kete-feedzirra 0.0.8.1 → 0.0.16.1

data/lib/feedzirra/parser/itunes_rss_item.rb

@@ -0,0 +1,31 @@
+module Feedzirra
+  
+  module Parser
+    # iTunes extensions to the standard RSS2.0 item
+    # Source: http://www.apple.com/itunes/whatson/podcasts/specs.html
+    class ITunesRSSItem
+      include SAXMachine
+      include FeedUtilities
+      element :author
+      element :guid
+      element :title
+      element :link, :as => :url
+      element :description, :as => :summary
+      element :pubDate, :as => :published
+
+      # If author is not present use author tag on the item
+      element :"itunes:author", :as => :itunes_author
+      element :"itunes:block", :as => :itunes_block
+      element :"itunes:duration", :as => :itunes_duration
+      element :"itunes:explicit", :as => :itunes_explicit
+      element :"itunes:keywords", :as => :itunes_keywords
+      element :"itunes:subtitle", :as => :itunes_subtitle
+      # If summary is not present, use the description tag
+      element :"itunes:summary", :as => :itunes_summary
+      element :enclosure, :value => :length, :as => :enclosure_length
+      element :enclosure, :value => :type, :as => :enclosure_type
+      element :enclosure, :value => :url, :as => :enclosure_url
+    end
+  end
+  
+end

data/lib/feedzirra/parser/itunes_rss_owner.rb

@@ -0,0 +1,12 @@
+module Feedzirra
+  
+  module Parser
+    class ITunesRSSOwner
+      include SAXMachine
+      include FeedUtilities
+      element :"itunes:name", :as => :name
+      element :"itunes:email", :as => :email
+    end
+  end
+  
+end

data/lib/feedzirra/parser/rss.rb

@@ -0,0 +1,40 @@
+module Feedzirra
+  
+  module Parser
+    # == Summary
+    # Parser for dealing with RSS feeds.
+    #
+    # == Attributes
+    # * prev_page
+    # * next_page
+    # * lat_page
+    # * title
+    # * feed_url
+    # * url
+    # * related
+    # * description
+    # * language
+    # * entries
+    class RSS
+      include SAXMachine
+      include FeedUtilities
+      element :"atom:link", :as => :prev_page, :value => :href, :with => {:rel => 'prev'}
+      element :"atom:link", :as => :next_page, :value => :href, :with => {:rel => 'next'}
+      element :"atom:link", :as => :last_page, :value => :href, :with => {:rel => 'last'}
+      element :title
+      element :link, :as => :url
+      elements :link, :as => :related, :value => :href, :with => {:rel => "related"}
+      element :description
+      element :language
+      elements :item, :as => :entries, :class => RSSEntry
+
+      attr_accessor :feed_url
+
+      def self.able_to_parse?(xml) #:nodoc:
+        xml =~ /\<rss|rdf/
+      end
+    end
+
+  end
+  
+end

data/lib/feedzirra/parser/rss_entry.rb

@@ -0,0 +1,55 @@
+module Feedzirra
+  
+  module Parser
+    # == Summary
+    # Parser for dealing with RDF feed entries.
+    #
+    # == Attributes
+    # * title
+    # * url
+    # * related
+    # * author
+    # * content
+    # * summary
+    # * published
+    # * updated
+    # * categories
+    # * media_content
+    # * media_description
+    # * media_thumbnail
+    # * enclosure
+    class RSSEntry
+      include SAXMachine
+      include FeedEntryUtilities
+      element :title
+      element :link, :as => :url
+      elements :link, :as => :related, :value => :href, :with => {:rel => "related"}
+
+      element :author
+      element :"dc:creator", :as => :author
+      element :author, :as => :author
+      element :"content:encoded", :as => :content
+      element :description, :as => :summary
+
+      element :pubDate, :as => :published
+      element :pubdate, :as => :published
+      element :"dc:date", :as => :published
+      element :"dc:Date", :as => :published
+      element :"dcterms:created", :as => :published
+
+
+      element :"dcterms:modified", :as => :updated
+      element :issued, :as => :published
+      elements :category, :as => :categories
+
+      element :"media:content", :as => :media_content, :value => :url
+      element :"media:description", :as => :media_description
+      element :"media:thumbnail", :as => :media_thumbnail, :value => :url
+      element :enclosure, :value => :url
+
+      element :guid, :as => :id
+    end
+
+  end
+  
+end

data/spec/feedzirra/feed_spec.rb

@@ -11,11 +11,11 @@ describe Feedzirra::Feed do
     end
     
     it "should parse the added element out of Atom Feedburner feeds" do
-      Feedzirra::AtomEntry.new.should respond_to(:comment_rss)
+      Feedzirra::Parser::AtomEntry.new.should respond_to(:comment_rss)
     end
     
     it "should parse the added element out of RSS feeds" do
-      Feedzirra::RSSEntry.new.should respond_to(:comment_rss)
+      Feedzirra::Parser::RSSEntry.new.should respond_to(:comment_rss)
     end
   end
   
