Merge from trunk

resources/recipes/bighollywood.recipe

@@ -0,0 +1,63 @@
+__license__   = 'GPL v3'
+__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
+'''
+bighollywood.breitbart.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class BigHollywood(BasicNewsRecipe):
+    title                 = 'Big Hollywood'
+    __author__            = 'Darko Miletic'
+    description           = 'News and articles from the media world'
+    publisher             = 'Big Hollywood'
+    category              = 'news, media, art, literature, movies, politics, USA, Hollywood'
+    oldest_article        = 7
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    use_embedded_content  = False
+    language              = 'en'
+    remove_empty_feeds    = True
+    publication_type      = 'blog'
+    extra_css             = """
+                               body{font-family: Arial,sans-serif }
+                            """
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    keep_only_tags=[dict(attrs={'class':'postcontent'})]
+    remove_tags = [
+                     dict(name=['meta','link','link','iframe','embed','object'])
+                    ,dict(name='p', attrs={'class':['post_meta_links','postfooter']})
+                  ]
+    remove_attributes=['original','onclick']
+
+    feeds = [(u'Articles', u'http://bighollywood.breitbart.com/feed/')]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll('a'):
+            limg = item.find('img')
+            if item.string is not None:
+               str = item.string
+               item.replaceWith(str)
+            else:
+               if limg:
+                  if limg['src'].endswith('BlogPrintButton.png'):
+                     limg.extract()
+                  item.name = 'div'
+                  item.attrs = []
+               else:
+                   str = self.tag_to_string(item)
+                   item.replaceWith(str)
+        for item in soup.findAll('img'):
+            if not item.has_key('alt'):
+               item['alt'] = 'image'
+        return soup

resources/templates/fb2.xsl

@@ -254,6 +254,13 @@
 	<xsl:template match="fb:empty-line">
 		<br/>
 	</xsl:template>
+    <!-- super/sub-scripts -->
+    <xsl:template match="fb:sup">
+        <sup><xsl:apply-templates/></sup>
+    </xsl:template>
+    <xsl:template match="fb:sub">
+        <sub><xsl:apply-templates/></sub>
+    </xsl:template>
 	<!-- link -->
 	<xsl:template match="fb:a">
 		<xsl:element name="a">

setup/resources.py

@@ -6,7 +6,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
-import os, cPickle, re, anydbm, shutil
+import os, cPickle, re, anydbm, shutil, marshal
 from zlib import compress
 
 from setup import Command, basenames, __appname__
@@ -194,7 +194,7 @@ class Resources(Command):
     def kanwaout(self, out):
         dic = anydbm.open(out, 'c')
         for (k, v) in self.records.iteritems():
-            dic[k] = compress(cPickle.dumps(v, -1))
+            dic[k] = compress(marshal.dumps(v))
         dic.close()
 
 

src/calibre/ebooks/conversion/preprocess.py

@@ -264,10 +264,17 @@ class Dehyphenator(object):
 class CSSPreProcessor(object):
 
     PAGE_PAT   = re.compile(r'@page[^{]*?{[^}]*?}')
+    # Remove some of the broken CSS Microsoft products
+    # create, slightly dangerous as it removes to end of line
+    # rather than semi-colon
+    MS_PAT     = re.compile(r'^\s*(mso-|panose-).+?$',
+            re.MULTILINE|re.IGNORECASE)
 
     def __call__(self, data, add_namespace=False):
         from calibre.ebooks.oeb.base import XHTML_CSS_NAMESPACE
         data = self.PAGE_PAT.sub('', data)
+        if '\n' in data:
+            data = self.MS_PAT.sub('', data)
         if not add_namespace:
             return data
         ans, namespaced = [], False

src/calibre/ebooks/pml/input.py

@@ -1,4 +1,3 @@
-import os.path
 # -*- coding: utf-8 -*-
 
 __license__   = 'GPL v3'

src/calibre/ebooks/pml/output.py

@@ -50,7 +50,10 @@ class PMLOutput(OutputFormatPlugin):
             with open(os.path.join(tdir, 'index.pml'), 'wb') as out:
                 out.write(pml.encode(opts.pml_output_encoding, 'replace'))
 
-            self.write_images(oeb_book.manifest, pmlmlizer.image_hrefs, tdir, opts)
+            img_path = os.path.join(tdir, 'index_img')
+            if not os.path.exists(img_path):
+                os.makedirs(img_path)
+            self.write_images(oeb_book.manifest, pmlmlizer.image_hrefs, img_path, opts)
 
             log.debug('Compressing output...')
             pmlz = ZipFile(output_path, 'w')

src/calibre/ebooks/pml/pmlml.py

@@ -181,6 +181,9 @@ class PMLMLizer(object):
         for unused in anchors.difference(links):
             text = text.replace('\\Q="%s"' % unused, '')
             
+        # Remove \Cn tags that are within \x and \Xn tags
+        text = re.sub(ur'(?msu)(?P<t>\\(x|X[0-4]))(?P<a>.*?)(?P<c>\\C[0-4]\s*=\s*"[^"]*")(?P<b>.*?)(?P=t)', '\g<t>\g<a>\g<b>\g<t>', text)
+
         # Replace bad characters.
         text = text.replace(u'\xc2', '')
         text = text.replace(u'\xa0', ' ')
@@ -255,7 +258,12 @@ class PMLMLizer(object):
         # TOC markers.
         toc_name = elem.attrib.get('name', None)
         toc_id = elem.attrib.get('id', None)
-        if (toc_id or toc_name) and tag  not in ('h1', 'h2','h3','h4','h5','h6',):
+        # Only write the TOC marker if the tag isn't a heading and we aren't in one.
+        if (toc_id or toc_name) and tag not in ('h1', 'h2','h3','h4','h5','h6') and \
+            'x' not in tag_stack+tags and 'X0' not in tag_stack+tags and \
+            'X1' not in tag_stack+tags and 'X2' not in tag_stack+tags and \
+            'X3' not in tag_stack+tags and 'X4' not in tag_stack+tags:
+
             toc_page = page.href
             if self.toc.get(toc_page, None):
                 for toc_x in (toc_name, toc_id):
@@ -264,8 +272,8 @@ class PMLMLizer(object):
                         toc_depth = max(min(toc_depth, 4), 0)
                         text.append('\\C%s="%s"' % (toc_depth, toc_title))
 
