
         if self.mime_type is None:
@@ -1000,7 +1000,7 @@ class OPF(object): # {{{
                 for t in ('cover', 'other.ms-coverimage-standard', 'other.ms-coverimage'):
                     for item in self.guide:
                         if item.type.lower() == t:
-                            self.create_manifest_item(item.href(), mimetypes.guess_type(path)[0])
+                            self.create_manifest_item(item.href(), guess_type(path)[0])
 
         return property(fget=fget, fset=fset)
 

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

@@ -274,26 +274,34 @@ class Source(Plugin):
 
         if authors:
             # Leave ' in there for Irish names
-            pat = re.compile(r'[-,:;+!@#$%^&*(){}.`~"\s\[\]/]')
+            remove_pat = re.compile(r'[,!@#$%^&*(){}`~"\s\[\]/]')
+            replace_pat = re.compile(r'[-+.:;]')
             if only_first_author:
                 authors = authors[:1]
             for au in authors:
+                au = replace_pat.sub(' ', au)
                 parts = au.split()
                 if ',' in au:
                     # au probably in ln, fn form
                     parts = parts[1:] + parts[:1]
                 for tok in parts:
-                    tok = pat.sub('', tok).strip()
+                    tok = remove_pat.sub('', tok).strip()
                     if len(tok) > 2 and tok.lower() not in ('von', ):
                         yield tok
 
 
-    def get_title_tokens(self, title):
+    def get_title_tokens(self, title, strip_joiners=True, strip_subtitle=False):
         '''
         Take a title and return a list of tokens useful for an AND search query.
-        Excludes connectives and punctuation.
+        Excludes connectives(optionally) and punctuation.
         '''
         if title:
+            # strip sub-titles
+            if strip_subtitle:
+                subtitle = re.compile(r'([\(\[\{].*?[\)\]\}]|[/:\\].*$)')
+                if len(subtitle.sub('', title)) > 1:
+                    title = subtitle.sub('', title)
+
             title_patterns = [(re.compile(pat, re.IGNORECASE), repl) for pat, repl in
             [
                 # Remove things like: (2010) (Omnibus) etc.
@@ -305,17 +313,20 @@ class Source(Plugin):
                 (r'(\d+),(\d+)', r'\1\2'),
                 # Remove hyphens only if they have whitespace before them
                 (r'(\s-)', ' '),
-                # Remove single quotes
+                # Remove single quotes not followed by 's'
-                (r"'", ''),
+                (r"'(?!s)", ''),
                 # Replace other special chars with a space
                 (r'''[:,;+!@#$%^&*(){}.`~"\s\[\]/]''', ' ')
             ]]
+
             for pat, repl in title_patterns:
                 title = pat.sub(repl, title)
+
             tokens = title.split()
             for token in tokens:
                 token = token.strip()
-                if token and token.lower() not in ('a', 'and', 'the'):
+                if token and (not strip_joiners or token.lower() not in ('a',
+                    'and', 'the', '&')):
                     yield token
 
     def split_jobs(self, jobs, num):
@@ -363,7 +374,12 @@ class Source(Plugin):
     def get_book_url(self, identifiers):
         '''
         Return the URL for the book identified by identifiers at this source.
-        If no URL is found, return None.
+        This URL must be browseable to by a human using a browser. It is meant
+        to provide a clickable link for the user to easily visit the books page
+        at this source.
+        If no URL is found, return None. This method must be quick, and
+        consistent, so only implement it if it is possible to construct the URL
+        from a known scheme given identifiers.
         '''
         return None
 

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

@@ -382,7 +382,11 @@ def identify(log, abort, # {{{
             log(plog)
         log('\n'+'*'*80)
 
+        dummy = Metadata(_('Unknown'))
         for i, result in enumerate(presults):
+            for f in plugin.prefs['ignore_fields']:
+                if ':' not in f:
+                    setattr(result, f, getattr(dummy, f))
             result.relevance_in_source = i
             result.has_cached_cover_url = (plugin.cached_cover_url_is_reliable
                     and plugin.get_cached_cover_url(result.identifiers) is not
@@ -433,7 +437,7 @@ def urls_from_identifiers(identifiers): # {{{
             pass
     isbn = identifiers.get('isbn', None)
     if isbn:
-        ans.append(('ISBN',
+        ans.append((isbn,
             'http://www.worldcat.org/search?q=bn%%3A%s&qt=advanced'%isbn))
     return ans
 # }}}
@@ -444,13 +448,18 @@ if __name__ == '__main__': # tests {{{
     from calibre.ebooks.metadata.sources.test import (test_identify,
             title_test, authors_test)
     tests = [
+            (
+                {'title':'Magykal Papers',
+                    'authors':['Sage']},
+                [title_test('The Magykal Papers', exact=True)],
+            ),
+
 
             ( # An e-book ISBN not on Amazon, one of the authors is
               # unknown to Amazon
                 {'identifiers':{'isbn': '9780307459671'},
                     'title':'Invisible Gorilla', 'authors':['Christopher Chabris']},
-                [title_test('The Invisible Gorilla',
+                [title_test('The Invisible Gorilla', exact=True)]
-                    exact=True), authors_test(['Christopher Chabris', 'Daniel Simons'])]
 