@@ -49,11 +49,14 @@ describe Feedzirra::Feed do
         feed.entries.size.should == 5
       end      
 
-      it "should parse an itunes feed" do
+      it "should parse an itunes feed as a standard RSS feed" do
         feed = Feedzirra::Feed.parse(sample_itunes_feed)
         feed.title.should == "All About Everything"
-        feed.entries.first.published.to_s.should == "Wed, 15 Jun 2005 19:00:00 GMT"
-        feed.entries.first.itunes_author.should == "John Doe"
+        feed.entries.first.published.should == Time.parse("Wed, 15 Jun 2005 19:00:00 GMT")
+        
+        # Since the commit 621957879, iTunes feeds will be parsed as standard RSS, so this
+        # entry should now not have a method for itunes_author.
+        feed.entries.first.should_not respond_to(:itunes_author)
         feed.entries.size.should == 3
       end
     end
@@ -75,28 +78,28 @@ describe Feedzirra::Feed do
   end
 
   describe "#determine_feed_parser_for_xml" do
-    it "should return the Feedzirra::Atom class for an atom feed" do
-      Feedzirra::Feed.determine_feed_parser_for_xml(sample_atom_feed).should == Feedzirra::Atom
+    it "should return the Feedzirra::Parser::Atom class for an atom feed" do
+      Feedzirra::Feed.determine_feed_parser_for_xml(sample_atom_feed).should == Feedzirra::Parser::Atom
     end
 
-    it "should return the Feedzirra::AtomFeedBurner class for an atom feedburner feed" do
-      Feedzirra::Feed.determine_feed_parser_for_xml(sample_feedburner_atom_feed).should == Feedzirra::AtomFeedBurner
+    it "should return the Feedzirra::Parser::AtomFeedBurner class for an atom feedburner feed" do
+      Feedzirra::Feed.determine_feed_parser_for_xml(sample_feedburner_atom_feed).should == Feedzirra::Parser::AtomFeedBurner
     end
 
-    it "should return the Feedzirra::RSS class for an rdf/rss 1.0 feed" do
-      Feedzirra::Feed.determine_feed_parser_for_xml(sample_rdf_feed).should == Feedzirra::RSS
+    it "should return the Feedzirra::Parser::RSS class for an rdf/rss 1.0 feed" do
+      Feedzirra::Feed.determine_feed_parser_for_xml(sample_rdf_feed).should == Feedzirra::Parser::RSS
     end
 
-    it "should return the Feedzirra::RSS class for an rss feedburner feed" do
-      Feedzirra::Feed.determine_feed_parser_for_xml(sample_rss_feed_burner_feed).should == Feedzirra::RSS
+    it "should return the Feedzirra::Parser::RSS class for an rss feedburner feed" do
+      Feedzirra::Feed.determine_feed_parser_for_xml(sample_rss_feed_burner_feed).should == Feedzirra::Parser::RSS
     end
 
-    it "should return the Feedzirra::RSS object for an rss 2.0 feed" do
-      Feedzirra::Feed.determine_feed_parser_for_xml(sample_rss_feed).should == Feedzirra::RSS
+    it "should return the Feedzirra::Parser::RSS object for an rss 2.0 feed" do
+      Feedzirra::Feed.determine_feed_parser_for_xml(sample_rss_feed).should == Feedzirra::Parser::RSS
     end
 
-    it "should return the Feedzirra::ITunesRSS object for an itunes feed" do
-      Feedzirra::Feed.determine_feed_parser_for_xml(sample_itunes_feed).should == Feedzirra::ITunesRSS
+    it "should return a Feedzirra::Parser::RSS object for an itunes feed" do
+      Feedzirra::Feed.determine_feed_parser_for_xml(sample_itunes_feed).should == Feedzirra::Parser::RSS
     end
 
   end
@@ -104,7 +107,7 @@ describe Feedzirra::Feed do
   describe "when adding feed types" do
     it "should prioritize added types over the built in ones" do
       feed_text = "Atom asdf"
-      Feedzirra::Atom.should be_able_to_parse(feed_text)
+      Feedzirra::Parser::Atom.should be_able_to_parse(feed_text)
       new_feed_type = Class.new do
         def self.able_to_parse?(val)
           true
@@ -193,7 +196,7 @@ describe Feedzirra::Feed do
       end
 
       it 'should set accepted encodings' do
-        Feedzirra::Feed.fetch_raw(@paul_feed[:url])
+        Feedzirra::Feed.fetch_raw(@paul_feed[:url], :compress => true)
         @curl.headers["Accept-encoding"].should == 'gzip, deflate'
       end
 
