Sync to pluginize

installer/windows/freeze.py

@@ -11,6 +11,7 @@ LIBUSB_DIR       = 'C:\\libusb'
 LIBUNRAR         = 'C:\\Program Files\\UnrarDLL\\unrar.dll'
 PDFTOHTML        = 'C:\\cygwin\\home\\kovid\\poppler-0.10.6\\rel\\pdftohtml.exe'
 IMAGEMAGICK_DIR  = 'C:\\ImageMagick'
+PDFTK            = 'C:\\pdftk.exe'
 FONTCONFIG_DIR   = 'C:\\fontconfig'
 VC90             = r'C:\VC90.CRT'
 
@@ -100,6 +101,9 @@ class BuildEXE(py2exe.build_exe.py2exe):
         shutil.copyfile(PDFTOHTML, os.path.join(PY2EXE_DIR, os.path.basename(PDFTOHTML)))
         shutil.copyfile(PDFTOHTML+'.manifest', os.path.join(PY2EXE_DIR,
             os.path.basename(PDFTOHTML)+'.manifest'))
+        print '\tAdding pdftk'
+        shutil.copyfile(PDFTK, os.path.join(PY2EXE_DIR, os.path.basename(PDFTK)))
+
         print '\tAdding ImageMagick'
         for f in os.listdir(IMAGEMAGICK_DIR):
             shutil.copyfile(os.path.join(IMAGEMAGICK_DIR, f), os.path.join(PY2EXE_DIR, f))

src/calibre/constants.py

@@ -2,7 +2,7 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.5.10'
+__version__   = '0.5.11'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 '''
 Various run time constants.

src/calibre/ebooks/metadata/pdf.py

@@ -17,6 +17,7 @@ try:
     _imagemagick_loaded = True
 except:
     _imagemagick_loaded = False
+from calibre.utils.pdftk import set_metadata as pdftk_set_metadata
 
 def get_metadata(stream, extract_cover=True):
     """ Return metadata as a L{MetaInfo} object """
@@ -67,6 +68,13 @@ class MetadataWriter(Thread):
 
 def set_metadata(stream, mi):
     stream.seek(0)
+    try:
+        pdftk_set_metadata(stream, mi)
+    except:
+        pass
+    else:
+        return
+
     # Use a StringIO object for the pdf because we will want to over
     # write it later and if we are working on the stream directly it
     # could cause some issues.
@@ -98,13 +106,13 @@ def get_cover(stream):
         with StreamReadWrapper(stream) as stream:
             pdf = PdfFileReader(stream)
             output = PdfFileWriter()
-    
+
             if len(pdf.pages) >= 1:
                 output.addPage(pdf.getPage(0))
-    
+
                 with TemporaryDirectory('_pdfmeta') as tdir:
                     cover_path = os.path.join(tdir, 'cover.pdf')
-    
+
                     with open(cover_path, "wb") as outputStream:
                         output.write(outputStream)
                     with ImageMagick():

src/calibre/parallel.py

@@ -49,7 +49,7 @@ PARALLEL_FUNCS = {
 
       'ebook-convert'     :
         ('calibre.ebooks.conversion.cli', 'main', {}, None),
-        
+
       'gui_convert'     :
         ('calibre.gui2.convert.gui_conversion', 'gui_convert', {}, 'notification'),
 }
@@ -142,8 +142,10 @@ class WorkerMother(object):
                 self.gui_executable = os.path.join(contents, 'MacOS',
                                                os.path.basename(sys.executable))
                 contents = os.path.join(contents, 'console.app', 'Contents')
-                self.executable = os.path.join(contents, 'MacOS',
-                                               os.path.basename(sys.executable))
+                exe = os.path.basename(sys.executable)
+                if 'python' not in exe:
+                    exe = 'python'
+                self.executable = os.path.join(contents, 'MacOS', exe)
 
                 resources = os.path.join(contents, 'Resources')
                 fd = os.path.join(contents, 'Frameworks')
@@ -479,9 +481,9 @@ class Overseer(object):
                     self.job.update_status(percent, msg)
             elif word == 'ERROR':
                 self.write('OK')
-                exception, traceback = cPickle.loads(msg)
-                self.job.output(u'%s\n%s'%(exception, traceback))
-                self.job.exception, self.job.traceback = exception, traceback
+                exception, tb = cPickle.loads(msg)
+                self.job.output(u'%s\n%s'%(exception, tb))
+                self.job.exception, self.job.traceback = exception, tb
                 return True
             else:
                 self.terminate()