             ),
 

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

@@ -0,0 +1,441 @@
+#!/usr/bin/env  python
+from __future__ import (unicode_literals, division, absolute_import,
+                        print_function)
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
+__docformat__ = 'restructuredtext en'
+
+'''
+Fetch metadata using Overdrive Content Reserve
+'''
+import re, random, mechanize, copy, json
+from threading import RLock
+from Queue import Queue, Empty
+
+from lxml import html
+from lxml.html import soupparser
+
+from calibre.ebooks.metadata import check_isbn
+from calibre.ebooks.metadata.sources.base import Source
+from calibre.ebooks.metadata.book.base import Metadata
+from calibre.ebooks.chardet import xml_to_unicode
+from calibre.library.comments import sanitize_comments_html
+
+ovrdrv_data_cache = {}
+cache_lock = RLock()
+base_url = 'http://search.overdrive.com/'
+
+
+class OverDrive(Source):
+
+    name = 'Overdrive'
+    description = _('Downloads metadata from Overdrive\'s Content Reserve')
+
+    capabilities = frozenset(['identify', 'cover'])
+    touched_fields = frozenset(['title', 'authors', 'tags', 'pubdate',
+        'comments', 'publisher', 'identifier:isbn', 'series', 'series_index',
+        'language', 'identifier:overdrive'])
+    has_html_comments = True
+    supports_gzip_transfer_encoding = False
+    cached_cover_url_is_reliable = True
+
+    def identify(self, log, result_queue, abort, title=None, authors=None, # {{{
+            identifiers={}, timeout=30):
+        ovrdrv_id = identifiers.get('overdrive', None)
+        isbn = identifiers.get('isbn', None)
+
+        br = self.browser
+        ovrdrv_data = self.to_ovrdrv_data(br, title, authors, ovrdrv_id)
+        if ovrdrv_data:
+            title = ovrdrv_data[8]
+            authors = ovrdrv_data[6]
+            mi = Metadata(title, authors)
+            self.parse_search_results(ovrdrv_data, mi)
+            if ovrdrv_id is None:
+                ovrdrv_id = ovrdrv_data[7]
+            if isbn is not None:
+                self.cache_isbn_to_identifier(isbn, ovrdrv_id)
+
+            self.get_book_detail(br, ovrdrv_data[1], mi, ovrdrv_id, log)
+
+            result_queue.put(mi)
+
+        return None
+    # }}}
+
+    def download_cover(self, log, result_queue, abort, # {{{
+            title=None, authors=None, identifiers={}, timeout=30):
+        cached_url = self.get_cached_cover_url(identifiers)
+        if cached_url is None:
+            log.info('No cached cover found, running identify')
+            rq = Queue()
+            self.identify(log, rq, abort, title=title, authors=authors,
+                    identifiers=identifiers)
+            if abort.is_set():
+                return
+            results = []
+            while True:
+                try:
+                    results.append(rq.get_nowait())
+                except Empty:
+                    break
+            results.sort(key=self.identify_results_keygen(
+                title=title, authors=authors, identifiers=identifiers))
+            for mi in results:
+                cached_url = self.get_cached_cover_url(mi.identifiers)
+                if cached_url is not None:
+                    break
+        if cached_url is None:
+            log.info('No cover found')
+            return
+
+        if abort.is_set():
+            return
+
+        ovrdrv_id = identifiers.get('overdrive', None)
+        br = self.browser
+        req = mechanize.Request(cached_url)
+        if ovrdrv_id is not None:
+            referer = self.get_base_referer()+'ContentDetails-Cover.htm?ID='+ovrdrv_id
+            req.add_header('referer', referer)
+        req.add_header('referer', referer)
+        log('Downloading cover from:', cached_url)
+        try:
+            cdata = br.open_novisit(req, timeout=timeout).read()
+            result_queue.put((self, cdata))
+        except:
+            log.exception('Failed to download cover from:', cached_url)
+    # }}}
+
+    def get_cached_cover_url(self, identifiers): # {{{
+        url = None
+        ovrdrv_id = identifiers.get('overdrive', None)
+        if ovrdrv_id is None:
+            isbn = identifiers.get('isbn', None)
+            if isbn is not None:
+                ovrdrv_id = self.cached_isbn_to_identifier(isbn)
+        if ovrdrv_id is not None:
+            url = self.cached_identifier_to_cover_url(ovrdrv_id)
+
+        return url
+    # }}}
+
+    def get_base_referer(self): # to be used for passing referrer headers to cover download
+        choices = [
+            'http://overdrive.chipublib.org/82DC601D-7DDE-4212-B43A-09D821935B01/10/375/en/',
+            'http://emedia.clevnet.org/9D321DAD-EC0D-490D-BFD8-64AE2C96ECA8/10/241/en/',
+            'http://singapore.lib.overdrive.com/F11D55BE-A917-4D63-8111-318E88B29740/10/382/en/',
+            'http://ebooks.nypl.org/20E48048-A377-4520-BC43-F8729A42A424/10/257/en/',
+            'http://spl.lib.overdrive.com/5875E082-4CB2-4689-9426-8509F354AFEF/10/335/en/'
+        ]
+        return choices[random.randint(0, len(choices)-1)]
+
+    def format_results(self, reserveid, od_title, subtitle, series, publisher, creators, thumbimage, worldcatlink, formatid):
+        fix_slashes = re.compile(r'\\/')
+        thumbimage = fix_slashes.sub('/', thumbimage)
+        worldcatlink = fix_slashes.sub('/', worldcatlink)
+        cover_url = re.sub('(?P<img>(Ima?g(eType-)?))200', '\g<img>100', thumbimage)
+        social_metadata_url = base_url+'TitleInfo.aspx?ReserveID='+reserveid+'&FormatID='+formatid
+        series_num = ''
+        if not series:
+            if subtitle:
+                title = od_title+': '+subtitle
+            else:
+                title = od_title
+        else:
+            title = od_title
+            m = re.search("([0-9]+$)", subtitle)
+            if m:
+                series_num = float(m.group(1))
+        return [cover_url, social_metadata_url, worldcatlink, series, series_num, publisher, creators, reserveid, title]
+
+    def safe_query(self, br, query_url, post=''):
+        '''
+        The query must be initialized by loading an empty search results page
+        this page attempts to set a cookie that Mechanize doesn't like
+        copy the cookiejar to a separate instance and make a one-off request with the temp cookiejar
+        '''
+        goodcookies = br._ua_handlers['_cookies'].cookiejar
+        clean_cj = mechanize.CookieJar()
+        cookies_to_copy = []
+        for cookie in goodcookies:
+            copied_cookie = copy.deepcopy(cookie)
+            cookies_to_copy.append(copied_cookie)
+        for copied_cookie in cookies_to_copy:
+            clean_cj.set_cookie(copied_cookie)
+
+        if post:
+            br.open_novisit(query_url, post)
+        else:
+            br.open_novisit(query_url)
+
+        br.set_cookiejar(clean_cj)
+
+    def overdrive_search(self, br, q, title, author):
+        # re-initialize the cookiejar to so that it's clean
+        clean_cj = mechanize.CookieJar()
+        br.set_cookiejar(clean_cj)
+        q_query = q+'default.aspx/SearchByKeyword'
+        q_init_search = q+'SearchResults.aspx'
+        # get first author as string - convert this to a proper cleanup function later
+        author_tokens = list(self.get_author_tokens(author,
+                only_first_author=True))
+        title_tokens = list(self.get_title_tokens(title,
+                strip_joiners=False, strip_subtitle=True))
+
+        if len(title_tokens) >= len(author_tokens):
+            initial_q = ' '.join(title_tokens)
+            xref_q = '+'.join(author_tokens)
+        else:
+            initial_q = ' '.join(author_tokens)
+            xref_q = '+'.join(title_tokens)
+
+        q_xref = q+'SearchResults.svc/GetResults?iDisplayLength=50&sSearch='+xref_q
+        query = '{"szKeyword":"'+initial_q+'"}'
+
+        # main query, requires specific Content Type header
+        req = mechanize.Request(q_query)
+        req.add_header('Content-Type', 'application/json; charset=utf-8')
+        br.open_novisit(req, query)
+
+        # initiate the search without messing up the cookiejar
+        self.safe_query(br, q_init_search)
+
+        # get the search results object
+        results = False
+        while results == False:
+            xreq = mechanize.Request(q_xref)
+            xreq.add_header('X-Requested-With', 'XMLHttpRequest')
+            xreq.add_header('Referer', q_init_search)
+            xreq.add_header('Accept', 'application/json, text/javascript, */*')
+            raw = br.open_novisit(xreq).read()
+            for m in re.finditer(ur'"iTotalDisplayRecords":(?P<displayrecords>\d+).*?"iTotalRecords":(?P<totalrecords>\d+)', raw):
+                if int(m.group('displayrecords')) >= 1:
+                    results = True
+                elif int(m.group('totalrecords')) >= 1:
+                    xref_q = ''
+                    q_xref = q+'SearchResults.svc/GetResults?iDisplayLength=50&sSearch='+xref_q
+                elif int(m.group('totalrecords')) == 0:
+                    return ''
+
+        return self.sort_ovrdrv_results(raw, title, title_tokens, author, author_tokens)
+
+
+    def sort_ovrdrv_results(self, raw, title=None, title_tokens=None, author=None, author_tokens=None, ovrdrv_id=None):
+        close_matches = []
+        raw = re.sub('.*?\[\[(?P<content>.*?)\]\].*', '[[\g<content>]]', raw)
+        results = json.loads(raw)
+        #print results
+        # The search results are either from a keyword search or a multi-format list from a single ID,
+        # sort through the results for closest match/format
+        if results:
+            for reserveid, od_title, subtitle, edition, series, publisher, format, formatid, creators, \
+                    thumbimage, shortdescription, worldcatlink, excerptlink, creatorfile, sorttitle, \
+                    availabletolibrary, availabletoretailer, relevancyrank, unknown1, unknown2, unknown3 in results:
+                #print "this record's title is "+od_title+", subtitle is "+subtitle+", author[s] are "+creators+", series is "+series
+                if ovrdrv_id is not None and int(formatid) in [1, 50, 410, 900]:
+                    #print "overdrive id is not None, searching based on format type priority"
+                    return self.format_results(reserveid, od_title, subtitle, series, publisher,
+                            creators, thumbimage, worldcatlink, formatid)
+                else:
+                    creators = creators.split(', ')
+                    # if an exact match in a preferred format occurs
+                    if (author and creators[0] == author[0]) and od_title == title and int(formatid) in [1, 50, 410, 900] and thumbimage:
+                        return self.format_results(reserveid, od_title, subtitle, series, publisher,
+                                creators, thumbimage, worldcatlink, formatid)
+                    else:
+                        close_title_match = False
+                        close_author_match = False
+                        for token in title_tokens:
+                            if od_title.lower().find(token.lower()) != -1:
+                                close_title_match = True
+                            else:
+                                close_title_match = False
+                                break
+                        for author in creators:
+                            for token in author_tokens:
+                                if author.lower().find(token.lower()) != -1:
+                                    close_author_match = True
+                                else:
+                                    close_author_match = False
+                                    break
+                            if close_author_match:
+                                break
+                        if close_title_match and close_author_match and int(formatid) in [1, 50, 410, 900] and thumbimage:
+                            if subtitle and series:
+                                close_matches.insert(0, self.format_results(reserveid, od_title, subtitle, series, publisher, creators, thumbimage, worldcatlink, formatid))
+                            else:
+                                close_matches.append(self.format_results(reserveid, od_title, subtitle, series, publisher, creators, thumbimage, worldcatlink, formatid))
+            if close_matches:
+                return close_matches[0]
+            else:
+                return ''
+        else:
+            return ''
+
+    def overdrive_get_record(self, br, q, ovrdrv_id):
+        search_url = q+'SearchResults.aspx?ReserveID={'+ovrdrv_id+'}'
+        results_url = q+'SearchResults.svc/GetResults?sEcho=1&iColumns=18&sColumns=ReserveID%2CTitle%2CSubtitle%2CEdition%2CSeries%2CPublisher%2CFormat%2CFormatID%2CCreators%2CThumbImage%2CShortDescription%2CWorldCatLink%2CExcerptLink%2CCreatorFile%2CSortTitle%2CAvailableToLibrary%2CAvailableToRetailer%2CRelevancyRank&iDisplayStart=0&iDisplayLength=10&sSearch=&bEscapeRegex=true&iSortingCols=1&iSortCol_0=17&sSortDir_0=asc'
+
+        # re-initialize the cookiejar to so that it's clean
+        clean_cj = mechanize.CookieJar()
+        br.set_cookiejar(clean_cj)
+        # get the base url to set the proper session cookie
+        br.open_novisit(q)
+
+        # initialize the search
+        self.safe_query(br, search_url)
+
+        # get the results
+        req = mechanize.Request(results_url)
+        req.add_header('X-Requested-With', 'XMLHttpRequest')
+        req.add_header('Referer', search_url)
+        req.add_header('Accept', 'application/json, text/javascript, */*')
+        raw = br.open_novisit(req)
+        raw = str(list(raw))
+        clean_cj = mechanize.CookieJar()
+        br.set_cookiejar(clean_cj)
+        return self.sort_ovrdrv_results(raw, None, None, None, ovrdrv_id)
+
+
+    def find_ovrdrv_data(self, br, title, author, isbn, ovrdrv_id=None):
+        q = base_url
+        if ovrdrv_id is None:
+           return self.overdrive_search(br, q, title, author)
+        else:
+           return self.overdrive_get_record(br, q, ovrdrv_id)
+
+
+
+    def to_ovrdrv_data(self, br, title=None, author=None, ovrdrv_id=None):
+        '''
+        Takes either a title/author combo or an Overdrive ID.  One of these
+        two must be passed to this function.
+        '''
+        if ovrdrv_id is not None:
+            with cache_lock:
+                ans = ovrdrv_data_cache.get(ovrdrv_id, None)
+            if ans:
+                return ans
+            elif ans is False:
+                return None
+            else:
+                ovrdrv_data = self.find_ovrdrv_data(br, title, author, ovrdrv_id)
+        else:
+            try:
+                ovrdrv_data = self.find_ovrdrv_data(br, title, author, ovrdrv_id)
+            except:
+                import traceback
+                traceback.print_exc()
+                ovrdrv_data = None
+        with cache_lock:
+            ovrdrv_data_cache[ovrdrv_id] = ovrdrv_data if ovrdrv_data else False
+
+        return ovrdrv_data if ovrdrv_data else False
+
+
+    def parse_search_results(self, ovrdrv_data, mi):
+        '''
+        Parse the formatted search results from the initial Overdrive query and
+        add the values to the metadta.
+
+        The list object has these values:
+        [cover_url[0], social_metadata_url[1], worldcatlink[2], series[3], series_num[4],
+        publisher[5], creators[6], reserveid[7], title[8]]
+
+        '''
+        ovrdrv_id = ovrdrv_data[7]
+        mi.set_identifier('overdrive', ovrdrv_id)
+
+        if len(ovrdrv_data[3]) > 1:
+            mi.series = ovrdrv_data[3]
+            if ovrdrv_data[4]:
+                try:
+                    mi.series_index = float(ovrdrv_data[4])
+                except:
+                    pass
+        mi.publisher = ovrdrv_data[5]
+        mi.authors = ovrdrv_data[6]
+        mi.title = ovrdrv_data[8]
+        cover_url = ovrdrv_data[0]
+        if cover_url:
+            self.cache_identifier_to_cover_url(ovrdrv_id,
+                    cover_url)
+
+
+    def get_book_detail(self, br, metadata_url, mi, ovrdrv_id, log):
+        try:
+            raw = br.open_novisit(metadata_url).read()
+        except Exception, e:
+            if callable(getattr(e, 'getcode', None)) and \
+                    e.getcode() == 404:
+                return False
+            raise
+        raw = xml_to_unicode(raw, strip_encoding_pats=True,
+                resolve_entities=True)[0]
+        try:
+            root = soupparser.fromstring(raw)
+        except:
+            return False
+
+        pub_date = root.xpath("//div/label[@id='ctl00_ContentPlaceHolder1_lblPubDate']/text()")
+        lang = root.xpath("//div/label[@id='ctl00_ContentPlaceHolder1_lblLanguage']/text()")
+        subjects = root.xpath("//div/label[@id='ctl00_ContentPlaceHolder1_lblSubjects']/text()")
+        ebook_isbn = root.xpath("//td/label[@id='ctl00_ContentPlaceHolder1_lblIdentifier']/text()")
+        desc = root.xpath("//div/label[@id='ctl00_ContentPlaceHolder1_lblDescription']/ancestor::div[1]")
+
+        if pub_date:
+            from calibre.utils.date import parse_date
+            try:
+                mi.pubdate = parse_date(pub_date[0].strip())
+            except:
+                pass
+        if lang:
+            lang = lang[0].strip().lower()
+            mi.language = {'english':'en', 'french':'fr', 'german':'de',
+                    'spanish':'es'}.get(lang, None)
+
+        if ebook_isbn:
+            #print "ebook isbn is "+str(ebook_isbn[0])
+            isbn = check_isbn(ebook_isbn[0].strip())
+            if isbn:
+                self.cache_isbn_to_identifier(isbn, ovrdrv_id)
+                mi.isbn = isbn
+        if subjects:
+            mi.tags = [tag.strip() for tag in subjects[0].split(',')]
+
+        if desc:
+            desc = desc[0]
+            desc = html.tostring(desc, method='html', encoding=unicode).strip()
+            # remove all attributes from tags
+            desc = re.sub(r'<([a-zA-Z0-9]+)\s[^>]+>', r'<\1>', desc)
+            # Remove comments
+            desc = re.sub(r'(?s)<!--.*?-->', '', desc)
+            mi.comments = sanitize_comments_html(desc)
+
+        return None
+
+
+if __name__ == '__main__':
+    # To run these test use:
+    # calibre-debug -e src/calibre/ebooks/metadata/sources/overdrive.py
+    from calibre.ebooks.metadata.sources.test import (test_identify_plugin,
+            title_test, authors_test)
+    test_identify_plugin(OverDrive.name,
+        [
+
+            (
+                {'title':'Foundation and Earth',
+                    'authors':['Asimov']},
+                [title_test('Foundation and Earth', exact=True),
+                    authors_test(['Isaac Asimov'])]
+            ),
+
+            (
+                {'title': 'Elephants', 'authors':['Agatha']},
+                [title_test('Elephants Can Remember', exact=False),
+                    authors_test(['Agatha Christie'])]
+            ),
+    ])
+

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

@@ -67,6 +67,23 @@ def authors_test(authors):
 
     return test
 
+def series_test(series, series_index):
+    series = series.lower()
+
+    def test(mi):
+        ms = mi.series.lower() if mi.series else ''
+        if (ms == series) and (series_index == mi.series_index):
+            return True
+        if mi.series:
+            prints('Series test failed. Expected: \'%s [%d]\' found \'%s[%d]\''% \
+                        (series, series_index, ms, mi.series_index))
+        else:
+            prints('Series test failed. Expected: \'%s [%d]\' found no series'% \
+                        (series, series_index))
+        return False
+
+    return test
+
 def init_test(tdir_name):
     tdir = tempfile.gettempdir()
     lf = os.path.join(tdir, tdir_name.replace(' ', '')+'_identify_test.txt')

src/calibre/ebooks/mobi/reader.py

@@ -20,7 +20,7 @@ from calibre.utils.filenames import ascii_filename
 from calibre.utils.date import parse_date
 from calibre.utils.cleantext import clean_ascii_chars
 from calibre.ptempfile import TemporaryDirectory
-from calibre.ebooks import DRMError
+from calibre.ebooks import DRMError, unit_convert
 from calibre.ebooks.chardet import ENCODING_PATS
 from calibre.ebooks.mobi import MobiError
 from calibre.ebooks.mobi.huffcdic import HuffReader
@@ -258,6 +258,8 @@ class MobiReader(object):
                 }
                 ''')
         self.tag_css_rules = {}
+        self.left_margins = {}
+        self.text_indents = {}
 
         if hasattr(filename_or_stream, 'read'):
             stream = filename_or_stream
@@ -567,9 +569,21 @@ class MobiReader(object):
                     elif tag.tag == 'img':
                         tag.set('width', width)
                     else:
-                        styles.append('text-indent: %s' % self.ensure_unit(width))
+                        ewidth = self.ensure_unit(width)
+                        styles.append('text-indent: %s' % ewidth)
+                        try:
+                            ewidth_val = unit_convert(ewidth, 12, 500, 166)
+                            self.text_indents[tag] = ewidth_val
+                        except:
+                            pass
                         if width.startswith('-'):
                             styles.append('margin-left: %s' % self.ensure_unit(width[1:]))
+                            try:
+                                ewidth_val = unit_convert(ewidth[1:], 12, 500, 166)
+                                self.left_margins[tag] = ewidth_val
+                            except:
+                                pass
+
             if attrib.has_key('align'):
                 align = attrib.pop('align').strip()
                 if align:
@@ -661,6 +675,26 @@ class MobiReader(object):
             if hasattr(parent, 'remove'):
                 parent.remove(tag)
 
+    def get_left_whitespace(self, tag):
+
+        def whitespace(tag):
+            lm = ti = 0.0
+            if tag.tag == 'p':
+                ti = unit_convert('1.5em', 12, 500, 166)
+            if tag.tag == 'blockquote':
+                lm = unit_convert('2em', 12, 500, 166)
+            lm = self.left_margins.get(tag, lm)
+            ti = self.text_indents.get(tag, ti)
+            return lm + ti
+
+        parent = tag
+        ans = 0.0
+        while parent is not None:
+            ans += whitespace(parent)
+            parent = parent.getparent()
+
+        return ans
+
     def create_opf(self, htmlfile, guide=None, root=None):
         mi = getattr(self.book_header.exth, 'mi', self.embedded_mi)
         if mi is None:
@@ -731,16 +765,45 @@ class MobiReader(object):
                             except:
                                 text = ''
                             text = ent_pat.sub(entity_to_unicode, text)
-                            tocobj.add_item(toc.partition('#')[0], href[1:],
+                            item = tocobj.add_item(toc.partition('#')[0], href[1:],
                                 text)
+                            item.left_space = int(self.get_left_whitespace(x))
                             found = True
                     if reached and found and x.get('class', None) == 'mbp_pagebreak':
                         break
             if tocobj is not None:
+                tocobj = self.structure_toc(tocobj)
                 opf.set_toc(tocobj)
 
         return opf, ncx_manifest_entry
 
+    def structure_toc(self, toc):
+        indent_vals = set()
+        for item in toc:
+            indent_vals.add(item.left_space)
+        if len(indent_vals) > 6 or len(indent_vals) < 2:
+            # Too many or too few levels, give up
+            return toc
+        indent_vals = sorted(indent_vals)
+
+        last_found = [None for i in indent_vals]
+
+        newtoc = TOC()
+
+        def find_parent(level):
+            candidates = last_found[:level]
+            for x in reversed(candidates):
+                if x is not None:
+                    return x
+            return newtoc
+
+        for item in toc:
+            level = indent_vals.index(item.left_space)
+            parent = find_parent(level)
+            last_found[level] = parent.add_item(item.href, item.fragment,
+                        item.text)
+
+        return newtoc
 
     def sizeof_trailing_entries(self, data):
         def sizeof_trailing_entry(ptr, psize):

src/calibre/ebooks/oeb/base.py

@@ -8,23 +8,18 @@ __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
 __docformat__ = 'restructuredtext en'
 
 import os, re, uuid, logging
-from mimetypes import types_map
 from collections import defaultdict
 from itertools import count
 from urlparse import urldefrag, urlparse, urlunparse, urljoin
 from urllib import unquote as urlunquote
 
 from lxml import etree, html
-from cssutils import CSSParser, parseString, parseStyle, replaceUrls
+from calibre.constants import filesystem_encoding, __version__
-from cssutils.css import CSSRule
-
-import calibre
-from calibre.constants import filesystem_encoding
 from calibre.translations.dynamic import translate
 from calibre.ebooks.chardet import xml_to_unicode
 from calibre.ebooks.oeb.entitydefs import ENTITYDEFS
 from calibre.ebooks.conversion.preprocess import CSSPreProcessor
-from calibre import isbytestring, as_unicode
+from calibre import isbytestring, as_unicode, get_types_map
 