@@ -265,7 +268,7 @@ describe Feedzirra::Feed do
       end
       
       it 'should set accepted encodings' do
-        Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
+        Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {:compress => true})
         @easy_curl.headers["Accept-encoding"].should == 'gzip, deflate'
       end
 
@@ -278,8 +281,8 @@ describe Feedzirra::Feed do
         before(:each) do
           @feed = mock('feed', :feed_url= => true, :etag= => true, :last_modified= => true)
           Feedzirra::Feed.stub!(:decode_content).and_return(@paul_feed[:xml])
-          Feedzirra::Feed.stub!(:determine_feed_parser_for_xml).and_return(Feedzirra::AtomFeedBurner)
-          Feedzirra::AtomFeedBurner.stub!(:parse).and_return(@feed)
+          Feedzirra::Feed.stub!(:determine_feed_parser_for_xml).and_return(Feedzirra::Parser::AtomFeedBurner)
+          Feedzirra::Parser::AtomFeedBurner.stub!(:parse).and_return(@feed)
           Feedzirra::Feed.stub!(:etag_from_header).and_return('ziEyTl4q9GH04BR4jgkImd0GvSE')
           Feedzirra::Feed.stub!(:last_modified_from_header).and_return('Wed, 28 Jan 2009 04:10:32 GMT')
         end
@@ -291,13 +294,13 @@ describe Feedzirra::Feed do
         end
         
         it 'should determine the xml parser class' do
-          Feedzirra::Feed.should_receive(:determine_feed_parser_for_xml).with(@paul_feed[:xml]).and_return(Feedzirra::AtomFeedBurner)
+          Feedzirra::Feed.should_receive(:determine_feed_parser_for_xml).with(@paul_feed[:xml]).and_return(Feedzirra::Parser::AtomFeedBurner)
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
           @easy_curl.on_success.call(@easy_curl)
         end
 
         it 'should parse the xml' do
-          Feedzirra::AtomFeedBurner.should_receive(:parse).with(@paul_feed[:xml]).and_return(@feed)
+          Feedzirra::Parser::AtomFeedBurner.should_receive(:parse).with(@paul_feed[:xml]).and_return(@feed)
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
           @easy_curl.on_success.call(@easy_curl)
         end
@@ -415,8 +418,8 @@ describe Feedzirra::Feed do
           @new_feed = @feed.clone
           @feed.stub!(:update_from_feed)
           Feedzirra::Feed.stub!(:decode_content).and_return(@paul_feed[:xml])
-          Feedzirra::Feed.stub!(:determine_feed_parser_for_xml).and_return(Feedzirra::AtomFeedBurner)
-          Feedzirra::AtomFeedBurner.stub!(:parse).and_return(@new_feed)
+          Feedzirra::Feed.stub!(:determine_feed_parser_for_xml).and_return(Feedzirra::Parser::AtomFeedBurner)
+          Feedzirra::Parser::AtomFeedBurner.stub!(:parse).and_return(@new_feed)
           Feedzirra::Feed.stub!(:etag_from_header).and_return('ziEyTl4q9GH04BR4jgkImd0GvSE')
           Feedzirra::Feed.stub!(:last_modified_from_header).and_return('Wed, 28 Jan 2009 04:10:32 GMT')
         end
@@ -424,7 +427,7 @@ describe Feedzirra::Feed do
         it 'should process the next feed in the queue'
         
         it 'should parse the updated feed' do
-          Feedzirra::AtomFeedBurner.should_receive(:parse).and_return(@new_feed)
+          Feedzirra::Parser::AtomFeedBurner.should_receive(:parse).and_return(@new_feed)
           Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
           @easy_curl.on_success.call(@easy_curl)
         end

