Merge from trunk

recipes/rebelion.recipe

@@ -0,0 +1,34 @@
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import unicode_literals
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class RebelionRecipe (BasicNewsRecipe):
+   __author__ = u'Marc Busqué <marc@lamarciana.com>' #Thanks to atlantique http://www.mobileread.com/forums/member.php?u=67876
+   __url__ = 'http://www.lamarciana.com'
+   __version__ = '1.0'
+   __license__   = 'GPL v3'
+   __copyright__ = '2012, Marc Busqué <marc@lamarciana.com>'
+   title = u'Rebelion.org'
+   description = u'Rebelión pretende ser un medio de información alternativa que publique las noticias que no son consideradas importantes por los medios de comunicación tradicionales. También, dar a las noticias un tratamiento diferente en la línea de mostrar los intereses que los poderes económicos y políticos del mundo capitalista ocultan para mantener sus privilegios y el status actual. Queremos servir y ayudarnos de todos los grupos, colectivos y personas que trabajan por cambiar este mundo en una perspectiva radicalmente diferente, más justa, igualitaria y equilibrada social y ecológicamente. Es nuestro objetivo contar con la participación y colaboración de todos vosotros para que Rebelión sea un espacio serio, riguroso y actualizado en la difusión de noticias.'
+   url = 'http://www.rebelion.org'
+   language = 'es'
+   tags = 'contrainformación, información alternativa'
+   oldest_article = 1
+   remove_empty_feeds = True
+   encoding = 'latin1' #
+   keep_only_tags = [
+     {'name': 'div', 'attrs': {'id': 'CuerpoNoticia'}}
+   ]
+   no_stylesheets = True
+   extra_css = '.autor {font-style: italic;} .titulo {font-size: 150%;} .titulo, .pretitulo {text-align: center;} #TextoNoticia {text-align:justify;} .autor, .fuente, .entradilla {font-size: 90%; text-align: left;}'
+
+   feeds = [
+         (u'Titulares del día', u'http://www.rebelion.org/rss_portada.php'),
+         ]
+
+   #See http://www.mobileread.com/forums/showthread.php?t=174501
+   def print_version(self, url):
+      id = re.compile('\d*$').search(url).group()
+      return u'http://www.rebelion.org/noticia.php?id=%s' % id

src/calibre/devices/android/driver.py

@@ -177,7 +177,7 @@ class ANDROID(USBMS):
             'TELECHIP', 'HUAWEI', 'T-MOBILE', 'SEMC', 'LGE', 'NVIDIA',
             'GENERIC-', 'ZTE', 'MID', 'QUALCOMM', 'PANDIGIT', 'HYSTON',
             'VIZIO', 'GOOGLE', 'FREESCAL', 'KOBO_INC', 'LENOVO', 'ROCKCHIP',
-            'POCKET', 'ONDA_MID', 'ZENITHIN', 'INGENIC', 'PMID701C']
+            'POCKET', 'ONDA_MID', 'ZENITHIN', 'INGENIC', 'PMID701C', 'PD']
     WINDOWS_MAIN_MEM = ['ANDROID_PHONE', 'A855', 'A853', 'INC.NEXUS_ONE',
             '__UMS_COMPOSITE', '_MB200', 'MASS_STORAGE', '_-_CARD', 'SGH-I897',
             'GT-I9000', 'FILE-STOR_GADGET', 'SGH-T959_CARD', 'SGH-T959', 'SAMSUNG_ANDROID',
@@ -193,7 +193,7 @@ class ANDROID(USBMS):
             'GT-I9003_CARD', 'XT912', 'FILE-CD_GADGET', 'RK29_SDK', 'MB855',
             'XT910', 'BOOK_A10', 'USB_2.0_DRIVER', 'I9100T', 'P999DW',
             'KTABLET_PC', 'INGENIC', 'GT-I9001_CARD', 'USB_2.0_DRIVER',
-            'GT-S5830L_CARD']
+            'GT-S5830L_CARD', 'UNIVERSE']
     WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
             'FILE-STOR_GADGET', 'SGH-T959_CARD', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
             'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD',

src/calibre/ebooks/conversion/plugins/epub_output.py

@@ -312,13 +312,9 @@ class EPUBOutput(OutputFormatPlugin):
         Perform various markup transforms to get the output to render correctly
         in the quirky ADE.
         '''
-        from calibre.ebooks.oeb.base import XPath, XHTML, OEB_STYLES, barename, urlunquote
+        from calibre.ebooks.oeb.base import XPath, XHTML, barename, urlunquote
 
-        stylesheet = None
+        stylesheet = self.oeb.manifest.main_stylesheet
-        for item in self.oeb.manifest:
-            if item.media_type.lower() in OEB_STYLES:
-                stylesheet = item
-                break
 
