0.7.53

Changelog.yaml

@@ -19,6 +19,75 @@
 #  new recipes:
 #    - title: 
 
+- version: 0.7.53
+  date: 2011-04-01
+
+  new features:
+    - title: "Email delivery: You can now specify a subject that calibre will use when sending emails per email account, configured in Preferences->Sending by email. The subject is a template of the same kind used in Save to Disk, etc. So youcan specift the title/authors/series/whatever in the template."
+      tickets: [743535]
+
+    - title: "Apple driver: When an iDevice is detected, inform the user about the Connect to iTunes method instead of trying to connect directly to the device, as the latter can be buggy. See http://www.mobileread.com/forums/showthread.php?t=127883 for details"
+
+    - title: "SONY driver: Search for books on the device in all directories not just database/media/books. This can be turned off by customizing the SONY plugin in Preferences->Plugins"
+
+    - title: "EPUB Output: Remove any margins specified via an Adobe page template in the input document. This means that the margins psecified in calibre are more likely to be the actual margins used."
+
+    - title: "When reading metadata from filenames, allow publisher and published date to be read from the filename"
+      tickets: [744020]
+
+    - title: "Remove the option to show a second tool bar from Preferences->Look & Feel. Instead go to Preferences->Toolbars and add items to the second toolbar to control exactly what is visible there."
+      tickets: [742686]
+
+    - title: "Add a tweak that can be used to have the calibre content server listen for IPv6 connections."
+      tickets: [743486]
+
+    - title: "When clicking Next or Previous in the edit metadata dialog, then active book in the main book list is also changed"
+      tickets: [743533]
+
+    - title: "Remember the previously used setting for Match all/Match any under the Tag Browser when calibre restarts"
+      tickets: [743645]
+
+    - title: "FB2 Output: Option to set the FB2 genre explicitly."
+      tickets: [743178]
+  
+  bug fixes:
+    - title: "Fix text color in the search bar set to black instead of the system font color"
+      tickets: [746846]
+
+    - title: "Workaround for Word bug where Word uses gb2312 as the encoding when exporting CHinese docs to HTML istead of gbk"
+      tickets: [745428]
+
+    - title: "Make sorting on the device view faster and more robust."
+      tickets: [742626]
+
+    - title: "E-book viewer: Fix viewer losing place in very long single file documents when window resized."
+      tickets: [745001]
+
+    - title: "MOBI Output: Workaround for Amazon's MOBI renderer not rendering top margins on ul and ol tags."
+      tickets: [744365]
+
+    - title: "EPUB Input: Workaround for invalid EPUBs produced by someone named 'ibooks, Inc.'."
+      tickets: [744122]
+
+    - title: "RTF Input: Handle RTF files with too many levels of list nesting."
+      tickets: [743243]
+
+  improved recipes:
+    - Irish Times
+    - LifeHacker
+    - Estadao
+    - Folha de Sao Paulo
+
+  new recipes:
+    - title: Financieele Dagblad
+      author: marvin_2
+
+    - title: "Prost Amerika, WV Hooligan and SB Nation"
+      author: rylsfan
+
+    - title: "Cracked.com"
+      author: Nudgenudge
+
 - version: 0.7.52
   date: 2011-03-25
 

recipes/estadao.recipe

@@ -1,4 +1,3 @@
-#!/usr/bin/env  python
 from calibre.web.feeds.news import BasicNewsRecipe
 from datetime import datetime, timedelta
 from calibre.ebooks.BeautifulSoup import Tag,BeautifulSoup
@@ -6,18 +5,17 @@ from calibre.utils.magick import Image, PixelWand
 from urllib2 import Request, urlopen, URLError
 
 class Estadao(BasicNewsRecipe):
-    THUMBALIZR_API        = "0123456789abcdef01234567890" # ---->Get your at http://www.thumbalizr.com/
+    THUMBALIZR_API        = '' # ---->Get your at http://www.thumbalizr.com/ and put here
     LANGUAGE              = 'pt_br'
-    language              = 'pt'
+    language = 'pt'
     LANGHTM               = 'pt-br'
     ENCODING              = 'utf'
     ENCHTM                = 'utf-8'
     directionhtm          = 'ltr'
-    requires_version      = (0,8,47)
+    requires_version      = (0,7,47)
     news                  = True
-    publication_type      = 'newsportal'
 
-    title                 = u'Estadao'
+    title                 = u'Estad\xe3o'
     __author__            = 'Euler Alves'
     description           = u'Brazilian news from Estad\xe3o'
     publisher             = u'Estad\xe3o'
@@ -33,14 +31,6 @@ class Estadao(BasicNewsRecipe):
     remove_empty_feeds    = True
     timefmt               = ' [%d %b %Y (%a)]'
 
-    html2lrf_options      = [
-                            '--comment', description
-                            ,'--category', category
-                            ,'--publisher', publisher
-    ]
-
-    html2epub_options     = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
-
     hoje                  = datetime.now()-timedelta(days=2)
     pubdate               = hoje.strftime('%a, %d %b')
     if hoje.hour<10:
@@ -69,6 +59,7 @@ class Estadao(BasicNewsRecipe):
                     ,dict(name='script')
     ]
 
+
     feeds = [
     (u'\xDAltimas Not\xEDcias', u'http://www.estadao.com.br/rss/ultimas.xml')
     ,(u'Manchetes', u'http://www.estadao.com.br/rss/manchetes.xml')
@@ -109,6 +100,8 @@ class Estadao(BasicNewsRecipe):
             img.open(iurl)
             width, height = img.size
             print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
+            if img < 0:
+                raise RuntimeError('Out of memory')
             pw = PixelWand()
             if( width > height and width > 590) :
                 print 'Rotate image'
@@ -117,18 +110,20 @@ class Estadao(BasicNewsRecipe):
         return soup
 
     def get_cover_url(self):
-        cover_url      = self.CAPA
+        if self.THUMBALIZR_API:
-        pedido         = Request(self.CAPA)
+            cover_url      = self.CAPA
-        pedido.add_header('User-agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; '+self.LANGHTM+'; userid='+self.THUMBALIZR_API+') Calibre/0.8.47 (like Gecko)')
+            pedido         = Request(self.CAPA)
-        pedido.add_header('Accept-Charset',self.ENCHTM)
+            pedido.add_header('User-agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; '+self.LANGHTM+'; userid='+self.THUMBALIZR_API+') Calibre/0.8.47 (like Gecko)')
-        pedido.add_header('Referer',self.SCREENSHOT)
+            pedido.add_header('Accept-Charset',self.ENCHTM)
-        try:
+            pedido.add_header('Referer',self.SCREENSHOT)
-            resposta   = urlopen(pedido)
+            try:
-            soup       = BeautifulSoup(resposta)
+                resposta   = urlopen(pedido)
-            cover_item = soup.find('body')
+                soup       = BeautifulSoup(resposta)
-            if cover_item:
+                cover_item = soup.find('body')
+                if cover_item:
+                    cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
+                return cover_url
+            except URLError:
                 cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
-            return cover_url
+                return cover_url
-        except URLError:
+
-            cover_url='http://api.thumbalizr.com/?api_key='+self.THUMBALIZR_API+'&url='+self.SCREENSHOT+'&width=600&quality=90'
-            return cover_url

