Pull from trunk

pyqtdistutils.py

@@ -144,7 +144,7 @@ def build_extension(self, ext):
                 return _build_ext.build_extension(self, ext)
 
             c_sources = [f for f in ext.sources if os.path.splitext(f)[1].lower() in ('.c', '.cpp', '.cxx')]
-            compile_args = '/c /nologo /Ox /MD /W3 /GX /DNDEBUG'.split()
+            compile_args = '/c /nologo /Ox /MD /W3 /EHsc /DNDEBUG'.split()
             compile_args += ext.extra_compile_args
             self.swig_opts = ''
             inc_dirs = self.include_dirs + [x.replace('/', '\\') for x in ext.include_dirs]
@@ -153,11 +153,12 @@ def build_extension(self, ext):
             for f in c_sources:
                 o = os.path.join(bdir, os.path.basename(f)+'.obj')
                 objects.append(o)
-                compiler =  cc + ['/Tc'+f, '/Fo'+o]
+                inf = '/Tp' if f.endswith('.cpp') else '/Tc'
+                compiler =  cc + [inf+f, '/Fo'+o]
                 self.spawn(compiler)
             out = os.path.join(bdir, base+'.pyd')
             linker = [msvc.linker] + '/DLL /nologo /INCREMENTAL:NO'.split()
-            linker += ['/LIBPATH:'+x for x in self.library_dirs]
+            linker += ['/LIBPATH:'+x for x in self.library_dirs+ext.library_dirs]
             linker += [x+'.lib' for x in ext.libraries]
             linker += ['/EXPORT:init'+base] + objects + ['/OUT:'+out]
             self.spawn(linker)

setup.py

@@ -66,10 +66,9 @@ def _ep_to_function(ep):
     podofo_lib = '/usr/lib' if islinux else r'C:\podofo' if iswindows else \
             '/Users/kovid/podofo/lib'
     if os.path.exists(os.path.join(podofo_inc, 'podofo.h')):
-        eca = ['/EHsc'] if iswindows else []
         optional.append(Extension('calibre.plugins.podofo',
                         sources=['src/calibre/utils/podofo/podofo.cpp'],
-                        libraries=['podofo'], extra_compile_args=eca,
+                        libraries=['podofo'],
                         library_dirs=[os.environ.get('PODOFO_LIB_DIR', podofo_lib)],
                         include_dirs=\
                         [os.environ.get('PODOFO_INC_DIR', podofo_inc)]))

src/calibre/constants.py

@@ -2,7 +2,7 @@
 __copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
 __docformat__ = 'restructuredtext en'
 __appname__   = 'calibre'
-__version__   = '0.5.11'
+__version__   = '0.5.12'
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"
 '''
 Various run time constants.

src/calibre/ebooks/metadata/opf2.py

@@ -508,6 +508,9 @@ def find_toc(self):
             else:
                 self.path_to_html_toc, self.html_toc_fragment = \
                     toc.partition('#')[0], toc.partition('#')[-1]
+                if not os.access(self.path_to_html_toc, os.R_OK) or \
+                        not os.path.isfile(self.path_to_html_toc):
+                    self.path_to_html_toc = None
                 self.toc.read_html_toc(toc)
         except:
             pass

src/calibre/gui2/dialogs/metadata_single.py

@@ -403,7 +403,7 @@ def hangcheck(self):
             pix = QPixmap()
             pix.loadFromData(self.cover_fetcher.cover_data)
             if pix.isNull():
-                error_dialog(self.window, _('Bad cover'),
+                error_dialog(self, _('Bad cover'),
                              _('The cover is not a valid picture')).exec_()
             else:
                 self.cover.setPixmap(pix)

