Fix for Python GC'ing menu objects with no explicit Python references.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-4
+version: 4-4-5
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 5, 10)
+    version             = (1, 5, 13)
     minimum_calibre_version = (0, 8, 30)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/ffdl_plugin.py

@@ -109,6 +109,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         # Assign our menu to this action
         self.menu = QMenu(self.gui)
         self.old_actions_unique_map = {}
+        # menu_actions is just to keep a live reference to the menu
+        # items to prevent GC removing it.
+        self.menu_actions = []
         self.qaction.setMenu(self.menu)
         self.menu.aboutToShow.connect(self.about_to_show_menu)
 
@@ -135,6 +138,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             do_user_config = self.interface_action_base_plugin.do_user_config
             self.menu.clear()
             self.actions_unique_map = {}
+            self.menu_actions = []
             self.add_action = self.create_menu_item_ex(self.menu, '&Add New from URL(s)', image='plus.png',
                                                        unique_name='Add New FanFiction Book(s) from URL(s)',
                                                        shortcut_name='Add New FanFiction Book(s) from URL(s)',
@@ -227,6 +231,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         ac = create_menu_action_unique(self, parent_menu, menu_text, image, tooltip,
                                        shortcut, triggered, is_checked, shortcut_name, unique_name)
         self.actions_unique_map[ac.calibre_shortcut_unique_name] = ac.calibre_shortcut_unique_name
+        self.menu_actions.append(ac)
         return ac
 
     def plugin_button(self):
@@ -768,7 +773,13 @@ make_firstimage_cover:true
             if epubmi.cover_data[1] is not None:
                 db.set_cover(book_id, epubmi.cover_data[1])
             #mi.cover = epubmi.cover_data[1]
-                
+
+        # set author link if found.  All current adapters have authorUrl.
+        if 'authorUrl' in book['all_metadata']:
+            autid=db.get_author_id(book['author'])
+            db.set_link_field_for_author(autid, unicode(book['all_metadata']['authorUrl']),
+                                         commit=False, notify=False)
+            
         db.set_metadata(book_id,mi)
 
         # do configured column updates here.

fanficdownloader/adapters/__init__.py

@@ -51,6 +51,7 @@ import adapter_thequidditchpitchorg
 import adapter_nfacommunitycom
 import adapter_midnightwhispersca
 import adapter_ksarchivecom
+import adapter_archiveskyehawkecom
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need

fanficdownloader/adapters/adapter_archiveskyehawkecom.py

@@ -0,0 +1,190 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+
+def getClass():
+    return ArchiveSkyeHawkeComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/story.php?no='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','ash')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%Y-%m-%d"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'archive.skyehawke.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/story.php?no=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/story.php?no=")+r"\d+$"
+
+
+        
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        data = self._fetchUrl(url)
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('div', {'class':"story border"}).find('span',{'class':'left'})
+        title=a.text.split('"')[1]
+        self.story.setMetadata('title',title)
+        
+        # Find authorid and URL from... author url.
+        author = a.find('a')
+        self.story.setMetadata('authorId',author['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+author['href'])
+        self.story.setMetadata('author',author.string)
+		
+        authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+		
+        chapter=soup.find('select',{'name':'chapter'}).findAll('option')
+	
+        for i in range(1,len(chapter)):
+            ch=chapter[i]
+            self.chapterUrls.append((stripHTML(ch),ch['value']))
+		
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+		
+        box=soup.find('div', {'class': "container borderridge"})
+        sum=box.find('span').text
+        self.setDescription(url,sum)
+
+        boxes=soup.findAll('div', {'class': "container bordersolid"})
+        for box in boxes:
+            if box.find('b') != None and box.find('b').text == "History and Story Information":
+			
+                for b in box.findAll('b'):
+                    if "words" in b.nextSibling:
+                        self.story.setMetadata('numWords', b.text)
+                    if "archived" in b.previousSibling:
+                        self.story.setMetadata('datePublished', makeDate(stripHTML(b.text), self.dateformat))
+                    if "updated" in b.previousSibling:
+                        self.story.setMetadata('dateUpdated', makeDate(stripHTML(b.text), self.dateformat))
+                    if "fandom" in b.nextSibling:
+                        self.story.addToList('category', b.text)
+						
+                for br in box.findAll('br'):
+                    br.replaceWith('split')
+                genre=box.text.split("Genre:")[1].split("split")[0]
+                if not "Unspecified" in genre:
+                    self.story.addToList('genre',genre)
+			
+			
+            if box.find('span') != None and box.find('span').text == "WARNING":
+			
+                rating=box.findAll('span')[1]
+                rating.find('br').replaceWith('split')
+                rating=rating.text.replace("This story is rated",'').split('split')[0]
+                self.story.setMetadata('rating',rating)
+                logging.debug(self.story.getMetadata('rating'))
+			
+                warnings=box.find('ol')
+                if warnings != None:
+                    warnings=warnings.text.replace(']', '').replace('[', '').split('  ')
+                    for warning in warnings:
+                        self.story.addToList('warnings',warning)
+	
+	
+        for asoup in authorSoup.findAll('div', {'class':"story bordersolid"}):
+            if asoup.find('a')['href'] == 'story.php?no='+self.story.getMetadata('storyId'):
+                if '[ Completed ]' in asoup.text:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+                chars=asoup.findNext('div').text.split('Characters')[1].split(']')[0]
+                for char in chars.split(','):
+                    if not "None" in char:
+                        self.story.addToList('characters',char)
+                break
+	
+	
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div',{'class':"chapter bordersolid"}).findNext('div').findNext('div')
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/base_adapter.py

@@ -331,10 +331,6 @@ class BaseSiteAdapter(Configurable):
         # This is primarily for epub updates.
         return re.sub(r"</?body>\r?\n?","",retval)
 