recipes/financieele_dagblad.recipe

@@ -0,0 +1,29 @@
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class fd(BasicNewsRecipe):
+    title          = u'Het Financieele Dagblad'
+    __author__ = 'marvin_2'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    cover_url = 'http://www.fd.nl/static/gfx/logo-fd-164x78.gif'
+    language = 'nl'
+
+    keep_only_tags = (dict(name = 'div', attrs = {'class': ['headlinearticle']}))
+    remove_tags    = [dict(name='span' , attrs={'class':['opties']})]
+
+    feeds          = [
+                        (u'Overzicht',u'http://www.fd.nl/nieuws/overzicht/?view=RSS&profiel=OPENBAAR')
+
+
+                     ]
+    extra_css = '''
+        h1 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:x-large;}
+        p{font-family:Arial,Helvetica,sans-serif;}
+        strong{font-weight:bold; margin-right:5pt;margin-top:20pt;}
+        .datum_ie {font-style:italic;font-size:small;}
+        img {align:left;}
+        '''
+
+

recipes/folhadesaopaulo.recipe

@@ -5,16 +5,15 @@ from calibre.utils.magick import Image, PixelWand
 from urllib2 import Request, urlopen, URLError
 
 class FolhaOnline(BasicNewsRecipe):
-    THUMBALIZR_API        = "0123456789abcdef01234567890" # ---->Get your at http://www.thumbalizr.com/
+    THUMBALIZR_API        = '' # ---->Get your at http://www.thumbalizr.com/ and put here
     LANGUAGE              = 'pt_br'
     language = 'pt'
     LANGHTM               = 'pt-br'
     ENCODING              = 'cp1252'
     ENCHTM                = 'iso-8859-1'
     directionhtm          = 'ltr'
-    requires_version      = (0,8,47)
+    requires_version      = (0,7,47)
     news                  = True
-    publication_type      = 'newsportal'
 
     title                 = u'Folha de S\xE3o Paulo'
     __author__            = 'Euler Alves'
@@ -96,6 +95,7 @@ class FolhaOnline(BasicNewsRecipe):
     ,(u'Valdo Cruz', u'http://http://feeds.folha.uol.com.br/folha/pensata/valdocruz/rss091.xml')
     ]
 
+
     conversion_options = {
     'title'            : title
     ,'comments'        : description
@@ -124,6 +124,8 @@ class FolhaOnline(BasicNewsRecipe):
             img.open(iurl)
             width, height = img.size
             print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
+            if img < 0:
+                raise RuntimeError('Out of memory')
             pw = PixelWand()
             if( width > height and width > 590) :
                 print 'Rotate image'

recipes/irish_times.recipe

@@ -1,5 +1,5 @@
 __license__   = 'GPL v3'
-__copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan"
+__copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan, 2011 Modified by Phil Burns"
 '''
 irishtimes.com
 '''
@@ -9,17 +9,20 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 class IrishTimes(BasicNewsRecipe):
     title          = u'The Irish Times'
-    __author__     = "Derry FitzGerald, Ray Kinsella and David O'Callaghan"
+    encoding  = 'ISO-8859-15'
+    __author__     = "Derry FitzGerald, Ray Kinsella, David O'Callaghan and Phil Burns"
     language = 'en_IE'
     timefmt = ' (%A, %B %d, %Y)'
 
-    oldest_article = 3
+
+    oldest_article = 1.0
+    max_articles_per_feed  = 100
     no_stylesheets = True
-    simultaneous_downloads= 1
+    simultaneous_downloads= 5
 
     r = re.compile('.*(?P<url>http:\/\/(www.irishtimes.com)|(rss.feedsportal.com\/c)\/.*\.html?).*')
     remove_tags    = [dict(name='div', attrs={'class':'footer'})]
-    extra_css      = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt  }'
+    extra_css      = 'p, div { margin: 0pt; border: 0pt; text-indent: 0.5em } .headline {font-size: large;} \n .fact { padding-top: 10pt  }'
 
     feeds          = [
                       ('Frontpage', 'http://www.irishtimes.com/feeds/rss/newspaper/index.rss'),
@@ -30,15 +33,29 @@ class IrishTimes(BasicNewsRecipe):
                       ('Sport', 'http://www.irishtimes.com/feeds/rss/newspaper/sport.rss'),
                       ('Opinion', 'http://www.irishtimes.com/feeds/rss/newspaper/opinion.rss'),
                       ('Letters', 'http://www.irishtimes.com/feeds/rss/newspaper/letters.rss'),
+                      ('Magazine', 'http://www.irishtimes.com/feeds/rss/newspaper/magazine.rss'),
+                      ('Health', 'http://www.irishtimes.com/feeds/rss/newspaper/health.rss'),
+                      ('Education & Parenting', 'http://www.irishtimes.com/feeds/rss/newspaper/education.rss'),
+                      ('Motors', 'http://www.irishtimes.com/feeds/rss/newspaper/motors.rss'),
+                      ('An Teanga Bheo', 'http://www.irishtimes.com/feeds/rss/newspaper/anteangabheo.rss'),
+                      ('Commercial Property', 'http://www.irishtimes.com/feeds/rss/newspaper/commercialproperty.rss'),
+                      ('Science Today', 'http://www.irishtimes.com/feeds/rss/newspaper/sciencetoday.rss'),
+                      ('Property', 'http://www.irishtimes.com/feeds/rss/newspaper/property.rss'),
+                      ('The Tickets', 'http://www.irishtimes.com/feeds/rss/newspaper/theticket.rss'),
+                      ('Weekend', 'http://www.irishtimes.com/feeds/rss/newspaper/weekend.rss'),
+                      ('News features', 'http://www.irishtimes.com/feeds/rss/newspaper/newsfeatures.rss'),
+                      ('Obituaries', 'http://www.irishtimes.com/feeds/rss/newspaper/obituaries.rss'),
                     ]
 
+
     def print_version(self, url):
-         if url.count('rss.feedsportal.com'):
+        if url.count('rss.feedsportal.com'):
-            u = 'http://www.irishtimes.com' + \
+            u = url.replace('0Bhtml/story01.htm','_pf0Bhtml/story01.htm')
-                     (((url[70:].replace('0C','/')).replace('0A','0'))).replace('0Bhtml/story01.htm','_pf.html')
+        else:
-         else:
+            u = url.replace('.html','_pf.html')
-             u = url.replace('.html','_pf.html')
+        return u
-         return u
 
     def get_article_url(self, article):
         return article.link
+
+

recipes/lifehacker.recipe

@@ -1,37 +1,100 @@
-__license__   = 'GPL v3'
-__copyright__ = '2010, NA'
-'''
-lifehacker.com
-'''
-
 from calibre.web.feeds.news import BasicNewsRecipe
+from datetime import datetime
+from calibre.ebooks.BeautifulSoup import Tag
+from calibre.utils.magick import Image, PixelWand
 