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

@@ -2,7 +2,7 @@
 
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
-import re, string, time
+import re, time
 from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
@@ -13,62 +13,51 @@ class Newsweek(BasicNewsRecipe):
     description    = 'Weekly news and current affairs in the US'
     no_stylesheets = True
     language = _('English')
-
-    extra_css = '''
-    #content { font-size:normal; font-family: serif }
-    .story  { font-size:normal }
-    .HorizontalHeader {font-size:xx-large}
-    .deck {font-size:x-large}
-    '''
-    keep_only_tags = [dict(name='div', id='content')]
-
     remove_tags = [
-        dict(name=['script',  'noscript']),
-        dict(name='div',  attrs={'class':['ad', 'SocialLinks', 'SocialLinksDiv',
-                                          'channel', 'bot', 'nav', 'top',
-                                          'EmailArticleBlock',
-                                          'comments-and-social-links-wrapper',
-                                          'inline-social-links-wrapper',
-                                          'inline-social-links',
-                                          ]}),
-        dict(name='div',  attrs={'class':re.compile('box')}),
-        dict(id=['ToolBox', 'EmailMain', 'EmailArticle', 'comment-box',
-                 'nw-comments'])
-    ]
+            {'class':['navbar', 'ad', 'sponsorLinksArticle', 'mm-content',
+                'inline-social-links-wrapper', 'email-article',
+                'comments-and-social-links-wrapper', 'EmailArticleBlock']},
+            {'id' : ['footer', 'ticker-data', 'topTenVertical',
+                'digg-top-five', 'mesothorax', 'nw-comments',
+                'ToolBox', 'EmailMain']},
+            {'class': re.compile('related-cloud')},
+            ]
+    keep_only_tags = [{'class':['article HorizontalHeader', 'articlecontent']}]
+
 
     recursions = 1
     match_regexps = [r'http://www.newsweek.com/id/\S+/page/\d+']
 
+    def find_title(self, section):
+        d = {'scope':'Scope', 'thetake':'The Take', 'features':'Features',
+        None:'Departments'}
+        ans = None
+        a = section.find('a', attrs={'name':True})
+        if a is not None:
+            ans = a['name']
+        return d[ans]
 
-    def get_sections(self, soup):
-        sections = []
 
-        def process_section(img):
-            articles = []
-            match = re.search(r'label_([^_.]+)', img['src'])
-            if match is None:
-                return
-            title =  match.group(1)
-            if title in ['coverstory', 'more', 'tipsheet']:
-                return
-            title = string.capwords(title)
+    def find_articles(self, section):
+        ans = []
+        for x in section.findAll('h5'):
+            title = ' '.join(x.findAll(text=True)).strip()
+            a = x.find('a')
+            if not a: continue
+            href = a['href']
+            ans.append({'title':title, 'url':href, 'description':'', 'date': strftime('%a, %d %b')})
+        if not ans:
+            for x in section.findAll('div', attrs={'class':'hdlItem'}):
+                a = x.find('a', href=True)
+                if not a : continue
+                title = ' '.join(a.findAll(text=True)).strip()
+                href = a['href']
+                if 'http://xtra.newsweek.com' in href: continue
+                ans.append({'title':title, 'url':href, 'description':'', 'date': strftime('%a, %d %b')})
 
-            for a in img.parent.findAll('a', href=True):
-                art, href = a.string, a['href']
-                if not re.search('\d+$', href) or not art or 'Preview Article' in art:
-                    continue
-                articles.append({
-                                 'title':art, 'url':href, 'description':'',
-                                 'content':'', 'date':''
-                    })
-            sections.append((title, articles))
-
-            img.parent.extract()
-
-        for img in soup.findAll(src=re.compile('/label_')):
-            process_section(img)
-
-        return sections
+        #for x in ans:
+        #    x['url'] += '/output/print'
+        return ans
 
 
     def parse_index(self):
@@ -83,49 +72,45 @@ def parse_index(self):
                 self.timefmt = strftime(' [%d %b, %Y]', time.strptime(match.group(1), '%y%m%d'))
             self.cover_url = small.replace('coversmall', 'coverlarge')
 
-        sections = self.get_sections(soup)
-        sections.insert(0, ('Main articles', []))
-
-        for tag in soup.findAll('h5'):
-            a = tag.find('a', href=True)
-            if a is not None:
-                title = self.tag_to_string(a)
-                if not title:
-                    a = 'Untitled article'
-                art = {
-                       'title' : title,
-                       'url'   : a['href'],
-                       'description':'', 'content':'',
-                       'date': strftime('%a, %d %b')
-                       }
-                if art['title'] and art['url']:
-                    sections[0][1].append(art)
-        return sections
-
+        sections = soup.findAll('div', attrs={'class':'featurewell'})
+        titles = map(self.find_title, sections)
+        articles = map(self.find_articles, sections)
+        ans = list(zip(titles, articles))
+        def fcmp(x, y):
+            tx, ty = x[0], y[0]
+            if tx == "Features": return cmp(1, 2)
+            if ty == "Features": return cmp(2, 1)
+            return cmp(tx, ty)
+        return sorted(ans, cmp=fcmp)
 
