GwR revisions

resources/recipes/newsweek.recipe

@@ -1,189 +1,76 @@
-__license__   = 'GPL v3'
-__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
-
-import re
-from calibre import strftime
-from calibre.ebooks.BeautifulSoup import BeautifulSoup
+import string
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class Newsweek(BasicNewsRecipe):
 
-
     title          = 'Newsweek'
-    __author__     = 'Kovid Goyal and Sujata Raman'
+    __author__     = 'Kovid Goyal'
     description    = 'Weekly news and current affairs in the US'
+    language       = 'en'
+    encoding       = 'utf-8'
     no_stylesheets = True
 
-    extra_css = '''
-                    h1{font-family:Arial,Helvetica,sans-serif; font-size:large; color:#383733;}
-                    .deck{font-family:Georgia,sans-serif; color:#383733;}
-                    .bylineDate{font-family:georgia ; color:#58544A; font-size:x-small;}
-                    .authorInfo{font-family:arial,helvetica,sans-serif; color:#0066CC; font-size:x-small;}
-                    .articleUpdated{font-family:arial,helvetica,sans-serif; color:#73726C; font-size:x-small;}
-                    .issueDate{font-family:arial,helvetica,sans-serif; color:#73726C; font-size:x-small; font-style:italic;}
-                    h5{font-family:arial,helvetica,sans-serif; color:#73726C; font-size:x-small;}
-                    h6{font-family:arial,helvetica,sans-serif; color:#73726C; font-size:x-small;}
-                    .story{font-family:georgia,sans-serif ;color:black;}
-                    .photoCredit{color:#999999; font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
-                    .photoCaption{color:#0A0A09;font-family:Arial,Helvetica,sans-serif;font-size:x-small;}
-                    .fwArticle{font-family:Arial,Helvetica,sans-serif;font-size:x-small;font-weight:bold;}
-                    '''
+    BASE_URL = 'http://www.newsweek.com'
+    INDEX = BASE_URL+'/topics.html'
 
-    encoding       = 'utf-8'
-    language = 'en'
+    keep_only_tags = dict(name='article', attrs={'class':'article-text'})
+    remove_tags = [dict(attrs={'data-dartad':True})]
+    remove_attributes = ['property']
 
-    remove_tags = [
-            {'class':['fwArticle noHr','fwArticle','hdlBulletItem','head-content','navbar','link', 'ad', 'sponsorLinksArticle', 'mm-content',
-                'inline-social-links-wrapper', 'email-article','ToolBox',
-                'inline-promo-link', 'sponsorship',
-                'inlineComponentRight',
-                'comments-and-social-links-wrapper', 'EmailArticleBlock']},
-            {'id' : ['footer', 'ticker-data', 'topTenVertical',
-                'digg-top-five', 'mesothorax', 'nw-comments', 'my-take-landing',
-                'ToolBox', 'EmailMain']},
-            {'class': re.compile('related-cloud')},
-            dict(name='li', attrs={'id':['slug_bigbox']})
-            ]
+    def postprocess_html(self, soup, first):
+        for tag in soup.findAll(name=['article', 'header']):
+            tag.name = 'div'
+        return soup
+
+    def newsweek_sections(self):
+        soup = self.index_to_soup(self.INDEX)
+        for a in soup.findAll('a', title='Primary tag', href=True):
+            yield (string.capitalize(self.tag_to_string(a)),
+                    self.BASE_URL+a['href'])
 
 
-    keep_only_tags = [{'class':['article HorizontalHeader',
-        'articlecontent','photoBox', 'article columnist first']}, ]
-    recursions = 1
-    match_regexps = [r'http://www.newsweek.com/id/\S+/page/\d+']
-    preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
-
-    def find_title(self, section):
-        d = {'scope':'Scope', 'thetake':'The Take', 'features':'Features',
-                None:'Departments', 'culture':'Culture'}
-        ans = None
-        a = section.find('a', attrs={'name':True})
-        if a is not None:
-            ans = a['name']
-        return d.get(ans, ans)
-
-
-    def find_articles(self, section):
-        ans = []
-        for x in section.findAll('h5'):
-            title = ' '.join(x.findAll(text=True)).strip()
-            a = x.find('a')
-            if not a: continue
-            href = a['href']
-            ans.append({'title':title, 'url':href, 'description':'', 'date': strftime('%a, %d %b')})
-        if not ans:
-            for x in section.findAll('div', attrs={'class':'hdlItem'}):
-                a = x.find('a', href=True)
-                if not a : continue
-                title = ' '.join(a.findAll(text=True)).strip()
-                href = a['href']
-                if 'http://xtra.newsweek.com' in href: continue
-                ans.append({'title':title, 'url':href, 'description':'', 'date': strftime('%a, %d %b')})
-
-        #for x in ans:
-        #    x['url'] += '/output/print'
-        return ans
+    def newsweek_parse_section_page(self, soup):
+        for article in soup.findAll('article', about=True,
+                attrs={'class':'stream-item'}):
+            title = article.find(attrs={'property': 'dc:title'})
+            if title is None: continue
+            title = self.tag_to_string(title)
+            url = self.BASE_URL + article['about']
+            desc = ''
+            author = article.find({'property':'dc:creator'})
+            if author:
+                desc = u'by %s. '%self.tag_to_string(author)
+            p = article.find(attrs={'property':'dc:abstract'})
+            if p is not None:
+                for a in p.find('a'): a.extract()
+                desc += self.tag_to_string(p)
+            t = article.find('time', attrs={'property':'dc:created'})
+            date = ''
+            if t is not None:
+                date = u' [%s]'%self.tag_to_string(t)
+            self.log('\tFound article:', title, 'at', url)
+            self.log('\t\t', desc)
+            yield {'title':title, 'url':url, 'description':desc, 'date':date}
 
 
     def parse_index(self):
-        soup = self.get_current_issue()
-        if not soup:
-            raise RuntimeError('Unable to connect to newsweek.com. Try again later.')
-        sections = soup.findAll('div', attrs={'class':'featurewell'})
-        titles = map(self.find_title, sections)
-        articles = map(self.find_articles, sections)
-        ans = list(zip(titles, articles))
-        def fcmp(x, y):
-            tx, ty = x[0], y[0]
-            if tx == "Features": return cmp(1, 2)
-            if ty == "Features": return cmp(2, 1)
-            return cmp(tx, ty)
-        return sorted(ans, cmp=fcmp)
-
-    def ensure_html(self, soup):
-        root = soup.find(name=True)
-        if root.name == 'html': return soup
-        nsoup = BeautifulSoup('<html><head></head><body/></html>')
-        nroot = nsoup.find(name='body')
-        for x in soup.contents:
-            if getattr(x, 'name', False):
-                x.extract()
-                nroot.insert(len(nroot), x)
-        return nsoup
-
-    def postprocess_html(self, soup, first_fetch):
-        if not first_fetch:
-            h1 = soup.find(id='headline')
-            if h1:
-                h1.extract()
-            div = soup.find(attrs={'class':'articleInfo'})
-            if div:
-                div.extract()
-        divs = list(soup.findAll('div', 'pagination'))
-        if not divs:
-            return self.ensure_html(soup)
-        for div in divs[1:]: div.extract()
-        all_a = divs[0].findAll('a', href=True)
-        divs[0]['style']="display:none"
-        if len(all_a) > 1:
-            all_a[-1].extract()
-        test = re.compile(self.match_regexps[0])
-        for a in soup.findAll('a', href=test):
-            if a not in all_a:
-                del a['href']
-        return self.ensure_html(soup)
-
-    def get_current_issue(self):
-        soup = self.index_to_soup('http://www.newsweek.com')
-        div = soup.find('div', attrs={'class':re.compile('more-from-mag')})
-        if div is None: return None
-        a = div.find('a')
-        if a is not None:
-            href = a['href'].split('#')[0]
-            return self.index_to_soup(href)
-
-    def get_cover_url(self):
-        cover_url = None
-        soup = self.index_to_soup('http://www.newsweek.com')
-        link_item = soup.find('div',attrs={'class':'cover-image'})
-        if link_item and link_item.a and link_item.a.img:
-           cover_url = link_item.a.img['src']
-        return cover_url
+        sections = []
+        for section, shref in self.newsweek_sections():
+            self.log('Processing section', section, shref)
+            articles = []
+            soups = [self.index_to_soup(shref)]
+            na = soups[0].find('a', rel='next')
+            if na:
+                soups.append(self.index_to_soup(self.BASE_URL+na['href']))
+            for soup in soups:
+                articles.extend(self.newsweek_parse_section_page(soup))
+                if self.test and len(articles) > 1:
+                    break
+            if articles:
+                sections.append((section, articles))
+            if self.test and len(sections) > 1:
+                break
+        return sections
 
 
-    def postprocess_book(self, oeb, opts, log) :
-
-        def extractByline(href) :
-            soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
-            byline = soup.find(True,attrs={'class':'authorInfo'})
-            byline = self.tag_to_string(byline) if byline is not None else ''
-            issueDate = soup.find(True,attrs={'class':'issueDate'})
-            issueDate = self.tag_to_string(issueDate) if issueDate is not None else ''
-            issueDate = re.sub(',','', issueDate)
-            if byline > '' and issueDate > '' :
-                return byline + ' | ' + issueDate
-            else :
-                return byline + issueDate
-
-        def extractDescription(href) :
-            soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
-            description = soup.find(True,attrs={'name':'description'})
-            if description is not None and description.has_key('content'):
-                description = description['content']
-                if description.startswith('Newsweek magazine online plus') :
-                    description = soup.find(True, attrs={'class':'story'})
-                    firstPara = soup.find('p')
-                    description = self.tag_to_string(firstPara)
-            else :
-                description = soup.find(True, attrs={'class':'story'})
-                firstPara = soup.find('p')
-                description = self.tag_to_string(firstPara)
-            return description
-
-        for section in oeb.toc :
-            for article in section :
-                if article.author is None :
-                    article.author = extractByline(article.href)
-                if article.description is None :
-                    article.description = extractDescription(article.href)
-        return
 

