Merge from trunk

recipes/edge_conversations.recipe

@@ -0,0 +1,50 @@
+__license__   = 'GPL v3'
+__copyright__ = '2012 Levien van Zon <levien@zonnetjes.net>'
+
+'''
+Fetch Edge.org conversations
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class EdgeConversationRSS(BasicNewsRecipe):
+    title          = u'Edge.org Conversations'
+    __author__ = 'levien'
+    language = 'en'
+    description = '''Edge.org offers "open-minded, free ranging, intellectually
+    playful ... an unadorned pleasure in curiosity, a collective expression of
+    wonder at the living and inanimate world ... an ongoing and thrilling
+    colloquium.'''
+    oldest_article = 60
+    max_articles_per_feed = 100
+    no_stylesheets = True
+
+    keep_only_tags = [dict(name='div', attrs={'class':'HomeLeftPannel IMGCTRL'}) ]
+    remove_tags    = [
+        dict(name='div',attrs={'class':'Logo'})
+        ]
+
+    feeds          = [(u'Edge RSS', u'http://edge.org/feeds/')]
+
+    def print_version(self, url):
+        return url.replace('conversation/', 'conversation.php?cid=')
+
+    def parse_feeds(self):
+
+        # Call parent's method.
+        feeds = BasicNewsRecipe.parse_feeds(self)
+
+        # Loop through all feeds.
+        for feed in feeds:
+
+            # Loop through all articles in feed.
+            for article in feed.articles[:]:
+
+            # Remove anything that is not a conversation, and remove PDF files as well...
+
+                if not ('CONVERSATION' in article.title):
+                    feed.articles.remove(article)
+                elif 'pdf' in article.url:
+                    feed.articles.remove(article)
+
+        return feeds
+

recipes/novilist_novine_hr.recipe

@@ -22,13 +22,16 @@ class NoviList_hr(BasicNewsRecipe):
     language              = 'hr'
     remove_empty_feeds    = True
     publication_type      = 'newspaper'
-    needs_subscription    = 'required'
+    needs_subscription    = True
     masthead_url          = 'http://novine.novilist.hr/images/system/novilist-logo.jpg'
+    index                 = 'http://novine.novilist.hr/'
     extra_css             = """
-                               body{font-family: Geneva,Arial,Helvetica,Swiss,sans-serif }
+                               @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
+                               body{font-family: Geneva,Arial,Helvetica,Swiss,sans1,sans-serif }
                                img{display:block; margin-bottom: 0.4em; margin-top: 0.4em}
-                               .nadnaslov,.podnaslov{font-size: small; text-align: center}
+                               .nadnaslov,.podnaslov{font-size: small; display: block; margin-bottom: 1em}
-                               .naslov{font-size: x-large; color: maroon; font-weight: bold}
+                               .naslov{font-size: x-large; color: maroon; font-weight: bold; display: block; margin-bottom: 1em;}
+                               p{display: block}
                             """
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
@@ -47,12 +50,12 @@ class NoviList_hr(BasicNewsRecipe):
                      ]
 
     remove_tags = [dict(name=['meta', 'link', 'iframe', 'embed', 'object'])]
-    remove_attributes=['border', 'lang']
+    remove_attributes=['border', 'lang', 'size', 'face', 'bgcolor']
 
     def get_browser(self):
         br = BasicNewsRecipe.get_browser()
         if self.username is not None and self.password is not None:
-            br.open('http://novine.novilist.hr/loginnow.asp')
+            br.open(self.index + 'loginnow.asp')
             br.select_form(nr=0)
             br['username'] = self.username
             br['password'] = self.password
@@ -62,11 +65,11 @@ class NoviList_hr(BasicNewsRecipe):
     def parse_index(self):
         articles = []
         count = 0
-        soup = self.index_to_soup('http://novine.novilist.hr/')
+        soup = self.index_to_soup(self.index)
         #cover url
         for alink in soup.findAll('a'):
            if alink['href'].startswith('images/clanci/DOC_'):
-              self.cover_url = 'http://novine.novilist.hr/' + alink['href']
+              self.cover_url = self.index + alink['href']
         #feeds
         for item in soup.findAll('td',attrs={'class':'tocrubrika'}):
             count = count +1
@@ -74,28 +77,24 @@ class NoviList_hr(BasicNewsRecipe):
                return articles
             aitem = item.a
             section  = self.tag_to_string(aitem)
-            feedlink = 'http://novine.novilist.hr/' + aitem['href']
+            feedlink = self.index + aitem['href']
             feedpage = self.index_to_soup(feedlink)
             self.report_progress(0, _('Fetching feed')+' %s...'%(section))
             inarts   = []
             for alink in feedpage.findAll('a',attrs={'class':'naslovlinkdesno'}):
-                url   = 'http://novine.novilist.hr/' + alink['href']
+                url   = self.index + alink['href']
-                title = self.tag_to_string(alink)
-                date = strftime(self.timefmt)
-                description = ''
                 inarts.append({
-                                  'title'      :title
+                                  'title'      :self.tag_to_string(alink)
-                                 ,'date'       :date
+                                 ,'date'       :strftime(self.timefmt)
                                  ,'url'        :url
-                                 ,'description':description
+                                 ,'description':''
                                 })
+            if self.remove_empty_feeds:
+                if inarts:
+                    articles.append((section,inarts))
+            else:
                 articles.append((section,inarts))
         return articles
 