data/spec/feedzirra/feed_utilities_spec.rb

@@ -42,19 +42,19 @@ describe Feedzirra::FeedUtilities do
     end
     
     it "should return a last_modified value from the entry with the most recent published date if the last_modified date hasn't been set" do
-      feed = Feedzirra::Atom.new
-      entry =Feedzirra::AtomEntry.new
+      feed = Feedzirra::Parser::Atom.new
+      entry =Feedzirra::Parser::AtomEntry.new
       entry.published = Time.now.to_s
       feed.entries << entry
       feed.last_modified.should == entry.published
     end
     
     it "should not throw an error if one of the entries has published date of nil" do
-      feed = Feedzirra::Atom.new
-      entry = Feedzirra::AtomEntry.new
+      feed = Feedzirra::Parser::Atom.new
+      entry = Feedzirra::Parser::AtomEntry.new
       entry.published = Time.now.to_s
       feed.entries << entry
-      feed.entries << Feedzirra::AtomEntry.new
+      feed.entries << Feedzirra::Parser::AtomEntry.new
       feed.last_modified.should == entry.published
     end
   end
@@ -64,7 +64,7 @@ describe Feedzirra::FeedUtilities do
       before(:each) do
         # I'm using the Atom class when I know I should be using a different one. However, this update_from_feed
         # method would only be called against a feed item.
-        @feed = Feedzirra::Atom.new
+        @feed = Feedzirra::Parser::Atom.new
         @feed.title    = "A title"
         @feed.url      = "http://pauldix.net"
         @feed.feed_url = "http://feeds.feedburner.com/PaulDixExplainsNothing"
@@ -112,16 +112,16 @@ describe Feedzirra::FeedUtilities do
       before(:each) do
         # I'm using the Atom class when I know I should be using a different one. However, this update_from_feed
         # method would only be called against a feed item.
-        @feed = Feedzirra::Atom.new
+        @feed = Feedzirra::Parser::Atom.new
         @feed.title    = "A title"
         @feed.url      = "http://pauldix.net"
         @feed.feed_url = "http://feeds.feedburner.com/PaulDixExplainsNothing"
         @feed.updated  = false
         @updated_feed = @feed.dup
-        @old_entry = Feedzirra::AtomEntry.new
+        @old_entry = Feedzirra::Parser::AtomEntry.new
         @old_entry.url = "http://pauldix.net/old.html"
         @old_entry.published = Time.now.to_s
-        @new_entry = Feedzirra::AtomEntry.new
+        @new_entry = Feedzirra::Parser::AtomEntry.new
         @new_entry.url = "http://pauldix.net/new.html"
         @new_entry.published = (Time.now + 10).to_s  
         @feed.entries << @old_entry

data/spec/feedzirra/{atom_entry_spec.rb → parser/atom_entry_spec.rb}

@@ -1,10 +1,10 @@
-require File.dirname(__FILE__) + '/../spec_helper'
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
 
-describe Feedzirra::AtomEntry do
+describe Feedzirra::Parser::AtomEntry do
   before(:each) do
     # I don't really like doing it this way because these unit test should only rely on AtomEntry,
     # but this is actually how it should work. You would never just pass entry xml straight to the AtomEnry
-    @entry = Feedzirra::Atom.parse(sample_atom_feed).entries.first
+    @entry = Feedzirra::Parser::Atom.parse(sample_atom_feed).entries.first
   end
   
   it "should parse the title" do
@@ -15,6 +15,10 @@ describe Feedzirra::AtomEntry do
     @entry.url.should == "http://aws.typepad.com/aws/2009/01/aws-job-architect-designer-position-in-turkey.html"
   end
   
+  it "should parse the url even when" do
+    Feedzirra::Parser::Atom.parse(load_sample("atom_with_link_tag_for_url_unmarked.xml")).entries.first.url.should == "http://www.innoq.com/blog/phaus/2009/07/ja.html"
+  end
+  
   it "should parse the author" do
     @entry.author.should == "AWS Editor"
   end

data/spec/feedzirra/{atom_feed_burner_entry_spec.rb → parser/atom_feed_burner_entry_spec.rb}

@@ -1,10 +1,10 @@
-require File.dirname(__FILE__) + '/../spec_helper'
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
 