-class Lifehacker(BasicNewsRecipe):
+class LifeHacker(BasicNewsRecipe):
-    title                 = 'Lifehacker'
+    THUMBALIZR_API        = '' # ---->Get your at http://www.thumbalizr.com/ and put here
-    __author__            = 'Kovid Goyal'
+    LANGUAGE              = 'en'
-    description           = "Computers make us more productive. Yeah, right. Lifehacker recommends the software downloads and web sites that actually save time. Don't live to geek; geek to live."
+    LANGHTM               = 'en'
-    publisher             = 'lifehacker.com'
+    language = 'en'
-    category              = 'news, IT, Internet, gadgets, tips and tricks, howto, diy'
+    ENCODING              = 'utf'
-    oldest_article        = 2
+    ENCHTM                = 'utf-8'
-    max_articles_per_feed = 100
+    requires_version      = (0,7,47)
+    news                  = True
+
+    title                 = u'LifeHacker'
+    __author__            = 'Euler Alves'
+    description           = u'Tips, tricks, and downloads for getting things done.'
+    publisher             = u'lifehacker.com'
+    author                = u'Adam Pash & Kevin Purdy & Adam Dachis & Whitson Gordon & Gina Trapani'
+    category              = 'news, rss'
+
+    oldest_article        = 4
+    max_articles_per_feed = 20
+    summary_length        = 1000
+
+    remove_javascript     = True
     no_stylesheets        = True
-    encoding              = 'utf-8'
     use_embedded_content  = True
-    language              = 'en'
+    remove_empty_feeds    = True
+    timefmt               = ' [%d %b %Y (%a)]'
+
+    hoje                  = datetime.now()
+    pubdate               = hoje.strftime('%a, %d %b')
+    cover_url             = 'http://api.thumbalizr.com/?api_key='+THUMBALIZR_API+'&url=http://lifehacker.com&width=600&quality=90'
+    cover_margins         = (0,0,'white')
     masthead_url          = 'http://cache.gawkerassets.com/assets/lifehacker.com/img/logo.png'
-    conversion_options = {
-                          'comment'   : description
-                        , 'tags'      : category
-                        , 'publisher' : publisher
-                        , 'language'  : language
-                        }
 
     remove_tags = [
-            {'class': 'feedflare'},
+                    {'class': 'feedflare'},
+                    dict(name='div',
+                        attrs={'class':[
+                            'ad_container'
+                            ,'ad_300x250'
+                            ,'ad_interstitial'
+                            ,'share-wrap'
+                            ,'ad_300x600'
+                            ,'ad_perma-footer-adsense'
+                            ,'ad_perma-panorama'
+                            ,'ad panorama'
+                            ,'ad_container'
+                        ]})
+                    ,dict(name='div',
+                        attrs={'id':[
+                            'agegate_container'
+                            ,'agegate_container_rejected'
+                            ,'sharemenu-wrap'
+                        ]})
     ]
 
     feeds = [(u'Articles', u'http://feeds.gawker.com/lifehacker/vip?format=xml')]
 
-    def preprocess_html(self, soup):
+    conversion_options = {
-        return self.adeify_images(soup)
+    'title'            : title
+    ,'comments'        : description
+    ,'publisher'       : publisher
+    ,'tags'            : category
+    ,'language'        : LANGUAGE
+    ,'linearize_tables': True
+    }
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        if not soup.find(attrs={'http-equiv':'Content-Language'}):
+            meta0 = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.LANGHTM)])
+            soup.head.insert(0,meta0)
+        if not soup.find(attrs={'http-equiv':'Content-Type'}):
+            meta1 = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset="+self.ENCHTM)])
+            soup.head.insert(0,meta1)
+        return soup
+
+    def postprocess_html(self, soup, first):
+        #process all the images. assumes that the new html has the correct path
+        for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
+            iurl = tag['src']
+            img = Image()
+            img.open(iurl)
+            width, height = img.size
+            print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
+            if img < 0:
+                raise RuntimeError('Out of memory')
+            pw = PixelWand()
+            if( width > height and width > 590) :
+                print 'Rotate image'
+                img.rotate(pw, -90)
+                img.save(iurl)
+        return soup
+
 

recipes/prostamerika.recipe

@@ -0,0 +1,68 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+__license__ = 'GPL 3'
+__copyright__ = 'zotzo'
+
+"""
+http://www.prostamerika.com/
+"""
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class ProstAmerika(BasicNewsRecipe):
+    title = 'Prost Amerika'
+    language = 'en'
+    __author__ = 'rylsfan'
+    #authors =
+    description = 'Seattle soccer with a European accent. News, features, and match reports.'
+    publisher =  'ProstAmerika' # 4464 fremont avenue n, # 209, Seattle, 98103, United States
+    category = 'Sports'
+
+    oldest_article = 7
+    max_articles_per_feed = 100
+
+    cover_url = 'http://img17.imageshack.us/img17/9498/prostamerika.jpg'
+    masthead_url = 'http://www.prostamerika.com/soundersfc/wp-content/uploads/2011/02/PASoccer_taglinewhole.jpg'
+
+    encoding = 'utf-8'
+
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_javascript = True
+
+    feeds =[
+               (u'Cascadia',   u'http://www.prostamerika.com/category/localfootball/feed/' ),
+               (u'MLS',        u'http://www.prostamerika.com/category/mls/feed/'),
+               (u'EPL',        u'http://www.prostamerika.com/category/epl/feed/'),
+               (u'World',      u'http://www.prostamerika.com/category/international-soccer/feed/'),
+               (u'Fan Culture',u'http://www.prostamerika.com/category/fan-culture/feed/')
+
+           ]
+
+    keep_only_tags = [dict(name='div', attrs={'id':'maincontent'})]
+    remove_tags =  [
+                       {'class':'tweetmeme_button'},
+                       {'class':'wp-caption-text'}
+                   ]
+
+
+    remove_tags_after =[
+                           {'class':'tweetmeme_button'}
+                       ]
+
+    extra_css = '''
+               h1{font-family:Didot,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+               h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+               p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+               body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+                '''
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+
+
+
+
+

recipes/sb_nation.recipe

@@ -0,0 +1,56 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = 'Zotzo'
+'''
+http://www.stumptownfooty.com/
+http://www.eightysixforever.com
+http://www.sounderatheart.com
+http://www.dailysoccerfix.com/
+
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class SBNation(BasicNewsRecipe):
+    title    = u'SBNation'
+    __author__ = 'rylsfan'
+    description           = u"More than 290 individual communities, each offering high quality year-round coverage and conversation led by fans who are passionate."
+    oldest_article        = 3
+    language = 'en'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+
+    #cover_url = 'http://img132.imageshack.us/img132/4913/2hyggjegqqdywzn9.png'
+
+    keep_only_tags = [
+                        dict(name='h2', attrs={'class':'title'})
+                       ,dict(name='div', attrs={'class':'entry-body'})
+                     ]
+
+    remove_tags_after = dict(name='div', attrs={'class':'footline entry-actions'})
+    remove_tags = [
+                     dict(name='div', attrs={'class':'footline entry-actions'}),
+                     {'class': 'extend-divide'}
+                  ]
+    # SBNation has 300 special blogs to choose from. These are just a couple!
+    feeds       =  [
+                       (u'Daily Fix', u'http://www.dailysoccerfix.com/rss/'),
+                       (u"Stumptown Footy", u'http://www.stumptownfooty.com/rss/'),
+                       (u'Sounders', u'http://www.sounderatheart.com/rss/'),
+                       (u'Whitecaps', u'http://www.eightysixforever.com/rss/'),
+                   ]
+
+    extra_css  =   """
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    p{font-family:Helvetica,sans-serif; display: block; text-align: left; text-decoration: none; text-indent: 0%;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+                         """
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
+
+    def populate_article_metadata(self, article, soup, first):
+       h2 = soup.find('h2')
+       h2.replaceWith(h2.prettify() + '<p><em> By ' + article.author + '</em></p>')