 RECOVER_PARSER = etree.XMLParser(recover=True, no_network=True)
 
@@ -179,6 +174,9 @@ def rewrite_links(root, link_repl_func, resolve_base_href=False):
     If the ``link_repl_func`` returns None, the attribute or
     tag text will be removed completely.
     '''
+    from cssutils import parseString, parseStyle, replaceUrls, log
+    log.setLevel(logging.WARN)
+
     if resolve_base_href:
         resolve_base_href(root)
     for el, attrib, link, pos in iterlinks(root, find_links_in_css=False):
@@ -248,7 +246,7 @@ def rewrite_links(root, link_repl_func, resolve_base_href=False):
                 el.attrib['style'] = repl
 
 
-
+types_map = get_types_map()
 EPUB_MIME      = types_map['.epub']
 XHTML_MIME     = types_map['.xhtml']
 CSS_MIME       = types_map['.css']
@@ -1075,7 +1073,9 @@ class Manifest(object):
 
 
         def _parse_css(self, data):
-
+            from cssutils.css import CSSRule
+            from cssutils import CSSParser, log
+            log.setLevel(logging.WARN)
             def get_style_rules_from_import(import_rule):
                 ans = []
                 if not import_rule.styleSheet:
@@ -2011,7 +2011,7 @@ class OEBBook(object):
             name='dtb:uid', content=unicode(self.uid))
         etree.SubElement(head, NCX('meta'),
             name='dtb:depth', content=str(self.toc.depth()))
-        generator = ''.join(['calibre (', calibre.__version__, ')'])
+        generator = ''.join(['calibre (', __version__, ')'])
         etree.SubElement(head, NCX('meta'),
             name='dtb:generator', content=generator)
         etree.SubElement(head, NCX('meta'),

src/calibre/ebooks/oeb/reader.py

@@ -10,11 +10,9 @@ import sys, os, uuid, copy, re, cStringIO
 from itertools import izip
 from urlparse import urldefrag, urlparse
 from urllib import unquote as urlunquote
-from mimetypes import guess_type
 from collections import defaultdict
 
 from lxml import etree
-import cssutils
 
 from calibre.ebooks.oeb.base import OPF1_NS, OPF2_NS, OPF2_NSMAP, DC11_NS, \
     DC_NSES, OPF, xml2text
@@ -30,6 +28,7 @@ from calibre.ebooks.oeb.entitydefs import ENTITYDEFS
 from calibre.utils.localization import get_lang
 from calibre.ptempfile import TemporaryDirectory
 from calibre.constants import __appname__, __version__
+from calibre import guess_type
 
 __all__ = ['OEBReader']
 
@@ -172,6 +171,7 @@ class OEBReader(object):
         return bad
 
     def _manifest_add_missing(self, invalid):
+        import cssutils
         manifest = self.oeb.manifest
         known = set(manifest.hrefs)
         unchecked = set(manifest.values())

src/calibre/ebooks/oeb/stylizer.py

@@ -12,17 +12,19 @@ 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, \
+from cssutils.css import (CSSStyleRule, CSSPageRule, CSSStyleDeclaration,
-    CSSValueList, CSSFontFaceRule, cssproperties
+    CSSValueList, CSSFontFaceRule, cssproperties)
 from cssutils import profile as cssprofiles
 from lxml import etree
 from lxml.cssselect import css_to_xpath, ExpressionError, SelectorSyntaxError
-
 from calibre import force_unicode
+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
 from calibre.ebooks.oeb.profile import PROFILES
 
+cssutils.log.setLevel(logging.WARN)
+
 _html_css_stylesheet = None
 
 def html_css_stylesheet():
@@ -443,7 +445,6 @@ class Stylizer(object):
 
 
 class Style(object):
-    UNIT_RE = re.compile(r'^(-*[0-9]*[.]?[0-9]*)\s*(%|em|ex|en|px|mm|cm|in|pt|pc)$')
     MS_PAT = re.compile(r'^\s*(mso-|panose-|text-underline|tab-interval)')
 
     def __init__(self, element, stylizer):
@@ -506,43 +507,11 @@ class Style(object):
         return result
 
     def _unit_convert(self, value, base=None, font=None):
-        ' Return value in pts'
+        'Return value in pts'
-        if isinstance(value, (int, long, float)):
+        if base is None:
-            return value
+            base = self.width
-        try:
+        font = font or self.fontSize
-            return float(value) * 72.0 / self._profile.dpi
+        return unit_convert(value, base, font, self._profile.dpi)
-        except:
-            pass
-        result = value
-        m = self.UNIT_RE.match(value)
-        if m is not None and m.group(1):
-            value = float(m.group(1))
-            unit = m.group(2)
-            if unit == '%':
-                if base is None:
-                    base = self.width
-                result = (value / 100.0) * base
-            elif unit == 'px':
-                result = value * 72.0 / self._profile.dpi
-            elif unit == 'in':
-                result = value * 72.0
-            elif unit == 'pt':
-                result = value
-            elif unit == 'em':
-                font = font or self.fontSize
-                result = value * font
-            elif unit in ('ex', 'en'):
-                # This is a hack for ex since we have no way to know
-                # the x-height of the font
-                font = font or self.fontSize
-                result = value * font * 0.5
-            elif unit == 'pc':
-                result = value * 12.0
-            elif unit == 'mm':
-                result = value * 0.04
-            elif unit == 'cm':
-                result = value * 0.40
-        return result
 
     def pt_to_px(self, value):
         return (self._profile.dpi / 72.0) * value

src/calibre/ebooks/oeb/transforms/filenames.py

@@ -9,7 +9,6 @@ import posixpath
 from urlparse import urldefrag, urlparse
 
 from lxml import etree
-import cssutils
 
 from calibre.ebooks.oeb.base import rewrite_links, urlnormalize
 
@@ -25,6 +24,7 @@ class RenameFiles(object): # {{{
         self.renamed_items_map = renamed_items_map
 
     def __call__(self, oeb, opts):
+        import cssutils
         self.log = oeb.logger
         self.opts = opts
         self.oeb = oeb

src/calibre/ebooks/oeb/transforms/trimmanifest.py

@@ -8,8 +8,6 @@ __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
 
 from urlparse import urldefrag
 
-import cssutils
-
 from calibre.ebooks.oeb.base import CSS_MIME, OEB_DOCS
 from calibre.ebooks.oeb.base import urlnormalize, iterlinks
 
@@ -23,6 +21,7 @@ class ManifestTrimmer(object):
         return cls()
 
     def __call__(self, oeb, context):
+        import cssutils
         oeb.logger.info('Trimming unused files from manifest...')
         self.opts = context
         used = set()

src/calibre/ebooks/pdb/ereader/writer.py

@@ -21,7 +21,6 @@ except ImportError:
 import cStringIO
 
 from calibre.ebooks.pdb.formatwriter import FormatWriter
-from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
 from calibre.ebooks.pdb.header import PdbHeaderBuilder
 from calibre.ebooks.pml.pmlml import PMLMLizer
 
@@ -135,6 +134,7 @@ class Writer(FormatWriter):
         62-...: Raw image data in 8 bit PNG format.
         '''
         images = []
+        from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
 
         for item in manifest:
             if item.media_type in OEB_RASTER_IMAGES and item.href in image_hrefs.keys():

src/calibre/ebooks/pml/output.py

@@ -18,7 +18,6 @@ from calibre.customize.conversion import OutputFormatPlugin
 from calibre.customize.conversion import OptionRecommendation
 from calibre.ptempfile import TemporaryDirectory
 from calibre.utils.zipfile import ZipFile
-from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
 from calibre.ebooks.pml.pmlml import PMLMLizer
 
 class PMLOutput(OutputFormatPlugin):
@@ -60,6 +59,7 @@ class PMLOutput(OutputFormatPlugin):
             pmlz.add_dir(tdir)
 
     def write_images(self, manifest, image_hrefs, out_dir, opts):
+        from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
         for item in manifest:
             if item.media_type in OEB_RASTER_IMAGES and item.href in image_hrefs.keys():
                 if opts.full_image_depth:

src/calibre/ebooks/pml/pmlml.py

@@ -12,8 +12,6 @@ import re
 
 from lxml import etree
 
-from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
-from calibre.ebooks.oeb.stylizer import Stylizer
 from calibre.ebooks.pdb.ereader import image_name
 from calibre.ebooks.pml import unipmlcode
 
@@ -110,6 +108,9 @@ class PMLMLizer(object):
         return output
 
     def get_cover_page(self):
+        from calibre.ebooks.oeb.stylizer import Stylizer
+        from calibre.ebooks.oeb.base import XHTML
+
         output = u''
         if 'cover' in self.oeb_book.guide:
             output += '\\m="cover.png"\n'
@@ -125,6 +126,9 @@ class PMLMLizer(object):
         return output
 
     def get_text(self):
+        from calibre.ebooks.oeb.stylizer import Stylizer
+        from calibre.ebooks.oeb.base import XHTML
+
         text = [u'']
         for item in self.oeb_book.spine:
             self.log.debug('Converting %s to PML markup...' % item.href)
@@ -214,6 +218,8 @@ class PMLMLizer(object):
         return text
 
     def dump_text(self, elem, stylizer, page, tag_stack=[]):
+        from calibre.ebooks.oeb.base import XHTML_NS, barename, namespace
+
         if not isinstance(elem.tag, basestring) \
            or namespace(elem.tag) != XHTML_NS:
             return []

src/calibre/ebooks/rb/rbml.py

@@ -11,8 +11,6 @@ Transform OEB content into RB compatible markup.
 import re
 
 from calibre import prepare_string_for_xml
-from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
-from calibre.ebooks.oeb.stylizer import Stylizer
 from calibre.ebooks.rb import unique_name
 
 TAGS = [
@@ -81,6 +79,8 @@ class RBMLizer(object):
         return output
 
     def get_cover_page(self):
+        from calibre.ebooks.oeb.stylizer import Stylizer
+        from calibre.ebooks.oeb.base import XHTML
         output = u''
         if 'cover' in self.oeb_book.guide:
             if self.name_map.get(self.oeb_book.guide['cover'].href, None):
@@ -109,6 +109,9 @@ class RBMLizer(object):
         return ''.join(toc)
 
     def get_text(self):
+        from calibre.ebooks.oeb.stylizer import Stylizer
+        from calibre.ebooks.oeb.base import XHTML
+
         output = [u'']
         for item in self.oeb_book.spine:
             self.log.debug('Converting %s to RocketBook HTML...' % item.href)
@@ -137,6 +140,8 @@ class RBMLizer(object):
         return text
 
     def dump_text(self, elem, stylizer, page, tag_stack=[]):
+        from calibre.ebooks.oeb.base import XHTML_NS, barename, namespace
+
         if not isinstance(elem.tag, basestring) \
            or namespace(elem.tag) != XHTML_NS:
             return [u'']

src/calibre/ebooks/rb/writer.py

@@ -18,7 +18,6 @@ import cStringIO
 from calibre.ebooks.rb.rbml import RBMLizer
 from calibre.ebooks.rb import HEADER
 from calibre.ebooks.rb import unique_name
-from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
 from calibre.constants import __appname__, __version__
 
 TEXT_RECORD_SIZE = 4096
@@ -111,6 +110,7 @@ class RBWriter(object):
         return (size, pages)
 
     def _images(self, manifest):
+        from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
         images = []
         used_names = []
 

src/calibre/ebooks/rtf/rtfml.py

@@ -14,9 +14,6 @@ import cStringIO
 
 from lxml import etree
 
-from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace, \
-    OEB_RASTER_IMAGES
-from calibre.ebooks.oeb.stylizer import Stylizer
 from calibre.ebooks.metadata import authors_to_string
 from calibre.utils.filenames import ascii_text
 from calibre.utils.magick.draw import save_cover_data_to, identify_data
@@ -100,6 +97,8 @@ class RTFMLizer(object):
         return self.mlize_spine()
 
     def mlize_spine(self):
+        from calibre.ebooks.oeb.base import XHTML
+        from calibre.ebooks.oeb.stylizer import Stylizer
         output = self.header()
         if 'titlepage' in self.oeb_book.guide:
             href = self.oeb_book.guide['titlepage'].href
@@ -154,6 +153,8 @@ class RTFMLizer(object):
         return ' }'
 
     def insert_images(self, text):
+        from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
+
         for item in self.oeb_book.manifest:
             if item.media_type in OEB_RASTER_IMAGES:
                 src = os.path.basename(item.href)
@@ -201,6 +202,8 @@ class RTFMLizer(object):
         return text
 
     def dump_text(self, elem, stylizer, tag_stack=[]):
+        from calibre.ebooks.oeb.base import XHTML_NS, namespace, barename
+
         if not isinstance(elem.tag, basestring) \
            or namespace(elem.tag) != XHTML_NS:
             p = elem.getparent()

src/calibre/ebooks/snb/input.py

@@ -7,7 +7,6 @@ __docformat__ = 'restructuredtext en'
 import os, uuid
 
 from calibre.customize.conversion import InputFormatPlugin
-from calibre.ebooks.oeb.base import DirContainer
 from calibre.ebooks.snb.snbfile import SNBFile
 from calibre.ptempfile import TemporaryDirectory
 from calibre.utils.filenames import ascii_filename
@@ -30,6 +29,7 @@ class SNBInput(InputFormatPlugin):
 