resources/recipes/nytimes.recipe

@@ -391,10 +391,14 @@ class NYTimes(BasicNewsRecipe):
         return ans
 
     def preprocess_html(self, soup):
-        # Skip ad pages before actual article
+        # Skip ad pages served before actual article
         skip_tag = soup.find(True, {'name':'skip'})
         if skip_tag is not None:
-            soup = self.index_to_soup(skip_tag.parent['href'])
+            self.log.error("Found forwarding link: %s" % skip_tag.parent['href'])
+            url = 'http://www.nytimes.com' + re.sub(r'\?.*', '', skip_tag.parent['href'])
+            url += '?pagewanted=all'
+            self.log.error("Skipping ad to article at '%s'" % url)
+            soup = self.index_to_soup(url)
         return self.strip_anchors(soup)
 
     def postprocess_html(self,soup, True):

resources/recipes/nytimes_sub.recipe

@@ -280,18 +280,14 @@ class NYTimes(BasicNewsRecipe):
         return ans
 
     def preprocess_html(self, soup):
-        '''
-        refresh = soup.find('meta', {'http-equiv':'refresh'})
-        if refresh is None:
-            return soup
-        content = refresh.get('content').partition('=')[2]
-        raw = self.browser.open('http://www.nytimes.com'+content).read()
-        return BeautifulSoup(raw.decode('cp1252', 'replace'))
-        '''
-        # Skip ad pages before actual article
+        # Skip ad pages served before actual article
         skip_tag = soup.find(True, {'name':'skip'})
         if skip_tag is not None:
-            soup = self.index_to_soup(skip_tag.parent['href'])
+            self.log.error("Found forwarding link: %s" % skip_tag.parent['href'])
+            url = 'http://www.nytimes.com' + re.sub(r'\?.*', '', skip_tag.parent['href'])
+            url += '?pagewanted=all'
+            self.log.error("Skipping ad to article at '%s'" % url)
+            soup = self.index_to_soup(url)
         return self.strip_anchors(soup)
 
     def postprocess_html(self,soup, True):

resources/recipes/sarajevo_x.recipe

@@ -0,0 +1,66 @@
+__license__   = 'GPL v3'
+__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
+
+'''
+sarajevo-x.com
+'''
+
+import re
+from calibre.web.feeds.recipes import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import Tag, NavigableString
+
+class SarajevoX(BasicNewsRecipe):
+    title                 = 'Sarajevo-x.com'
+    __author__            = 'Darko Miletic'
+    description           = 'Sarajevo-x.com - najposjeceniji bosanskohercegovacki internet portal'
+    publisher             = 'InterSoft d.o.o.'
+    category              = 'news, politics, Bosnia and Herzegovina,Sarajevo-x.com, internet, portal, vijesti, bosna i hercegovina, sarajevo'
+    oldest_article        = 2
+    delay                 = 1
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    encoding              = 'cp1250'
+    use_embedded_content  = False
+    language              = 'bs'
+    extra_css = ' @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: Arial,Verdana,Helvetica,sans1,sans-serif} .article_description{font-family: sans1, sans-serif} div#fotka{display: block} img{margin-bottom: 0.5em} '
+
+    conversion_options = {
+                          'comment'          : description
+                        , 'tags'             : category
+                        , 'publisher'        : publisher
+                        , 'language'         : language
+                        }
+
+    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
+
+    keep_only_tags    = [dict(name='div', attrs={'class':'content-bg'})]
+    remove_tags_after = dict(name='div',attrs={'class':'izvor'})
+    remove_tags       = [dict(name=['object','link','base','table'])]
+    remove_attributes = ['height','width','alt','border']
+
+    feeds = [
+               (u'BIH'          , u'http://www.sarajevo-x.com/rss/bih'          )
+              ,(u'Svijet'       , u'http://www.sarajevo-x.com/rss/svijet'       )
+              ,(u'Biznis'       , u'http://www.sarajevo-x.com/rss/biznis'       )
+              ,(u'Sport'        , u'http://www.sarajevo-x.com/rss/sport'        )
+              ,(u'Showtime'     , u'http://www.sarajevo-x.com/rss/showtime'     )
+              ,(u'Scitech'      , u'http://www.sarajevo-x.com/rss/scitech'      )
+              ,(u'Lifestyle'    , u'http://www.sarajevo-x.com/rss/lifestyle'    )
+              ,(u'Kultura'      , u'http://www.sarajevo-x.com/rss/kultura'      )
+              ,(u'Zanimljivosti', u'http://www.sarajevo-x.com/rss/zanimljivosti')
+            ]
+
+    def preprocess_html(self, soup):
+        dtag = soup.find('div',attrs={'id':'fotka'})
+        if dtag:
+           sp = soup.find('div',attrs={'id':'opisslike'})
+           img = soup.find('img')
+           if sp:
+               sp
+           else:
+               mtag  = Tag(soup,'div',[("id","opisslike"),("class","opscitech")])
+               mopis = NavigableString("Opis")
+               mtag.insert(0,mopis)
+               img.append(mtag)
+        return soup
+

src/calibre/customize/__init__.py

@@ -29,7 +29,7 @@ class Plugin(object):
 
     '''
     #: List of platforms this plugin works on
-    #: For example: ``['windows', 'osx', 'linux']
+    #: For example: ``['windows', 'osx', 'linux']``
     supported_platforms = []
 
     #: The name of this plugin. You must set it something other
@@ -214,10 +214,8 @@ class MetadataReaderPlugin(Plugin):
         Return metadata for the file represented by stream (a file like object
         that supports reading). Raise an exception when there is an error
         with the input data.
-
         :param type: The type of file. Guaranteed to be one of the entries
         in :attr:`file_types`.
-
         :return: A :class:`calibre.ebooks.metadata.MetaInformation` object
         '''
         return None
@@ -245,11 +243,9 @@ class MetadataWriterPlugin(Plugin):
         Set metadata for the file represented by stream (a file like object
         that supports reading). Raise an exception when there is an error
         with the input data.
-
         :param type: The type of file. Guaranteed to be one of the entries
         in :attr:`file_types`.
         :param mi: A :class:`calibre.ebooks.metadata.MetaInformation` object
-
         '''
         pass
 

src/calibre/customize/profiles.py

@@ -240,6 +240,9 @@ class OutputProfile(Plugin):
     # Device supports displaying a nested TOC
     supports_nested_toc = True
 
+    # If True output should be optimized for a touchscreen interface
+    touchscreen = False
+
     @classmethod
     def tags_to_string(cls, tags):
         return escape(', '.join(tags))

src/calibre/ebooks/conversion/preprocess.py

@@ -14,8 +14,14 @@ XMLDECL_RE    = re.compile(r'^\s*<[?]xml.*?[?]>')
 SVG_NS       = 'http://www.w3.org/2000/svg'
 XLINK_NS     = 'http://www.w3.org/1999/xlink'
 
-convert_entities = functools.partial(entity_to_unicode, exceptions=['quot',
-    'apos', 'lt', 'gt', 'amp', '#60', '#62'])
+convert_entities = functools.partial(entity_to_unicode,
+        result_exceptions = {
+            u'<' : '&lt;',
+            u'>' : '&gt;',
+            u"'" : '&apos;',
+            u'"' : '&quot;',
+            u'&' : '&amp;',
+        })
 _span_pat = re.compile('<span.*?</span>', re.DOTALL|re.IGNORECASE)
 
 LIGATURES = {

src/calibre/ebooks/html/input.py

@@ -416,9 +416,9 @@ class HTMLInput(InputFormatPlugin):
         link = unquote(link).replace('/', os.sep)
         if not link.strip():
             return link_
-        if base and not os.path.isabs(link):
-            link = os.path.join(base, link)
         try:
+            if base and not os.path.isabs(link):
+                link = os.path.join(base, link)
             link = os.path.abspath(link)
         except:
             return link_

src/calibre/ebooks/lrf/objects.py

@@ -3,7 +3,7 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 import struct, array, zlib, cStringIO, collections, re
 
 from calibre.ebooks.lrf import LRFParseError, PRS500_PROFILE
-from calibre import entity_to_unicode
+from calibre import entity_to_unicode, prepare_string_for_xml
 from calibre.ebooks.lrf.tags import Tag
 
 ruby_tags = {
@@ -870,7 +870,7 @@ class Text(LRFStream):
         open_containers = collections.deque()
         for c in self.content:
             if isinstance(c, basestring):
-                s += c
+                s += prepare_string_for_xml(c)
             elif c is None:
                 if open_containers:
                     p = open_containers.pop()

src/calibre/ebooks/metadata/html.py

@@ -11,7 +11,7 @@ import re
 
 from calibre.ebooks.metadata import MetaInformation
 from calibre.ebooks.chardet import xml_to_unicode
-
+from calibre import entity_to_unicode
 
 def get_metadata(stream):
     src = stream.read()
@@ -43,6 +43,10 @@ def get_metadata_(src, encoding=None):
     if match:
         author = match.group(2).replace(',', ';')
 
+    ent_pat = re.compile(r'&(\S+)?;')
+    title = ent_pat.sub(entity_to_unicode, title)
+    if author:
+        author = ent_pat.sub(entity_to_unicode, author)
     mi = MetaInformation(title, [author] if author else None)
 
     # Publisher

src/calibre/ebooks/oeb/base.py

@@ -787,7 +787,6 @@ class Manifest(object):
             data = self.oeb.decode(data)
             data = self.oeb.html_preprocessor(data)
 
-
             # Remove DOCTYPE declaration as it messes up parsing
             # In particular, it causes tostring to insert xmlns
             # declarations, which messes up the coercing logic