recipes/wvhooligan.recipe

@@ -0,0 +1,61 @@
+#!/usr/bin/env  python
+__license__ = 'GPL 3'
+__copyright__ = 'zotzo'
+__docformat__ = 'restructuredtext en'
+'''
+http://wvhooligan.com/
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+#import re
+
+class wvHooligan(BasicNewsRecipe):
+    authors = u'Drew Epperley'
+    __author__ = 'rylsfan'
+    language = 'en'
+    version = 2
+
+    title = u'WV Hooligan'
+    publisher = u'Drew Epperley'
+    publication_type = 'Blog'
+    category = u'Soccer'
+    description = u'A look at Major League Soccer (MLS) through the eyes of a MLS writer and fan.'
+
+    cover_url = 'http://wvhooligan.com/wp-content/themes/urbanelements/images/logo3.png'
+
+    oldest_article = 15
+    max_articles_per_feed = 150
+    use_embedded_content = True
+    no_stylesheets = True
+    remove_javascript = True
+    encoding = 'utf8'
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_tags =  [
+                       {'class': 'feedflare'},
+                       {'class': 'tweetmeme_button'},
+                   ]
+
+    def preprocess_html(self, soup):
+       return self.adeify_images(soup)
+
+    feeds =[
+               (u'Stories', u'http://feeds2.feedburner.com/wvhooligan'),
+               (u'MLS', u'http://wvhooligan.com/category/mls/feed/'),
+               (u'MLS Power Rankings', u'http://wvhooligan.com/category/power-rankings/feed/'),
+               (u'MLS Expansion', u'http://wvhooligan.com/category/mls/expansion-talk/feed/'),
+               (u'US National Team', u'http://wvhooligan.com/category/us-national-team/feed/'),
+               (u'College', u'http://wvhooligan.com/category/college-soccer/feed/'),
+           ]
+
+    extra_css = '''
+               h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+               h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+               p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+               body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+               '''

setup/upload.py

@@ -5,7 +5,8 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
-import os, re, cStringIO, base64, httplib, subprocess, hashlib, shutil, time, glob
+import os, re, cStringIO, base64, httplib, subprocess, hashlib, shutil, time, \
+    glob, stat
 from subprocess import check_call
 from tempfile import NamedTemporaryFile, mkdtemp
 from zipfile import ZipFile
@@ -344,6 +345,8 @@ class UploadUserManual(Command): # {{{
     def build_plugin_example(self, path):
         from calibre import CurrentDir
         with NamedTemporaryFile(suffix='.zip') as f:
+            os.fchmod(f.fileno(),
+                stat.S_IRUSR|stat.S_IRGRP|stat.S_IROTH|stat.S_IWRITE)
             with CurrentDir(self.d(path)):
                 with ZipFile(f, 'w') as zf:
                     for x in os.listdir('.'):
@@ -352,8 +355,8 @@ class UploadUserManual(Command): # {{{
                             for y in os.listdir(x):
                                 zf.write(os.path.join(x, y))
             bname = self.b(path) + '_plugin.zip'
-            subprocess.check_call(['scp', f.name, 'divok:%s/%s'%(DOWNLOADS,
+            dest = '%s/%s'%(DOWNLOADS, bname)
-                bname)])
+            subprocess.check_call(['scp', f.name, 'divok:'+dest])
 
     def run(self, opts):
         path = self.j(self.SRC, 'calibre', 'manual', 'plugin_examples')

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.7.52'
+__version__   = '0.7.53'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 
 import re, importlib

src/calibre/devices/bambook/libbambookcore.py

@@ -10,7 +10,7 @@ Sanda library wrapper
 
 import ctypes, uuid, hashlib, os, sys
 from threading import Event, Lock
-from calibre.constants import iswindows, islinux, isosx
+from calibre.constants import iswindows
 from calibre import load_library
 
 try:
@@ -29,12 +29,9 @@ try:
 except:
     lib_handle = None
 
+text_encoding = 'utf-8'
 if iswindows:
     text_encoding = 'mbcs'
-elif islinux:
-    text_encoding = 'utf-8'
-elif isosx:
-    text_encoding = 'utf-8'
 
 def is_bambook_lib_ready():
     return lib_handle != None

src/calibre/ebooks/chardet/__init__.py

@@ -110,4 +110,11 @@ def xml_to_unicode(raw, verbose=False, strip_encoding_pats=False,
     if resolve_entities:
         raw = substitute_entites(raw)
 
+    if encoding and encoding.lower().replace('_', '-').strip() in (
+            'gb2312', 'chinese', 'csiso58gb231280', 'euc-cn', 'euccn',
+            'eucgb2312-cn', 'gb2312-1980', 'gb2312-80', 'iso-ir-58'):
+        # Microsoft Word exports to HTML with encoding incorrectly set to
+        # gb2312 instead of gbk. gbk is a superset of gb2312, anyway.
+        encoding = 'gbk'
+
     return raw, encoding

src/calibre/ebooks/lrf/input.py

@@ -6,7 +6,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
-import os, textwrap
+import os, textwrap, sys
 from copy import deepcopy
 
 from lxml import etree
@@ -413,7 +413,12 @@ class LRFInput(InputFormatPlugin):
                 ('calibre', 'image-block'): image_block,
                 }
         transform = etree.XSLT(styledoc, extensions=extensions)
-        result = transform(doc)
+        try:
+            result = transform(doc)
+        except RuntimeError:
+            sys.setrecursionlimit(5000)
+            result = transform(doc)
+
         with open('content.opf', 'wb') as f:
             f.write(result)
         styles.write()

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

@@ -198,8 +198,10 @@ class Metadata(object):
         return copy.deepcopy(ans)
 
     def _clean_identifier(self, typ, val):
-        typ = icu_lower(typ).strip().replace(':', '').replace(',', '')
+        if typ:
-        val = val.strip().replace(',', '|').replace(':', '|')
+            typ = icu_lower(typ).strip().replace(':', '').replace(',', '')
+        if val:
+            val = val.strip().replace(',', '|').replace(':', '|')
         return typ, val
 
     def set_identifiers(self, identifiers):

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

@@ -483,7 +483,6 @@ class Amazon(Source):
             log.exception('Failed to download cover from:', cached_url)
     # }}}
 