     def convert(self, stream, options, file_ext, log,
                 accelerators):
+        from calibre.ebooks.oeb.base import DirContainer
         log.debug("Parsing SNB file...")
         snbFile = SNBFile()
         try:

src/calibre/ebooks/snb/snbfile.py

@@ -5,7 +5,8 @@ __copyright__ = '2010, Li Fanxi <lifanxi@freemindworld.com>'
 __docformat__ = 'restructuredtext en'
 
 import sys, struct, zlib, bz2, os
-from mimetypes import types_map
+
+from calibre import guess_type
 
 class FileStream:
     def IsBinary(self):
@@ -180,7 +181,7 @@ class SNBFile:
                 file = open(os.path.join(path, fname), 'wb')
                 file.write(f.fileBody)
                 file.close()
-                fileNames.append((fname, types_map[ext]))
+                fileNames.append((fname, guess_type('a'+ext)[0]))
         return fileNames
 
     def Output(self, outputFile):

src/calibre/ebooks/snb/snbml.py

@@ -13,8 +13,6 @@ import re
 
 from lxml import etree
 
-from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
-from calibre.ebooks.oeb.stylizer import Stylizer
 
 def ProcessFileName(fileName):
     # Flat the path
@@ -81,6 +79,8 @@ class SNBMLizer(object):
                     body.append(entity)
 
     def mlize(self):
+        from calibre.ebooks.oeb.base import XHTML
+        from calibre.ebooks.oeb.stylizer import Stylizer
         output = [ u'' ]
         stylizer = Stylizer(self.item.data, self.item.href, self.oeb_book, self.opts, self.opts.output_profile)
         content = unicode(etree.tostring(self.item.data.find(XHTML('body')), encoding=unicode))
@@ -208,6 +208,7 @@ class SNBMLizer(object):
         return text
 
     def dump_text(self, subitems, elem, stylizer, end='', pre=False, li = ''):
+        from calibre.ebooks.oeb.base import XHTML_NS, barename, namespace
 
         if not isinstance(elem.tag, basestring) \
            or namespace(elem.tag) != XHTML_NS:

src/calibre/ebooks/txt/output.py

@@ -11,7 +11,6 @@ from lxml import etree
 
 from calibre.customize.conversion import OutputFormatPlugin, \
     OptionRecommendation
-from calibre.ebooks.oeb.base import OEB_IMAGES
 from calibre.ebooks.txt.txtml import TXTMLizer
 from calibre.ebooks.txt.newlines import TxtNewlines, specified_newlines
 from calibre.ptempfile import TemporaryDirectory, TemporaryFile
@@ -109,6 +108,7 @@ class TXTZOutput(TXTOutput):
     file_type = 'txtz'
 
     def convert(self, oeb_book, output_path, input_plugin, opts, log):
+        from calibre.ebooks.oeb.base import OEB_IMAGES
         with TemporaryDirectory('_txtz_output') as tdir:
             # TXT
             with TemporaryFile('index.txt') as tf:

src/calibre/ebooks/txt/txtml.py

@@ -12,8 +12,6 @@ import re
 
 from lxml import etree
 
-from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
-from calibre.ebooks.oeb.stylizer import Stylizer
 
 BLOCK_TAGS = [
     'div',
@@ -64,6 +62,8 @@ class TXTMLizer(object):
         return self.mlize_spine()
 
     def mlize_spine(self):
+        from calibre.ebooks.oeb.base import XHTML
+        from calibre.ebooks.oeb.stylizer import Stylizer
         output = [u'']
         output.append(self.get_toc())
         for item in self.oeb_book.spine:
@@ -185,6 +185,7 @@ class TXTMLizer(object):
         @stylizer: The style information attached to the element.
         @page: OEB page used to determine absolute urls.
         '''
+        from calibre.ebooks.oeb.base import XHTML_NS, barename, namespace
 
         if not isinstance(elem.tag, basestring) \
            or namespace(elem.tag) != XHTML_NS:

src/calibre/gui2/__init__.py

@@ -4,19 +4,17 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 import os, sys, Queue, threading
 from threading import RLock
 from urllib import unquote
-
+from PyQt4.Qt import (QVariant, QFileInfo, QObject, SIGNAL, QBuffer, Qt,
-from PyQt4.Qt import QVariant, QFileInfo, QObject, SIGNAL, QBuffer, Qt, \
+                    QByteArray, QTranslator, QCoreApplication, QThread,
-                         QByteArray, QTranslator, QCoreApplication, QThread, \
+                    QEvent, QTimer, pyqtSignal, QDate, QDesktopServices,
-                         QEvent, QTimer, pyqtSignal, QDate, QDesktopServices, \
+                    QFileDialog, QFileIconProvider,
-                         QFileDialog, QFileIconProvider, \
+                    QIcon, QApplication, QDialog, QUrl, QFont)
-                         QIcon, QApplication, QDialog, QUrl, QFont
 
 ORG_NAME = 'KovidsBrain'
 APP_UID  = 'libprs500'
 from calibre.constants import islinux, iswindows, isfreebsd, isfrozen, isosx
 from calibre.utils.config import Config, ConfigProxy, dynamic, JSONConfig
 from calibre.utils.localization import set_qt_translator
-from calibre.ebooks.metadata.meta import get_metadata, metadata_from_formats
 from calibre.ebooks.metadata import MetaInformation
 from calibre.utils.date import UNDEFINED_DATE
 
@@ -156,7 +154,9 @@ def _config():
     c.add_opt('plugin_search_history', default=[],
         help='Search history for the recipe scheduler')
     c.add_opt('worker_limit', default=6,
-            help=_('Maximum number of waiting worker processes'))
+            help=_(
+        'Maximum number of simultaneous conversion/news download jobs. '
+        'This number is twice the actual value for historical reasons.'))
     c.add_opt('get_social_metadata', default=True,
             help=_('Download social metadata (tags/rating/etc.)'))
     c.add_opt('overwrite_author_title_metadata', default=True,
@@ -330,6 +330,7 @@ class GetMetadata(QObject):
                   id, args, kwargs)
 
     def _from_formats(self, id, args, kwargs):
+        from calibre.ebooks.metadata.meta import metadata_from_formats
         try:
             mi = metadata_from_formats(*args, **kwargs)
         except:
@@ -337,6 +338,7 @@ class GetMetadata(QObject):
         self.emit(SIGNAL('metadataf(PyQt_PyObject, PyQt_PyObject)'), id, mi)
 
     def _get_metadata(self, id, args, kwargs):
+        from calibre.ebooks.metadata.meta import get_metadata
         try:
             mi = get_metadata(*args, **kwargs)
         except:
@@ -738,3 +740,4 @@ def build_forms(srcdir, info=None):
 _df = os.environ.get('CALIBRE_DEVELOP_FROM', None)
 if _df and os.path.exists(_df):
     build_forms(_df)
+

src/calibre/gui2/actions/annotate.py

@@ -22,7 +22,7 @@ class FetchAnnotationsAction(InterfaceAction):
     action_type = 'current'
 
     def genesis(self):
-        pass
+        self.qaction.triggered.connect(self.fetch_annotations)
 
     def fetch_annotations(self, *args):
         # Generate a path_map from selected ids
@@ -52,6 +52,10 @@ class FetchAnnotationsAction(InterfaceAction):
             return path_map
 
         device = self.gui.device_manager.device
+        if not getattr(device, 'SUPPORTS_ANNOTATIONS', False):
+            return error_dialog(self.gui, _('Not supported'),
+                    _('Fetching annotations is not supported for this device'),
+                    show=True)
 
         if self.gui.current_view() is not self.gui.library_view:
             return error_dialog(self.gui, _('Use library only'),

src/calibre/gui2/actions/edit_metadata.py

@@ -37,8 +37,6 @@ class EditMetadataAction(InterfaceAction):
         md.addSeparator()
         if test_eight_code:
             dall = self.download_metadata
-            dident = partial(self.download_metadata, covers=False)
-            dcovers = partial(self.download_metadata, identify=False)
         else:
             dall = partial(self.download_metadata_old, False, covers=True)
             dident = partial(self.download_metadata_old, False, covers=False)
@@ -47,9 +45,9 @@ class EditMetadataAction(InterfaceAction):
 
         md.addAction(_('Download metadata and covers'), dall,
                 Qt.ControlModifier+Qt.Key_D)
-        md.addAction(_('Download only metadata'), dident)
-        md.addAction(_('Download only covers'), dcovers)
         if not test_eight_code:
+            md.addAction(_('Download only metadata'), dident)
+            md.addAction(_('Download only covers'), dcovers)
             md.addAction(_('Download only social metadata'),
                 partial(self.download_metadata_old, False, covers=False,
                     set_metadata=False, set_social_metadata=True))
@@ -80,7 +78,7 @@ class EditMetadataAction(InterfaceAction):
         self.qaction.setEnabled(enabled)
         self.action_merge.setEnabled(enabled)
 
-    def download_metadata(self, identify=True, covers=True, ids=None):
+    def download_metadata(self, ids=None):
         if ids is None:
             rows = self.gui.library_view.selectionModel().selectedRows()
             if not rows or len(rows) == 0:
@@ -90,7 +88,7 @@ class EditMetadataAction(InterfaceAction):
             ids = [db.id(row.row()) for row in rows]
         from calibre.gui2.metadata.bulk_download2 import start_download
         start_download(self.gui, ids,
-                Dispatcher(self.bulk_metadata_downloaded), identify, covers)
+                Dispatcher(self.bulk_metadata_downloaded))
 
     def bulk_metadata_downloaded(self, job):
         if job.failed:

src/calibre/gui2/actions/store.py

@@ -47,16 +47,21 @@ class StoreAction(InterfaceAction):
         if self.config.get('first_run', True):
             self.config['first_run'] = False
             from calibre.gui2 import info_dialog
-            info_dialog(self.gui, _('Get Books Disclaimer'),
+            info_dialog(self.gui, _('About Get Books'), '<p>' +
-                _('<p>Calibre helps you find books to read by connecting you with outside stores. '
+            _('Calibre helps you find the ebooks you want by searching '
-                'The stores are a variety of big, independent, free, and public domain sources.</p>'
+            'the websites of a variety of commercial and public domain '
-                '<p>Using the integrated search you can easily find what store has the book you\'re '
+            'book sources for you.') +
-                'looking for. It will also give you a price, DRM status as well as a lot of '
+            '<p>' +
-                'other useful information.</p>'
+            _('Using the integrated search you can easily find which '
-                '<p>All transaction (paid or otherwise) are handled between you and the store. '
+            'store has the book you are looking for, at the best price. '
-                'Calibre is not part of this process and any issues related to a purchase need to '
+            'You will also get DRM status and other useful information.')
-                'be directed to the actual store. Be sure to double check that any books you get '
+            + '<p>' +
-                'will work with you device. Double check for format and '
+            _('All transactions (paid or otherwise) are handled between '
-                '<a href="http://en.wikipedia.org/wiki/Digital_rights_management">DRM</a> '
+            'you and the particular website. '
-                'restrictions.</p>'),
+            'Calibre is not part of this process and any issues related '
-                show=True, show_copy_button=False)
+            'to a purchase should be directed to the website you are '
+            'buying from. Be sure to double check that any books you get '
+            'will work with your e-book reader, especially if the book you '
+            'are buying has '
+            '<a href="http://drmfree.calibre-ebook.com/about#drm">DRM</a>.'
+            ), show=True, show_copy_button=False)

src/calibre/gui2/book_details.py

@@ -418,6 +418,7 @@ class BookDetails(QWidget): # {{{
             if y is None:
                 # Local image
                 self.cover_view.paste_from_clipboard(x)
+                self.update_layout()
             else:
                 self.remote_file_dropped.emit(x, y)
                 # We do not support setting cover *and* adding formats for
@@ -449,6 +450,7 @@ class BookDetails(QWidget): # {{{
         self.setAcceptDrops(True)
         self._layout = DetailsLayout(vertical, self)
         self.setLayout(self._layout)
+        self.current_path = ''
 
         self.cover_view = CoverView(vertical, self)
         self.cover_view.cover_changed.connect(self.cover_changed.emit)
@@ -482,15 +484,19 @@ class BookDetails(QWidget): # {{{
     def show_data(self, data):
         self.book_info.show_data(data)
         self.cover_view.show_data(data)
+        self.current_path = data.get(_('Path'), '')
+        self.update_layout()
+
+    def update_layout(self):
         self._layout.do_layout(self.rect())
         try:
             sz = self.cover_view.pixmap.size()
         except:
             sz = QSize(0, 0)
         self.setToolTip(
-                '<p>'+_('Double-click to open Book Details window') +
+            '<p>'+_('Double-click to open Book Details window') +
-                '<br><br>' + _('Path') + ': ' + data.get(_('Path'), '') +
+            '<br><br>' + _('Path') + ': ' + self.current_path +
-                '<br><br>' + _('Cover size: %dx%d')%(sz.width(), sz.height())
+            '<br><br>' + _('Cover size: %dx%d')%(sz.width(), sz.height())
         )
 
     def reset_info(self):

src/calibre/gui2/custom_column_widgets.py

@@ -289,6 +289,7 @@ class Series(Base):
         values = self.all_values = list(self.db.all_custom(num=self.col_id))
         values.sort(key=sort_key)
         w = MultiCompleteComboBox(parent)
+        w.set_separator(None)
         w.setSizeAdjustPolicy(w.AdjustToMinimumContentsLengthWithIcon)
         w.setMinimumContentsLength(25)
         self.name_widget = w

src/calibre/gui2/device.py

@@ -7,7 +7,7 @@ import os, traceback, Queue, time, cStringIO, re, sys
 from threading import Thread
 
 from PyQt4.Qt import QMenu, QAction, QActionGroup, QIcon, SIGNAL, \
-                     Qt, pyqtSignal, QDialog
+                     Qt, pyqtSignal, QDialog, QObject
 
 from calibre.customize.ui import available_input_formats, available_output_formats, \
     device_plugins
@@ -25,12 +25,10 @@ from calibre.devices.errors import FreeSpaceError
 from calibre.devices.apple.driver import ITUNES_ASYNC
 from calibre.devices.folder_device.driver import FOLDER_DEVICE
 from calibre.devices.bambook.driver import BAMBOOK, BAMBOOKWifi
-from calibre.ebooks.metadata.meta import set_metadata
 from calibre.constants import DEBUG
 from calibre.utils.config import prefs, tweaks
 from calibre.utils.magick.draw import thumbnail
-from calibre.library.save_to_disk import plugboard_any_device_value, \
+from calibre.library.save_to_disk import find_plugboard
-                                         plugboard_any_format_value
 # }}}
 
 class DeviceJob(BaseJob): # {{{
@@ -93,23 +91,6 @@ class DeviceJob(BaseJob): # {{{
 