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

@@ -136,6 +136,8 @@ class CoverManager(object):
                 href = g['cover'].href
             else:
                 href = self.default_cover()
+            if href is None:
+                return
             width, height = self.inspect_cover(href)
             if width is None or height is None:
                 self.log.warning('Failed to read cover dimensions')

src/calibre/gui2/__init__.py

@@ -97,7 +97,8 @@ def _config():
             help=_('Overwrite author and title with new metadata'))
     c.add_opt('enforce_cpu_limit', default=True,
             help=_('Limit max simultaneous jobs to number of CPUs'))
-
+    c.add_opt('tag_browser_hidden_categories', default=set(),
+            help=_('tag browser categories not to display'))
     return ConfigProxy(c)
 
 config = _config()

src/calibre/gui2/convert/regex_builder.py

@@ -14,6 +14,7 @@ from calibre.gui2.convert.regex_builder_ui import Ui_RegexBuilder
 from calibre.gui2.convert.xexp_edit_ui import Ui_Form as Ui_Edit
 from calibre.gui2 import error_dialog, choose_files
 from calibre.ebooks.oeb.iterator import EbookIterator
+from calibre.ebooks.conversion.preprocess import convert_entities
 from calibre.gui2.dialogs.choose_format import ChooseFormatDialog
 
 class RegexBuilder(QDialog, Ui_RegexBuilder):
@@ -87,8 +88,10 @@ class RegexBuilder(QDialog, Ui_RegexBuilder):
         self.iterator = EbookIterator(pathtoebook)
         self.iterator.__enter__(only_input_plugin=True)
         text = [u'']
+        ent_pat = re.compile(r'&(\S+?);')
         for path in self.iterator.spine:
             html = open(path, 'rb').read().decode('utf-8', 'replace')
+            html = ent_pat.sub(convert_entities, html)
             text.append(html)
         self.preview.setPlainText('\n---\n'.join(text))
 

src/calibre/gui2/device.py

@@ -1123,12 +1123,12 @@ class DeviceGUI(object):
             if cache:
                 if id in cache['db_ids']:
                     loc[i] = True
-                    break
+                    continue
                 if mi.authors and \
                         re.sub('(?u)\W|[_]', '', authors_to_string(mi.authors).lower()) \
                         in cache['authors']:
                     loc[i] = True
-                    break
+                    continue
         return loc
 
     def set_books_in_library(self, booklists, reset=False):

src/calibre/gui2/dialogs/config/__init__.py

@@ -14,7 +14,7 @@ from PyQt4.Qt import    QDialog, QListWidgetItem, QIcon, \
 from calibre.constants import iswindows, isosx
 from calibre.gui2.dialogs.config.config_ui import Ui_Dialog
 from calibre.gui2.dialogs.config.create_custom_column import CreateCustomColumn
-from calibre.gui2 import choose_dir, error_dialog, config, \
+from calibre.gui2 import choose_dir, error_dialog, config, gprefs, \
                          ALL_COLUMNS, NONE, info_dialog, choose_files, \
                          warning_dialog, ResizableDialog, question_dialog
 from calibre.utils.config import prefs
@@ -480,6 +480,8 @@ class ConfigDialog(ResizableDialog, Ui_Dialog):
         self.opt_enforce_cpu_limit.setChecked(config['enforce_cpu_limit'])
         self.device_detection_button.clicked.connect(self.debug_device_detection)
         self.port.editingFinished.connect(self.check_port_value)
+        self.show_splash_screen.setChecked(gprefs.get('show_splash_screen',
+            True))
 
     def check_port_value(self, *args):
         port = self.port.value()
@@ -852,6 +854,7 @@ class ConfigDialog(ResizableDialog, Ui_Dialog):
         config['get_social_metadata'] = self.opt_get_social_metadata.isChecked()
         config['overwrite_author_title_metadata'] = self.opt_overwrite_author_title_metadata.isChecked()
         config['enforce_cpu_limit'] = bool(self.opt_enforce_cpu_limit.isChecked())
+        gprefs['show_splash_screen'] = bool(self.show_splash_screen.isChecked())
         fmts = []
         for i in range(self.viewer.count()):
             if self.viewer.item(i).checkState() == Qt.Checked:

src/calibre/gui2/dialogs/config/config.ui

@@ -331,8 +331,8 @@
             </layout>
            </widget>
            <widget class="QWidget" name="page">
-            <layout class="QVBoxLayout" name="verticalLayout_4">
-             <item>
+            <layout class="QGridLayout" name="gridLayout_8">
+             <item row="0" column="0">
               <widget class="QCheckBox" name="roman_numerals">
                <property name="text">
                 <string>Use &amp;Roman numerals for series number</string>
@@ -342,28 +342,35 @@
                </property>
               </widget>
              </item>
-             <item>
+             <item row="1" column="0">
               <widget class="QCheckBox" name="systray_icon">
                <property name="text">
                 <string>Enable system &amp;tray icon (needs restart)</string>
                </property>
               </widget>
              </item>
-             <item>
+             <item row="1" column="1">
               <widget class="QCheckBox" name="systray_notifications">
                <property name="text">
                 <string>Show &amp;notifications in system tray</string>
                </property>
               </widget>
              </item>
-             <item>
+             <item row="2" column="0" colspan="2">
+              <widget class="QCheckBox" name="show_splash_screen">
+               <property name="text">
+                <string>Show &amp;splash screen at startup</string>
+               </property>
+              </widget>
+             </item>
+             <item row="3" column="0" colspan="2">
               <widget class="QCheckBox" name="separate_cover_flow">
                <property name="text">
                 <string>Show cover &amp;browser in a separate window (needs restart)</string>
                </property>
               </widget>
              </item>
-             <item>
+             <item row="4" column="0">
               <widget class="QCheckBox" name="search_as_you_type">
                <property name="text">
                 <string>Search as you type</string>
@@ -373,21 +380,21 @@
                </property>
               </widget>
              </item>
-             <item>
+             <item row="5" column="0" colspan="2">
               <widget class="QCheckBox" name="sync_news">
                <property name="text">
                 <string>Automatically send downloaded &amp;news to ebook reader</string>
                </property>
               </widget>
              </item>
-             <item>
+             <item row="6" column="0" colspan="2">
               <widget class="QCheckBox" name="delete_news">
                <property name="text">
                 <string>&amp;Delete news from library when it is automatically sent to reader</string>
                </property>
               </widget>
              </item>
-             <item>
+             <item row="7" column="0" colspan="2">
               <layout class="QHBoxLayout" name="horizontalLayout">
                <item>
                 <widget class="QLabel" name="label_6">
@@ -404,7 +411,7 @@
                </item>
               </layout>
              </item>
-             <item>
+             <item row="8" column="0" colspan="2">
               <widget class="QGroupBox" name="groupBox_2">
                <property name="title">
                 <string>Toolbar</string>
@@ -452,7 +459,7 @@
                </layout>
               </widget>
              </item>
-             <item>
+             <item row="9" column="0" colspan="2">
               <layout class="QHBoxLayout" name="horizontalLayout_7">
                <item>
                 <widget class="QGroupBox" name="groupBox">
@@ -527,12 +534,12 @@
                       </item>
                       <item>
                        <widget class="QToolButton" name="add_custcol_button">
-                        <property name="text">
-                         <string>...</string>
-                        </property>
                         <property name="toolTip">
                          <string>Add a user-defined column</string>
                         </property>
+                        <property name="text">
+                         <string>...</string>
+                        </property>
                         <property name="icon">
                          <iconset resource="../../../../../resources/images.qrc">
                           <normaloff>:/images/plus.svg</normaloff>:/images/plus.svg</iconset>

src/calibre/gui2/dialogs/saved_search_editor.py

@@ -0,0 +1,86 @@
+__license__   = 'GPL v3'
+
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+
+
+from PyQt4.QtCore import SIGNAL, Qt
+from PyQt4.QtGui import QDialog, QIcon, QListWidgetItem
+
+from calibre.gui2.dialogs.saved_search_editor_ui import Ui_SavedSearchEditor
+from calibre.utils.config import prefs
+from calibre.utils.search_query_parser import saved_searches
+from calibre.gui2.dialogs.confirm_delete import confirm
+from calibre.constants import islinux
+
+class SavedSearchEditor(QDialog, Ui_SavedSearchEditor):
+
+    def __init__(self, window, initial_search=None):
+        QDialog.__init__(self, window)
+        Ui_SavedSearchEditor.__init__(self)
+        self.setupUi(self)
+
+        self.connect(self.add_search_button, SIGNAL('clicked()'), self.add_search)
+        self.connect(self.search_name_box, SIGNAL('currentIndexChanged(int)'),
+                                    self.current_index_changed)
+        self.connect(self.delete_search_button, SIGNAL('clicked()'), self.del_search)
+
+        self.current_search_name = None
+        self.searches = {}
+        self.searches_to_delete = []
+        for name in saved_searches.names():
+            self.searches[name] = saved_searches.lookup(name)
+
+        self.populate_search_list()
+        if initial_search is not None and initial_search in self.searches:
+            self.select_search(initial_search)
+
+    def populate_search_list(self):
+        self.search_name_box.clear()
+        for name in sorted(self.searches.keys()):
+            self.search_name_box.addItem(name)
+
+    def add_search(self):
+        search_name = unicode(self.input_box.text()).strip()
+        if search_name == '':
+            return False
+        if search_name not in self.searches:
+            self.searches[search_name] = ''
+            self.populate_search_list()
+            self.select_search(search_name)
+        else:
+            self.select_search(search_name)
+        return True
+
+    def del_search(self):
+        if self.current_search_name is not None:
+            if not confirm('<p>'+_('The current saved search will be '
+                           '<b>permanently deleted</b>. Are you sure?')
+                        +'</p>', 'saved_search_editor_delete', self):
+                return
+            del self.searches[self.current_search_name]
+            self.searches_to_delete.append(self.current_search_name)
+            self.current_search_name = None
+            self.search_name_box.removeItem(self.search_name_box.currentIndex())
+
+    def select_search(self, name):
+        self.search_name_box.setCurrentIndex(self.search_name_box.findText(name))
+
+    def current_index_changed(self, idx):
+        if self.current_search_name:
+            self.searches[self.current_search_name] = unicode(self.search_text.toPlainText())
+        name = unicode(self.search_name_box.itemText(idx))
+        if name:
+            self.current_search_name = name
+            self.search_text.setPlainText(self.searches[name])
+        else:
+            self.current_search_name  = None
+            self.search_text.setPlainText('')
+
+    def accept(self):
+        if self.current_search_name:
+            self.searches[self.current_search_name] = unicode(self.search_text.toPlainText())
+        for name in self.searches_to_delete:
+            saved_searches.delete(name)
+        for name in self.searches:
+            saved_searches.add(name, self.searches[name])
+        QDialog.accept(self)