-
 if __name__ == '__main__': # tests {{{
     # To run these test use: calibre-debug -e
     # src/calibre/ebooks/metadata/sources/amazon.py
@@ -504,7 +503,7 @@ if __name__ == '__main__': # tests {{{
             (  # This isbn not on amazon
                 {'identifiers':{'isbn': '8324616489'}, 'title':'Learning Python',
                     'authors':['Lutz']},
-                [title_test('Learning Python: Powerful Object-Oriented Programming',
+                [title_test('Learning Python, 3rd Edition',
                     exact=True), authors_test(['Mark Lutz'])
                  ]
 

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

@@ -15,6 +15,7 @@ from calibre.customize import Plugin
 from calibre.utils.logging import ThreadSafeLog, FileStream
 from calibre.utils.config import JSONConfig
 from calibre.utils.titlecase import titlecase
+from calibre.ebooks.metadata import check_isbn
 
 msprefs = JSONConfig('metadata_sources.json')
 
@@ -236,6 +237,7 @@ class Source(Plugin):
             mi.title = fixcase(mi.title)
         mi.authors = list(map(fixcase, mi.authors))
         mi.tags = list(map(fixcase, mi.tags))
+        mi.isbn = check_isbn(mi.isbn)
 
     # }}}
 

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

@@ -14,6 +14,7 @@ from io import BytesIO
 
 from calibre.customize.ui import metadata_plugins
 from calibre.ebooks.metadata.sources.base import create_log
+from calibre.ebooks.metadata.xisbn import xisbn
 
 # How long to wait for more results after first result is found
 WAIT_AFTER_FIRST_RESULT = 30 # seconds
@@ -42,6 +43,7 @@ def is_worker_alive(workers):
     return False
 
 def identify(log, abort, title=None, authors=None, identifiers=[], timeout=30):
+    start_time = time.time()
     plugins = list(metadata_plugins['identify'])
 
     kwargs = {
@@ -105,3 +107,55 @@ def identify(log, abort, title=None, authors=None, identifiers=[], timeout=30):
             log(plog)
             log('\n'+'*'*80)
 
+        for i, result in enumerate(results):
+            result.relevance_in_source = i
+            result.has_cached_cover_url = \
+                plugin.get_cached_cover_url(result.identifiers) is not None
+            result.identify_plugin = plugin
+
+    log('The identify phase took %.2f seconds'%(time.time() - start_time))
+    log('Merging results from different sources and finding earliest',
+            'publication dates')
+    start_time = time.time()
+    merged_results = merge_identify_results(results, log)
+    log('We have %d merged results, merging took: %.2f seconds' %
+            (len(merged_results), time.time() - start_time))
+
+class ISBNMerge(object):
+
+    def __init__(self):
+        self.pools = {}
+
+    def isbn_in_pool(self, isbn):
+        if isbn:
+            for p in self.pools:
+                if isbn in p:
+                    return p
+        return None
+
+    def pool_has_result_from_same_source(self, pool, result):
+        results = self.pools[pool][1]
+        for r in results:
+            if r.identify_plugin is result.identify_plugin:
+                return True
+        return False
+
+    def add_result(self, result, isbn):
+        pool = self.isbn_in_pool(isbn)
+        if pool is None:
+            isbns, min_year = xisbn.get_isbn_pool(isbn)
+            if not isbns:
+                isbns = frozenset([isbn])
+            self.pool[isbns] = pool = (min_year, [])
+
+        if not self.pool_has_result_from_same_source(pool, result):
+            pool[1].append(result)
+
+def merge_identify_results(result_map, log):
+    for plugin, results in result_map.iteritems():
+        for result in results:
+            isbn = result.isbn
+            if isbn:
+                isbns, min_year = xisbn.get_isbn_pool(isbn)
+
+

src/calibre/ebooks/metadata/xisbn.py

@@ -71,14 +71,28 @@ class xISBN(object):
                 ans.add(i)
         return ans
 
+    def get_isbn_pool(self, isbn):
+        data = self.get_data(isbn)
+        isbns = frozenset([x.get('isbn') for x in data if 'isbn' in x])
+        min_year = 100000
+        for x in data:
+            try:
+                year = int(x['year'])
+                if year < min_year:
+                    min_year = year
+            except:
+                continue
+        if min_year == 100000:
+            min_year = None
+        return isbns, min_year
 
 
 xisbn = xISBN()
 
 if __name__ == '__main__':
-    import sys
+    import sys, pprint
     isbn = sys.argv[-1]
-    print xisbn.get_data(isbn)
+    print pprint.pprint(xisbn.get_data(isbn))
     print
     print xisbn.get_associated_isbns(isbn)
 

src/calibre/ebooks/pdf/input.py

@@ -34,7 +34,7 @@ class PDFInput(InputFormatPlugin):
         from calibre.ebooks.pdf.reflow import PDFDocument
         if pdfreflow_err:
             raise RuntimeError('Failed to load pdfreflow: ' + pdfreflow_err)
-        pdfreflow.reflow(stream.read())
+        pdfreflow.reflow(stream.read(), 1, -1)
         xml = open('index.xml', 'rb').read()
         PDFDocument(xml, self.opts, self.log)
         return os.path.join(os.getcwd(), 'metadata.opf')

src/calibre/ebooks/pdf/main.cpp

@@ -24,13 +24,14 @@ extern "C" {
     pdfreflow_reflow(PyObject *self, PyObject *args) {
         char *pdfdata;
         Py_ssize_t size;
+        int first_page, last_page, num = 0;
 
-        if (!PyArg_ParseTuple(args, "s#", &pdfdata, &size))
+        if (!PyArg_ParseTuple(args, "s#ii", &pdfdata, &size, &first_page, &last_page))
             return NULL;
 
         try {
             Reflow reflow(pdfdata, static_cast<std::ifstream::pos_type>(size));
-            reflow.render();
+            num = reflow.render(first_page, last_page);
         } catch (std::exception &e) {
             PyErr_SetString(PyExc_RuntimeError, e.what()); return NULL;
         } catch (...) {
@@ -38,7 +39,7 @@ extern "C" {
                     "Unknown exception raised while rendering PDF"); return NULL;
         }
 
-        Py_RETURN_NONE;
+        return Py_BuildValue("i", num);
     }
 
     static PyObject *
@@ -166,8 +167,8 @@ extern "C" {
     static 
     PyMethodDef pdfreflow_methods[] = {
         {"reflow", pdfreflow_reflow, METH_VARARGS,
-        "reflow(pdf_data)\n\n"
+        "reflow(pdf_data, first_page, last_page)\n\n"
-                "Reflow the specified PDF."
+                "Reflow the specified PDF. Returns the number of pages in the PDF. If last_page is -1 renders to end of document."
         },
         {"get_metadata", pdfreflow_get_metadata, METH_VARARGS,
         "get_metadata(pdf_data, cover)\n\n"

src/calibre/ebooks/pdf/reflow.cpp

@@ -712,16 +712,18 @@ Reflow::Reflow(char *pdfdata, size_t sz) :
 