-fullmon = {"January":"01", "February":"02", "March":"03", "April":"04", "May":"05",
-           "June":"06","July":"07", "August":"08", "September":"09", "October":"10",
-           "November":"11", "December":"12" }
-
 def cachedfetch(realfetch,cache,url):
     if url in cache:
         print("cache hit")
@@ -342,6 +338,9 @@ def cachedfetch(realfetch,cache,url):
     else:
         return realfetch(url)
     
+fullmon = {"January":"01", "February":"02", "March":"03", "April":"04", "May":"05",
+           "June":"06","July":"07", "August":"08", "September":"09", "October":"10",
+           "November":"11", "December":"12" }
 
 def makeDate(string,format):
     # Surprise!  Abstracting this turned out to be more useful than

fanficdownloader/htmlcleanup.py

@@ -23,11 +23,16 @@ def _unirepl(match):
         radix=16
     else:
         radix=10
-    value = int(match.group(2), radix )
-    return unichr(value)
+    value = int(match.group(2), radix)
+    return "%s%s"%(unichr(value),match.group(3))
 
 def _replaceNumberEntities(data):
-    p = re.compile(r'&#(x?)([0-9a-fA-F]+);')
+    # The same brokenish entity parsing in SGMLParser that inserts ';'
+    # after non-entities will also insert ';' incorrectly after number
+    # entities, including part of the next word if it's a-z.
+    # "Don't&#8212ever&#8212do&#8212that&#8212again," becomes
+    # "Don't&#8212e;ver&#8212d;o—that&#8212a;gain,"
+    p = re.compile(r'&#(x?)([0-9a-fA-F]{,4})([0-9a-fA-F]*);')
     return p.sub(_unirepl, data)
 
 def _replaceNotEntities(data):
@@ -50,9 +55,6 @@ def removeAllEntities(text):
     return removeEntities(text).replace('&lt;', '<').replace('&gt;', '>').replace('&amp;', '&')
 
 def removeEntities(text):
-
-    # replace numeric versions of [&<>] with named versions,
-    # then replace named versions with actual characters,
     
     if text is None:
         return ""
@@ -67,6 +69,8 @@ def removeEntities(text):
         except UnicodeEncodeError, e:
             t = text
     text = t 
+    # replace numeric versions of [&<>] with named versions,
+    # then replace named versions with actual characters,
     text = re.sub(r'&#0*38;','&amp;',text)
     text = re.sub(r'&#0*60;','&lt;',text)
     text = re.sub(r'&#0*62;','&gt;',text)

fanficdownloader/story.py

@@ -216,7 +216,7 @@ class Story:
         for (p,v) in self.replacements:
             if (isinstance(value,str) or isinstance(value,unicode)) and re.match(p,value):
                 value = re.sub(p,v,value)                
-        return value;
+        return value
         
     def getMetadata(self, key, removeallentities=False):
         value = None

index.html

@@ -56,17 +56,17 @@
 	  <!-- put announcements here, h3 is a good title size. -->
 	  <h3>New Site Added</h3>
 	  <p>
-	    Support for ksarchive.com has been added.  Thanks for Jade AislinSam implementing this.
+	    Support for archive.skyehawke.com has been added.  Thanks to Ida Leter for implementing this.
 	  </p>
 	  <p>
-	    Questions?  Check out our new 
-	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.  Thanks to Wyndham for writing these.
+	    Questions?  Check out our 
+	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
 	    </p>
 	  <p>
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>.  The
-	    <a href="http://4-4-3.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-4.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -248,10 +248,6 @@
 	    <br /><a href="http://ficbook.net/readfic/93626">http://ficbook.net/readfic/93626</a>.
 	    <br /><a href="http://ficbook.net/readfic/93626/246417#part_content">http://ficbook.net/readfic/93626/246417#part_content</a>.
 	  </dd>
-	  <dt>gayauthors.org</dt>
-	  <dd>
-	    Removed following complaints by the site administration.
-	  </dd>
 	  <dt>fanfiction.mugglenet.com</dt>
 	  <dd>
 	    Use the URL of the story's chapter list, such as
@@ -287,18 +283,23 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://ksarchive.com/viewstory.php?sid=1124">http://ksarchive.com/viewstory.php?sid=1124</a>.
 	  </dd>
+	  <dt>archive.skyehawke.com</dt>
+	  <dd>
+	    Use the URL of the story's summary, such as
+	    <br /><a href="http://archive.skyehawke.com/story.php?no=17466">http://archive.skyehawke.com/story.php?no=17466</a>.
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:
 	</p>
 	<ol>
 	  <li>
-	    First thing to know: I do not use your Google login and password. In fact, all I know about it is your ID &ndash; password
+	    First thing to know: We do not use your Google login and password. In fact, all we know about it is your ID &ndash; password
 	    is being verified by Google and is absolutely, totally unknown to anyone but you.
 	  </li>
 	  <li>
 	    
-	    Small <a href="http://www.sigizmund.com/reading-fanfiction-off-line-in-stanza-and-oth">post written by me</a>
+	    Small <a href="http://www.sigizmund.com/reading-fanfiction-off-line-in-stanza-and-oth">post written by Roman</a>
 	    &mdash; how to read fiction in Stanza or any other ebook reader.
 	  </li>
 	  <li>
@@ -314,7 +315,7 @@
 	  </li>
 	  <li>
 	    If you think that something that should work in fact doesn't, post a message to
-	    our <a href="http://groups.google.com/group/fanfic-downloader">Google Group</a>. I also encourage you to join it so
+	    our <a href="http://groups.google.com/group/fanfic-downloader">Google Group</a>. we also encourage you to join it so
 	    you will find out about latest updates and fixes as soon as possible
 	  </li>
 	</ol>