src/calibre/gui2/dialogs/saved_search_editor.ui

@@ -0,0 +1,185 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>SavedSearchEditor</class>
+ <widget class="QDialog" name="SavedSearchEditor">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>548</width>
+    <height>148</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>Saved Search Editor</string>
+  </property>
+  <property name="windowIcon">
+   <iconset>
+    <normaloff>:/images/chapters.svg</normaloff>:/images/chapters.svg</iconset>
+  </property>
+  <layout class="QGridLayout">
+   <item row="2" column="0" colspan="2">
+    <widget class="QDialogButtonBox" name="buttonBox">
+     <property name="orientation">
+      <enum>Qt::Horizontal</enum>
+     </property>
+     <property name="standardButtons">
+      <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
+     </property>
+     <property name="centerButtons">
+      <bool>true</bool>
+     </property>
+    </widget>
+   </item>
+   <item row="0" column="0" colspan="2">
+    <layout class="QGridLayout" name="gridLayout">
+     <item row="0" column="0">
+      <widget class="QLabel" name="label_3">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Fixed" vsizetype="Preferred">
+         <horstretch>0</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="minimumSize">
+        <size>
+         <width>100</width>
+         <height>0</height>
+        </size>
+       </property>
+       <property name="text">
+        <string>Saved Search: </string>
+       </property>
+       <property name="alignment">
+        <set>Qt::AlignLeading|Qt::AlignLeft|Qt::AlignVCenter</set>
+       </property>
+       <property name="buddy">
+        <cstring>search_name_box</cstring>
+       </property>
+      </widget>
+     </item>
+     <item row="0" column="1">
+      <widget class="QComboBox" name="search_name_box">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Fixed" vsizetype="Fixed">
+         <horstretch>160</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="minimumSize">
+        <size>
+         <width>145</width>
+         <height>0</height>
+        </size>
+       </property>
+       <property name="toolTip">
+        <string>Select a saved search to edit</string>
+       </property>
+       <property name="editable">
+        <bool>false</bool>
+       </property>
+      </widget>
+     </item>
+     <item row="0" column="2">
+      <widget class="QToolButton" name="delete_search_button">
+       <property name="toolTip">
+        <string>Delete this selected saved search</string>
+       </property>
+       <property name="text">
+        <string>...</string>
+       </property>
+       <property name="icon">
+        <iconset>
+         <normaloff>:/images/minus.svg</normaloff>:/images/minus.svg</iconset>
+       </property>
+      </widget>
+     </item>
+     <item row="0" column="3">
+      <spacer>
+       <property name="orientation">
+        <enum>Qt::Horizontal</enum>
+       </property>
+       <property name="sizeHint" stdset="0">
+        <size>
+         <width>40</width>
+         <height>20</height>
+        </size>
+       </property>
+      </spacer>
+     </item>
+     <item row="0" column="4">
+      <widget class="QLineEdit" name="input_box">
+       <property name="sizePolicy">
+        <sizepolicy hsizetype="Expanding" vsizetype="Fixed">
+         <horstretch>60</horstretch>
+         <verstretch>0</verstretch>
+        </sizepolicy>
+       </property>
+       <property name="toolTip">
+        <string>Enter a new saved search name.</string>
+       </property>
+      </widget>
+     </item>
+     <item row="0" column="5">
+      <widget class="QToolButton" name="add_search_button">
+       <property name="toolTip">
+        <string>Add the new saved search</string>
+       </property>
+       <property name="text">
+        <string>...</string>
+       </property>
+       <property name="icon">
+        <iconset>
+         <normaloff>:/images/plus.svg</normaloff>:/images/plus.svg</iconset>
+       </property>
+      </widget>
+     </item>
+    </layout>
+   </item>
+   <item row="1" column="0">
+    <widget class="QPlainTextEdit" name="search_text">
+     <property name="toolTip">
+      <string>Change the contents of the saved search</string>
+     </property>
+    </widget>
+   </item>
+  </layout>
+ </widget>
+ <resources>
+  <include location="../../../../../calibre_datesearch/resources/images"/>
+ </resources>
+ <connections>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>accepted()</signal>
+   <receiver>SavedSearchEditor</receiver>
+   <slot>accept()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>248</x>
+     <y>254</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>157</x>
+     <y>274</y>
+    </hint>
+   </hints>
+  </connection>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>rejected()</signal>
+   <receiver>SavedSearchEditor</receiver>
+   <slot>reject()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>316</x>
+     <y>260</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>286</x>
+     <y>274</y>
+    </hint>
+   </hints>
+  </connection>
+ </connections>
+</ui>

src/calibre/gui2/dialogs/tag_categories.py

@@ -24,13 +24,12 @@ class Item:
 class TagCategories(QDialog, Ui_TagCategories):
     category_labels_orig =   ['', 'authors', 'series', 'publishers', 'tags']
 
-    def __init__(self, window, db, index=None):
+    def __init__(self, window, db, on_category=None):
         QDialog.__init__(self, window)
         Ui_TagCategories.__init__(self)
         self.setupUi(self)
 
         self.db = db
-        self.index = index
         self.applied_items = []
 
         cc_icon = QIcon(I('column.svg'))
@@ -102,8 +101,10 @@ class TagCategories(QDialog, Ui_TagCategories):
         self.connect(self.applied_items_box,   SIGNAL('itemActivated(QListWidgetItem*)'), self.unapply_tags)
 
         self.populate_category_list()
-        return
-        self.select_category(0)
+        if on_category is not None:
+            l = self.category_box.findText(on_category)
+            if l >= 0:
+                self.category_box.setCurrentIndex(l)
 
     def make_list_widget(self, item):
         n = item.name if item.exists else item.name + _(' (not on any book)')

src/calibre/gui2/dialogs/tag_categories.ui

@@ -11,7 +11,7 @@
    </rect>
   </property>
   <property name="windowTitle">
-   <string>Tag Editor</string>
+   <string>User Categories Editor</string>
   </property>
   <property name="windowIcon">
    <iconset>

src/calibre/gui2/dialogs/tag_list_editor.py

@@ -0,0 +1,89 @@
+__license__   = 'GPL v3'
+__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
+from PyQt4.QtCore import SIGNAL, Qt
+from PyQt4.QtGui import QDialog, QListWidgetItem
+
+from calibre.gui2.dialogs.tag_list_editor_ui import Ui_TagListEditor
+from calibre.gui2 import question_dialog, error_dialog
+
+class TagListEditor(QDialog, Ui_TagListEditor):
+
+    def tag_cmp(self, x, y):
+        return cmp(x.lower(), y.lower())
+
+    def __init__(self, window, db, tag_to_match):
+        QDialog.__init__(self, window)
+        Ui_TagListEditor.__init__(self)
+        self.setupUi(self)
+
+        self.to_rename = {}
+        self.to_delete = []
+        self.db = db
+        self.all_tags = {}
+        for k,v in db.get_tags_with_ids():
+            self.all_tags[v] = k
+        for tag in sorted(self.all_tags.keys(), cmp=self.tag_cmp):
+            item = QListWidgetItem(tag)
+            item.setData(Qt.UserRole, self.all_tags[tag])
+            self.available_tags.addItem(item)
+
+        items = self.available_tags.findItems(tag_to_match, Qt.MatchExactly)
+        if len(items) == 1:
+            self.available_tags.setCurrentItem(items[0])
+
+        self.connect(self.delete_button,  SIGNAL('clicked()'), self.delete_tags)
+        self.connect(self.rename_button,  SIGNAL('clicked()'), self.rename_tag)
+        self.connect(self.available_tags, SIGNAL('itemDoubleClicked(QListWidgetItem *)'), self._rename_tag)
+        self.connect(self.available_tags, SIGNAL('itemChanged(QListWidgetItem *)'), self.finish_editing)
+
+    def finish_editing(self, item):
+        if item.text() != self.item_before_editing.text():
+            if item.text() in self.all_tags.keys() or item.text() in self.to_rename.keys():
+                error_dialog(self, 'Tag already used',
+                             'The tag %s is already used.'%(item.text())).exec_()
+                item.setText(self.item_before_editing.text())
+                return
+            id,ign = self.item_before_editing.data(Qt.UserRole).toInt()
+            self.to_rename[item.text()] = id
+
+    def rename_tag(self):
+        item = self.available_tags.currentItem()
+        self._rename_tag(item)
+
+    def _rename_tag(self, item):
+        if item is None:
+            error_dialog(self, 'No tag selected', 'You must select one tag from the list of Available tags.').exec_()
+            return
+        self.item_before_editing = item.clone()
+        item.setFlags (item.flags() | Qt.ItemIsEditable);
+        self.available_tags.editItem(item)
+
+    def delete_tags(self, item=None):
+        confirms, deletes = [], []
+        items = self.available_tags.selectedItems() if item is None else [item]
+        if not items:
+            error_dialog(self, 'No tags selected', 'You must select at least one tag from the list of Available tags.').exec_()
+            return
+        for item in items:
+            if self.db.is_tag_used(unicode(item.text())):
+                confirms.append(item)
+            else:
+                deletes.append(item)
+        if confirms:
+            ct = ', '.join([unicode(item.text()) for item in confirms])
+            if question_dialog(self, _('Are your sure?'),
+                '<p>'+_('The following tags are used by one or more books. '
+                    'Are you certain you want to delete them?')+'<br>'+ct):
+                deletes += confirms
+
+        for item in deletes:
+            self.to_delete.append(item)
+            self.available_tags.takeItem(self.available_tags.row(item))
+
+    def accept(self):
+        for text in self.to_rename:
+            self.db.rename_tag(self.to_rename[text], unicode(text))
+        for item in self.to_delete:
+            self.db.delete_tag(unicode(item.text()))
+        QDialog.accept(self)
+