     # }}}
 
-def find_plugboard(device_name, format, plugboards):
-    cpb = None
-    if format in plugboards:
-        cpb = plugboards[format]
-    elif plugboard_any_format_value in plugboards:
-        cpb = plugboards[plugboard_any_format_value]
-    if cpb is not None:
-        if device_name in cpb:
-            cpb = cpb[device_name]
-        elif plugboard_any_device_value in cpb:
-            cpb = cpb[plugboard_any_device_value]
-        else:
-            cpb = None
-    if DEBUG:
-        prints('Device using plugboard', format, device_name, cpb)
-    return cpb
-
 def device_name_for_plugboards(device_class):
     if hasattr(device_class, 'DEVICE_PLUGBOARD_NAME'):
         return device_class.DEVICE_PLUGBOARD_NAME
@@ -352,6 +333,7 @@ class DeviceManager(Thread): # {{{
 
     def _upload_books(self, files, names, on_card=None, metadata=None, plugboards=None):
         '''Upload books to device: '''
+        from calibre.ebooks.metadata.meta import set_metadata
         if hasattr(self.connected_device, 'set_plugboards') and \
                 callable(self.connected_device.set_plugboards):
             self.connected_device.set_plugboards(plugboards, find_plugboard)
@@ -605,6 +587,24 @@ class DeviceMenu(QMenu): # {{{
 
     # }}}
 
+class DeviceSignals(QObject):
+    #: This signal is emitted once, after metadata is downloaded from the
+    #: connected device.
+    #: The sequence: gui.device_manager.is_device_connected will become True,
+    #: and the device_connection_changed signal will be emitted,
+    #: then sometime later gui.device_metadata_available will be signaled.
+    #: This does not mean that there are no more jobs running. Automatic metadata
+    #: management might have kicked off a sync_booklists to write new metadata onto
+    #: the device, and that job might still be running when the signal is emitted.
+    device_metadata_available = pyqtSignal()
+
+    #: This signal is emitted once when the device is detected and once when
+    #: it is disconnected. If the parameter is True, then it is a connection,
+    #: otherwise a disconnection.
+    device_connection_changed = pyqtSignal(object)
+
+device_signals = DeviceSignals()
+
 class DeviceMixin(object): # {{{
 
     def __init__(self):
@@ -753,6 +753,7 @@ class DeviceMixin(object): # {{{
             self.location_manager.update_devices()
             self.library_view.set_device_connected(self.device_connected)
             self.refresh_ondevice()
+        device_signals.device_connection_changed.emit(connected)
 
     def info_read(self, job):
         '''
@@ -791,6 +792,7 @@ class DeviceMixin(object): # {{{
         self.sync_news()
         self.sync_catalogs()
         self.refresh_ondevice()
+        device_signals.device_metadata_available.emit()
 
     def refresh_ondevice(self, reset_only = False):
         '''

src/calibre/gui2/dialogs/confirm_delete.py

@@ -24,11 +24,16 @@ class Dialog(QDialog, Ui_Dialog):
         dynamic[confirm_config_name(self.name)] = self.again.isChecked()
 
 
-def confirm(msg, name, parent=None, pixmap='dialog_warning.png'):
+def confirm(msg, name, parent=None, pixmap='dialog_warning.png', title=None,
+        show_cancel_button=True):
     if not dynamic.get(confirm_config_name(name), True):
         return True
     d = Dialog(msg, name, parent)
     d.label.setPixmap(QPixmap(I(pixmap)))
     d.setWindowIcon(QIcon(I(pixmap)))
+    if title is not None:
+        d.setWindowTitle(title)
+    if not show_cancel_button:
+        d.buttonBox.button(d.buttonBox.Cancel).setVisible(False)
     d.resize(d.sizeHint())
     return d.exec_() == d.Accepted

src/calibre/gui2/dialogs/metadata_bulk.py

@@ -13,7 +13,6 @@ from calibre.gui2.dialogs.metadata_bulk_ui import Ui_MetadataBulkDialog
 from calibre.gui2.dialogs.tag_editor import TagEditor
 from calibre.ebooks.metadata import string_to_authors, authors_to_string, title_sort
 from calibre.ebooks.metadata.book.base import composite_formatter
-from calibre.ebooks.metadata.meta import get_metadata
 from calibre.gui2.custom_column_widgets import populate_metadata_page
 from calibre.gui2 import error_dialog, ResizableDialog, UNDEFINED_QDATE, \
     gprefs, question_dialog
@@ -26,6 +25,7 @@ from calibre.utils.magick.draw import identify_data
 from calibre.utils.date import qt_to_dt
 
 def get_cover_data(path): # {{{
+    from calibre.ebooks.metadata.meta import get_metadata
     old = prefs['read_file_metadata']
     if not old:
         prefs['read_file_metadata'] = True

src/calibre/gui2/dialogs/metadata_single.py

@@ -25,7 +25,6 @@ from calibre.ebooks import BOOK_EXTENSIONS
 from calibre.ebooks.metadata import string_to_authors, \
         authors_to_string, check_isbn, title_sort
 from calibre.ebooks.metadata.covers import download_cover
-from calibre.ebooks.metadata.meta import get_metadata
 from calibre.ebooks.metadata import MetaInformation
 from calibre.utils.config import prefs, tweaks
 from calibre.utils.date import qt_to_dt, local_tz, utcfromtimestamp
@@ -353,6 +352,7 @@ class MetadataSingleDialog(ResizableDialog, Ui_MetadataSingleDialog):
             self.formats_changed = True
 
     def get_selected_format_metadata(self):
+        from calibre.ebooks.metadata.meta import get_metadata
         old = prefs['read_file_metadata']
         if not old:
             prefs['read_file_metadata'] = True

src/calibre/gui2/dialogs/tweak_epub.py

@@ -12,7 +12,7 @@ from zipfile import ZipFile, ZIP_DEFLATED, ZIP_STORED
 
 from PyQt4.Qt import QDialog
 
-from calibre.constants import isosx, iswindows
+from calibre.constants import isosx
 from calibre.gui2 import open_local_file
 from calibre.gui2.dialogs.tweak_epub_ui import Ui_Dialog
 from calibre.libunzip import extract as zipextract

src/calibre/gui2/layout.py

@@ -156,8 +156,6 @@ class SearchBar(QWidget): # {{{
         x = ComboBoxWithHelp(self)
         x.setMaximumSize(QSize(150, 16777215))
         x.setObjectName("search_restriction")
-        x.setToolTip(_('Books display will be restricted to those matching the '
-                       'selected saved search'))
         l.addWidget(x)
         parent.search_restriction = x
 

src/calibre/gui2/library/models.py

@@ -18,7 +18,6 @@ from calibre.ptempfile import PersistentTemporaryFile
 from calibre.utils.config import tweaks, prefs
 from calibre.utils.date import dt_factory, qt_to_dt, isoformat
 from calibre.utils.icu import sort_key
-from calibre.ebooks.metadata.meta import set_metadata as _set_metadata
 from calibre.utils.search_query_parser import SearchQueryParser
 from calibre.library.caches import _match, CONTAINS_MATCH, EQUALS_MATCH, \
     REGEXP_MATCH, MetadataBackup, force_to_bool
@@ -478,6 +477,7 @@ class BooksModel(QAbstractTableModel): # {{{
     def get_preferred_formats_from_ids(self, ids, formats,
                               set_metadata=False, specific_format=None,
                               exclude_auto=False, mode='r+b'):
+        from calibre.ebooks.metadata.meta import set_metadata as _set_metadata
         ans = []
         need_auto = []
         if specific_format is not None:
@@ -526,6 +526,7 @@ class BooksModel(QAbstractTableModel): # {{{
     def get_preferred_formats(self, rows, formats, paths=False,
                               set_metadata=False, specific_format=None,
                               exclude_auto=False):
+        from calibre.ebooks.metadata.meta import set_metadata as _set_metadata
         ans = []
         need_auto = []
         if specific_format is not None:

src/calibre/gui2/main.py

@@ -19,6 +19,9 @@ from calibre.utils.config import prefs, dynamic
 from calibre.library.database2 import LibraryDatabase2
 from calibre.library.sqlite import sqlite, DatabaseException
 
+if iswindows:
+    winutil = plugins['winutil'][0]
+
 def option_parser():
     parser = _option_parser('''\
 %prog [opts] [path_to_ebook]
@@ -80,8 +83,7 @@ def get_library_path(parent=None):
     if library_path is None: # Need to migrate to new database layout
         base = os.path.expanduser('~')
         if iswindows:
-            base = plugins['winutil'][0].special_folder_path(
+            base = winutil.special_folder_path(winutil.CSIDL_PERSONAL)
-                    plugins['winutil'][0].CSIDL_PERSONAL)
             if not base or not os.path.exists(base):
                 from PyQt4.Qt import QDir
                 base = unicode(QDir.homePath()).replace('/', os.sep)

src/calibre/gui2/metadata/basic_widgets.py

@@ -24,7 +24,7 @@ from calibre.ebooks.metadata.meta import get_metadata
 from calibre.gui2 import file_icon_provider, UNDEFINED_QDATE, UNDEFINED_DATE, \
         choose_files, error_dialog, choose_images, question_dialog
 from calibre.utils.date import local_tz, qt_to_dt
-from calibre import strftime, fit_image
+from calibre import strftime
 from calibre.ebooks import BOOK_EXTENSIONS
 from calibre.customize.ui import run_plugins_on_import
 from calibre.utils.date import utcfromtimestamp
@@ -278,11 +278,13 @@ class AuthorSortEdit(EnLineEdit):
 
     def copy_to_authors(self):
         aus = self.current_val
+        meth = tweaks['author_sort_copy_method']
         if aus:
             ln, _, rest = aus.partition(',')
             if rest:
-                au = rest.strip() + ' ' + ln.strip()
+                if meth in ('invert', 'nocomma', 'comma'):
-                self.authors_edit.current_val = [au]
+                    aus = rest.strip() + ' ' + ln.strip()
+            self.authors_edit.current_val = [aus]
 
     def auto_generate(self, *args):
         au = unicode(self.authors_edit.text())
@@ -465,16 +467,22 @@ class FormatsManager(QWidget): # {{{
         self.metadata_from_format_button = QToolButton(self)
         self.metadata_from_format_button.setIcon(QIcon(I('edit_input.png')))
         self.metadata_from_format_button.setIconSize(QSize(32, 32))
+        self.metadata_from_format_button.setToolTip(
+                _('Set metadata for the book from the selected format'))
 
         self.add_format_button = QToolButton(self)
         self.add_format_button.setIcon(QIcon(I('add_book.png')))
         self.add_format_button.setIconSize(QSize(32, 32))
         self.add_format_button.clicked.connect(self.add_format)
+        self.add_format_button.setToolTip(
+                _('Add a format to this book'))
 
         self.remove_format_button = QToolButton(self)
         self.remove_format_button.setIcon(QIcon(I('trash.png')))
         self.remove_format_button.setIconSize(QSize(32, 32))
         self.remove_format_button.clicked.connect(self.remove_format)
+        self.remove_format_button.setToolTip(
+                _('Remove the selected format from this book'))
 
         self.formats = FormatList(self)
         self.formats.setAcceptDrops(True)
@@ -664,12 +672,7 @@ class Cover(ImageView): # {{{
         self.frame_size = (sz.width()//3, sz.height())
 
     def sizeHint(self):
-        sz = ImageView.sizeHint(self)
+        sz = QSize(self.frame_size[0], self.frame_size[1])
-        w, h = sz.width(), sz.height()
-        resized, nw, nh = fit_image(w, h, self.frame_size[0],
-                self.frame_size[1])
-        if resized:
-            sz = QSize(nw, nh)
         return sz
 
     def select_cover(self, *args):
@@ -939,7 +942,13 @@ class IdentifiersEdit(QLineEdit): # {{{
         def fset(self, val):
             if not val:
                 val = {}
-            txt = ', '.join(['%s:%s'%(k, v) for k, v in val.iteritems()])
+            def keygen(x):
+                x = x[0]
+                if x == 'isbn':
+                    x = '00isbn'
+                return x
+            ids = sorted(val.iteritems(), key=keygen)
+            txt = ', '.join(['%s:%s'%(k, v) for k, v in ids])
             self.setText(txt.strip())
             self.setCursorPosition(0)
         return property(fget=fget, fset=fset)
@@ -959,7 +968,7 @@ class IdentifiersEdit(QLineEdit): # {{{
         tt = self.BASE_TT
         extra = ''
         if not isbn:
-            col = 'rgba(0,255,0,0%)'
+            col = 'none'
         elif check_isbn(isbn) is not None:
             col = 'rgba(0,255,0,20%)'
             extra = '\n\n'+_('This ISBN number is valid')

src/calibre/gui2/metadata/bulk_download2.py

@@ -12,7 +12,8 @@ from functools import partial
 from itertools import izip
 
 from PyQt4.Qt import (QIcon, QDialog, QVBoxLayout, QTextBrowser, QSize,
-        QDialogButtonBox, QApplication, QTimer, QLabel, QProgressBar)
+        QDialogButtonBox, QApplication, QTimer, QLabel, QProgressBar,
+        QGridLayout, QPixmap, Qt)
 
 from calibre.gui2.dialogs.message_box import MessageBox
 from calibre.gui2.threaded_jobs import ThreadedJob
@@ -25,37 +26,86 @@ from calibre.ebooks.metadata.book.base import Metadata
 from calibre.customize.ui import metadata_plugins
 from calibre.ptempfile import PersistentTemporaryFile
 
+# Start download {{{
 def show_config(gui, parent):
     from calibre.gui2.preferences import show_config_widget
     show_config_widget('Sharing', 'Metadata download', parent=parent,
             gui=gui, never_shutdown=True)
 