     def print_version(self, url):
         return url.replace('?WCI=Rubrike&','?WCI=Pretrazivac&')
-
-    def preprocess_html(self, soup):
-        for item in soup.findAll(style=True):
-            del item['style']
-        return soup

src/calibre/__init__.py

@@ -10,7 +10,10 @@ from math import floor
 from functools import partial
 
 warnings.simplefilter('ignore', DeprecationWarning)
-
+try:
+    os.getcwdu()
+except:
+    os.chdir(os.path.expanduser('~'))
 
 from calibre.constants import (iswindows, isosx, islinux, isfrozen,
         isbsd, preferred_encoding, __appname__, __version__, __author__,

src/calibre/devices/eb600/driver.py

@@ -97,7 +97,7 @@ class POCKETBOOK360(EB600):
 
     VENDOR_NAME = ['PHILIPS', '__POCKET', 'POCKETBO']
     WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = ['MASS_STORGE', 'BOOK_USB_STORAGE',
-            'POCKET_611_61']
+            'OK_POCKET_611_61']
 
     OSX_MAIN_MEM = OSX_CARD_A_MEM = 'Philips Mass Storge Media'
     OSX_MAIN_MEM_VOL_PAT = re.compile(r'/Pocket')

src/calibre/devices/iriver/driver.py

@@ -6,6 +6,8 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
 __docformat__ = 'restructuredtext en'
 
+import re
+
 from calibre.devices.usbms.driver import USBMS
 
 class IRIVER_STORY(USBMS):
@@ -25,7 +27,9 @@ class IRIVER_STORY(USBMS):
 
     VENDOR_NAME = 'IRIVER'
     WINDOWS_MAIN_MEM = ['STORY', 'STORY_EB05', 'STORY_WI-FI', 'STORY_EB07']
+    WINDOWS_MAIN_MEM = re.compile(r'(%s)&'%('|'.join(WINDOWS_MAIN_MEM)))
     WINDOWS_CARD_A_MEM = ['STORY', 'STORY_SD']
+    WINDOWS_CARD_A_MEM = re.compile(r'(%s)&'%('|'.join(WINDOWS_CARD_A_MEM)))
 
     #OSX_MAIN_MEM = 'Kindle Internal Storage Media'
     #OSX_CARD_A_MEM = 'Kindle Card Storage Media'

src/calibre/ebooks/oeb/base.py

@@ -942,12 +942,12 @@ class Manifest(object):
             if isinstance(data, etree._Element):
                 ans = xml2str(data, pretty_print=self.oeb.pretty_print)
                 if self.media_type in OEB_DOCS:
-                    # Convert self closing div|span|a tags to normally closed
+                    # Convert self closing div|span|a|video|audio|iframe tags
-                    # ones, as they are interpreted incorrectly by some browser
+                    # to normally closed ones, as they are interpreted
-                    # based renderers
+                    # incorrectly by some browser based renderers
                     ans = re.sub(
                         # tag name followed by either a space or a /
-                        r'<(?P<tag>div|a|span)(?=[\s/])(?P<arg>[^>]*)/>',
+                        r'<(?P<tag>div|a|span|video|audio|iframe)(?=[\s/])(?P<arg>[^>]*)/>',
                         r'<\g<tag>\g<arg>></\g<tag>>', ans)
                 return ans
             if isinstance(data, unicode):

src/calibre/ebooks/oeb/display/cfi.coffee

@@ -398,8 +398,8 @@ class CanonicalFragmentIdentifier
                 break
 
             rect = target.getBoundingClientRect()
-            x = x - rect.x
+            x -= rect.left
-            y = y - rect.y
+            y -= rect.top
             cdoc = cd
             cwin = cdoc.defaultView
 