src/calibre/gui2/dialogs/tag_list_editor.ui

@@ -0,0 +1,163 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ui version="4.0">
+ <class>TagListEditor</class>
+ <widget class="QDialog" name="TagListEditor">
+  <property name="geometry">
+   <rect>
+    <x>0</x>
+    <y>0</y>
+    <width>397</width>
+    <height>335</height>
+   </rect>
+  </property>
+  <property name="windowTitle">
+   <string>Tag Editor</string>
+  </property>
+  <property name="windowIcon">
+   <iconset>
+    <normaloff>:/images/chapters.svg</normaloff>:/images/chapters.svg</iconset>
+  </property>
+  <layout class="QGridLayout">
+   <item row="0" column="0">
+    <layout class="QVBoxLayout">
+     <item>
+      <layout class="QHBoxLayout">
+       <item>
+        <widget class="QLabel" name="label">
+         <property name="text">
+          <string>Tags in use</string>
+         </property>
+         <property name="buddy">
+          <cstring>available_tags</cstring>
+         </property>
+        </widget>
+       </item>
+       <item>
+        <spacer>
+         <property name="orientation">
+          <enum>Qt::Horizontal</enum>
+         </property>
+         <property name="sizeHint" stdset="0">
+          <size>
+           <width>40</width>
+           <height>20</height>
+          </size>
+         </property>
+        </spacer>
+       </item>
+      </layout>
+     </item>
+     <item>
+      <layout class="QHBoxLayout">
+       <item>
+        <layout class="QVBoxLayout" name="verticalLayout_2">
+         <item>
+          <widget class="QToolButton" name="delete_button">
+           <property name="toolTip">
+            <string>Delete tag from database. This will unapply the tag from all books and then remove it from the database.</string>
+           </property>
+           <property name="text">
+            <string>...</string>
+           </property>
+           <property name="icon">
+            <iconset>
+             <normaloff>:/images/trash.svg</normaloff>:/images/trash.svg</iconset>
+           </property>
+           <property name="iconSize">
+            <size>
+             <width>32</width>
+             <height>32</height>
+            </size>
+           </property>
+          </widget>
+         </item>
+         <item>
+          <widget class="QToolButton" name="rename_button">
+           <property name="toolTip">
+            <string>Rename the tag everywhere it is used.</string>
+           </property>
+           <property name="text">
+            <string>...</string>
+           </property>
+           <property name="icon">
+            <iconset>
+             <normaloff>:/images/edit_input.svg</normaloff>:/images/edit_input.svg</iconset>
+           </property>
+           <property name="iconSize">
+            <size>
+             <width>32</width>
+             <height>32</height>
+            </size>
+           </property>
+           <property name="shortcut">
+            <string>Ctrl+S</string>
+           </property>
+          </widget>
+         </item>
+        </layout>
+       </item>
+       <item>
+        <widget class="QListWidget" name="available_tags">
+         <property name="alternatingRowColors">
+          <bool>true</bool>
+         </property>
+         <property name="selectionMode">
+          <enum>QAbstractItemView::ExtendedSelection</enum>
+         </property>
+         <property name="selectionBehavior">
+          <enum>QAbstractItemView::SelectRows</enum>
+         </property>
+        </widget>
+       </item>
+      </layout>
+     </item>
+    </layout>
+   </item>
+   <item row="1" column="0" colspan="2">
+    <widget class="QDialogButtonBox" name="buttonBox">
+     <property name="orientation">
+      <enum>Qt::Horizontal</enum>
+     </property>
+     <property name="standardButtons">
+      <set>QDialogButtonBox::Cancel|QDialogButtonBox::Ok</set>
+     </property>
+    </widget>
+   </item>
+  </layout>
+ </widget>
+ <resources/>
+ <connections>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>accepted()</signal>
+   <receiver>TagListEditor</receiver>
+   <slot>accept()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>248</x>
+     <y>254</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>157</x>
+     <y>274</y>
+    </hint>
+   </hints>
+  </connection>
+  <connection>
+   <sender>buttonBox</sender>
+   <signal>rejected()</signal>
+   <receiver>TagListEditor</receiver>
+   <slot>reject()</slot>
+   <hints>
+    <hint type="sourcelabel">
+     <x>316</x>
+     <y>260</y>
+    </hint>
+    <hint type="destinationlabel">
+     <x>286</x>
+     <y>274</y>
+    </hint>
+   </hints>
+  </connection>
+ </connections>
+</ui>

src/calibre/gui2/main.py

@@ -5,13 +5,15 @@ import sys, os, time, socket, traceback
 from functools import partial
 
 from PyQt4.Qt import QCoreApplication, QIcon, QMessageBox, QObject, QTimer, \
-        QThread, pyqtSignal, Qt, QProgressDialog, QString
+        QThread, pyqtSignal, Qt, QProgressDialog, QString, QPixmap, \
+        QSplashScreen, QApplication
 
 from calibre import prints, plugins
-from calibre.constants import iswindows, __appname__, isosx, filesystem_encoding
+from calibre.constants import iswindows, __appname__, isosx, DEBUG, \
+        filesystem_encoding
 from calibre.utils.ipc import ADDRESS, RC
 from calibre.gui2 import ORG_NAME, APP_UID, initialize_file_icon_provider, \
-    Application, choose_dir, error_dialog, question_dialog
+    Application, choose_dir, error_dialog, question_dialog, gprefs
 from calibre.gui2.main_window import option_parser as _option_parser
 from calibre.utils.config import prefs, dynamic
 from calibre.library.database2 import LibraryDatabase2
@@ -113,15 +115,25 @@ class GuiRunner(QObject):
     initialization'''
 
     def __init__(self, opts, args, actions, listener, app):
+        self.startup_time = time.time()
         self.opts, self.args, self.listener, self.app = opts, args, listener, app
         self.actions = actions
         self.main = None
         QObject.__init__(self)
+        self.splash_screen = None
         self.timer = QTimer.singleShot(1, self.initialize)
+        if DEBUG:
+            prints('Starting up...')
 
     def start_gui(self):
         from calibre.gui2.ui import Main
-        main = Main(self.library_path, self.db, self.listener, self.opts, self.actions)
+        main = Main(self.opts)
+        if self.splash_screen is not None:
+            self.splash_screen.showMessage(_('Initializing user interface...'))
+            self.splash_screen.finish(main)
+        main.initialize(self.library_path, self.db, self.listener, self.actions)
+        if DEBUG:
+            prints('Started up in', time.time() - self.startup_time)
         add_filesystem_book = partial(main.add_filesystem_book, allow_device=False)
         sys.excepthook = main.unhandled_exception
         if len(self.args) > 1:
@@ -142,7 +154,7 @@ class GuiRunner(QObject):
 
         if db is None and tb is not None:
             # DB Repair failed
-            error_dialog(None, _('Repairing failed'),
+            error_dialog(self.splash_screen, _('Repairing failed'),
                     _('The database repair failed. Starting with '
                         'a new empty library.'),
                     det_msg=tb, show=True)
@@ -159,7 +171,7 @@ class GuiRunner(QObject):
                     os.makedirs(x)
                 except:
                     x = os.path.expanduser('~')
-            candidate = choose_dir(None, 'choose calibre library',
+            candidate = choose_dir(self.splash_screen, 'choose calibre library',
                 _('Choose a location for your new calibre e-book library'),
                 default_dir=x)
 
@@ -170,7 +182,7 @@ class GuiRunner(QObject):
                 self.library_path = candidate
                 db = LibraryDatabase2(candidate)
             except:
-                error_dialog(None, _('Bad database location'),
+                error_dialog(self.splash_screen, _('Bad database location'),
                     _('Bad database location %r. calibre will now quit.'
                      )%self.library_path,
                     det_msg=traceback.format_exc(), show=True)
@@ -184,7 +196,7 @@ class GuiRunner(QObject):
         try:
             db = LibraryDatabase2(self.library_path)
         except (sqlite.Error, DatabaseException):
-            repair = question_dialog(None, _('Corrupted database'),
+            repair = question_dialog(self.splash_screen, _('Corrupted database'),
                     _('Your calibre database appears to be corrupted. Do '
                     'you want calibre to try and repair it automatically? '
                     'If you say No, a new empty calibre library will be created.'),
@@ -203,14 +215,27 @@ class GuiRunner(QObject):
                 self.repair.start()
                 return
         except:
-            error_dialog(None, _('Bad database location'),
+            error_dialog(self.splash_screen, _('Bad database location'),
                     _('Bad database location %r. Will start with '
                     ' a new, empty calibre library')%self.library_path,
                     det_msg=traceback.format_exc(), show=True)
 
         self.initialize_db_stage2(db, None)
 
+    def show_splash_screen(self):
+        self.splash_pixmap = QPixmap()
+        self.splash_pixmap.load(I('library.png'))
+        self.splash_screen = QSplashScreen(self.splash_pixmap,
+            Qt.SplashScreen|Qt.WindowStaysOnTopHint)
+        self.splash_screen.showMessage(_('Starting %s: Loading books...') %
+                __appname__)
+        self.splash_screen.show()
+        QApplication.instance().processEvents()
+
     def initialize(self, *args):
+        if gprefs.get('show_splash_screen', True):
+            self.show_splash_screen()
+
         self.library_path = get_library_path()
         if self.library_path is None:
             self.initialization_failed()

src/calibre/gui2/tag_view.py

@@ -8,10 +8,11 @@ Browsing book collection by tags.
 '''
 
 from itertools import izip
+from functools import partial
 
 from PyQt4.Qt import Qt, QTreeView, QApplication, pyqtSignal, \
                      QFont, QSize, QIcon, QPoint, \
-                     QAbstractItemModel, QVariant, QModelIndex
+                     QAbstractItemModel, QVariant, QModelIndex, QMenu
 from calibre.gui2 import config, NONE
 from calibre.utils.config import prefs
 from calibre.library.field_metadata import TagsIcons
@@ -19,9 +20,12 @@ from calibre.utils.search_query_parser import saved_searches
 
 class TagsView(QTreeView): # {{{
 
-    need_refresh    = pyqtSignal()
-    restriction_set = pyqtSignal(object)
-    tags_marked     = pyqtSignal(object, object)
+    need_refresh        = pyqtSignal()
+    restriction_set     = pyqtSignal(object)
+    tags_marked         = pyqtSignal(object, object)
+    user_category_edit  = pyqtSignal(object)
+    tag_list_edit       = pyqtSignal(object)
+    saved_search_edit   = pyqtSignal(object)
 
     def __init__(self, *args):
         QTreeView.__init__(self, *args)
@@ -31,13 +35,16 @@ class TagsView(QTreeView): # {{{
         self.tag_match = None
 
     def set_database(self, db, tag_match, popularity, restriction):
-        self._model = TagsModel(db, parent=self)
+        self.hidden_categories = config['tag_browser_hidden_categories']
+        self._model = TagsModel(db, parent=self, hidden_categories=self.hidden_categories)
         self.popularity = popularity
         self.restriction = restriction
         self.tag_match = tag_match
         self.db = db
         self.setModel(self._model)
+        self.setContextMenuPolicy(Qt.CustomContextMenu)
         self.clicked.connect(self.toggle)
+        self.customContextMenuRequested.connect(self.show_context_menu)
         self.popularity.setChecked(config['sort_by_popularity'])
         self.popularity.stateChanged.connect(self.sort_changed)
         self.restriction.activated[str].connect(self.search_restriction_set)
@@ -45,10 +52,6 @@ class TagsView(QTreeView): # {{{
         db.add_listener(self.database_changed)
         self.saved_searches_changed(recount=False)
 
