Sync to trunk

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.4.126'
+__version__   = '0.4.127'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 '''
 Various run time constants.

src/calibre/devices/interface.py

@@ -41,6 +41,20 @@ class Device(object):
         '''Return the FDI description of this device for HAL on linux.'''
         return ''
     
+    @classmethod
+    def can_handle(cls, device_info):
+        '''
+        Optional method to perform further checks on a device to see if this driver
+        is capable of handling it. If it is not it should return False. This method
+        is only called after the vendor, product ids and the bcd have matched, so
+        it can do some relatively time intensive checks. The default implementation
+        returns True.
+        
+        :param device_info: On windows a device ID string. On Unix a tuple of 
+        ``(vendor_id, product_id, bcd)``. 
+        '''
+        return True
+    
     def open(self):
         '''
         Perform any device specific initialization. Called after the device is

src/calibre/devices/scanner.py

@@ -63,12 +63,14 @@ class DeviceScanner(object):
             for device_id in self.devices:
                 if vid in device_id and pid in device_id:
                     if self.test_bcd_windows(device_id, getattr(device, 'BCD', None)):
-                        return True
+                        if device.can_handle(device_id):
+                            return True
         else:
             for vendor, product, bcdDevice in self.devices:
                 if device.VENDOR_ID == vendor and device.PRODUCT_ID == product:
                     if self.test_bcd(bcdDevice, getattr(device, 'BCD', None)):
-                        return True
+                        if device.can_handle((vendor, product, bcdDevice)):
+                            return True
         return False
 
 

src/calibre/ebooks/epub/from_any.py

@@ -67,6 +67,7 @@ def txt2opf(path, tdir, opts):
 def pdf2opf(path, tdir, opts):
     from calibre.ebooks.lrf.pdf.convert_from import generate_html
     generate_html(path, tdir)
+    opts.dont_split_on_page_breaks = True
     return os.path.join(tdir, 'metadata.opf')
 
 def epub2opf(path, tdir, opts):

src/calibre/ebooks/html.py

@@ -560,7 +560,7 @@ class Processor(Parser):
                 hr = etree.Element('hr')
                 if elem.getprevious() is None:
                     elem.getparent()[:0] = [hr]
-                else:
+                elif elem.getparent() is not None:
                     insert = None
                     for i, c in enumerate(elem.getparent()):
                         if c is elem:
@@ -796,7 +796,18 @@ class Processor(Parser):
                 setting = ''
             face = font.attrib.pop('face', None)
             if face is not None:
-                setting += 'font-face:%s;'%face
+                faces = []
+                for face in face.split(','):
+                    if ' ' in face:
+                        face = "%s" % face
+                    faces.append(face)
+                for generic in ('serif', 'sans-serif', 'monospace'):
+                    if generic in faces:
+                        break
+                else:
+                    faces.append('serif')
+                family = ', '.join(faces)
+                setting += 'font-family: %s;' % family
             color = font.attrib.pop('color', None)
             if color is not None:
                 setting += 'color:%s'%color

src/calibre/ebooks/lrf/comic/convert_from.py

@@ -425,7 +425,7 @@ def do_convert(path_to_file, opts, notification=lambda m, p: p, output_format='l
     thumbnail = None
     if not pages:
         raise ValueError('Could not find any pages in the comic: %s'%source)
-    if not opts.no_process:
+    if not getattr(opts, 'no_process', False):
         pages, failures, tdir2 = process_pages(pages, opts, notification)
         if not pages:
             raise ValueError('Could not find any valid pages in the comic: %s'%source)

src/calibre/ebooks/pdf/pdftrim.py

@@ -29,7 +29,7 @@ def config(defaults=None):
     c.add_opt('top_right_y', [ '-w', '--righty'], default=default_crop,
           help=_('Number of pixels to crop from the right most y (default is %d)')%default_crop )
     c.add_opt('bounding', ['-b', '--bounding'],
-          help=_('A file generated by ghostscript which allows each page to be individually cropped'))
+          help=_('A file generated by ghostscript which allows each page to be individually cropped [gs -dSAFER -dNOPAUSE -dBATCH -sDEVICE=bbox > bounding] '))
     return c
 
