Content server:Set metadata in EPUB files before sending. Fixes #2734 (Wrong ebook title/author)

src/calibre/ebooks/oeb/reader.py

@@ -192,6 +192,7 @@ class OEBReader(object):
                         if not scheme and href not in known:
                             new.add(href)
             unchecked.clear()
+            warned = set([])
             for href in new:
                 known.add(href)
                 is_invalid = False
@@ -202,9 +203,13 @@ class OEBReader(object):
                 if is_invalid:
                     continue
                 if not self.oeb.container.exists(href):
-                    self.logger.warn('Referenced file %r not found' % href)
+                    if href not in warned:
+                        self.logger.warn('Referenced file %r not found' % href)
+                        warned.add(href)
                     continue
-                self.logger.warn('Referenced file %r not in manifest' % href)
+                if href not in warned:
+                    self.logger.warn('Referenced file %r not in manifest' % href)
+                    warned.add(href)
                 id, _ = manifest.generate(id='added')
                 guessed = guess_type(href)[0]
                 media_type = guessed or BINARY_MIME

src/calibre/gui2/library.py

@@ -15,6 +15,7 @@ from PyQt4.QtCore import QAbstractTableModel, QVariant, Qt, QString, \
 
 from calibre import strftime
 from calibre.ptempfile import PersistentTemporaryFile
+from calibre.utils.pyparsing import ParseException
 from calibre.library.database2 import FIELD_MAP
 from calibre.gui2 import NONE, TableView, qstring_to_unicode, config, \
                          error_dialog
@@ -240,7 +241,11 @@ class BooksModel(QAbstractTableModel):
             self.count_changed()
 
     def search(self, text, refinement, reset=True):
-        self.db.search(text)
+        try:
+            self.db.search(text)
+        except ParseException:
+            self.emit(SIGNAL('parse_exception()'))
+            return
         self.last_search = text
         if reset:
             self.clear_caches()
@@ -856,7 +861,12 @@ class DeviceBooksModel(BooksModel):
         if not text or not text.strip():
             self.map = list(range(len(self.db)))
         else:
-            matches = self.search_engine.parse(text)
+            try:
+                matches = self.search_engine.parse(text)
+            except ParseException:
+                self.emit(SIGNAL('parse_exception()'))
+                return
+
             self.map = []
             for i in range(len(self.db)):
                 if i in matches:

src/calibre/library/server.py

@@ -221,9 +221,20 @@ class LibraryServer(object):
 
     def get_format(self, id, format):
         format = format.upper()
-        fmt = self.db.format(id, format, index_is_id=True, as_file=True, mode='rb')
+        fmt = self.db.format(id, format, index_is_id=True, as_file=True,
+                mode='r+b')
         if fmt is None:
             raise cherrypy.HTTPError(404, 'book: %d does not have format: %s'%(id, format))
+        if format == 'EPUB':
+            from tempfile import TemporaryFile
+            from calibre.ebooks.metadata.meta import set_metadata
+            raw = fmt.read()
+            fmt = TemporaryFile()
+            fmt.write(raw)
+            fmt.seek(0)
+            set_metadata(fmt, self.db.get_metadata(id, index_is_id=True),
+                    'epub')
+            fmt.seek(0)
         mt = guess_type('dummy.'+format.lower())[0]
         if mt is None:
             mt = 'application/octet-stream'

src/calibre/web/feeds/recipes/recipe_wsj.py

@@ -10,17 +10,31 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class WallStreetJournal(BasicNewsRecipe):
 
         title = 'The Wall Street Journal'
-        __author__ = 'Kovid Goyal'
+        __author__ = 'Kovid Goyal and Sujata Raman'
         description = 'News and current affairs.'
         needs_subscription = True
         language = _('English')
         max_articles_per_feed = 10
         timefmt  = ' [%a, %b %d, %Y]'
         no_stylesheets = True
+
+        extra_css      = '''h1{color:#093D72 ; font-size:large ; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; }
+                        h2{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
+                        .subhead{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
+                        .insettipUnit {color:#666666; font-family:Arial,Sans-serif;font-size:xx-small }
+                        .targetCaption{ font-size:x-small; color:#333333; font-family:Arial,Helvetica,sans-serif}
+                        .article{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
+                        .tagline {color:#333333; font-size:xx-small}
+                        .dateStamp {color:#666666; font-family:Arial,Helvetica,sans-serif}
+                         h3{color:blue ;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
+                         .byline{color:blue;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
+                         h6{color:#333333; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small;font-style:italic; }
+                        .paperLocation{color:#666666; font-size:xx-small}'''
+
         remove_tags_before = dict(name='h1')
         remove_tags = [
-                       dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive"]),
+                       dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive","articleTabs_tab_video","articleTabs_tab_map","articleTabs_tab_slideshow"]),
-                       {'class':['more_in', "insetContent", 'articleTools_bottom', 'aTools', "tooltip", "adSummary", "nav-inline"]},
+                       {'class':['footer_columns','network','insetCol3wide','interactive','video','slideshow','map','insettip','more_in', "insetContent", 'articleTools_bottom', 'aTools', "tooltip", "adSummary", "nav-inline"]},
                        dict(rel='shortcut icon'),
                       ]
         remove_tags_after = [dict(id="article_story_body"), {'class':"article story"},]