-    def create_tag_category(self, name, tag_list):
-        self._model.create_tag_category(name, tag_list)
-        self.recount()
-
     def database_changed(self, event, ids):
         self.need_refresh.emit()
 
@@ -72,12 +75,87 @@ class TagsView(QTreeView): # {{{
         self.recount() # Must happen after the emission of the restriction_set signal
         self.tags_marked.emit(self._model.tokens(), self.match_all)
 
+    def mouseReleaseEvent(self, event):
+        # Swallow everything except leftButton so context menus work correctly
+        if event.button() == Qt.LeftButton:
+            QTreeView.mouseReleaseEvent(self, event)
+
     def toggle(self, index):
         modifiers = int(QApplication.keyboardModifiers())
         exclusive = modifiers not in (Qt.CTRL, Qt.SHIFT)
         if self._model.toggle(index, exclusive):
             self.tags_marked.emit(self._model.tokens(), self.match_all)
 
+    def context_menu_handler(self, action=None, category=None):
+        if not action:
+            return
+        try:
+            if action == 'manage_tags':
+                self.tag_list_edit.emit(category)
+                return
+            if action == 'manage_categories':
+                self.user_category_edit.emit(category)
+                return
+            if action == 'manage_searches':
+                self.saved_search_edit.emit(category)
+                return
+            if action == 'hide':
+                self.hidden_categories.add(category)
+            elif action == 'show':
+                self.hidden_categories.discard(category)
+            elif action == 'defaults':
+                self.hidden_categories.clear()
+            config.set('tag_browser_hidden_categories', self.hidden_categories)
+            self.set_new_model()
+        except:
+            return
+
+    def show_context_menu(self, point):
+        index = self.indexAt(point)
+        if not index.isValid():
+            return False
+        item = index.internalPointer()
+        tag_name = ''
+        if item.type == TagTreeItem.TAG:
+            tag_name = item.tag.name
+            item = item.parent
+        if item.type == TagTreeItem.CATEGORY:
+            category = unicode(item.name.toString())
+            self.context_menu = QMenu(self)
+            self.context_menu.addAction(_('Hide %s') % category,
+                partial(self.context_menu_handler, action='hide', category=category))
+
+            if self.hidden_categories:
+                self.context_menu.addSeparator()
+                m = self.context_menu.addMenu(_('Show category'))
+                for col in self.hidden_categories:
+                    m.addAction(col,
+                        partial(self.context_menu_handler, action='show', category=col))
+                self.context_menu.addSeparator()
+                self.context_menu.addAction(_('Restore defaults'),
+                            partial(self.context_menu_handler, action='defaults'))
+
+            self.context_menu.addSeparator()
+            self.context_menu.addAction(_('Manage Tags'),
+                        partial(self.context_menu_handler, action='manage_tags',
+                                category=tag_name))
+
+            if category in prefs['user_categories'].keys():
+                self.context_menu.addAction(_('Manage User Categories'),
+                        partial(self.context_menu_handler, action='manage_categories',
+                                category=category))
+            else:
+                self.context_menu.addAction(_('Manage User Categories'),
+                        partial(self.context_menu_handler, action='manage_categories',
+                                category=None))
+
+            self.context_menu.addAction(_('Manage Saved Searches'),
+                    partial(self.context_menu_handler, action='manage_searches',
+                            category=tag_name))
+
+            self.context_menu.popup(self.mapToGlobal(point))
+        return True
+
     def clear(self):
         self.model().clear_state()
 
@@ -110,13 +188,12 @@ class TagsView(QTreeView): # {{{
                 self.setCurrentIndex(idx)
                 self.scrollTo(idx, QTreeView.PositionAtCenter)
 
-    '''
-    If the number of user categories changed, or if custom columns have come or gone,
-    we must rebuild the model. Reason: it is much easier to do that than to reconstruct
-    the browser tree.
-    '''
+    # If the number of user categories changed,  if custom columns have come or
+    # gone, or if columns have been hidden or restored, we must rebuild the
+    # model. Reason: it is much easier than reconstructing the browser tree.
     def set_new_model(self):
-        self._model = TagsModel(self.db, parent=self)
+        self._model = TagsModel(self.db, parent=self,
+                                hidden_categories=self.hidden_categories)
         self.setModel(self._model)
     # }}}
 
@@ -200,7 +277,7 @@ class TagTreeItem(object): # {{{
 
 class TagsModel(QAbstractItemModel): # {{{
 
-    def __init__(self, db, parent=None):
+    def __init__(self, db, parent=None, hidden_categories=None):
         QAbstractItemModel.__init__(self, parent)
 
         # must do this here because 'QPixmap: Must construct a QApplication
@@ -220,6 +297,7 @@ class TagsModel(QAbstractItemModel): # {{{
 
         self.icon_state_map = [None, QIcon(I('plus.svg')), QIcon(I('minus.svg'))]
         self.db = db
+        self.hidden_categories = hidden_categories
         self.search_restriction = ''
         self.ignore_next_search = 0
 
@@ -237,6 +315,8 @@ class TagsModel(QAbstractItemModel): # {{{
         data = self.get_node_tree(config['sort_by_popularity'])
         self.root_item = TagTreeItem()
         for i, r in enumerate(self.row_map):
+            if self.hidden_categories and self.categories[i] in self.hidden_categories:
+                continue
             if self.db.field_metadata[r]['kind'] != 'user':
                 tt = _('The lookup/search name is "{0}"').format(r)
             else:
@@ -271,12 +351,16 @@ class TagsModel(QAbstractItemModel): # {{{
 
     def refresh(self):
         data = self.get_node_tree(config['sort_by_popularity']) # get category data
+        row_index = -1
         for i, r in enumerate(self.row_map):
-            category = self.root_item.children[i]
+            if self.hidden_categories and self.categories[i] in self.hidden_categories:
+                continue
+            row_index += 1
+            category = self.root_item.children[row_index]
             names = [t.tag.name for t in category.children]
             states = [t.tag.state for t in category.children]
             state_map = dict(izip(names, states))
-            category_index = self.index(i, 0, QModelIndex())
+            category_index = self.index(row_index, 0, QModelIndex())
             if len(category.children) > 0:
                 self.beginRemoveRows(category_index, 0,
                         len(category.children)-1)
@@ -401,16 +485,20 @@ class TagsModel(QAbstractItemModel): # {{{
     def tokens(self):
         ans = []
         tags_seen = set()
+        row_index = -1
         for i, key in enumerate(self.row_map):
+            if self.hidden_categories and self.categories[i] in self.hidden_categories:
+                continue
+            row_index += 1
             if key.endswith(':'): # User category, so skip it. The tag will be marked in its real category
                 continue
-            category_item = self.root_item.children[i]
+            category_item = self.root_item.children[row_index]
             for tag_item in category_item.children:
                 tag = tag_item.tag
                 if tag.state > 0:
                     prefix = ' not ' if tag.state == 2 else ''
                     category = key if key != 'news' else 'tag'
-                    if tag.name[0] == u'\u2605': # char is a star. Assume rating
+                    if tag.name and tag.name[0] == u'\u2605': # char is a star. Assume rating
                         ans.append('%s%s:%s'%(prefix, category, len(tag.name)))
                     else:
                         if category == 'tags':

src/calibre/gui2/ui.py

@@ -61,6 +61,8 @@ from calibre.library.database2 import LibraryDatabase2
 from calibre.library.caches import CoverCache
 from calibre.gui2.dialogs.confirm_delete import confirm
 from calibre.gui2.dialogs.tag_categories import TagCategories
+from calibre.gui2.dialogs.tag_list_editor import TagListEditor
+from calibre.gui2.dialogs.saved_search_editor import SavedSearchEditor
 
 class SaveMenu(QMenu):
 
@@ -127,13 +129,18 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
                 pixmap_to_data(pixmap))
 
         self.last_time = datetime.datetime.now()
-    def __init__(self, library_path, db, listener, opts, actions, parent=None):
+
+    def __init__(self, opts, parent=None):
+        MainWindow.__init__(self, opts, parent)
+        self.opts = opts
+
+    def initialize(self, library_path, db, listener, actions):
+        opts = self.opts
         self.last_time = datetime.datetime.now()
         self.preferences_action, self.quit_action = actions
         self.library_path = library_path
         self.spare_servers = []
         self.must_restart_before_config = False
-        MainWindow.__init__(self, opts, parent)
         # Initialize fontconfig in a separate thread as this can be a lengthy
         # process if run for the first time on this machine
         from calibre.utils.fonts import fontconfig
@@ -537,19 +544,23 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
         self.cover_cache = CoverCache(self.library_path)
         self.cover_cache.start()
         self.library_view.model().cover_cache = self.cover_cache
-        self.connect(self.edit_categories, SIGNAL('clicked()'), self.do_edit_categories)
+        self.connect(self.edit_categories, SIGNAL('clicked()'), self.do_user_categories_edit)
         self.tags_view.set_database(db, self.tag_match, self.popularity, self.search_restriction)
         self.tags_view.tags_marked.connect(self.search.search_from_tags)
         for x in (self.saved_search.clear_to_help, self.mark_restriction_set):
             self.tags_view.restriction_set.connect(x)
         self.tags_view.tags_marked.connect(self.saved_search.clear_to_help)
+        self.tags_view.tag_list_edit.connect(self.do_tags_list_edit)
+        self.tags_view.user_category_edit.connect(self.do_user_categories_edit)
+        self.tags_view.saved_search_edit.connect(self.do_saved_search_edit)
         self.search.search.connect(self.tags_view.model().reinit)
         for x in (self.location_view.count_changed, self.tags_view.recount,
                 self.restriction_count_changed):
             self.library_view.model().count_changed_signal.connect(x)
 
         self.connect(self.search, SIGNAL('cleared()'), self.search_box_cleared)
-        self.connect(self.saved_search, SIGNAL('changed()'), self.tags_view.saved_searches_changed, Qt.QueuedConnection)
+        self.connect(self.saved_search, SIGNAL('changed()'),
+                     self.tags_view.saved_searches_changed, Qt.QueuedConnection)
         if not gprefs.get('quick_start_guide_added', False):
             from calibre.ebooks.metadata import MetaInformation
             mi = MetaInformation(_('Calibre Quick Start Guide'), ['John Schember'])
@@ -642,13 +653,28 @@ class Main(MainWindow, Ui_MainWindow, DeviceGUI):
         self._add_filesystem_book = Dispatcher(self.__add_filesystem_book)
         self.keyboard_interrupt.connect(self.quit, type=Qt.QueuedConnection)
 