-def start_download(gui, ids, callback, identify, covers):
+class ConfirmDialog(QDialog):
-    q = MessageBox(MessageBox.QUESTION,  _('Schedule download?'),
+
+    def __init__(self, ids, parent):
+        QDialog.__init__(self, parent)
+        self.setWindowTitle(_('Schedule download?'))
+        self.setWindowIcon(QIcon(I('dialog_question.png')))
+
+        l = self.l = QGridLayout()
+        self.setLayout(l)
+
+        i = QLabel(self)
+        i.setPixmap(QPixmap(I('dialog_question.png')))
+        l.addWidget(i, 0, 0)
+
+        t = QLabel(
             '<p>'+_('The download of metadata for the <b>%d selected book(s)</b> will'
                 ' run in the background. Proceed?')%len(ids) +
             '<p>'+_('You can monitor the progress of the download '
                 'by clicking the rotating spinner in the bottom right '
                 'corner.') +
             '<p>'+_('When the download completes you will be asked for'
-                ' confirmation before calibre applies the downloaded metadata.'),
+                ' confirmation before calibre applies the downloaded metadata.')
-            show_copy_button=False, parent=gui)
+            )
-    b = q.bb.addButton(_('Configure download'), q.bb.ActionRole)
+        t.setWordWrap(True)
-    b.setIcon(QIcon(I('config.png')))
+        l.addWidget(t, 0, 1)
-    b.clicked.connect(partial(show_config, gui, q))
+        l.setColumnStretch(0, 1)
-    q.det_msg_toggle.setVisible(False)
+        l.setColumnStretch(1, 100)
 
-    ret = q.exec_()
+        self.identify = self.covers = True
-    b.clicked.disconnect()
+        self.bb = QDialogButtonBox(QDialogButtonBox.Cancel)
-    if ret != q.Accepted:
+        self.bb.rejected.connect(self.reject)
+        b = self.bb.addButton(_('Download only &metadata'),
+                self.bb.AcceptRole)
+        b.clicked.connect(self.only_metadata)
+        b.setIcon(QIcon(I('edit_input.png')))
+        b = self.bb.addButton(_('Download only &covers'),
+                self.bb.AcceptRole)
+        b.clicked.connect(self.only_covers)
+        b.setIcon(QIcon(I('default_cover.png')))
+        b = self.b = self.bb.addButton(_('&Configure download'), self.bb.ActionRole)
+        b.setIcon(QIcon(I('config.png')))
+        b.clicked.connect(partial(show_config, parent, self))
+        l.addWidget(self.bb, 1, 0, 1, 2)
+        b = self.bb.addButton(_('Download &both'),
+                self.bb.AcceptRole)
+        b.clicked.connect(self.accept)
+        b.setDefault(True)
+        b.setAutoDefault(True)
+        b.setIcon(QIcon(I('ok.png')))
+
+        self.resize(self.sizeHint())
+        b.setFocus(Qt.OtherFocusReason)
+
+    def only_metadata(self):
+        self.covers = False
+        self.accept()
+
+    def only_covers(self):
+        self.identify = False
+        self.accept()
+
+def start_download(gui, ids, callback):
+    d = ConfirmDialog(ids, gui)
+    ret = d.exec_()
+    d.b.clicked.disconnect()
+    if ret != d.Accepted:
         return
 
     job = ThreadedJob('metadata bulk download',
             _('Download metadata for %d books')%len(ids),
-            download, (ids, gui.current_db, identify, covers), {}, callback)
+            download, (ids, gui.current_db, d.identify, d.covers), {}, callback)
     gui.job_manager.run_threaded_job(job)
     gui.status_bar.show_message(_('Metadata download started'), 3000)
-
+# }}}
 
 class ViewLog(QDialog): # {{{
 
@@ -93,9 +143,10 @@ def view_log(job, parent):
 
 # }}}
 
+# Apply downloaded metadata {{{
 class ApplyDialog(QDialog):
 
-    def __init__(self, id_map, gui):
+    def __init__(self, gui):
         QDialog.__init__(self, gui)
 
         self.l = l = QVBoxLayout()
@@ -104,27 +155,33 @@ class ApplyDialog(QDialog):
 
         self.pb = QProgressBar(self)
         l.addWidget(self.pb)
-        self.pb.setMinimum(0)
-        self.pb.setMaximum(len(id_map))
 
         self.bb = QDialogButtonBox(QDialogButtonBox.Cancel)
         self.bb.rejected.connect(self.reject)
-        self.bb.accepted.connect(self.accept)
         l.addWidget(self.bb)
 
         self.gui = gui
+        self.timer = QTimer(self)
+        self.timer.timeout.connect(self.do_one)
+
+    def start(self, id_map):
         self.id_map = list(id_map.iteritems())
         self.current_idx = 0
-
         self.failures = []
         self.ids = []
         self.canceled = False
-
+        self.pb.setMinimum(0)
-        QTimer.singleShot(20, self.do_one)
+        self.pb.setMaximum(len(id_map))
+        self.timer.start(50)
 
     def do_one(self):
         if self.canceled:
             return
+        if self.current_idx >= len(self.id_map):
+            self.timer.stop()
+            self.finalize()
+            return
+
         i, mi = self.id_map[self.current_idx]
         db = self.gui.current_db
         try:
@@ -144,15 +201,11 @@ class ApplyDialog(QDialog):
             pass
 
         self.pb.setValue(self.pb.value()+1)
-
+        self.current_idx += 1
-        if self.current_idx >= len(self.id_map) - 1:
-            self.finalize()
-        else:
-            self.current_idx += 1
-            QTimer.singleShot(20, self.do_one)
 
     def reject(self):
         self.canceled = True
+        self.timer.stop()
         QDialog.reject(self)
 
     def finalize(self):
@@ -169,17 +222,18 @@ class ApplyDialog(QDialog):
                     title += ' - ' + authors_to_string(authors)
                 msg.append(title+'\n\n'+tb+'\n'+('*'*80))
 
-            error_dialog(self, _('Some failures'),
+            parent = self if self.isVisible() else self.parent()
+            error_dialog(parent, _('Some failures'),
                 _('Failed to apply updated metadata for some books'
                     ' in your library. Click "Show Details" to see '
                     'details.'), det_msg='\n\n'.join(msg), show=True)
-        self.accept()
         if self.ids:
             cr = self.gui.library_view.currentIndex().row()
             self.gui.library_view.model().refresh_ids(
                 self.ids, cr)
             if self.gui.cover_flow:
                 self.gui.cover_flow.dataChanged()
+        self.accept()
 
 _amd = None
 def apply_metadata(job, gui, q, result):
@@ -188,7 +242,7 @@ def apply_metadata(job, gui, q, result):
     q.finished.disconnect()
     if result != q.Accepted:
         return
-    id_map, failed_ids, failed_covers, title_map = job.result
+    id_map, failed_ids, failed_covers, title_map, all_failed = job.result
     id_map = dict([(k, v) for k, v in id_map.iteritems() if k not in
         failed_ids])
     if not id_map:
@@ -217,41 +271,55 @@ def apply_metadata(job, gui, q, result):
                     'Do you want to proceed?'), det_msg='\n'.join(modified)):
             return
 
-    _amd = ApplyDialog(id_map, gui)
+    if _amd is None:
-    _amd.exec_()
+        _amd = ApplyDialog(gui)
+    _amd.start(id_map)
+    if len(id_map) > 3:
+        _amd.exec_()
 
 def proceed(gui, job):
     gui.status_bar.show_message(_('Metadata download completed'), 3000)
-    id_map, failed_ids, failed_covers, title_map = job.result
+    id_map, failed_ids, failed_covers, title_map, all_failed = job.result
-    fmsg = det_msg = ''
+    det_msg = []
-    if failed_ids or failed_covers:
+    for i in failed_ids | failed_covers:
-        fmsg = '<p>'+_('Could not download metadata and/or covers for %d of the books. Click'
+        title = title_map[i]
-                ' "Show details" to see which books.')%len(failed_ids)
+        if i in failed_ids:
-        det_msg = []
+            title += (' ' + _('(Failed metadata)'))
-        for i in failed_ids | failed_covers:
+        if i in failed_covers:
-            title = title_map[i]
+            title += (' ' + _('(Failed cover)'))
-            if i in failed_ids:
+        det_msg.append(title)
-                title += (' ' + _('(Failed metadata)'))
+    det_msg = '\n'.join(det_msg)
-            if i in failed_covers:
+
-                title += (' ' + _('(Failed cover)'))
+    if all_failed:
-            det_msg.append(title)
+        q = error_dialog(gui, _('Download failed'),
-    msg = '<p>' + _('Finished downloading metadata for <b>%d book(s)</b>. '
+            _('Failed to download metadata or covers for any of the %d'
-        'Proceed with updating the metadata in your library?')%len(id_map)
+               ' book(s).') % len(id_map), det_msg=det_msg)
-    q = MessageBox(MessageBox.QUESTION, _('Download complete'),
+    else:
-            msg + fmsg, det_msg='\n'.join(det_msg), show_copy_button=bool(failed_ids),
+        fmsg = ''
-            parent=gui)
+        if failed_ids or failed_covers:
+            fmsg = '<p>'+_('Could not download metadata and/or covers for %d of the books. Click'
+                    ' "Show details" to see which books.')%len(failed_ids)
+        msg = '<p>' + _('Finished downloading metadata for <b>%d book(s)</b>. '
+            'Proceed with updating the metadata in your library?')%len(id_map)
+        q = MessageBox(MessageBox.QUESTION, _('Download complete'),
+                msg + fmsg, det_msg=det_msg, show_copy_button=bool(failed_ids),
+                parent=gui)
+        q.finished.connect(partial(apply_metadata, job, gui, q))
+
     q.vlb = q.bb.addButton(_('View log'), q.bb.ActionRole)
     q.vlb.setIcon(QIcon(I('debug.png')))
     q.vlb.clicked.connect(partial(view_log, job, q))
     q.det_msg_toggle.setVisible(bool(failed_ids | failed_covers))
     q.setModal(False)
     q.show()
-    q.finished.connect(partial(apply_metadata, job, gui, q))
+
+# }}}
 
 def merge_result(oldmi, newmi):
     dummy = Metadata(_('Unknown'))
     for f in msprefs['ignore_fields']:
-        setattr(newmi, f, getattr(dummy, f))
+        if ':' not in f:
+            setattr(newmi, f, getattr(dummy, f))
     fields = set()
     for plugin in metadata_plugins(['identify']):
         fields |= plugin.touched_fields
@@ -276,6 +344,7 @@ def download(ids, db, do_identify, covers,
     title_map = {}
     ans = {}
     count = 0
+    all_failed = True
     for i, mi in izip(ids, metadata):
         if abort.is_set():
             log.error('Aborting...')
@@ -290,6 +359,7 @@ def download(ids, db, do_identify, covers,
             except:
                 pass
             if results:
+                all_failed = False
                 mi = merge_result(mi, results[0])
                 identifiers = mi.identifiers
                 if not mi.is_null('rating'):
@@ -307,6 +377,7 @@ def download(ids, db, do_identify, covers,
                 with PersistentTemporaryFile('.jpg', 'downloaded-cover-') as f:
                     f.write(cdata[-1])
                     mi.cover = f.name
+                all_failed = False
             else:
                 failed_covers.add(i)
         ans[i] = mi
@@ -314,7 +385,7 @@ def download(ids, db, do_identify, covers,
         notifications.put((count/len(ids),
             _('Downloaded %d of %d')%(count, len(ids))))
     log('Download complete, with %d failures'%len(failed_ids))
-    return (ans, failed_ids, failed_covers, title_map)
+    return (ans, failed_ids, failed_covers, title_map, all_failed)
 
 
 

src/calibre/gui2/metadata/single.py

@@ -156,6 +156,9 @@ class MetadataSingleDialogBase(ResizableDialog):
 
         self.identifiers = IdentifiersEdit(self)
         self.basic_metadata_widgets.append(self.identifiers)
+        self.clear_identifiers_button = QToolButton(self)
+        self.clear_identifiers_button.setIcon(QIcon(I('trash.png')))
+        self.clear_identifiers_button.clicked.connect(self.identifiers.clear)
 
         self.publisher = PublisherEdit(self)
         self.basic_metadata_widgets.append(self.publisher)
@@ -323,7 +326,8 @@ class MetadataSingleDialogBase(ResizableDialog):
             mi = d.book
             dummy = Metadata(_('Unknown'))
             for f in msprefs['ignore_fields']:
-                setattr(mi, f, getattr(dummy, f))
+                if ':' not in f:
+                    setattr(mi, f, getattr(dummy, f))
             if mi is not None:
                 self.update_from_mi(mi)
             if d.cover_pixmap is not None:
@@ -541,8 +545,8 @@ class MetadataSingleDialog(MetadataSingleDialogBase): # {{{
         sto(self.rating, self.tags)
         create_row2(2, self.tags, self.tags_editor_button)
         sto(self.tags_editor_button, self.identifiers)
-        create_row2(3, self.identifiers)
+        create_row2(3, self.identifiers, self.clear_identifiers_button)
-        sto(self.identifiers, self.timestamp)
+        sto(self.clear_identifiers_button, self.timestamp)
         create_row2(4, self.timestamp, self.timestamp.clear_button)
         sto(self.timestamp.clear_button, self.pubdate)
         create_row2(5, self.pubdate, self.pubdate.clear_button)
@@ -657,7 +661,8 @@ class MetadataSingleDialogAlt1(MetadataSingleDialogBase): # {{{
         create_row(9, self.publisher, self.timestamp)
         create_row(10, self.timestamp, self.identifiers,
                    button=self.timestamp.clear_button, icon='trash.png')
-        create_row(11, self.identifiers, self.comments)
+        create_row(11, self.identifiers, self.comments,
+                   button=self.clear_identifiers_button, icon='trash.png')
         tl.addItem(QSpacerItem(1, 1, QSizePolicy.Fixed, QSizePolicy.Expanding),
                    12, 1, 1 ,1)
 

src/calibre/gui2/metadata/single_download.py

@@ -116,6 +116,10 @@ class CoverDelegate(QStyledItemDelegate): # {{{
 
     def paint(self, painter, option, index):
         QStyledItemDelegate.paint(self, painter, option, index)
+        # Ensure the cover is rendered over any selection rect
+        style = QApplication.style()
+        style.drawItemPixmap(painter, option.rect, Qt.AlignTop|Qt.AlignHCenter,
+            QPixmap(index.data(Qt.DecorationRole)))
         if self.timer.isActive() and index.data(Qt.UserRole).toBool():
             rect = QRect(0, 0, self.spinner_width, self.spinner_width)
             rect.moveCenter(option.rect.center())

src/calibre/gui2/preferences/__init__.py

@@ -337,7 +337,13 @@ def show_config_widget(category, name, gui=None, show_restart_msg=False,
     bb.button(bb.RestoreDefaults).setEnabled(w.supports_restoring_to_defaults)
     bb.button(bb.Apply).setEnabled(False)
     bb.button(bb.Apply).clicked.connect(d.accept)
-    w.changed_signal.connect(lambda : bb.button(bb.Apply).setEnabled(True))
+    def onchange():
+        b = bb.button(bb.Apply)
+        b.setEnabled(True)
+        b.setDefault(True)
+        b.setAutoDefault(True)
+    w.changed_signal.connect(onchange)
+    bb.button(bb.Cancel).setFocus(True)
     l = QVBoxLayout()
     d.setLayout(l)
     l.addWidget(w)

src/calibre/gui2/preferences/misc.py

@@ -6,19 +6,27 @@ __copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
 
-from calibre.gui2.preferences import ConfigWidgetBase, test_widget
+from calibre.gui2.preferences import ConfigWidgetBase, test_widget, Setting
 from calibre.gui2.preferences.misc_ui import Ui_Form
 from calibre.gui2 import error_dialog, config, open_local_file, info_dialog
 from calibre.constants import isosx
 