     def postprocess_html(self, soup, first_fetch):
-        divs = list(soup.findAll('div', 'pagination'))
-        if not divs:
-            return
-        divs[0].extract()
-        if len(divs) > 1:
-            soup.find('body')['style'] = 'page-break-after:avoid'
-            divs[1].extract()
-
-            h1 = soup.find('h1')
+        if not first_fetch:
+            h1 = soup.find(id='headline')
             if h1:
                 h1.extract()
-            ai = soup.find('div', 'articleInfo')
-            ai.extract()
-        else:
-            soup.find('body')['style'] = 'page-break-before:always; page-break-after:avoid;'
+            div = soup.find(attrs={'class':'articleInfo'})
+            if div:
+                div.extract()
+        divs = list(soup.findAll('div', 'pagination'))
+        if not divs:
+            return soup
+        for div in divs[1:]: div.extract()
+        all_a = divs[0].findAll('a', href=True)
+        divs[0]['style']="display:none"
+        if len(all_a) > 1:
+            all_a[-1].extract()
+        test = re.compile(self.match_regexps[0])
+        for a in soup.findAll('a', href=test):
+            if a not in all_a:
+                del a['href']
         return soup
 
     def get_current_issue(self):
-        #from urllib2 import urlopen # For some reason mechanize fails
-        #home = urlopen('http://www.newsweek.com').read()
-        soup = self.index_to_soup('http://www.newsweek.com')#BeautifulSoup(home)
-        img  = soup.find('img', alt='Current Magazine')
-        if img and img.parent.has_key('href'):
-            return self.index_to_soup(img.parent['href'])
+        soup = self.index_to_soup('http://www.newsweek.com')
+        div = soup.find('div', attrs={'class':re.compile('more-from-mag')})
+        if div is None: return None
+        a = div.find('a')
+        if a is not None:
+            href = a['href'].split('#')[0]
+            return self.index_to_soup(href)
 

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

@@ -0,0 +1,39 @@
+#!/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'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Slashdot(BasicNewsRecipe):
+             title          = u'Slashdot.org'
+             oldest_article = 7
+             max_articles_per_feed = 100
+             language = _('English')
+             __author__ = 'floweros'
+             no_stylesheets = True
+             keep_only_tags = [dict(name='div',attrs={'id':'article'})]
+             remove_tags    = [
+                 dict(name='div',attrs={'id':'userlogin-title'}),
+                 dict(name='div',attrs={'id':'userlogin-content'}),
+                 dict(name='div',attrs={'id':'commentwrap'}),
+                 dict(name='span',attrs={'id':'more_comments_num_a'}),
+                 ]
+
+             feeds          = [
+                 (u'Slashdot',
+ u'http://rss.slashdot.org/Slashdot/slashdot?m=5072'),
+                 (u'/. IT',
+ u'http://rss.slashdot.org/Slashdot/slashdotIT'),
+                 (u'/. Hardware',
+ u'http://rss.slashdot.org/Slashdot/slashdotHardware'),
+                 (u'/. Linux',
+ u'http://rss.slashdot.org/Slashdot/slashdotLinux'),
+                 (u'/. Your Rights Online',
+ u'http://rss.slashdot.org/Slashdot/slashdotYourRightsOnline')
+                 ]
+
+

upload.py

@@ -99,11 +99,11 @@ def run(self):
             tempdir = tempfile.mkdtemp()
             pygettext(buf, ['-k', '__', '-p', tempdir]+files)
             src = buf.getvalue()
-            pot = os.path.join(tempdir, __appname__+'.pot')
+            pot = os.path.join(self.PATH, __appname__+'.pot')
             f = open(pot, 'wb')
             f.write(src)
             f.close()
-            print 'Translations template:', pot
+            print 'Translations template:', os.path.abspath(pot)
             return pot
         finally:
             sys.path.remove(os.path.abspath(self.PATH))
@@ -709,6 +709,7 @@ class upload(OptionlessCommand):
     description = 'Build and upload calibre to the servers'
 
     sub_commands = [
+            ('pot', None),
             ('stage1', None),
             ('stage2', None),
             ('stage3', None)