         # ADE cries big wet tears when it encounters an invalid fragment
         # identifier in the NCX toc.

src/calibre/ebooks/conversion/plugins/pdf_output.py

@@ -99,12 +99,8 @@ class PDFOutput(OutputFormatPlugin):
 
         # Remove page-break-before on <body> element as it causes
         # blank pages in PDF Output
-        from calibre.ebooks.oeb.base import OEB_STYLES, XPath
+        from calibre.ebooks.oeb.base import XPath
-        stylesheet = None
+        stylesheet = self.oeb.manifest.main_stylesheet
-        for item in self.oeb.manifest:
-            if item.media_type.lower() in OEB_STYLES:
-                stylesheet = item
-                break
         if stylesheet is not None:
             from cssutils.css import CSSRule
             classes = set(['.calibre'])

src/calibre/ebooks/conversion/utils.py

@@ -5,7 +5,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
-import re
+import re, error as re_error
 from math import ceil
 from calibre.ebooks.conversion.preprocess import DocAnalysis, Dehyphenator
 from calibre.utils.logging import default_log
@@ -148,7 +148,7 @@ class HeuristicProcessor(object):
         return wordcount.words
 
     def markup_italicis(self, html):
-        self.log.debug("\n\n\nitalicize debugging \n\n\n")
+        #self.log.debug("\n\n\nitalicize debugging \n\n\n")
         ITALICIZE_WORDS = [
             'Etc.', 'etc.', 'viz.', 'ie.', 'i.e.', 'Ie.', 'I.e.', 'eg.',
             'e.g.', 'Eg.', 'E.g.', 'et al.', 'et cetera', 'n.b.', 'N.b.',
@@ -184,6 +184,9 @@ class HeuristicProcessor(object):
                 except OverflowError:
                     # match.group(0) was too large to be compiled into a regex
                     continue
+                except re_error:
+                    # the match was not a valid regular expression
+                    continue
 
         return html
 

src/calibre/ebooks/oeb/base.py

@@ -81,6 +81,23 @@ _css_url_re = re.compile(r'url\s*\([\'"]{0,1}(.*?)[\'"]{0,1}\)', re.I)
 _css_import_re = re.compile(r'@import "(.*?)"')
 _archive_re = re.compile(r'[^ ]+')
 
+# Tags that should not be self closed in epub output
+self_closing_bad_tags = {'a', 'abbr', 'address', 'article', 'aside', 'audio', 'b',
+'bdo', 'blockquote', 'body', 'button', 'cite', 'code', 'dd', 'del', 'details',
+'dfn', 'div', 'dl', 'dt', 'em', 'fieldset', 'figcaption', 'figure', 'footer',
+'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'header', 'hgroup', 'i', 'ins', 'kbd',
+'label', 'legend', 'li', 'map', 'mark', 'meter', 'nav', 'ol', 'output', 'p',
+'pre', 'progress', 'q', 'rp', 'rt', 'samp', 'section', 'select', 'small',
+'span', 'strong', 'sub', 'summary', 'sup', 'textarea', 'time', 'ul', 'var',
+'video'}
+
+_self_closing_pat = re.compile(
+    r'<(?P<tag>%s)(?=[\s/])(?P<arg>[^>]*)/>'%('|'.join(self_closing_bad_tags)),
+    re.IGNORECASE)
+
+def close_self_closing_tags(raw):
+    return _self_closing_pat.sub(r'<\g<tag>\g<arg>></\g<tag>>', raw)
+
 def iterlinks(root, find_links_in_css=True):
     '''
     Iterate over all links in a OEB Document.
@@ -938,13 +955,10 @@ class Manifest(object):
             if isinstance(data, etree._Element):
                 ans = xml2str(data, pretty_print=self.oeb.pretty_print)
                 if self.media_type in OEB_DOCS:
-                    # Convert self closing div|span|a|video|audio|iframe tags
+                    # Convert self closing div|span|a|video|audio|iframe|etc tags
                     # to normally closed ones, as they are interpreted
                     # incorrectly by some browser based renderers
-                    ans = re.sub(
+                    ans = close_self_closing_tags(ans)
-                        # tag name followed by either a space or a /
-                        r'<(?P<tag>div|a|span|video|audio|iframe)(?=[\s/])(?P<arg>[^>]*)/>',
-                        r'<\g<tag>\g<arg>></\g<tag>>', ans)
                 return ans
             if isinstance(data, unicode):
                 return data.encode('utf-8')
@@ -1142,6 +1156,19 @@ class Manifest(object):
             element(elem, OPF('item'), attrib=attrib)
         return elem
 
+    @dynamic_property
+    def main_stylesheet(self):
+        def fget(self):
+            ans = getattr(self, '_main_stylesheet', None)
+            if ans is None:
+                for item in self:
+                    if item.media_type.lower() in OEB_STYLES:
+                        ans = item
+                        break
+            return ans
+        def fset(self, item):
+            self._main_stylesheet = item
+        return property(fget=fget, fset=fset)
 
 class Spine(object):
     """Collection of manifest items composing an OEB data model book's main