 
@@ -38,14 +38,24 @@ def option_parser():
     return c.option_parser(usage=_('''\
 	%prog [options] file.pdf
 
-	Crop a pdf. 
+	Crops a pdf. 
 	'''))
 
 def main(args=sys.argv):
     parser = option_parser()
     opts, args = parser.parse_args(args)
-    source = os.path.abspath(args[1])
+    try:
-    input_pdf = PdfFileReader(file(source, "rb"))
+        source = os.path.abspath(args[1])
+        input_pdf = PdfFileReader(file(source, "rb"))
+    except:
+        print "Unable to read input"
+	return 2
+    info = input_pdf.getDocumentInfo()
+    title   = 'Unknown'
+    author  = 'Unknown'
+    if info.title:
+       title   = info.title
+       author  = info.author
     if opts.bounding != None:
         try:
             bounding = open( opts.bounding , 'r' )
@@ -53,7 +63,7 @@ def main(args=sys.argv):
         except:
             print 'Error opening %s' % opts.bounding 
             return 1
-    output_pdf = PdfFileWriter()
+    output_pdf = PdfFileWriter(title=title,author=author)
     for page_number in range (0, input_pdf.getNumPages() ):
         page = input_pdf.getPage(page_number)
         if opts.bounding != None:

src/calibre/gui2/dialogs/scheduler.py

@@ -75,7 +75,13 @@ def save_recipes(recipes):
     
 def load_recipes():
     config.refresh()
-    return [Recipe().unpickle(r) for r in config.get('scheduled_recipes', [])]
+    recipes = []
+    for r in config.get('scheduled_recipes', []):
+        r = Recipe().unpickle(r)
+        if r.builtin and not str(r.id).startswith('recipe_'):
+            continue
+        recipes.append(r)
+    return recipes
 
 class RecipeModel(QAbstractListModel, SearchQueryParser):
     
@@ -438,7 +444,7 @@ class Scheduler(QObject):
             self.lock.unlock()
 
 def main(args=sys.argv):
-    app = QApplication([])
+    QApplication([])
     from calibre.library.database2 import LibraryDatabase2
     d = SchedulerDialog(LibraryDatabase2('/home/kovid/documents/library'))
     d.exec_()

src/calibre/trac/donations/server.py

@@ -217,8 +217,7 @@ class Server(object):
                     pos = pos.replace(month = 1)
                 else:
                     pos = pos.replace(month = pos.month + 1)
-
+        _months = list(months(self.earliest, self.latest))[:-1][-12:]
-        _months = list(months(self.earliest, self.latest))[:-1][:12]
         _months = [range_for_month(*m) for m in _months]
         _months = [self.get_slice(*m) for m in _months]
         x = [m.min for m in _months]

src/calibre/trac/plugins/download.py

@@ -35,7 +35,7 @@ class Distribution(object):
         ('xdg-utils', '1.0.2', 'xdg-utils', 'xdg-utils', 'xdg-utils'),
         ('dbus-python', '0.82.2', 'dbus-python', 'python-dbus', 'dbus-python'),
         ('lxml', '2.0.5', 'lxml', 'python-lxml', 'python-lxml'),
-        ('BeautifulSoup', '3.0.5', 'beautifulsoup', 'python-beautifulsoup', 'python-beautifulsoup'),
+        ('BeautifulSoup', '3.0.5', 'beautifulsoup', 'python-beautifulsoup', 'python-BeautifulSoup'),
         ('help2man', '1.36.4', 'help2man', 'help2man', 'help2man'),
         ]
     

src/calibre/web/feeds/news.py

@@ -765,6 +765,8 @@ class BasicNewsRecipe(object, LoggingInterface):
             self.log_debug(traceback.format_exc())
         if cu is not None:
             ext = cu.rpartition('.')[-1]
+            if '?' in ext:
+                ext = ''
             ext = ext.lower() if ext else 'jpg'
             self.report_progress(1, _('Downloading cover from %s')%cu)
             cpath = os.path.join(self.output_dir, 'cover.'+ext)