 }
 
-void
+int
-Reflow::render() {
+Reflow::render(int first_page, int last_page) {
 
     if (!this->doc->okToCopy()) 
         cout << "Warning, this document has the copy protection flag set, ignoring." << endl;
 
     globalParams->setTextEncoding(encoding);
 
-    int first_page = 1;
+    int doc_pages = doc->getNumPages();
-    int last_page = doc->getNumPages();
+    if (last_page < 1 || last_page > doc_pages) last_page = doc_pages;
+    if (first_page < 1) first_page = 1;
+    if (first_page > last_page) first_page = last_page;
 
     XMLOutputDev *xml_out = new XMLOutputDev(this->doc);
     doc->displayPages(xml_out, first_page, last_page,
@@ -733,9 +735,12 @@ Reflow::render() {
               false //Printing
     );
     
-    this->dump_outline();
+    if (last_page - first_page == doc_pages - 1)
+        this->dump_outline();
 
     delete xml_out;
+
+    return doc_pages;
 }
 
 void Reflow::dump_outline() {

src/calibre/ebooks/pdf/reflow.h

@@ -66,7 +66,7 @@ class Reflow {
         ~Reflow();
         
         /* Convert the PDF to XML. All files are output to the current directory */
-        void render();
+        int render(int first_page, int last_page);
 
         /* Get the PDF Info Dictionary */
         map<string, string> get_info();

src/calibre/gui2/actions/convert.py

@@ -51,7 +51,7 @@ class ConvertAction(InterfaceAction):
         self.queue_convert_jobs(jobs, changed, bad, rows, previous,
                 self.book_auto_converted, extra_job_args=[on_card])
 
-    def auto_convert_mail(self, to, fmts, delete_from_library, book_ids, format):
+    def auto_convert_mail(self, to, fmts, delete_from_library, book_ids, format, subject):
         previous = self.gui.library_view.currentIndex()
         rows = [x.row() for x in \
                 self.gui.library_view.selectionModel().selectedRows()]
@@ -59,7 +59,7 @@ class ConvertAction(InterfaceAction):
         if jobs == []: return
         self.queue_convert_jobs(jobs, changed, bad, rows, previous,
                 self.book_auto_converted_mail,
-                extra_job_args=[delete_from_library, to, fmts])
+                extra_job_args=[delete_from_library, to, fmts, subject])
 
     def auto_convert_news(self, book_ids, format):
         previous = self.gui.library_view.currentIndex()
@@ -145,9 +145,10 @@ class ConvertAction(InterfaceAction):
         self.gui.sync_to_device(on_card, False, specific_format=fmt, send_ids=[book_id], do_auto_convert=False)
 
     def book_auto_converted_mail(self, job):
-        temp_files, fmt, book_id, delete_from_library, to, fmts = self.conversion_jobs[job]
+        temp_files, fmt, book_id, delete_from_library, to, fmts, subject = self.conversion_jobs[job]
         self.book_converted(job)
-        self.gui.send_by_mail(to, fmts, delete_from_library, specific_format=fmt, send_ids=[book_id], do_auto_convert=False)
+        self.gui.send_by_mail(to, fmts, delete_from_library, subject=subject,
+                specific_format=fmt, send_ids=[book_id], do_auto_convert=False)
 
     def book_auto_converted_news(self, job):
         temp_files, fmt, book_id = self.conversion_jobs[job]

src/calibre/gui2/actions/device.py

@@ -82,7 +82,8 @@ class ShareConnMenu(QMenu): # {{{
             keys = sorted(opts.accounts.keys())
             for account in keys:
                 formats, auto, default = opts.accounts[account]
-                dest = 'mail:'+account+';'+formats
+                subject = opts.subjects.get(account, '')
+                dest = 'mail:'+account+';'+formats+';'+subject
                 action1 = DeviceAction(dest, False, False, I('mail.png'),
                         account)
                 action2 = DeviceAction(dest, True, False, I('mail.png'),

src/calibre/gui2/actions/fetch_news.py

@@ -5,6 +5,8 @@ __license__   = 'GPL v3'
 __copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
+import gc
+
 from PyQt4.Qt import Qt
 
 from calibre.gui2 import Dispatcher
@@ -53,11 +55,11 @@ class FetchNewsAction(InterfaceAction):
 
     def scheduled_recipe_fetched(self, job):
         temp_files, fmt, arg = self.conversion_jobs.pop(job)
-        pt = temp_files[0]
+        fname = temp_files[0].name
         if job.failed:
             self.scheduler.recipe_download_failed(arg)
             return self.gui.job_exception(job)
-        id = self.gui.library_view.model().add_news(pt.name, arg)
+        id = self.gui.library_view.model().add_news(fname, arg)
 
         # Arg may contain a "keep_issues" variable. If it is non-zero,
         # delete all but newest x issues.
@@ -81,5 +83,6 @@ class FetchNewsAction(InterfaceAction):
         self.gui.status_bar.show_message(arg['title'] + _(' fetched.'), 3000)
         self.gui.email_news(id)
         self.gui.sync_news()
+        gc.collect()
 
 

src/calibre/gui2/device.py

@@ -887,9 +887,14 @@ class DeviceMixin(object): # {{{
                 on_card = dest
             self.sync_to_device(on_card, delete, fmt)
         elif dest == 'mail':
-            to, fmts = sub_dest.split(';')
+            sub_dest_parts = sub_dest.split(';')
+            while len(sub_dest_parts) < 3:
+                sub_dest_parts.append('')
+            to = sub_dest_parts[0]
+            fmts = sub_dest_parts[1]
+            subject = ';'.join(sub_dest_parts[2:]) 
             fmts = [x.strip().lower() for x in fmts.split(',')]
-            self.send_by_mail(to, fmts, delete)
+            self.send_by_mail(to, fmts, delete, subject=subject)
 
     def cover_to_thumbnail(self, data):
         if self.device_manager.device and \

src/calibre/gui2/email.py

@@ -22,6 +22,7 @@ from calibre.customize.ui import available_input_formats, available_output_forma
 from calibre.ebooks.metadata import authors_to_string
 from calibre.constants import preferred_encoding
 from calibre.gui2 import config, Dispatcher, warning_dialog
+from calibre.library.save_to_disk import get_components
 from calibre.utils.config import tweaks
 
 class EmailJob(BaseJob): # {{{
@@ -210,7 +211,7 @@ class EmailMixin(object): # {{{
     def __init__(self):
         self.emailer = Emailer(self.job_manager)
 