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

@@ -378,7 +378,7 @@ class CSSFlattener(object):
         for child in node:
             self.flatten_node(child, stylizer, names, styles, psize, item_id, left)
 
-    def flatten_head(self, item, stylizer, href):
+    def flatten_head(self, item, href, global_href):
         html = item.data
         head = html.find(XHTML('head'))
         for node in head:
@@ -390,34 +390,56 @@ class CSSFlattener(object):
                  and node.get('type', CSS_MIME) in OEB_STYLES:
                 head.remove(node)
         href = item.relhref(href)
-        etree.SubElement(head, XHTML('link'),
+        l = etree.SubElement(head, XHTML('link'),
             rel='stylesheet', type=CSS_MIME, href=href)
-        stylizer.page_rule['margin-top'] = '%gpt'%\
+        l.tail='\n'
-                float(self.context.margin_top)
+        href = item.relhref(global_href)
-        stylizer.page_rule['margin-bottom'] = '%gpt'%\
+        l = etree.SubElement(head, XHTML('link'),
-                float(self.context.margin_bottom)
+            rel='stylesheet', type=CSS_MIME, href=href)
-
+        l.tail = '\n'
-        items = stylizer.page_rule.items()
-        items.sort()
-        css = '; '.join("%s: %s" % (key, val) for key, val in items)
-        style = etree.SubElement(head, XHTML('style'), type=CSS_MIME)
-        style.text = "\n\t\t@page { %s; }" % css
-        rules = [r.cssText for r in stylizer.font_face_rules]
-        raw = '\n\n'.join(rules)
-        # Make URLs referring to fonts relative to this item
-        sheet = cssutils.parseString(raw, validate=False)
-        cssutils.replaceUrls(sheet, item.relhref, ignoreImportRules=True)
-        style.text += '\n' + sheet.cssText
 
     def replace_css(self, css):
         manifest = self.oeb.manifest
-        id, href = manifest.generate('css', 'stylesheet.css')
         for item in manifest.values():
             if item.media_type in OEB_STYLES:
                 manifest.remove(item)
-        item = manifest.add(id, href, CSS_MIME, data=css)
+        id, href = manifest.generate('css', 'stylesheet.css')
+        item = manifest.add(id, href, CSS_MIME, data=cssutils.parseString(css,
+            validate=False))
+        self.oeb.manifest.main_stylesheet = item
         return href
 
+    def collect_global_css(self):
+        global_css = defaultdict(list)
+        for item in self.oeb.spine:
+            stylizer = self.stylizers[item]
+            stylizer.page_rule['margin-top'] = '%gpt'%\
+                    float(self.context.margin_top)
+            stylizer.page_rule['margin-bottom'] = '%gpt'%\
+                    float(self.context.margin_bottom)
+            items = stylizer.page_rule.items()
+            items.sort()
+            css = ';\n'.join("%s: %s" % (key, val) for key, val in items)
+            css = '@page {\n%s\n}\n'%css
+            rules = [r.cssText for r in stylizer.font_face_rules]
+            raw = '\n\n'.join(rules)
+            css += '\n\n' + raw
+            global_css[css].append(item)
+
+        gc_map = {}
+        manifest = self.oeb.manifest
+        for css in global_css:
+            id_, href = manifest.generate('page_css', 'page_styles.css')
+            manifest.add(id_, href, CSS_MIME, data=cssutils.parseString(css,
+                validate=False))
+            gc_map[css] = href
+
+        ans = {}
+        for css, items in global_css.iteritems():
+            for item in items:
+                ans[item] = gc_map[css]
+        return ans
+
     def flatten_spine(self):
         names = defaultdict(int)
         styles = {}
@@ -433,7 +455,8 @@ class CSSFlattener(object):
         items.sort()
         css = ''.join(".%s {\n%s;\n}\n\n" % (key, val) for key, val in items)
         href = self.replace_css(css)
+        global_css = self.collect_global_css()
         for item in self.oeb.spine:
             stylizer = self.stylizers[item]
-            self.flatten_head(item, stylizer, href)
+            self.flatten_head(item, href, global_css[item])
 

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

@@ -9,7 +9,7 @@ __docformat__ = 'restructuredtext en'
 
 from collections import Counter
 
-from calibre.ebooks.oeb.base import OEB_STYLES, barename, XPath
+from calibre.ebooks.oeb.base import barename, XPath
 
 class RemoveAdobeMargins(object):
     '''
@@ -51,10 +51,7 @@ class RemoveFakeMargins(object):
         self.stats = {}
         self.selector_map = {}
 