src/calibre/ptempfile.py

@@ -1,8 +1,8 @@
 from __future__ import with_statement
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
-""" 
-Provides platform independent temporary files that persist even after 
+"""
+Provides platform independent temporary files that persist even after
 being closed.
 """
 import tempfile, os, atexit, shutil
@@ -15,38 +15,38 @@ def cleanup(path):
         if os.path.exists(path):
             os.remove(path)
     except:
-        pass   
-    
+        pass
+
 class PersistentTemporaryFile(object):
-    """ 
+    """
     A file-like object that is a temporary file that is available even after being closed on
     all platforms. It is automatically deleted on normal program termination.
     """
     _file = None
-    
+
     def __init__(self, suffix="", prefix="", dir=None, mode='w+b'):
-        if prefix == None: 
+        if prefix == None:
             prefix = ""
         fd, name = tempfile.mkstemp(suffix, __appname__+"_"+ __version__+"_" + prefix,
                                     dir=dir)
-        self._file = os.fdopen(fd, 'w+b')
+        self._file = os.fdopen(fd, mode)
         self._name = name
         atexit.register(cleanup, name)
-        
+
     def __getattr__(self, name):
         if name == 'name':
             return self.__dict__['_name']
         return getattr(self.__dict__['_file'], name)
-    
+
     def __enter__(self):
         return self
-    
+
     def __exit__(self, *args):
         self.close()
-        
+
     def __del__(self):
         self.close()
-          
+
 
 def PersistentTemporaryDirectory(suffix='', prefix='', dir=None):
     '''
@@ -66,12 +66,37 @@ class TemporaryDirectory(object):
         self.prefix = prefix
         self.dir = dir
         self.keep = keep
-    
+
     def __enter__(self):
         self.tdir = tempfile.mkdtemp(self.suffix, __appname__+"_"+ __version__+"_" +self.prefix, self.dir)
         return self.tdir
-    
+
     def __exit__(self, *args):
         if not self.keep and os.path.exists(self.tdir):
             shutil.rmtree(self.tdir, ignore_errors=True)
-            
+
+class TemporaryFile(object):
+
+    def __init__(self, suffix="", prefix="", dir=None, mode='w+b'):
+        if prefix == None:
+            prefix = ''
+        if suffix is None:
+            suffix = ''
+        self.prefix, self.suffix, self.dir, self.mode = prefix, suffix, dir, mode
+        self._file = None
+
+    def __enter__(self):
+        fd, name = tempfile.mkstemp(self.suffix,
+                __appname__+"_"+ __version__+"_" + self.prefix,
+                                    dir=self.dir)
+        self._file = os.fdopen(fd, self.mode)
+        self._name = name
+        self._file.close()
+        return name
+
+    def __exit__(self, *args):
+        cleanup(self._name)
+
+
+
+

src/calibre/trac/plugins/download.py

@@ -20,6 +20,7 @@ DEPENDENCIES = [
             ('BeautifulSoup', '3.0.5', 'beautifulsoup', 'python-beautifulsoup', 'python-BeautifulSoup'),
             ('dnspython', '1.6.0', 'dnspython', 'dnspython', 'dnspython', 'dnspython'),
             ('poppler', '0.10.5', 'poppler', 'poppler', 'poppler', 'poppler'),
+            ('pdftk', '1.12', 'pdftk', 'pdftk', 'pdftk', 'pdftk'),
             ]
 
 