-        # Process style information that needs holds a single tag
+        # Process style information that needs holds a single tag.
-        # Commented out because every page in an OEB book starts with this style
+        # Commented out because every page in an OEB book starts with this style.
         if style['page-break-before'] == 'always':
             text.append('\\p')
 

src/calibre/gui2/complete.py

@@ -160,6 +160,7 @@ class MultiCompleteComboBox(EnComboBox):
         c.setCaseSensitivity(Qt.CaseSensitive)
         self.dummy_model = CompleteModel(self)
         c.setModel(self.dummy_model)
+        self.lineEdit()._completer.setWidget(self)
 
     def update_items_cache(self, complete_items):
         self.lineEdit().update_items_cache(complete_items)

src/calibre/gui2/pictureflow/pictureflow.sip

@@ -1,7 +1,7 @@
 //Define the SIP wrapper to the pictureflow widget
 //Author - Kovid Goyal <kovid@kovidgoyal.net>
 
-%Module pictureflow 1
+%Module(name=pictureflow, version=1)
 
 %Import QtCore/QtCoremod.sip
 %Import QtGui/QtGuimod.sip

src/calibre/gui2/preferences/tweaks.py

@@ -260,6 +260,9 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
         self.restore_default_button.clicked.connect(self.restore_to_default)
         self.apply_button.clicked.connect(self.apply_tweak)
         self.plugin_tweaks_button.clicked.connect(self.plugin_tweaks)
+        self.splitter.setStretchFactor(0, 1)
+        self.splitter.setStretchFactor(1, 100)
+
 
     def plugin_tweaks(self):
         raw = self.tweaks.plugin_tweaks_string

src/calibre/gui2/preferences/tweaks.ui

@@ -13,8 +13,16 @@
   <property name="windowTitle">
    <string>Form</string>
   </property>
-  <layout class="QGridLayout" name="gridLayout_2">
+  <layout class="QVBoxLayout" name="verticalLayout_4">
-   <item row="0" column="0" rowspan="2">
+   <item>
+    <widget class="QSplitter" name="splitter">
+     <property name="orientation">
+      <enum>Qt::Horizontal</enum>
+     </property>
+     <property name="childrenCollapsible">
+      <bool>false</bool>
+     </property>
+     <widget class="QWidget" name="layoutWidget">
       <layout class="QVBoxLayout" name="verticalLayout_2">
        <item>
         <widget class="QLabel" name="label_18">
@@ -62,8 +70,10 @@
         </widget>
        </item>
       </layout>
-   </item>
+     </widget>
-   <item row="0" column="1">
+     <widget class="QWidget" name="layoutWidget">
+      <layout class="QVBoxLayout" name="verticalLayout_3">
+       <item>
         <widget class="QGroupBox" name="groupBox">
          <property name="title">
           <string>Help</string>
@@ -82,7 +92,7 @@
          </layout>
         </widget>
        </item>
-   <item row="1" column="1">
+       <item>
         <widget class="QGroupBox" name="groupBox_2">
          <property name="title">
           <string>Edit tweak</string>
@@ -120,6 +130,10 @@
        </item>
       </layout>
      </widget>
+    </widget>
+   </item>
+  </layout>
+ </widget>
  <resources/>
  <connections/>
 </ui>

src/calibre/gui2/progress_indicator/QProgressIndicator.sip

@@ -1,7 +1,7 @@
 //Define the SIP wrapper to the QProgressIndicator widget
 //Author - Kovid Goyal <kovid@kovidgoyal.net>
 
-%Module progress_indicator 1
+%Module(name=progress_indicator, version=1)
 
 %Import QtCore/QtCoremod.sip
 %Import QtGui/QtGuimod.sip

src/calibre/linux.py

@@ -186,6 +186,7 @@ class PostInstall:
             from calibre.ebooks.metadata.fetch import option_parser as fem_op
             from calibre.gui2.main import option_parser as guiop
             from calibre.utils.smtp import option_parser as smtp_op
+            from calibre.library.server.main import option_parser as serv_op
             from calibre.ebooks.epub.fix.main import option_parser as fix_op
             any_formats = ['epub', 'htm', 'html', 'xhtml', 'xhtm', 'rar', 'zip',
                 'txt', 'lit', 'rtf', 'pdf', 'prc', 'mobi', 'fb2', 'odt', 'lrf', 'snb']
@@ -208,6 +209,7 @@ class PostInstall:
                 f.write(opts_and_exts('ebook-viewer', viewer_op, any_formats))
                 f.write(opts_and_words('fetch-ebook-metadata', fem_op, []))
                 f.write(opts_and_words('calibre-smtp', smtp_op, []))
+                f.write(opts_and_words('calibre-server', serv_op, []))
                 f.write(opts_and_exts('epub-fix', fix_op, ['epub']))
                 f.write(textwrap.dedent('''
                 _ebook_device_ls()