-    def send_by_mail(self, to, fmts, delete_from_library, send_ids=None,
+    def send_by_mail(self, to, fmts, delete_from_library, subject='', send_ids=None,
             do_auto_convert=True, specific_format=None):
         ids = [self.library_view.model().id(r) for r in self.library_view.selectionModel().selectedRows()] if send_ids is None else send_ids
         if not ids or len(ids) == 0:
@@ -239,7 +240,14 @@ class EmailMixin(object): # {{{
                 remove_ids.append(id)
                 jobnames.append(t)
                 attachments.append(f)
-                subjects.append(_('E-book:')+ ' '+t)
+                if not subject:
+                    subjects.append(_('E-book:')+ ' '+t)
+                else:
+                    components = get_components(subject, mi, id)
+                    if not components:
+                        components = [mi.title]
+                    subject = os.path.join(*components)
+                    subjects.append(subject)
                 a = authors_to_string(mi.authors if mi.authors else \
                         [_('Unknown')])
                 texts.append(_('Attached, you will find the e-book') + \
@@ -292,7 +300,7 @@ class EmailMixin(object): # {{{
                 if self.auto_convert_question(
                     _('Auto convert the following books before sending via '
                         'email?'), autos):
-                    self.iactions['Convert Books'].auto_convert_mail(to, fmts, delete_from_library, auto, format)
+                    self.iactions['Convert Books'].auto_convert_mail(to, fmts, delete_from_library, auto, format, subject)
 
         if bad:
             bad = '\n'.join('%s'%(i,) for i in bad)

src/calibre/gui2/library/models.py

@@ -7,7 +7,6 @@ __docformat__ = 'restructuredtext en'
 
 import shutil, functools, re, os, traceback
 from contextlib import closing
-from operator import attrgetter
 
 from PyQt4.Qt import QAbstractTableModel, Qt, pyqtSignal, QIcon, QImage, \
         QModelIndex, QVariant, QDate, QColor
@@ -18,7 +17,7 @@ from calibre.ebooks.metadata import fmt_sidx, authors_to_string, string_to_autho
 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, strcmp as icu_strcmp
+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, \
@@ -984,6 +983,21 @@ class OnDeviceSearch(SearchQueryParser): # {{{
 
 # }}}
 
+class DeviceDBSortKeyGen(object): # {{{
+
+    def __init__(self, attr, keyfunc, db):
+        self.attr = attr
+        self.db = db
+        self.keyfunc = keyfunc
+
+    def __call__(self, x):
+        try:
+            ans = self.keyfunc(getattr(self.db[x], self.attr))
+        except:
+            ans = None
+        return ans
+# }}}
+
 class DeviceBooksModel(BooksModel): # {{{
 
     booklist_dirtied = pyqtSignal()
@@ -1089,59 +1103,40 @@ class DeviceBooksModel(BooksModel): # {{{
 
     def sort(self, col, order, reset=True):
         descending = order != Qt.AscendingOrder
-        def strcmp(attr):
-            ag = attrgetter(attr)
-            def _strcmp(x, y):
-                x = ag(self.db[x])
-                y = ag(self.db[y])
-                if x == None:
-                    x = ''
-                if y == None:
-                    y = ''
-                return icu_strcmp(x.strip(), y.strip())
-            return _strcmp
-        def datecmp(x, y):
-            x = self.db[x].datetime
-            y = self.db[y].datetime
-            return cmp(dt_factory(x, assume_utc=True), dt_factory(y,
-                assume_utc=True))
-        def sizecmp(x, y):
-            x, y = int(self.db[x].size), int(self.db[y].size)
-            return cmp(x, y)
-        def tagscmp(x, y):
-            x = ','.join(sorted(getattr(self.db[x], 'device_collections', []),key=sort_key))
-            y = ','.join(sorted(getattr(self.db[y], 'device_collections', []),key=sort_key))
-            return cmp(x, y)
-        def libcmp(x, y):
-            x, y = self.db[x].in_library, self.db[y].in_library
-            return cmp(x, y)
-        def authorcmp(x, y):
-            ax = getattr(self.db[x], 'author_sort', None)
-            ay = getattr(self.db[y], 'author_sort', None)
-            if ax and ay:
-                x = ax
-                y = ay
-            else:
-                x, y = authors_to_string(self.db[x].authors), \
-                                authors_to_string(self.db[y].authors)
-            return cmp(x, y)
         cname = self.column_map[col]
-        fcmp = {
+        def author_key(x):
-                'title': strcmp('title_sorter'),
+            try:
-                'authors' : authorcmp,
+                ax = self.db[x].author_sort
-                'size' : sizecmp,
+                if not ax:
-                'timestamp': datecmp,
+                    raise Exception('')
-                'collections': tagscmp,
+            except:
-                'inlibrary': libcmp,
+                try:
+                    ax = authors_to_string(self.db[x].authors)
+                except:
+                    ax = ''
+            return ax
+
+        keygen = {
+                'title': ('title_sorter', lambda x: sort_key(x) if x else ''),
+                'authors' : author_key,
+                'size' : ('size', int),
+                'timestamp': ('datetime', functools.partial(dt_factory, assume_utc=True)),
+                'collections': ('device_collections', lambda x:sorted(x,
+                    key=sort_key)),
+                'inlibrary': ('in_library', lambda x: x),
                 }[cname]
-        self.map.sort(cmp=fcmp, reverse=descending)
+        keygen = keygen if callable(keygen) else DeviceDBSortKeyGen(
+            keygen[0], keygen[1], self.db)
+        self.map.sort(key=keygen, reverse=descending)
         if len(self.map) == len(self.db):
             self.sorted_map = list(self.map)
         else:
             self.sorted_map = list(range(len(self.db)))
-            self.sorted_map.sort(cmp=fcmp, reverse=descending)
+            self.sorted_map.sort(key=keygen, reverse=descending)
         self.sorted_on = (self.column_map[col], order)
         self.sort_history.insert(0, self.sorted_on)
+        if hasattr(keygen, 'db'):
+            keygen.db = None
         if reset:
             self.reset()
 

src/calibre/gui2/preferences/emailp.py

@@ -5,6 +5,8 @@ __license__   = 'GPL v3'
 __copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
+import textwrap
+
 from PyQt4.Qt import QAbstractTableModel, QVariant, QFont, Qt
 
 
@@ -17,25 +19,30 @@ from calibre.utils.smtp import config as smtp_prefs
 
 class EmailAccounts(QAbstractTableModel): # {{{
 
-    def __init__(self, accounts):
+    def __init__(self, accounts, subjects):
         QAbstractTableModel.__init__(self)
         self.accounts = accounts
+        self.subjects = subjects
         self.account_order = sorted(self.accounts.keys())
-        self.headers  = map(QVariant, [_('Email'), _('Formats'), _('Auto send')])
+        self.headers  = map(QVariant, [_('Email'), _('Formats'), _('Subject'), _('Auto send')])
         self.default_font = QFont()
         self.default_font.setBold(True)
         self.default_font = QVariant(self.default_font)
-        self.tooltips =[NONE] + map(QVariant,
+        self.tooltips =[NONE] + list(map(QVariant, map(textwrap.fill,
             [_('Formats to email. The first matching format will be sent.'),
+             _('Subject of the email to use when sending. When left blank '
+               'the title will be used for the subject. Also, the same '
+               'templates used for "Save to disk" such as {title} and '
+               '{author_sort} can be used here.'),
              '<p>'+_('If checked, downloaded news will be automatically '
                      'mailed <br>to this email address '
-                     '(provided it is in one of the listed formats).')])
+                     '(provided it is in one of the listed formats).')])))
 