src/calibre/ebooks/oeb/display/test-cfi/cfi-test.coffee

@@ -32,10 +32,12 @@ window_ypos = (pos=null) ->
 mark_and_reload = (evt) ->
     # Remove image in case the click was on the image itself, we want the cfi to
     # be on the underlying element
+    x = evt.clientX
+    y = evt.clientY
     if evt.button == 2
         return # Right mouse click, generated only in firefox
     reset = document.getElementById('reset')
-    if document.elementFromPoint(evt.clientX, evt.clientY) == reset
+    if document.elementFromPoint(x, y) == reset
         return
     ms = document.getElementById("marker")
     if ms
@@ -43,7 +45,7 @@ mark_and_reload = (evt) ->
 
     fn = () ->
         try
-            window.current_cfi = window.cfi.at(evt.clientX, evt.clientY)
+            window.current_cfi = window.cfi.at(x, y)
         catch err
             alert("Failed to calculate cfi: #{ err }")
             return
@@ -57,6 +59,28 @@ mark_and_reload = (evt) ->
     setTimeout(fn, 1)
     null
 
+window_scroll_pos = (win) ->
+    if typeof(win.pageXOffset) == 'number'
+        x = win.pageXOffset
+        y = win.pageYOffset
+    else # IE < 9
+        if document.body and ( document.body.scrollLeft or document.body.scrollTop )
+            x = document.body.scrollLeft
+            y = document.body.scrollTop
+        else if document.documentElement and ( document.documentElement.scrollLeft or document.documentElement.scrollTop)
+            y = document.documentElement.scrollTop
+            x = document.documentElement.scrollLeft
+    return [x, y]
+
+frame_clicked = (evt) ->
+    iframe = evt.target.ownerDocument.defaultView.frameElement
+    # We know that the offset parent of the iframe is body
+    # So we can easily calculate the event co-ords w.r.t. the browser window
+    [winx, winy] = window_scroll_pos(window)
+    x = evt.clientX + iframe.offsetLeft - winx
+    y = evt.clientY + iframe.offsetTop  - winy
+    mark_and_reload({'clientX':x, 'clientY':y, 'button':evt.button})
+
 window.onload = ->
     try
         window.cfi.is_compatible()
@@ -64,6 +88,9 @@ window.onload = ->
         alert(error)
         return
     document.onclick = mark_and_reload
+    for iframe in document.getElementsByTagName("iframe")
+        iframe.contentWindow.document.onclick = frame_clicked
+
     r = location.hash.match(/#(\d*)epubcfi\((.+)\)$/)
     if r
         window.current_cfi = r[2]

src/calibre/ebooks/oeb/display/test-cfi/iframe.html

@@ -0,0 +1,30 @@
+<!DOCTYPE html>
+<html>
+    <head>
+        <title>Testing EPUB CFI</title>
+    </head>
+    <body>
+            <p id="whitespace">But I must explain to you how all this mistaken
+            idea of denouncing pleasure and praising pain was born and I will
+            give you a complete account of the system, and expound the actual
+            teachings of the great explorer of the truth, the master-builder of
+            human happiness. No one rejects, dislikes, or avoids pleasure
+            itself, because it is pleasure, but because those who do not know
+            how to pursue pleasure rationally encounter consequences that are
+            extremely painful. Nor again is there anyone who <b>loves or
+                pursues or desires</b> to obtain pain of itself, because it is
+            pain, but because occasionally circumstances occur in which toil
+            and pain can procure him some great pleasure. To take a trivial
+            example, which of us ever undertakes laborious physical exercise,
+            except to obtain some advantage from it? But who has any right to
+            find fault with a man who chooses to enjoy a pleasure that has no
+            annoying consequences, or one who avoids a pain that produces no
+            resultant pleasure? On the other hand, we denounce with righteous
+            indignation and dislike men who are so beguiled and demoralized by
+            the charms of pleasure of the moment, so blinded by desire, that
+            they cannot foresee</p>
+
+    </body>
+</html>
+
+

src/calibre/ebooks/oeb/display/test-cfi/index.html

@@ -118,6 +118,10 @@
             <img src="marker.png" width="150" height="200" alt="Test Image"
             style="border: solid 1px black"/>
 
+            <h2>Iframes</h2>
+            <p>Try clicking anywhere in the iframe below:</p>
+            <iframe src="iframe.html"></iframe>
+
             <h2>Video</h2>
             <p>Try clicking on this video while it is playing. The page should
             reload with the video paused at the point it was at when you
@@ -125,7 +129,7 @@
             play (otherwise the click will cause a reload). 
             </p>
             <video width="320" height="240" controls="controls" preload="auto"
-            src="birds.webm" type="video/webm" />
+            src="birds.webm" type="video/webm"></video>
 