-# Check Integrity {{{
+class WorkersSetting(Setting):
+
+    def set_gui_val(self, val):
+        val = val//2
+        Setting.set_gui_val(self, val)
+
+    def get_gui_val(self):
+        val = Setting.get_gui_val(self)
+        return val * 2
 
 class ConfigWidget(ConfigWidgetBase, Ui_Form):
 
     def genesis(self, gui):
         self.gui = gui
         r = self.register
-        r('worker_limit', config, restart_required=True)
+        r('worker_limit', config, restart_required=True, setting=WorkersSetting)
         r('enforce_cpu_limit', config, restart_required=True)
         self.device_detection_button.clicked.connect(self.debug_device_detection)
         self.button_open_config_dir.clicked.connect(self.open_config_dir)

src/calibre/gui2/preferences/misc.ui

@@ -17,7 +17,7 @@
    <item row="0" column="0">
     <widget class="QLabel" name="label_5">
      <property name="text">
-      <string>&amp;Maximum number of waiting worker processes (needs restart):</string>
+      <string>Max. simultaneous conversion/news download jobs:</string>
      </property>
      <property name="buddy">
       <cstring>opt_worker_limit</cstring>
@@ -27,13 +27,7 @@
    <item row="0" column="1">
     <widget class="QSpinBox" name="opt_worker_limit">
      <property name="minimum">
-      <number>2</number>
+      <number>1</number>
-     </property>
-     <property name="maximum">
-      <number>10000</number>
-     </property>
-     <property name="singleStep">
-      <number>2</number>
      </property>
     </widget>
    </item>

src/calibre/gui2/preferences/plugboard.py

@@ -7,6 +7,7 @@ __docformat__ = 'restructuredtext en'
 
 from PyQt4.Qt import Qt, QLineEdit, QComboBox, SIGNAL, QListWidgetItem
 
+from calibre.customize.ui import is_disabled
 from calibre.gui2 import error_dialog
 from calibre.gui2.device import device_name_for_plugboards
 from calibre.gui2.dialogs.template_dialog import TemplateDialog
@@ -15,6 +16,8 @@ from calibre.gui2.preferences.plugboard_ui import Ui_Form
 from calibre.customize.ui import metadata_writers, device_plugins
 from calibre.library.save_to_disk import plugboard_any_format_value, \
                         plugboard_any_device_value, plugboard_save_to_disk_value
+from calibre.library.server.content import plugboard_content_server_value, \
+                                        plugboard_content_server_formats
 from calibre.utils.formatter import validation_formatter
 
 
@@ -68,19 +71,26 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
             self.device_label.setText(_('Device currently connected: None'))
 
         self.devices = ['', 'APPLE', 'FOLDER_DEVICE']
+        self.device_to_formats_map = {}
         for device in device_plugins():
             n = device_name_for_plugboards(device)
+            self.device_to_formats_map[n] = device.FORMATS
             if n not in self.devices:
                 self.devices.append(n)
         self.devices.sort(cmp=lambda x, y: cmp(x.lower(), y.lower()))
         self.devices.insert(1, plugboard_save_to_disk_value)
-        self.devices.insert(2, plugboard_any_device_value)
+        self.devices.insert(1, plugboard_content_server_value)
+        self.device_to_formats_map[plugboard_content_server_value] = \
+                        plugboard_content_server_formats
+        self.devices.insert(1, plugboard_any_device_value)
         self.new_device.addItems(self.devices)
 
         self.formats = ['']
         for w in metadata_writers():
-            for f in w.file_types:
+            if not is_disabled(w):
-                self.formats.append(f)
+                for f in w.file_types:
+                    if not f in self.formats:
+                        self.formats.append(f)
         self.formats.append('device_db')
         self.formats.sort()
         self.formats.insert(1, plugboard_any_format_value)
@@ -230,6 +240,15 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
                      show=True)
             self.new_device.setCurrentIndex(0)
             return
+        if self.current_device in self.device_to_formats_map:
+            allowable_formats = self.device_to_formats_map[self.current_device]
+            if self.current_format not in allowable_formats:
+                error_dialog(self, '',
+                     _('The {0} device does not support the {1} format.').
+                                format(self.current_device, self.current_format),
+                     show=True)
+                self.new_device.setCurrentIndex(0)
+                return
         self.set_fields()
 
     def new_format_changed(self, txt):

src/calibre/gui2/preferences/plugins.py

@@ -13,9 +13,9 @@ from PyQt4.Qt import Qt, QModelIndex, QAbstractItemModel, QVariant, QIcon, \
 
 from calibre.gui2.preferences import ConfigWidgetBase, test_widget
 from calibre.gui2.preferences.plugins_ui import Ui_Form
-from calibre.customize.ui import initialized_plugins, is_disabled, enable_plugin, \
+from calibre.customize.ui import (initialized_plugins, is_disabled, enable_plugin,
-                                 disable_plugin, plugin_customization, add_plugin, \
+                                 disable_plugin, plugin_customization, add_plugin,
-                                 remove_plugin
+                                 remove_plugin, NameConflict)
 from calibre.gui2 import NONE, error_dialog, info_dialog, choose_files, \
         question_dialog, gprefs
 from calibre.utils.search_query_parser import SearchQueryParser
@@ -279,7 +279,11 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
                         ' Are you sure you want to proceed?'),
                     show_copy_button=False):
                 return
-            plugin = add_plugin(path)
+            try:
+                plugin = add_plugin(path)
+            except NameConflict as e:
+                return error_dialog(self, _('Already exists'),
+                        unicode(e), show=True)
             self._plugin_model.populate()
             self._plugin_model.reset()
             self.changed_signal.emit()

src/calibre/gui2/search_restriction_mixin.py

@@ -17,6 +17,10 @@ class SearchRestrictionMixin(object):
         self.search_restriction.setMinimumContentsLength(10)
         self.search_restriction.setStatusTip(self.search_restriction.toolTip())
         self.search_count.setText(_("(all books)"))
+        self.search_restriction_tooltip = \
+            _('Books display will be restricted to those matching a '
+              'selected saved search')
+        self.search_restriction.setToolTip(self.search_restriction_tooltip)
 
     def apply_named_search_restriction(self, name):
         if not name:
@@ -30,29 +34,38 @@ class SearchRestrictionMixin(object):
             self.apply_search_restriction(r)
 
     def apply_text_search_restriction(self, search):
+        search = unicode(search)
         if not search:
-            self.search_restriction.setItemText(1, _('*Current search'))
             self.search_restriction.setCurrentIndex(0)
         else:
-            self.search_restriction.setCurrentIndex(1)
+            s = '*' + search
-            self.search_restriction.setItemText(1, search)
+            if self.search_restriction.count() > 1:
+                txt = unicode(self.search_restriction.itemText(2))
+                if txt.startswith('*'):
+                    self.search_restriction.setItemText(2, s)
+                else:
+                    self.search_restriction.insertItem(2, s)
+            else:
+                self.search_restriction.insertItem(2, s)
+            self.search_restriction.setCurrentIndex(2)
+            self.search_restriction.setToolTip('<p>' +
+                    self.search_restriction_tooltip +
+                     _(' or the search ') + "'" + search + "'</p>")
             self._apply_search_restriction(search)
 
     def apply_search_restriction(self, i):
-        self.search_restriction.setItemText(1, _('*Current search'))
         if i == 1:
-            restriction = unicode(self.search.currentText())
+            self.apply_text_search_restriction(unicode(self.search.currentText()))
-            if not restriction:
+        elif i == 2 and unicode(self.search_restriction.currentText()).startswith('*'):
-                self.search_restriction.setCurrentIndex(0)
+            self.apply_text_search_restriction(
-            else:
+                                unicode(self.search_restriction.currentText())[1:])
-                self.search_restriction.setItemText(1, restriction)
         else:
             r = unicode(self.search_restriction.currentText())
             if r is not None and r != '':
                 restriction = 'search:"%s"'%(r)
             else:
                 restriction = ''
-        self._apply_search_restriction(restriction)
+            self._apply_search_restriction(restriction)
 
     def _apply_search_restriction(self, restriction):
         self.saved_search.clear()

src/calibre/gui2/store/amazon_plugin.py

@@ -154,6 +154,13 @@ class AmazonKindleStore(StorePlugin):
                     cover_img = data.xpath('//div[@class="productImage"]/a[@href="%s"]/img/@src' % asin_href)
                     if cover_img:
                         cover_url = cover_img[0]
+                        parts = cover_url.split('/')
+                        bn = parts[-1]
+                        f, _, ext = bn.rpartition('.')
+                        if '_' in f:
+                            bn = f.partition('_')[0]+'_SL160_.'+ext
+                            parts[-1] = bn
+                            cover_url = '/'.join(parts)
 
                 title = ''.join(data.xpath('div[@class="productTitle"]/a/text()'))
                 author = ''.join(data.xpath('div[@class="productTitle"]/span[@class="ptBrand"]/text()'))

src/calibre/gui2/store/search.ui

@@ -11,7 +11,11 @@
    </rect>
   </property>
   <property name="windowTitle">
-   <string>calibre Store Search</string>
+   <string>Get Books</string>
+  </property>
+  <property name="windowIcon">
+   <iconset resource="../../../../resources/images.qrc">
+    <normaloff>:/images/store.png</normaloff>:/images/store.png</iconset>
   </property>
   <property name="sizeGripEnabled">
    <bool>true</bool>
@@ -58,8 +62,8 @@
            <rect>
             <x>0</x>
             <y>0</y>
-            <width>215</width>
+            <width>170</width>
-            <height>116</height>
+            <height>138</height>
            </rect>
           </property>
          </widget>
@@ -174,7 +178,9 @@
    </item>
   </layout>
  </widget>
- <resources/>
+ <resources>
+  <include location="../../../../resources/images.qrc"/>
+ </resources>
  <connections>
   <connection>
    <sender>close</sender>

src/calibre/gui2/store/web_control.py

@@ -70,16 +70,17 @@ class NPWebView(QWebView):
         if ext not in BOOK_EXTENSIONS:
             if ext == 'acsm':
                 from calibre.gui2.dialogs.confirm_delete import confirm
-                confirm(_('<p>You have selected to download an ebook that uses '
+                if not confirm('<p>' + _('This ebook is a DRMed EPUB file.  '
-                          'the ACSM format. ACSM files are not ebook files but '
+                          'You will be prompted to save this file to your '
-                          'pointers '
+                          'computer. Once it is saved, open it with '
                           '<a href="http://www.adobe.com/products/digitaleditions/">'
-                          'Adobe Digital Editions</a> (ADE) uses so it can download '
+                          'Adobe Digital Editions</a> (ADE).<p>ADE, in turn '
-                          'the ebook and apply DRM to it. You will be prompted to save this '
+                          'will download the actual ebook, which will be a '
-                          'file to your computer. Then open it using ADE. Once ADE has '
+                          '.epub file. You can add this book to calibre '
-                          'downloaded the actual ebook you can add the book to calibre '
+                          'using "Add Books" and selecting the file from '
-                          'using Add and selecting the file from the ADE library folder.'),
+                          'the ADE library folder.'),
-                          'acsm_download', self)
+                          'acsm_download', self):
+                    return
             home = os.path.expanduser('~')
             name = QFileDialog.getSaveFileName(self,
                 _('File is not a supported ebook type. Save to disk?'),

src/calibre/gui2/widgets.py

@@ -19,7 +19,6 @@ from calibre.gui2 import NONE, error_dialog, pixmap_to_data, gprefs
 from calibre.gui2.filename_pattern_ui import Ui_Form
 from calibre import fit_image
 from calibre.ebooks import BOOK_EXTENSIONS
-from calibre.ebooks.metadata.meta import metadata_from_filename
 from calibre.utils.config import prefs, XMLConfig, tweaks
 from calibre.gui2.progress_indicator import ProgressIndicator as _ProgressIndicator
 from calibre.gui2.dnd import dnd_has_image, dnd_get_image, dnd_get_files, \
@@ -95,6 +94,7 @@ class FilenamePattern(QWidget, Ui_Form):
         self.re.setCurrentIndex(0)
 
     def do_test(self):
+        from calibre.ebooks.metadata.meta import metadata_from_filename
         try:
             pat = self.pattern()
         except Exception as err:

src/calibre/library/caches.py

@@ -707,7 +707,10 @@ class ResultCache(SearchQueryParser): # {{{
             for loc in location: # location is now an array of field indices
                 if loc == db_col['authors']:
                     ### DB stores authors with commas changed to bars, so change query
-                    q = query.replace(',', '|');
+                    if matchkind == REGEXP_MATCH:
+                        q = query.replace(',', r'\|');
+                    else:
+                        q = query.replace(',', '|');
                 else:
                     q = query
 

src/calibre/library/catalog.py

@@ -15,7 +15,6 @@ from calibre.customize import CatalogPlugin
 from calibre.customize.conversion import OptionRecommendation, DummyReporter
 from calibre.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, Tag, NavigableString
 from calibre.ebooks.chardet import substitute_entites
-from calibre.ebooks.oeb.base import XHTML_NS
 from calibre.ptempfile import PersistentTemporaryDirectory
 from calibre.utils.config import config_dir
 from calibre.utils.date import format_date, isoformat, is_date_undefined, now as nowf
@@ -4322,6 +4321,8 @@ Author '{0}':
             '''
             Generate description header from template
             '''
+            from calibre.ebooks.oeb.base import XHTML_NS
+
             def generate_html():
                 args = dict(
                             author=author,

src/calibre/library/cli.py

@@ -10,8 +10,7 @@ Command line interface to the calibre database.
 import sys, os, cStringIO, re
 from textwrap import TextWrapper
 
