Pull from trunk

src/calibre/__init__.py

@@ -3,11 +3,14 @@ __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 import sys, os, re, logging, time, subprocess, atexit, mimetypes, \
-       __builtin__
+       __builtin__, warnings
 __builtin__.__dict__['dynamic_property'] = lambda(func): func(None)
 from htmlentitydefs import name2codepoint
 from math import floor
 
+warnings.simplefilter('ignore', DeprecationWarning)
+
+
 from PyQt4.QtCore import QUrl
 from PyQt4.QtGui  import QDesktopServices
 from calibre.startup import plugins, winutil, winutilerror

src/calibre/ebooks/html.py

@@ -857,7 +857,7 @@ class Processor(Parser):
             except ValueError:
                 setting = ''
             face = font.attrib.pop('face', None)
-            if face is not None:
+            if face:
                 faces = []
                 for face in face.split(','):
                     face = face.strip()

src/calibre/ebooks/mobi/reader.py

@@ -389,7 +389,13 @@ class MobiReader(object):
             opf.cover = 'images/%05d.jpg'%(self.book_header.exth.cover_offset+1)
         elif mi.cover is not None:
             opf.cover = mi.cover
-        manifest = [(htmlfile, 'text/x-oeb1-document'), 
+        else:
+            opf.cover = 'images/%05d.jpg'%1
+            if not os.path.exists(os.path.join(os.path.dirname(htmlfile),
+                                               *opf.cover.split('/'))):
+                opf.cover = None
+
+        manifest = [(htmlfile, 'text/x-oeb1-document'),
                     (os.path.abspath('styles.css'), 'text/css')]
         bp = os.path.dirname(htmlfile)
         for i in getattr(self, 'image_names', []):

src/calibre/linux.py

@@ -393,43 +393,27 @@ def option_parser():
                       help='Save a manifest of all installed files to the specified location')
     return parser
 
-def install_man_pages(fatal_errors):
-    from bz2 import compress
-    import subprocess
+def install_man_pages(fatal_errors, use_destdir=False):
+    from calibre.utils.help2man import create_man_page
+    prefix = os.environ.get('DESTDIR', '/') if use_destdir else '/'
+    manpath = os.path.join(prefix, 'usr/share/man/man1')
+    if not os.path.exists(manpath):
+        os.makedirs(manpath)
     print 'Installing MAN pages...'
-    manpath = '/usr/share/man/man1'
-    f = NamedTemporaryFile()
-    f.write('[see also]\nhttp://%s.kovidgoyal.net\n'%__appname__)
-    f.flush()
     manifest = []
-    os.environ['PATH'] += ':'+os.path.expanduser('~/bin')
     for src in entry_points['console_scripts']:
-        prog = src[:src.index('=')].strip()
-        if prog in ('ebook-device', 'markdown-calibre', 
-                    'calibre-fontconfig', 'calibre-parallel'):
+        prog, right = src.split('=')
+        prog = prog.strip()
+        module = __import__(right.split(':')[0].strip(), fromlist=['a'])
+        parser = getattr(module, 'option_parser', None)
+        if parser is None:
             continue
-
-        help2man = ('help2man', prog, '--name', 'part of %s'%__appname__,
-                    '--section', '1', '--no-info', '--include',
-                    f.name, '--manual', __appname__)
+        parser = parser()
+        raw = create_man_page(prog, parser)
         manfile = os.path.join(manpath, prog+'.1'+__appname__+'.bz2')
         print '\tInstalling MAN page for', prog
-        try:
-            p = subprocess.Popen(help2man, stdout=subprocess.PIPE)
-        except OSError, err:
-            import errno
-            if err.errno != errno.ENOENT:
-                raise
-            print 'Failed to install MAN pages as help2man is missing from your system'
-            break
-        o = p.stdout.read()
-        raw = re.compile(r'^\.IP\s*^([A-Z :]+)$', re.MULTILINE).sub(r'.SS\n\1', o)
-        if not raw.strip():
-            print 'Unable to create MAN page for', prog
-            continue
-        f2 = open_file(manfile)
-        manifest.append(f2.name)
-        f2.write(compress(raw))
+        open(manfile, 'wb').write(raw)
+        manifest.append(manfile)
     return manifest
 
 def post_install():
@@ -441,9 +425,9 @@ def post_install():
     manifest = []
     setup_desktop_integration(opts.fatal_errors)
     if opts.no_root or os.geteuid() == 0:
+        manifest += install_man_pages(opts.fatal_errors, use_destdir)
         manifest += setup_udev_rules(opts.group_file, not opts.dont_reload, opts.fatal_errors)
         manifest += setup_completion(opts.fatal_errors)
-        manifest += install_man_pages(opts.fatal_errors)
     else:
         print "Skipping udev, completion, and man-page install for non-root user."
 