-    def do_edit_categories(self):
-        d = TagCategories(self, self.library_view.model().db)
+    def do_user_categories_edit(self, on_category=None):
+        d = TagCategories(self, self.library_view.model().db, on_category)
         d.exec_()
         if d.result() == d.Accepted:
             self.tags_view.set_new_model()
             self.tags_view.recount()
 
+    def do_tags_list_edit(self, tag):
+        d = TagListEditor(self, self.library_view.model().db, tag)
+        d.exec_()
+        if d.result() == d.Accepted:
+            self.tags_view.set_new_model()
+            self.tags_view.recount()
+            self.library_view.model().refresh()
+
+    def do_saved_search_edit(self, search):
+        d = SavedSearchEditor(self, search)
+        d.exec_()
+        if d.result() == d.Accepted:
+            self.tags_view.saved_searches_changed(recount=True)
+            self.saved_search.clear_to_help()
+
     def resizeEvent(self, ev):
         MainWindow.resizeEvent(self, ev)
         self.search.setMaximumWidth(self.width()-150)

src/calibre/library/caches.py

@@ -17,7 +17,7 @@ from calibre.utils.config import tweaks
 from calibre.utils.date import parse_date, now, UNDEFINED_DATE
 from calibre.utils.search_query_parser import SearchQueryParser
 from calibre.utils.pyparsing import ParseException
-# from calibre.library.field_metadata import FieldMetadata
+from calibre.ebooks.metadata import title_sort
 
 class CoverCache(QThread):
 
@@ -564,7 +564,8 @@ class ResultCache(SearchQueryParser):
     def seriescmp(self, x, y):
         sidx = self.FIELD_MAP['series']
         try:
-            ans = cmp(self._data[x][sidx].lower(), self._data[y][sidx].lower())
+            ans = cmp(title_sort(self._data[x][sidx].lower()),
+                    title_sort(self._data[y][sidx].lower()))
         except AttributeError: # Some entries may be None
             ans = cmp(self._data[x][sidx], self._data[y][sidx])
         if ans != 0: return ans

src/calibre/library/database2.py

@@ -648,6 +648,11 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
         self.conn.execute(st%dict(ltable='publishers', table='publishers', ltable_col='publisher'))
         self.conn.execute(st%dict(ltable='tags', table='tags', ltable_col='tag'))
         self.conn.execute(st%dict(ltable='series', table='series', ltable_col='series'))
+        for id_, tag in self.conn.get('SELECT id, name FROM tags', all=True):
+            if not tag.strip():
+                self.conn.execute('DELETE FROM books_tags_link WHERE tag=?',
+                        (id_,))
+                self.conn.execute('DELETE FROM tags WHERE id=?', (id_,))
         self.clean_custom()
         self.conn.commit()
 
@@ -725,6 +730,9 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
             categories[category] = [Tag(formatter(r[1]), count=r[2], id=r[0],
                                         icon=icon, tooltip = tooltip)
                                     for r in data if item_not_zero_func(r)]
+            if category == 'series':
+                categories[category].sort(cmp=lambda x,y:cmp(title_sort(x.name),
+                    title_sort(y.name)))
 
         # We delayed computing the standard formats category because it does not
         # use a view, but is computed dynamically
@@ -977,6 +985,20 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
             if notify:
                 self.notify('metadata', [id])
 
+    # Convenience method for tags_list_editor
+    def get_tags_with_ids(self):
+        result = self.conn.get('SELECT * FROM tags')
+        if not result:
+            return {}
+        r = []
+        for k,v in result:
+            r.append((k,v))
+        return r
+
+    def rename_tag(self, id, new):
+        self.conn.execute('UPDATE tags SET name=? WHERE id=?', (new, id))
+        self.conn.commit()
+
     def get_tags(self, id):
         result = self.conn.get(
         'SELECT name FROM tags WHERE id IN (SELECT tag FROM books_tags_link WHERE book=?)',

src/calibre/library/server/content.py

@@ -16,7 +16,7 @@ except ImportError:
 
 from calibre import fit_image, guess_type
 from calibre.utils.date import fromtimestamp
-
+from calibre.ebooks.metadata import title_sort
 
 class ContentServer(object):
 
@@ -67,7 +67,7 @@ class ContentServer(object):
     def seriescmp(self, x, y):
         si = self.db.FIELD_MAP['series']
         try:
-            ans = cmp(x[si].lower(), y[si].lower())
+            ans = cmp(title_sort(x[si].lower()), title_sort(y[si].lower()))
         except AttributeError: # Some entries may be None
             ans = cmp(x[si], y[si])
         if ans != 0: return ans

src/calibre/manual/conversion.rst

@@ -453,7 +453,7 @@ as HTML and then convert the resulting HTML file with |app|. When saving as HTML
 
 There is a Word macro package that can automate the conversion of Word documents using |app|. It also makes
 generating the Table of Contents much simpler. It is called BookCreator and is available for free
-`here <http://www.mobileread.com/forums/showthread.php?t=28313>`_.
+at `mobileread <http://www.mobileread.com/forums/showthread.php?t=28313>`_.
 