src/calibre/utils/pdftk.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import with_statement
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
+__docformat__ = 'restructuredtext en'
+
+
+import sys, subprocess, os, errno
+from functools import partial
+from contextlib import nested
+
+from calibre.ptempfile import TemporaryFile
+from calibre.constants import iswindows
+
+PDFTK = 'pdftk'
+popen = subprocess.Popen
+#if isosx and hasattr(sys, 'frameworks_dir'):
+#    PDFTK = os.path.join(getattr(sys, 'frameworks_dir'), 'pdftk')
+if iswindows and hasattr(sys, 'frozen'):
+    PDFTK = os.path.join(os.path.dirname(sys.executable), 'pdftk.exe')
+    popen = partial(subprocess.Popen, creationflags=0x08) # CREATE_NO_WINDOW=0x08 so that no ugly console is popped up
+
+class PdftkError(Exception): pass
+
+def mi_to_info(mi):
+    ans = []
+    if mi.title:
+        ans.extend(('InfoKey: Title', 'InfoValue: '+mi.title))
+    if mi.authors:
+        from calibre.ebooks.metadata import authors_to_string
+        ans.extend(('InfoKey: Author', 'InfoValue: ' +
+            authors_to_string(mi.authors)))
+    return u'\n'.join(ans)
+
+def set_metadata(stream, mi):
+    raw = mi_to_info(mi)
+    if not raw: return
+    raw = raw.encode('utf-8')
+    with nested(TemporaryFile('.pdf'), TemporaryFile('.pdf'),
+            TemporaryFile('.info')) as (input, output, meta):
+        oi = getattr(stream, 'name', None)
+        if not oi or not os.access(oi, os.R_OK):
+            stream.seek(0)
+            with open(input, 'wb') as f: f.write(stream.read())
+        else:
+            input = oi
+        with open(meta, 'wb') as f: f.write(raw)
+        if os.path.exists(output):
+            os.remove(output)
+        cmd = (PDFTK, input, 'update_info', meta, 'output', output)
+        p = popen(cmd)
+
+        while True:
+            try:
+                ret = p.wait()
+                break
+            except OSError, e:
+                if e.errno == errno.EINTR:
+                    continue
+                else:
+                    raise
+
+        if os.stat(output).st_size < 2048:
+            raise PdftkError('Output file too small')
+
+        with open(output, 'rb') as f: raw = f.read()
+        if raw:
+            stream.seek(0)
+            stream.truncate()
+            stream.write(raw)
+            stream.flush()
+
+if __name__ == '__main__':
+    args = sys.argv
+    from calibre.ebooks.metadata import MetaInformation
+    mi = MetaInformation(args[2], [args[3]])
+    x = open(args[1], 'r+b')
+    set_metadata(x, mi)

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

@@ -42,6 +42,7 @@ recipe_modules = ['recipe_' + r for r in (
            'moneynews', 'der_standard', 'diepresse', 'nzz_ger', 'hna',
            'seattle_times', 'scott_hanselman', 'coding_horror', 'twitchfilms',
            'stackoverflow', 'telepolis_artikel', 'zaobao', 'usnews',
+           'straitstimes',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,56 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+www.straitstimes.com
+'''
+
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class StraitsTimes(BasicNewsRecipe):
+    title                  = 'The Straits Times'
+    __author__             = 'Darko Miletic'
+    description            = 'Singapore newspaper'
+    oldest_article         = 2
+    max_articles_per_feed  = 100
+    no_stylesheets         = True
+    use_embedded_content   = False
+    encoding               = 'cp1252'
+    publisher              = 'Singapore Press Holdings Ltd.'
+    category               = 'news, politics, singapore, asia'    
+    language               = _('English')    
+
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        , '--ignore-tables'
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True' 
+
+    remove_tags = [
+                     dict(name=['object','link'])
+                    ,dict(name='table', attrs={'width':'980'})
+                    ,dict(name='td'   , attrs={'class':'padlrt10'})
+                  ]
+                            
+    feeds = [ 
+               (u'Singapore'       , u'http://www.straitstimes.com/STI/STIFILES/rss/break_singapore.xml' )
+              ,(u'SE Asia'         , u'http://www.straitstimes.com/STI/STIFILES/rss/break_sea.xml'       )
+              ,(u'Money'           , u'http://www.straitstimes.com/STI/STIFILES/rss/break_money.xml'     )
+              ,(u'Sport'           , u'http://www.straitstimes.com/STI/STIFILES/rss/break_sport.xml'     )
+              ,(u'World'           , u'http://www.straitstimes.com/STI/STIFILES/rss/break_world.xml'     )
+              ,(u'Tech & Science'  , u'http://www.straitstimes.com/STI/STIFILES/rss/break_tech.xml'      )
+              ,(u'Lifestyle'       , u'http://www.straitstimes.com/STI/STIFILES/rss/break_lifestyle.xml' )
+            ]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']        
+        return soup
+
+    def print_version(self, url):
+        return url.replace('http://www.straitstimes.com','http://www.straitstimes.com/print')
+