     def rowCount(self, *args):
         return len(self.account_order)
 
     def columnCount(self, *args):
-        return 3
+        return len(self.headers)
 
     def headerData(self, section, orientation, role):
         if role == Qt.DisplayRole and orientation == Qt.Horizontal:
@@ -56,14 +63,16 @@ class EmailAccounts(QAbstractTableModel): # {{{
                 return QVariant(account)
             if col ==  1:
                 return QVariant(self.accounts[account][0])
+            if col == 2:
+                return QVariant(self.subjects.get(account, ''))
         if role == Qt.FontRole and self.accounts[account][2]:
             return self.default_font
-        if role == Qt.CheckStateRole and col == 2:
+        if role == Qt.CheckStateRole and col == 3:
             return QVariant(Qt.Checked if self.accounts[account][1] else Qt.Unchecked)
         return NONE
 
     def flags(self, index):
-        if index.column() == 2:
+        if index.column() == 3:
             return QAbstractTableModel.flags(self, index)|Qt.ItemIsUserCheckable
         else:
             return QAbstractTableModel.flags(self, index)|Qt.ItemIsEditable
@@ -73,8 +82,10 @@ class EmailAccounts(QAbstractTableModel): # {{{
             return False
         row, col = index.row(), index.column()
         account = self.account_order[row]
-        if col == 2:
+        if col == 3:
             self.accounts[account][1] ^= True
+        if col == 2:
+            self.subjects[account] = unicode(value.toString())
         elif col == 1:
             self.accounts[account][0] = unicode(value.toString()).upper()
         else:
@@ -143,7 +154,7 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
         self.send_email_widget.initialize(self.preferred_to_address)
         self.send_email_widget.changed_signal.connect(self.changed_signal.emit)
         opts = self.send_email_widget.smtp_opts
-        self._email_accounts = EmailAccounts(opts.accounts)
+        self._email_accounts = EmailAccounts(opts.accounts, opts.subjects)
         self._email_accounts.dataChanged.connect(lambda x,y:
                 self.changed_signal.emit())
         self.email_view.setModel(self._email_accounts)
@@ -170,6 +181,7 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
         if not self.send_email_widget.set_email_settings(to_set):
             raise AbortCommit('abort')
         self.proxy['accounts'] =  self._email_accounts.accounts
+        self.proxy['subjects'] = self._email_accounts.subjects
 
         return ConfigWidgetBase.commit(self)
 

src/calibre/gui2/search_box.py

@@ -109,7 +109,7 @@ class SearchBox2(QComboBox): # {{{
     def normalize_state(self):
         self.setToolTip(self.tool_tip_text)
         self.line_edit.setStyleSheet(
-            'QLineEdit{color:black;background-color:%s;}' % self.normal_background)
+            'QLineEdit{color:none;background-color:%s;}' % self.normal_background)
 
     def text(self):
         return self.currentText()

src/calibre/gui2/viewer/documentview.py

@@ -171,10 +171,11 @@ class Document(QWebPage): # {{{
             self.misc_config()
             self.after_load()
 
-    def __init__(self, shortcuts, parent=None):
+    def __init__(self, shortcuts, parent=None, resize_callback=lambda: None):
         QWebPage.__init__(self, parent)
         self.setObjectName("py_bridge")
         self.debug_javascript = False
+        self.resize_callback = resize_callback
         self.current_language = None
         self.loaded_javascript = False
 
@@ -237,6 +238,12 @@ class Document(QWebPage): # {{{
         if self.loaded_javascript:
             return
         self.loaded_javascript = True
+        self.javascript(
+            '''
+            window.onresize = function(event) {
+                window.py_bridge.window_resized();
+            }
+            ''')
         if jquery is None:
             jquery = P('content_server/jquery.js', data=True)
         self.javascript(jquery)
@@ -298,6 +305,10 @@ class Document(QWebPage): # {{{
     def debug(self, msg):
         prints(msg)
 
+    @pyqtSignature('')
+    def window_resized(self):
+        self.resize_callback()
+
     def reference_mode(self, enable):
         self.javascript(('enter' if enable else 'leave')+'_reference_mode()')
 
@@ -424,12 +435,19 @@ class Document(QWebPage): # {{{
     def xpos(self):
         return self.mainFrame().scrollPosition().x()
 
-    @property
+    @dynamic_property
     def scroll_fraction(self):
-        try:
+        def fget(self):
-            return float(self.ypos)/(self.height-self.window_height)
+            try:
-        except ZeroDivisionError:
+                return float(self.ypos)/(self.height-self.window_height)
-            return 0.
+            except ZeroDivisionError:
+                return 0.
+        def fset(self, val):
+            npos = val * (self.height - self.window_height)
+            if npos < 0:
+                npos = 0
+            self.scroll_to(x=self.xpos, y=npos)
+        return property(fget=fget, fset=fset)
 
     @property
     def hscroll_fraction(self):
@@ -493,7 +511,8 @@ class DocumentView(QWebView): # {{{
         self._size_hint = QSize(510, 680)
         self.initial_pos = 0.0
         self.to_bottom = False
-        self.document = Document(self.shortcuts, parent=self)
+        self.document = Document(self.shortcuts, parent=self,
+                resize_callback=self.viewport_resized)
         self.setPage(self.document)
         self.manager = None
         self._reference_mode = False
@@ -630,9 +649,13 @@ class DocumentView(QWebView): # {{{
     def sizeHint(self):
         return self._size_hint
 
-    @property
+    @dynamic_property
     def scroll_fraction(self):
-        return self.document.scroll_fraction
+        def fget(self):
+            return self.document.scroll_fraction
+        def fset(self, val):
+            self.document.scroll_fraction = float(val)
+        return property(fget=fget, fset=fset)
 
     @property
     def hscroll_fraction(self):
@@ -968,9 +991,11 @@ class DocumentView(QWebView): # {{{
     def resizeEvent(self, event):
         ret = QWebView.resizeEvent(self, event)
         QTimer.singleShot(10, self.initialize_scrollbar)
+        return ret
+
+    def viewport_resized(self):
         if self.manager is not None:
             self.manager.viewport_resized(self.scroll_fraction)
-        return ret
 
     def event(self, ev):
         typ = ev.type()

src/calibre/gui2/viewer/main.py

@@ -240,7 +240,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
         self.connect(self.action_reference_mode, SIGNAL('triggered(bool)'),
                      lambda x: self.view.reference_mode(x))
         self.connect(self.action_metadata, SIGNAL('triggered(bool)'), lambda x:self.metadata.setVisible(x))
-        self.connect(self.action_table_of_contents, SIGNAL('toggled(bool)'), lambda x:self.toc.setVisible(x))
+        self.action_table_of_contents.toggled[bool].connect(self.set_toc_visible)
         self.connect(self.action_copy, SIGNAL('triggered(bool)'), self.copy)
         self.connect(self.action_font_size_larger, SIGNAL('triggered(bool)'),
                      self.font_size_larger)
@@ -310,6 +310,9 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
 
         self.restore_state()
 
+    def set_toc_visible(self, yes):
+        self.toc.setVisible(yes)
+
     def clear_recent_history(self, *args):
         vprefs.set('viewer_open_history', [])
         self.build_recent_menu()