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

@@ -21,7 +21,7 @@ recipe_modules = ['recipe_' + r for r in (
            'linux_magazine', 'telegraph_uk', 'utne', 'sciencedaily', 'forbes',
            'time_magazine', 'endgadget', 'fudzilla', 'nspm_int', 'nspm', 'pescanik',
            'spiegel_int', 'themarketticker', 'tomshardware', 'xkcd', 'ftd', 'zdnet',
-           'joelonsoftware',
+           'joelonsoftware', 'telepolis', 'common_dreams',
           )]
 
 import re, imp, inspect, time, os

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

@@ -42,3 +42,9 @@ class ChristianScienceMonitor(BasicNewsRecipe):
                     feeds[-1][1].append(art)
         return feeds
       
+    def postprocess_html(self, soup, first_fetch):
+        html = soup.find('html')
+        if html is None:
+            return soup
+        html.extract()
+        return html

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

@@ -0,0 +1,16 @@
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class CommonDreams(BasicNewsRecipe):
+    title          = u'Common Dreams'
+    description    = u'Progressive news and views'
+    __author__     = u'XanthanGum'
+    oldest_article = 7
+    max_articles_per_feed = 100
+    
+    feeds          = [
+                       (u'Common Dreams Headlines', 
+                       u'http://www.commondreams.org/feed/headlines_rss'), 
+                       (u'Common Dreams Views', u'http://www.commondreams.org/feed/views_rss'), 
+                       (u'Common Dreams Newswire', u'http://www.commondreams.org/feed/newswire_rss')
+                       ]

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

@@ -49,8 +49,10 @@ class Economist(BasicNewsRecipe):
                 if not index_started:
                     continue
                 text = string.capwords(text)
-                feeds[text] = []
+                if text not in feeds.keys():
-                ans.append(text)
+                    feeds[text] = []
+                if text not in ans:
+                    ans.append(text)
                 key = text
                 continue
             if key is None:

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

@@ -0,0 +1,34 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.heise.de/tp
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Telepolis(BasicNewsRecipe):
+    title                 = 'Telepolis'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Germany in German'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+    
+    html2lrf_options = [  '--comment'       , description
+                        , '--category'      , 'blog,news'
+                       ]
+
+    keep_only_tags = [
+                       dict(name='table', attrs={'class':'inhalt-table'})
+                      ,dict(name='table', attrs={'class':'blogtable'   })
+                     ]
+    remove_tags = [
+                     dict(name='table', attrs={'class':'img'    })
+                    ,dict(name='img'  , attrs={'src':'/tp/r4/icons/inline/extlink.gif'})
+                  ]
+
+    feeds       = [(u'Telepolis Newsfeed', u'http://www.heise.de/tp/news.rdf')]

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

@@ -33,6 +33,7 @@ class TimesOnline(BasicNewsRecipe):
                         ('Sports News', 'http://www.timesonline.co.uk/tol/feeds/rss/sport.xml'),
                         ('Film News', 'http://www.timesonline.co.uk/tol/feeds/rss/film.xml'),
                         ('Tech news', 'http://www.timesonline.co.uk/tol/feeds/rss/tech.xml'),
+                        ('Literary Supplement', 'http://www.timesonline.co.uk/tol/feeds/rss/thetls.xml'),
                      ]
 
     def print_version(self, url):

src/pyPdf/pdf.py

@@ -55,7 +55,7 @@ from utils import readNonWhitespace, readUntilWhitespace, ConvertFunctionsToVirt
 # This class supports writing PDF files out, given pages produced by another
 # class (typically {@link #PdfFileReader PdfFileReader}).
 class PdfFileWriter(object):
-    def __init__(self):
+    def __init__(self,title=u"Unknown",author=u"Unknown"):
         self._header = "%PDF-1.3"
         self._objects = []  # array of indirect objects
 
@@ -71,7 +71,9 @@ class PdfFileWriter(object):
         # info object
         info = DictionaryObject()
         info.update({
-                NameObject("/Producer"): createStringObject(u"Python PDF Library - http://pybrary.net/pyPdf/")
+                NameObject("/Producer"): createStringObject(u"Python PDF Library - http://pybrary.net/pyPdf/"),
+                NameObject("/Author"): createStringObject(author),
+                NameObject("/Title"): createStringObject(title),
                 })
         self._info = self._addObject(info)