src/calibre/trac/plugins/download.py

@@ -18,7 +18,6 @@ DEPENDENCIES = [
             ('lxml', '2.1.5', 'lxml', 'python-lxml', 'python-lxml'),
             ('python-dateutil', '1.4.1', 'python-dateutil', 'python-dateutil', 'python-dateutil'),
             ('BeautifulSoup', '3.0.5', 'beautifulsoup', 'python-beautifulsoup', 'python-BeautifulSoup'),
-            ('help2man', '1.36.4', 'help2man', 'help2man', 'help2man'),
             ]
         
 

src/calibre/trac/plugins/templates/linux.html

@@ -88,7 +88,7 @@ sudo python -c "import urllib2; exec urllib2.urlopen('http://calibre.kovidgoyal.
                                     be ignored.
                                 </li>
                                 <li>
-                                    You must have help2man and xdg-utils installed 
+                                    You must have xdg-utils installed 
                                     on your system before running the installer.
                                 </li>
                                 <li>

src/calibre/utils/help2man.py

@@ -0,0 +1,59 @@
+from __future__ import with_statement
+__license__ = 'GPL 3'
+__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
+__docformat__ = 'restructuredtext en'
+
+import time, bz2
+
+from calibre.constants import __version__, __appname__, __author__
+
+
+def create_man_page(prog, parser):
+    usage  = parser.usage.splitlines()
+    for i, line in enumerate(list(usage)):
+        if not line.strip():
+            usage[i] = '.PP'
+        else:
+            usage[i] = line.replace('%prog', prog)
+    lines = [
+             '.TH ' + prog.upper() + ' "1" ' + time.strftime('"%B %Y"') + 
+             ' "%s (%s %s)" "%s"'%(prog, __appname__, __version__, __appname__),
+             '.SH NAME',
+             prog + r' \- part of '+__appname__,
+             '.SH SYNOPSIS',
+             '.B "%s"'%prog + r'\fR '+' '.join(usage[0].split()[1:]),
+             '.SH DESCRIPTION',
+             ]
+    lines += usage[1:]
+    
+    lines += [
+              '.SH OPTIONS'
+              ]
+    def format_option(opt):
+        ans = ['.TP']
+        opts = []
+        opts += opt._short_opts
+        opts.append(opt.get_opt_string())
+        opts = [r'\fB'+x.replace('-', r'\-')+r'\fR' for x in opts]
+        ans.append(', '.join(opts))
+        help = opt.help if opt.help else ''
+        ans.append(help.replace('%prog', prog).replace('%default', str(opt.default)))
+        return ans
+    
+    for opt in parser.option_list:
+        lines.extend(format_option(opt))
+    for group in parser.option_groups:
+        lines.append('.SS '+group.title)
+        if group.description:
+            lines.extend(['.PP', group.description])
+        for opt in group.option_list:
+            lines.extend(format_option(opt))
+    
+    lines += ['.SH SEE ALSO', 
+              'The User Manual is available at '
+              'http://calibre.kovidgoyal.net/user_manual',
+              '.PP', '.B Created by '+__author__]
+    
+    return  bz2.compress('\n'.join(lines))
+
+

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

@@ -33,7 +33,7 @@ recipe_modules = ['recipe_' + r for r in (
            'la_republica', 'physics_today', 'chicago_tribune', 'e_novine',
            'al_jazeera', 'winsupersite', 'borba', 'courrierinternational',
            'lamujerdemivida', 'soldiers', 'theonion', 'news_times',
-           'el_universal', 'mediapart',
+           'el_universal', 'mediapart', 'wikinews_en',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,70 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+en.wikinews.org
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class WikiNews(BasicNewsRecipe):
+    title                 = 'Wikinews'
+    __author__            = 'Darko Miletic'
+    description           = 'News from wikipedia'
+    category              = 'news, world'
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    publisher             = 'Wiki'
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+    remove_javascript     = True
+    language              = _('English')
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    keep_only_tags = [ 
+                        dict(name='h1', attrs={'id':'firstHeading'}) 
+                       ,dict(name='div', attrs={'id':'bodyContent'}) 
+                     ]
+    
+    remove_tags = [
+                    dict(name='link')
+                   ,dict(name='div',attrs={'id':['printfooter','catlinks','footer']})
+                   ,dict(name='div',attrs={'class':['thumb left','thumb right']})
+                  ]
+
+    remove_tags_after = dict(name='h2')
+                  
+    feeds = [(u'News', u'http://feeds.feedburner.com/WikinewsLatestNews')]
+
+    def get_article_url(self, article):
+        artl  = article.get('link',  None)
+        rest, sep, article_id  = artl.rpartition('/')
+        return 'http://en.wikinews.org/wiki/' + article_id
+            
+    def print_version(self, url):
+        rest, sep, article_id  = url.rpartition('/')
+        return 'http://en.wikinews.org/w/index.php?title=' + article_id + '&printable=yes'
+
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Language" content="en"/><meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
+        soup.head.insert(0,mtag)
+        btag = soup.find('div',attrs={'id':'bodyContent'})
+        for item in btag.findAll('div'):
+            item.extract()        
+        for item in btag.findAll('h2'):
+            item.extract()        
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(font=True):
+            del item['font']
+        return soup
+