 Convert TXT documents
 ~~~~~~~~~~~~~~~~~~~~~~
@@ -493,7 +493,7 @@ TXT input supports a number of options to differentiate how paragraphs are detec
         allows for basic formatting to be added to TXT documents, such as bold, italics, section headings, tables,
         lists, a Table of Contents, etc. Marking chapter headings with a leading # and setting the chapter XPath detection
         expression to "//h:h1" is the easiest way to have a proper table of contents generated from a TXT document.
-        You can learn more about the markdown syntax `here <http://daringfireball.net/projects/markdown/syntax>`_.
+        You can learn more about the markdown syntax at `daringfireball <http://daringfireball.net/projects/markdown/syntax>`_.
 
 
 Convert PDF documents
@@ -540,7 +540,7 @@ EPUB advanced formatting demo
 Various advanced formatting for EPUB files is demonstrated in this `demo file <http://calibre-ebook.com/downloads/demos/demo.epub>`_.
 The file was created from hand coded HTML using calibre and is meant to be used as a template for your own EPUB creation efforts. 
 
-The source HTML it was created from is available `here <http://calibre-ebook.com/downloads/demos/demo.zip>`_. The settings used to create the
+The source HTML it was created from is available `demo.zip <http://calibre-ebook.com/downloads/demos/demo.zip>`_. The settings used to create the
 EPUB from the ZIP file are::
 
     ebook-convert demo.zip .epub -vv --authors "Kovid Goyal" --language en --level1-toc '//*[@class="title"]' --disable-font-rescaling --page-breaks-before / --no-default-epub-cover

src/calibre/manual/faq.rst

@@ -133,7 +133,7 @@ Can I use the collections feature of the SONY reader?
 turned into a collection on the reader. Note that the PRS-500 does not support collections for books stored on the SD card. The PRS-505 does. 
 
 How do I use |app| with my iPad/iPhone/iTouch?
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 You can access your calibre library on a iPad/iPhone/iTouch over the air using the calibre content server. 
 

src/calibre/manual/news_recipe.rst

@@ -115,7 +115,7 @@ Pre/post processing of downloaded HTML
 
 .. automethod:: BasicNewsRecipe.postprocess_html
 
-
+.. automethod:: BasicNewsRecipe.populate_article_metadata
     
 
 Convenience methods

src/calibre/utils/magick_draw.py

@@ -51,6 +51,8 @@ class FontMetrics(object):
 
 
 def get_font_metrics(image, d_wand, text):
+    if isinstance(text, unicode):
+        text = text.encode('utf-8')
     ret = p.MagickQueryFontMetrics(image, d_wand, text)
     return FontMetrics(ret)
 

src/calibre/web/feeds/news.py

@@ -146,7 +146,7 @@ class BasicNewsRecipe(Recipe):
     #: If True empty feeds are removed from the output.
     #: This option has no effect if parse_index is overriden in
     #: the sub class. It is meant only for recipes that return a list
-    #: of feeds using :member:`feeds` or :method:`get_feeds`.
+    #: of feeds using `feeds` or :method:`get_feeds`.
     remove_empty_feeds = False
 
     #: List of regular expressions that determines which links to follow
@@ -256,7 +256,7 @@ class BasicNewsRecipe(Recipe):
 
     #: The CSS that is used to style the templates, i.e., the navigation bars and
     #: the Tables of Contents. Rather than overriding this variable, you should
-    #: use :member:`extra_css` in your recipe to customize look and feel.
+    #: use `extra_css` in your recipe to customize look and feel.
     template_css = u'''
             .article_date {
                 color: gray; font-family: monospace;
@@ -506,7 +506,7 @@ class BasicNewsRecipe(Recipe):
 
     def get_obfuscated_article(self, url):
         '''
-        If you set :member:`articles_are_obfuscated` this method is called with
+        If you set `articles_are_obfuscated` this method is called with
         every article URL. It should return the path to a file on the filesystem
         that contains the article HTML. That file is processed by the recursive
         HTML fetching engine, so it can contain links to pages/images on the web.
@@ -517,20 +517,18 @@ class BasicNewsRecipe(Recipe):
         '''
         raise NotImplementedError
 
-    def extract_author(self, soup):
+    def populate_article_metadata(self, article, soup, first):
         '''
-        Parse downloaded articles for author, add to OEBBook object.
-        :param soup:
+        Called when each HTML page belonging to article is downloaded.
+        Intended to be used to get article metadata like author/summary/etc.
+        from the parsed HTML (soup).
+        :param article: A object of class :class:`calibre.web.feeds.Article`.
+                       If you change the sumamry, remember to also change the
+                       text_summary
+        :param soup: Parsed HTML belonging to this article
+        :param first: True iff the parsed HTML is the first page of the article.
         '''
-        return None
-
-    def extract_description(self, soup):
-        '''
-        Parse downloaded articles for description, add to OEBBook object.
-        :param soup:
-        '''
-        return None
-
+        pass
 
     def postprocess_book(self, oeb, opts, log):
         '''
@@ -559,8 +557,8 @@ class BasicNewsRecipe(Recipe):
         self.username = options.username
         self.password = options.password
         self.lrf = options.lrf
-        self.output_profile = options.output_profile.name
-        self.touchscreen = getattr(options.output_profile,'touchscreen',False)
+        self.output_profile = options.output_profile
+        self.touchscreen = getattr(self.output_profile, 'touchscreen', False)
 
         self.output_dir = os.path.abspath(self.output_dir)
         if options.test:
@@ -655,7 +653,15 @@ class BasicNewsRecipe(Recipe):
         for base in list(soup.findAll(['base', 'iframe'])):
             base.extract()
 
-        return self.postprocess_html(soup, first_fetch)
+        ans = self.postprocess_html(soup, first_fetch)
+        try:
+            article = self.feed_objects[f].articles[a]
+        except:
+            self.log.exception('Failed to get article object for postprocessing')
+            pass
+        else:
+            self.populate_article_metadata(article, ans, first_fetch)
+        return ans
 
 
     def download(self):
@@ -879,6 +885,7 @@ class BasicNewsRecipe(Recipe):
                 if hasattr(feed, 'reverse'):
                     feed.reverse()
 
+        self.feed_objects = feeds
         for f, feed in enumerate(feeds):
             feed_dir = os.path.join(self.output_dir, 'feed_%d'%f)
             if not os.path.isdir(feed_dir):
@@ -927,41 +934,9 @@ class BasicNewsRecipe(Recipe):
 
         #feeds.restore_duplicates()
 
-        # GwR Populate any missing author/description fields in feed
         for f, feed in enumerate(feeds):
-            feed_dir = os.path.join(self.output_dir, 'feed_%d'%f)
-            for article in feed.articles:
-                if article.summary == '' or article.author == '':
-                    file = os.path.join(self.output_dir,feed_dir, article.url)
-                    if os.path.exists(file):
-                        with open(file, 'rb') as fi:
-                            src = fi.read().decode('utf-8')
-                            soup = BeautifulSoup(src)
-                            if article.author == '':
-                                    author = self.extract_author(soup)
-                                    if author and not isinstance(author, unicode):
-                                        author = author.decode('utf-8', 'replace')
-                                    article.author = author
-
-                            if article.summary == '':
-                                summary = article.summary = self.extract_description(soup)
-                                if summary and not isinstance(summary, unicode):
-                                    summary = summary.decode('utf-8', 'replace')
-                                if summary and '<' in summary:
-                                    try:
-                                        s = html.fragment_fromstring(summary, create_parent=True)
-                                        summary = html.tostring(s, method='text', encoding=unicode)
-                                    except:
-                                        print 'Failed to process article summary, deleting:'
-                                        print summary.encode('utf-8')
-                                        traceback.print_exc()
-                                        summary = u''
-                                article.text_summary = summary
-
-
-        for f, feed in enumerate(feeds):
-            feed_dir = os.path.join(self.output_dir, 'feed_%d'%f)
             html = self.feed2index(feed)
+            feed_dir = os.path.join(self.output_dir, 'feed_%d'%f)
             with open(os.path.join(feed_dir, 'index.html'), 'wb') as fi:
                 fi.write(html)
         self.create_opf(feeds)
@@ -1040,47 +1015,13 @@ class BasicNewsRecipe(Recipe):
         Create a generic cover for recipes that dont have a cover
         '''
         try:
-            try:
-                from PIL import Image, ImageDraw, ImageFont
-                Image, ImageDraw, ImageFont
-            except ImportError:
-                import Image, ImageDraw, ImageFont
-            font_path = P('fonts/liberation/LiberationSerif-Bold.ttf')
+            from calibre.utils.magick_draw import create_cover_page, TextLine
             title = self.title if isinstance(self.title, unicode) else \
                     self.title.decode(preferred_encoding, 'replace')
             date = strftime(self.timefmt)
-            app = '['+__appname__ +' '+__version__+']'
-
-            COVER_WIDTH, COVER_HEIGHT = 590, 750
-            img = Image.new('RGB', (COVER_WIDTH, COVER_HEIGHT), 'white')
-            draw = ImageDraw.Draw(img)
-            # Title
-            font = ImageFont.truetype(font_path, 44)
-            width, height = draw.textsize(title, font=font)
-            left = max(int((COVER_WIDTH - width)/2.), 0)
-            top = 15
-            draw.text((left, top), title, fill=(0,0,0), font=font)
-            bottom = top + height
-            # Date
-            font = ImageFont.truetype(font_path, 32)
-            width, height = draw.textsize(date, font=font)
-            left = max(int((COVER_WIDTH - width)/2.), 0)
-            draw.text((left, bottom+15), date, fill=(0,0,0), font=font)
-            # Vanity
-            font = ImageFont.truetype(font_path, 28)
-            width, height = draw.textsize(app, font=font)
-            left = max(int((COVER_WIDTH - width)/2.), 0)
-            top = COVER_HEIGHT - height - 15
-            draw.text((left, top), app, fill=(0,0,0), font=font)
-            # Logo
-            logo = Image.open(I('library.png'), 'r')
-            width, height = logo.size
-            left = max(int((COVER_WIDTH - width)/2.), 0)
-            top = max(int((COVER_HEIGHT - height)/2.), 0)
-            img.paste(logo, (left, top))
-            img = img.convert('RGB').convert('P', palette=Image.ADAPTIVE)
-
-            img.convert('RGB').save(cover_file, 'JPEG')
+            lines = [TextLine(title, 44), TextLine(date, 32)]
+            img_data = create_cover_page(lines, I('library.png'), output_format='jpg')
+            cover_file.write(img_data)
             cover_file.flush()
         except:
             self.log.exception('Failed to generate default cover')
@@ -1173,21 +1114,20 @@ class BasicNewsRecipe(Recipe):
                 pw.DestroyMagickWand(x)
 
     def create_opf(self, feeds, dir=None):
-
         if dir is None:
             dir = self.output_dir
         mi = MetaInformation(self.short_title() + strftime(self.timefmt), [__appname__])
-        mi.author_sort = __appname__
-        if self.output_profile == 'iPad':
-            mi = MetaInformation(self.short_title(), [strftime('%A, %d %B %Y')])
-            mi.author_sort = strftime('%Y-%m-%d')
         mi.publisher = __appname__
+        mi.author_sort = __appname__
+        if self.output_profile.name == 'iPad':
+            date_as_author = '%s, %s %s, %s' % (strftime('%A'), strftime('%B'), strftime('%d').lstrip('0'), strftime('%Y'))
+            mi.authors = [date_as_author]
+            mi.author_sort = strftime('%Y-%m-%d')
         mi.publication_type = 'periodical:'+self.publication_type
         mi.timestamp = nowf()
         mi.comments = self.description
         if not isinstance(mi.comments, unicode):
             mi.comments = mi.comments.decode('utf-8', 'replace')
-        mi.tags = ['News']
         mi.pubdate = nowf()
         opf_path = os.path.join(dir, 'index.opf')
         ncx_path = os.path.join(dir, 'index.ncx')
@@ -1230,7 +1170,7 @@ class BasicNewsRecipe(Recipe):
 
         entries = ['index.html']
         toc = TOC(base_path=dir)
-        self.play_order_counter = 1
+        self.play_order_counter = 0
         self.play_order_map = {}
 
         def feed_index(num, parent):
@@ -1342,7 +1282,6 @@ class BasicNewsRecipe(Recipe):
         Create a list of articles from the list of feeds returned by :meth:`BasicNewsRecipe.get_feeds`.
         Return a list of :class:`Feed` objects.
         '''
-        print "\nweb.feeds.news:parse_feeds()\n"
         feeds = self.get_feeds()
         parsed_feeds = []
         for obj in feeds:

src/calibre/web/feeds/templates.py

@@ -120,6 +120,7 @@ class TouchscreenNavBarTemplate(Template):
             href = '%s%s/%s/index.html'%(prefix, up, next)
             navbar.text = '| '
             navbar.append(A('Next', href=href))
+
         href = '%s../index.html#article_%d'%(prefix, art)
         navbar.iterchildren(reversed=True).next().tail = ' | '
         navbar.append(A('Section Menu', href=href))
@@ -130,6 +131,7 @@ class TouchscreenNavBarTemplate(Template):
             href = '%s../article_%d/index.html'%(prefix, art-1)
             navbar.iterchildren(reversed=True).next().tail = ' | '
             navbar.append(A('Previous', href=href))
+
         navbar.iterchildren(reversed=True).next().tail = ' | '
         if not bottom:
             navbar.append(HR())
@@ -165,8 +167,14 @@ class TouchscreenIndexTemplate(Template):
     def _generate(self, title, masthead, datefmt, feeds, extra_css=None, style=None):
         if isinstance(datefmt, unicode):
             datefmt = datefmt.encode(preferred_encoding)
-        date = strftime(datefmt)
-        masthead_img = IMG(src=masthead,alt="masthead")
+        date = '%s, %s %s, %s' % (strftime('%A'), strftime('%B'), strftime('%d').lstrip('0'), strftime('%Y'))
+        masthead_p = etree.Element("p")
+        masthead_p.set("style","text-align:center")
+        masthead_img = etree.Element("img")
+        masthead_img.set("src",masthead)
+        masthead_img.set("alt","masthead")
+        masthead_p.append(masthead_img)
+
         head = HEAD(TITLE(title))
         if style:
             head.append(STYLE(style, type='text/css'))
@@ -178,11 +186,11 @@ class TouchscreenIndexTemplate(Template):
             if feed:
                 tr = TR()
                 tr.append(TD( CLASS('toc_item'), A(feed.title, href='feed_%d/index.html'%i)))
-                tr.append(TD( CLASS('article_count'),'%d' % len(feed.articles)))
+                tr.append(TD( CLASS('article_count'),'%3.3s' % len(feed.articles)))
                 toc.append(tr)
 
         div = DIV(
-                PT(masthead_img,style='text-align:center'),
+                masthead_p,
                 PT(date, style='text-align:center'),
                 toc,
                 CLASS('calibre_rescale_100'))

src/calibre/web/fetch/simple.py

@@ -329,7 +329,7 @@ class RecursiveFetcher(object):
             try:
                 data = self.fetch_url(iurl)
                 if data == 'GIF89a\x01':
-                    # Skip empty GIF files
+                    # Skip empty GIF files as PIL errors on them anyway
                     continue
             except Exception:
                 self.log.exception('Could not fetch image %s'% iurl)