-        for item in self.oeb.manifest:
+        stylesheet = self.oeb.manifest.main_stylesheet
-            if item.media_type.lower() in OEB_STYLES:
-                stylesheet = item
-                break
         if stylesheet is None:
             return
 

src/calibre/gui2/preferences/coloring.py

@@ -259,33 +259,36 @@ class RuleEditor(QDialog): # {{{
         l.addWidget(l3, 2, 2)
 
         self.color_box = QComboBox(self)
+        self.color_label = QLabel('Sample text Sample text')
+        self.color_label.setTextFormat(Qt.RichText)
         l.addWidget(self.color_box, 2, 3)
-        l.addItem(QSpacerItem(10, 10, QSizePolicy.Expanding), 2, 4)
+        l.addWidget(self.color_label, 2, 4)
+        l.addItem(QSpacerItem(10, 10, QSizePolicy.Expanding), 2, 5)
 
         self.l4 = l4 = QLabel(
             _('Only if the following conditions are all satisfied:'))
-        l.addWidget(l4, 3, 0, 1, 5)
+        l.addWidget(l4, 3, 0, 1, 6)
 
         self.scroll_area = sa = QScrollArea(self)
         sa.setMinimumHeight(300)
         sa.setMinimumWidth(950)
         sa.setWidgetResizable(True)
-        l.addWidget(sa, 4, 0, 1, 5)
+        l.addWidget(sa, 4, 0, 1, 6)
 
         self.add_button = b = QPushButton(QIcon(I('plus.png')),
                 _('Add another condition'))
-        l.addWidget(b, 5, 0, 1, 5)
+        l.addWidget(b, 5, 0, 1, 6)
         b.clicked.connect(self.add_blank_condition)
 
         self.l5 = l5 = QLabel(_('You can disable a condition by'
             ' blanking all of its boxes'))
-        l.addWidget(l5, 6, 0, 1, 5)
+        l.addWidget(l5, 6, 0, 1, 6)
 
         self.bb = bb = QDialogButtonBox(
                 QDialogButtonBox.Ok|QDialogButtonBox.Cancel)
         bb.accepted.connect(self.accept)
         bb.rejected.connect(self.reject)
-        l.addWidget(bb, 7, 0, 1, 5)
+        l.addWidget(bb, 7, 0, 1, 6)
 
         self.conditions_widget = QWidget(self)
         sa.setWidget(self.conditions_widget)
@@ -308,8 +311,21 @@ class RuleEditor(QDialog): # {{{
         self.color_box.addItems(QColor.colorNames())
         self.color_box.setCurrentIndex(0)
 
+        self.update_color_label()
+        self.color_box.currentIndexChanged.connect(self.update_color_label)
         self.resize(self.sizeHint())
 
+    def update_color_label(self):
+        pal = QApplication.palette()
+        bg1 = unicode(pal.color(pal.Base).name())
+        bg2 = unicode(pal.color(pal.AlternateBase).name())
+        c = unicode(self.color_box.currentText())
+        self.color_label.setText('''
+            <span style="color: {c}; background-color: {bg1}">&nbsp;{st}&nbsp;</span>
+            <span style="color: {c}; background-color: {bg2}">&nbsp;{st}&nbsp;</span>
+            '''.format(c=c, bg1=bg1, bg2=bg2, st=_('Sample Text')))
+
+
     def add_blank_condition(self):
         c = ConditionEditor(self.fm, parent=self.conditions_widget)
         self.conditions.append(c)
@@ -617,7 +633,7 @@ if __name__ == '__main__':
 
     db = db()
 
-    if False:
+    if True:
         d = RuleEditor(db.field_metadata)
         d.add_blank_condition()
         d.exec_()

src/calibre/gui2/update.py

@@ -9,7 +9,7 @@ import mechanize
 
 from calibre.constants import (__appname__, __version__, iswindows, isosx,
         isportable)
-from calibre import browser
+from calibre import browser, prints, as_unicode
 from calibre.utils.config import prefs
 from calibre.gui2 import config, dynamic, open_url
 from calibre.gui2.dialogs.plugin_updater import get_plugin_updates_available
@@ -45,14 +45,14 @@ class CheckForUpdates(QThread):
                 version = get_newest_version()
                 if version and version != __version__ and len(version) < 10:
                     calibre_update_version = version
-            except:
+            except Exception as e:
-                traceback.print_exc()
+                prints('Failed to check for calibre update:', as_unicode(e))
             try:
                 update_plugins = get_plugin_updates_available()
                 if update_plugins is not None:
                     plugins_update_found = len(update_plugins)
-            except:
+            except Exception as e:
-                traceback.print_exc()
+                prints('Failed to check for plugin update:', as_unicode(e))
             if (calibre_update_version != NO_CALIBRE_UPDATE or
                     plugins_update_found > 0):
                 self.update_found.emit('%s%s%d'%(calibre_update_version,