         </div>
         <img id="marker" style="position: absolute; display:none; z-index:10"

src/calibre/gui2/viewer/documentview.py

@@ -179,14 +179,16 @@ class Document(QWebPage): # {{{
             self.misc_config()
             self.after_load()
 
-    def __init__(self, shortcuts, parent=None, resize_callback=lambda: None):
+    def __init__(self, shortcuts, parent=None, resize_callback=lambda: None,
+            debug_javascript=False):
         QWebPage.__init__(self, parent)
         self.setObjectName("py_bridge")
-        self.debug_javascript = False
+        self.debug_javascript = debug_javascript
         self.resize_callback = resize_callback
         self.current_language = None
         self.loaded_javascript = False
-        self.js_loader = None
+        self.js_loader = JavaScriptLoader(
+                    dynamic_coffeescript=self.debug_javascript)
 
         self.setLinkDelegationPolicy(self.DelegateAllLinks)
         self.scroll_marks = []
@@ -252,9 +254,6 @@ class Document(QWebPage): # {{{
                 window.py_bridge.window_resized();
             }
             ''')
-        if self.js_loader is None:
-            self.js_loader = JavaScriptLoader(
-                    dynamic_coffeescript=self.debug_javascript)
         self.loaded_lang = self.js_loader(self.mainFrame().evaluateJavaScript,
                 self.current_language, self.hyphenate_default_lang)
 
@@ -470,11 +469,10 @@ class DocumentView(QWebView): # {{{
     magnification_changed = pyqtSignal(object)
     DISABLED_BRUSH = QBrush(Qt.lightGray, Qt.Dense5Pattern)
 
-    def __init__(self, *args):
+    def initialize_view(self, debug_javascript=False):
-        QWebView.__init__(self, *args)
         self.flipper = SlideFlip(self)
         self.is_auto_repeat_event = False
-        self.debug_javascript = False
+        self.debug_javascript = debug_javascript
         self.shortcuts =  Shortcuts(SHORTCUTS, 'shortcuts/viewer')
         self.self_closing_pat = re.compile(r'<([a-z1-6]+)\s+([^>]+)/>',
                 re.IGNORECASE)
@@ -483,7 +481,8 @@ class DocumentView(QWebView): # {{{
         self.initial_pos = 0.0
         self.to_bottom = False
         self.document = Document(self.shortcuts, parent=self,
-                resize_callback=self.viewport_resized)
+                resize_callback=self.viewport_resized,
+                debug_javascript=debug_javascript)
         self.setPage(self.document)
         self.manager = None
         self._reference_mode = False

src/calibre/gui2/viewer/javascript.py

@@ -39,14 +39,14 @@ class JavaScriptLoader(object):
         self._cache = {}
         self._hp_cache = {}
 
-    def __getattr__(self, name):
+    def get(self, name):
         ans = self._cache.get(name, None)
         if ans is None:
             src = self.CS.get(name, None)
             if src is None:
                 src = self.JS.get(name, None)
                 if src is None:
-                    raise AttributeError('No such resource: %s'%name)
+                    raise KeyError('No such resource: %s'%name)
                 ans = P(src, data=True,
                         allow_user_override=False).decode('utf-8')
             else:
@@ -70,7 +70,7 @@ class JavaScriptLoader(object):
 
     def __call__(self, evaljs, lang, default_lang):
         for x in self.ORDER:
-            src = getattr(self, x)
+            src = self.get(x)
             evaljs(src)
 
         def lang_name(l):

src/calibre/gui2/viewer/main.py

@@ -175,6 +175,7 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
     def __init__(self, pathtoebook=None, debug_javascript=False, open_at=None):
         MainWindow.__init__(self, None)
         self.setupUi(self)
+        self.view.initialize_view(debug_javascript)
         self.view.magnification_changed.connect(self.magnification_changed)
         self.show_toc_on_open = False
         self.current_book_has_toc = False
@@ -215,7 +216,6 @@ class EbookViewer(MainWindow, Ui_EbookViewer):
         self.search.setMinimumWidth(200)
         self.tool_bar2.insertWidget(self.action_find_next, self.search)
         self.view.set_manager(self)
-        self.view.document.debug_javascript = debug_javascript
         self.pi = ProgressIndicator(self)
         self.toc.setVisible(False)
         self.action_quit = QAction(self)