-from calibre import terminal_controller, preferred_encoding, prints, \
+from calibre import preferred_encoding, prints, isbytestring
-    isbytestring
 from calibre.utils.config import OptionParser, prefs, tweaks
 from calibre.ebooks.metadata.meta import get_metadata
 from calibre.library.database2 import LibraryDatabase2
@@ -53,6 +52,8 @@ def get_db(dbpath, options):
 
 def do_list(db, fields, afields, sort_by, ascending, search_text, line_width, separator,
             prefix, subtitle='Books in the calibre database'):
+    from calibre.constants import terminal_controller as tc
+    terminal_controller = tc()
     if sort_by:
         db.sort(sort_by, ascending)
     if search_text:
@@ -1087,6 +1088,9 @@ def command_list_categories(args, dbpath):
     fields = ['category', 'tag_name', 'count', 'rating']
 
     def do_list():
+        from calibre.constants import terminal_controller as tc
+        terminal_controller = tc()
+
         separator = ' '
         widths = list(map(lambda x : 0, fields))
         for i in data:

src/calibre/library/database2.py

@@ -15,7 +15,8 @@ from math import ceil
 from PyQt4.QtGui import QImage
 
 from calibre import prints
-from calibre.ebooks.metadata import title_sort, author_to_author_sort
+from calibre.ebooks.metadata import (title_sort, author_to_author_sort,
+        string_to_authors, authors_to_string)
 from calibre.ebooks.metadata.opf2 import metadata_to_opf
 from calibre.library.database import LibraryDatabase
 from calibre.library.field_metadata import FieldMetadata, TagsIcons
@@ -24,9 +25,7 @@ from calibre.library.caches import ResultCache
 from calibre.library.custom_columns import CustomColumns
 from calibre.library.sqlite import connect, IntegrityError
 from calibre.library.prefs import DBPrefs
-from calibre.ebooks.metadata import string_to_authors, authors_to_string
 from calibre.ebooks.metadata.book.base import Metadata
-from calibre.ebooks.metadata.meta import get_metadata, metadata_from_formats
 from calibre.constants import preferred_encoding, iswindows, isosx, filesystem_encoding
 from calibre.ptempfile import PersistentTemporaryFile
 from calibre.customize.ui import run_plugins_on_import
@@ -853,6 +852,7 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
         mi.pubdate     = row[fm['pubdate']]
         mi.uuid        = row[fm['uuid']]
         mi.title_sort  = row[fm['sort']]
+        mi.book_size   = row[fm['size']]
         mi.last_modified = row[fm['last_modified']]
         formats = row[fm['formats']]
         if not formats:
@@ -1378,13 +1378,15 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
             for (cat, dex, mult, is_comp) in md:
                 if not book[dex]:
                     continue
+                tid_cat = tids[cat]
+                tcats_cat = tcategories[cat]
                 if not mult:
                     val = book[dex]
                     if is_comp:
-                        item = tcategories[cat].get(val, None)
+                        item = tcats_cat.get(val, None)
                         if not item:
                             item = tag_class(val, val)
-                            tcategories[cat][val] = item
+                            tcats_cat[val] = item
                         item.c += 1
                         item.id = val
                         if rating > 0:
@@ -1392,11 +1394,11 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
                             item.rc += 1
                         continue
                     try:
-                        (item_id, sort_val) = tids[cat][val] # let exceptions fly
+                        (item_id, sort_val) = tid_cat[val] # let exceptions fly
-                        item = tcategories[cat].get(val, None)
+                        item = tcats_cat.get(val, None)
                         if not item:
                             item = tag_class(val, sort_val)
-                            tcategories[cat][val] = item
+                            tcats_cat[val] = item
                         item.c += 1
                         item.id_set.add(book[0])
                         item.id = item_id
@@ -1410,21 +1412,15 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
                     if is_comp:
                         vals = [v.strip() for v in vals if v.strip()]
                         for val in vals:
-                            if val not in tids:
+                            if val not in tid_cat:
-                                tids[cat][val] = (val, val)
+                                tid_cat[val] = (val, val)
-                            item = tcategories[cat].get(val, None)
-                            if not item:
-                                item = tag_class(val, val)
-                                tcategories[cat][val] = item
-                            item.c += 1
-                            item.id = val
                     for val in vals:
                         try:
-                            (item_id, sort_val) = tids[cat][val] # let exceptions fly
+                            (item_id, sort_val) = tid_cat[val] # let exceptions fly
-                            item = tcategories[cat].get(val, None)
+                            item = tcats_cat.get(val, None)
                             if not item:
                                 item = tag_class(val, sort_val)
-                                tcategories[cat][val] = item
+                                tcats_cat[val] = item
                             item.c += 1
                             item.id_set.add(book[0])
                             item.id = item_id
@@ -2732,6 +2728,8 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
         self.set_identifier(id_, 'isbn', isbn, notify=notify, commit=commit)
 
     def add_catalog(self, path, title):
+        from calibre.ebooks.metadata.meta import get_metadata
+
         format = os.path.splitext(path)[1][1:].lower()
         with lopen(path, 'rb') as stream:
             matches = self.data.get_matches('title', '='+title)
@@ -2767,6 +2765,8 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
 
 
     def add_news(self, path, arg):
+        from calibre.ebooks.metadata.meta import get_metadata
+
         format = os.path.splitext(path)[1][1:].lower()
         stream = path if hasattr(path, 'read') else lopen(path, 'rb')
         stream.seek(0)
@@ -3160,6 +3160,8 @@ books_series_link      feeds
                 yield formats
 
     def import_book_directory_multiple(self, dirpath, callback=None):
+        from calibre.ebooks.metadata.meta import metadata_from_formats
+
         duplicates = []
         for formats in self.find_books_in_directory(dirpath, False):
             mi = metadata_from_formats(formats)
@@ -3175,6 +3177,7 @@ books_series_link      feeds
         return duplicates
 
     def import_book_directory(self, dirpath, callback=None):
+        from calibre.ebooks.metadata.meta import metadata_from_formats
         dirpath = os.path.abspath(dirpath)
         formats = self.find_books_in_directory(dirpath, True)
         formats = list(formats)[0]

src/calibre/library/field_metadata.py

@@ -35,7 +35,7 @@ category_icon_map = {
                     'custom:'    : 'column.png',
                     'user:'      : 'tb_folder.png',
                     'search'     : 'search.png',
-                    'identifiers': 'id_card.png'
+                    'identifiers': 'identifiers.png'
             }
 
 

src/calibre/library/save_to_disk.py

@@ -14,7 +14,6 @@ from calibre.utils.formatter import TemplateFormatter
 from calibre.utils.filenames import shorten_components_to, supports_long_names, \
                                     ascii_filename
 from calibre.ebooks.metadata.opf2 import metadata_to_opf
-from calibre.ebooks.metadata.meta import set_metadata
 from calibre.constants import preferred_encoding
 from calibre.ebooks.metadata import fmt_sidx
 from calibre.ebooks.metadata import title_sort
@@ -51,6 +50,23 @@ for x in FORMAT_ARG_DESCS:
     FORMAT_ARGS[x] = ''
 
 
+def find_plugboard(device_name, format, plugboards):
+    cpb = None
+    if format in plugboards:
+        cpb = plugboards[format]
+    elif plugboard_any_format_value in plugboards:
+        cpb = plugboards[plugboard_any_format_value]
+    if cpb is not None:
+        if device_name in cpb:
+            cpb = cpb[device_name]
+        elif plugboard_any_device_value in cpb:
+            cpb = cpb[plugboard_any_device_value]
+        else:
+            cpb = None
+    if DEBUG:
+        prints('Device using plugboard', format, device_name, cpb)
+    return cpb
+
 def config(defaults=None):
     if defaults is None:
         c = Config('save_to_disk', _('Options to control saving to disk'))
@@ -181,7 +197,6 @@ def get_components(template, mi, id, timefmt='%b %Y', length=250,
     for key in custom_metadata:
         if key in format_args:
             cm = custom_metadata[key]
-            ## TODO: NEWMETA: should ratings be divided by 2? The standard rating isn't...
             if cm['datatype'] == 'series':
                 format_args[key] = title_sort(format_args[key], order=tsorder)
                 if key+'_index' in format_args:
@@ -235,6 +250,7 @@ def save_book_to_disk(id_, db, root, opts, length):
 
 def do_save_book_to_disk(id_, mi, cover, plugboards,
         format_map, root, opts, length):
+    from calibre.ebooks.metadata.meta import set_metadata
     available_formats = [x.lower().strip() for x in format_map.keys()]
     if opts.formats == 'all':
         asked_formats = available_formats
@@ -279,20 +295,7 @@ def do_save_book_to_disk(id_, mi, cover, plugboards,
     written = False
     for fmt in formats:
         global plugboard_save_to_disk_value, plugboard_any_format_value
-        dev_name = plugboard_save_to_disk_value
+        cpb = find_plugboard(plugboard_save_to_disk_value, fmt, plugboards)
-        cpb = None
-        if fmt in plugboards:
-            cpb = plugboards[fmt]
-            if dev_name in cpb:
-                cpb = cpb[dev_name]
-            else:
-                cpb = None
-        if cpb is None and plugboard_any_format_value in plugboards:
-            cpb = plugboards[plugboard_any_format_value]
-            if dev_name in cpb:
-                cpb = cpb[dev_name]
-            else:
-                cpb = None
         # Leave this here for a while, in case problems arise.
         if cpb is not None:
             prints('Save-to-disk using plugboard:', fmt, cpb)

src/calibre/library/server/content.py

@@ -12,9 +12,14 @@ import cherrypy
 from calibre import fit_image, guess_type
 from calibre.utils.date import fromtimestamp
 from calibre.library.caches import SortKeyGenerator
+from calibre.library.save_to_disk import find_plugboard
+
 from calibre.utils.magick.draw import save_cover_data_to, Image, \
         thumbnail as generate_thumbnail
 
+plugboard_content_server_value = 'content_server'
+plugboard_content_server_formats = ['epub']
+
 class CSSortKeyGenerator(SortKeyGenerator):
 
     def __init__(self, fields, fm, db_prefs):
@@ -183,16 +188,30 @@ class ContentServer(object):
         if fmt is None:
             raise cherrypy.HTTPError(404, 'book: %d does not have format: %s'%(id, format))
         if format == 'EPUB':
+            # Get the original metadata
+            mi = self.db.get_metadata(id, index_is_id=True)
+
+            # Get any EPUB plugboards for the content server
+            plugboards = self.db.prefs.get('plugboards', {})
+            cpb = find_plugboard(plugboard_content_server_value,
+                                 'epub', plugboards)
+            if cpb:
+                # Transform the metadata via the plugboard
+                newmi = mi.deepcopy_metadata()
+                newmi.template_to_attribute(mi, cpb)
+            else:
+                newmi = mi
+
+            # Write the updated file
             from tempfile import TemporaryFile
             from calibre.ebooks.metadata.meta import set_metadata
             raw = fmt.read()
             fmt = TemporaryFile()
             fmt.write(raw)
             fmt.seek(0)
-            set_metadata(fmt, self.db.get_metadata(id, index_is_id=True,
+            set_metadata(fmt, newmi, 'epub')
-                get_cover=True),
-                    'epub')
             fmt.seek(0)
+
         mt = guess_type('dummy.'+format.lower())[0]
         if mt is None:
             mt = 'application/octet-stream'

src/calibre/manual/faq.rst

@@ -549,17 +549,6 @@ How do I run calibre from my USB stick?
 
 A portable version of calibre is available at: `portableapps.com <http://portableapps.com/node/20518>`_. However, this is usually out of date. You can also setup your own portable calibre install by following :ref:`these instructions <portablecalibre>`.
 
-Why are there so many calibre-parallel processes on my system?
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-|app| maintains two separate worker process pools. One is used for adding books/saving to disk and the other for conversions. You can control the number of worker processes via :guilabel:`Preferences->Advanced->Miscellaneous`. So if you set it to 6 that means a maximum of 3 conversions will run simultaneously. And that is why you will see the number of worker processes changes by two when you use the up and down arrows. On windows, you can set the priority that these processes run with. This can be useful on older, single CPU machines, if you find them slowing down to a crawl when conversions are running.
-
-In addition to this some conversion plugins run tasks in their own pool of processes, so for example if you bulk convert comics, each comic conversion will use three separate processes to render the images. The job manager knows this so it will run only a single comic conversion simultaneously.
-
-And since I'm sure someone will ask: The reason adding/saving books are in separate processes is because of PDF. PDF processing libraries can crash on reading PDFs and I dont want the crash to take down all of calibre. Also when adding EPUB books, in order to extract the cover you have to sometimes render the HTML of the first page, which means that it either has to run in the GUI thread of the main process or in a separate process.
-
-Finally, the reason calibre keep workers alive and idle instead of launching on demand is to workaround the slow startup time of python processes.
-
 How do I run parts of |app| like news download and the content server on my own linux server?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

src/calibre/manual/template_lang.rst

@@ -230,6 +230,7 @@ The following functions are available in addition to those described in single-f
 
     * ``add(x, y)`` -- returns x + y. Throws an exception if either x or y are not numbers.
     * ``assign(id, val)`` -- assigns val to id, then returns val. id must be an identifier, not an expression
+    * ``booksize()`` -- returns the value of the |app| 'size' field. Returns '' if there are no formats.
     * ``cmp(x, y, lt, eq, gt)`` -- compares x and y after converting both to numbers. Returns ``lt`` if x < y. Returns ``eq`` if x == y. Otherwise returns ``gt``.
     * ``divide(x, y)`` -- returns x / y. Throws an exception if either x or y are not numbers.
     * ``field(name)`` -- returns the metadata field named by ``name``.