-describe Feedzirra::AtomFeedBurnerEntry do
+describe Feedzirra::Parser::AtomFeedBurnerEntry do
   before(:each) do
     # I don't really like doing it this way because these unit test should only rely on AtomEntry,
     # but this is actually how it should work. You would never just pass entry xml straight to the AtomEnry
-    @entry = Feedzirra::AtomFeedBurner.parse(sample_feedburner_atom_feed).entries.first
+    @entry = Feedzirra::Parser::AtomFeedBurner.parse(sample_feedburner_atom_feed).entries.first
   end
   
   it "should parse the title" do
@@ -12,7 +12,7 @@ describe Feedzirra::AtomFeedBurnerEntry do
   end
   
   it "should be able to fetch a url via the 'alternate' rel if no origLink exists" do
-    entry = Feedzirra::AtomFeedBurner.parse(File.read("#{File.dirname(__FILE__)}/../sample_feeds/PaulDixExplainsNothingAlternate.xml")).entries.first
+    entry = Feedzirra::Parser::AtomFeedBurner.parse(File.read("#{File.dirname(__FILE__)}/../../sample_feeds/PaulDixExplainsNothingAlternate.xml")).entries.first
     entry.url.should == 'http://feeds.feedburner.com/~r/PaulDixExplainsNothing/~3/519925023/making-a-ruby-c-library-even-faster.html'
   end
 

data/spec/feedzirra/{atom_feed_burner_spec.rb → parser/atom_feed_burner_spec.rb}

@@ -1,23 +1,23 @@
-require File.dirname(__FILE__) + '/../spec_helper'
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
 
-describe Feedzirra::AtomFeedBurner do
+describe Feedzirra::Parser::AtomFeedBurner do
   describe "#will_parse?" do
     it "should return true for a feedburner atom feed" do
-      Feedzirra::AtomFeedBurner.should be_able_to_parse(sample_feedburner_atom_feed)
+      Feedzirra::Parser::AtomFeedBurner.should be_able_to_parse(sample_feedburner_atom_feed)
     end
     
     it "should return false for an rdf feed" do
-      Feedzirra::AtomFeedBurner.should_not be_able_to_parse(sample_rdf_feed)
+      Feedzirra::Parser::AtomFeedBurner.should_not be_able_to_parse(sample_rdf_feed)
     end
     
     it "should return false for a regular atom feed" do
-      Feedzirra::AtomFeedBurner.should_not be_able_to_parse(sample_atom_feed)
+      Feedzirra::Parser::AtomFeedBurner.should_not be_able_to_parse(sample_atom_feed)
     end
   end
 
   describe "parsing" do
     before(:each) do
-      @feed = Feedzirra::AtomFeedBurner.parse(sample_feedburner_atom_feed)
+      @feed = Feedzirra::Parser::AtomFeedBurner.parse(sample_feedburner_atom_feed)
     end
     
     it "should parse the title" do

data/spec/feedzirra/{atom_spec.rb → parser/atom_spec.rb}

@@ -1,19 +1,19 @@
-require File.dirname(__FILE__) + '/../spec_helper'
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
 
-describe Feedzirra::Atom do
+describe Feedzirra::Parser::Atom do
   describe "#will_parse?" do
     it "should return true for an atom feed" do
-      Feedzirra::Atom.should be_able_to_parse(sample_atom_feed)
+      Feedzirra::Parser::Atom.should be_able_to_parse(sample_atom_feed)
     end
     
     it "should return false for an rdf feed" do
-      Feedzirra::Atom.should_not be_able_to_parse(sample_rdf_feed)
+      Feedzirra::Parser::Atom.should_not be_able_to_parse(sample_rdf_feed)
     end
   end
   
   describe "parsing" do
     before(:each) do
-      @feed = Feedzirra::Atom.parse(sample_atom_feed)
+      @feed = Feedzirra::Parser::Atom.parse(sample_atom_feed)
     end
     
     it "should parse the title" do
@@ -23,7 +23,7 @@ describe Feedzirra::Atom do
     it "should parse the url" do
       @feed.url.should == "http://aws.typepad.com/aws/"
     end
-
+    
     it "should parse updated" do
       @feed.updated.should == "2009-01-16T18:21:00Z"
     end
@@ -32,10 +32,18 @@ describe Feedzirra::Atom do
       @feed.subtitle.should == "Amazon Web Services, Products, Tools, and Developer Information..."
     end
 
+    it "should parse the url even when it doesn't have the type='text/html' attribute" do
+      Feedzirra::Parser::Atom.parse(load_sample("atom_with_link_tag_for_url_unmarked.xml")).url.should == "http://www.innoq.com/planet/"
+    end
+    
+    it "should parse the feed_url even when it doesn't have the type='application/atom+xml' attribute" do
+      Feedzirra::Parser::Atom.parse(load_sample("atom_with_link_tag_for_url_unmarked.xml")).feed_url.should == "http://www.innoq.com/planet/atom.xml"
+    end
+    
     it "should parse the feed_url" do
       @feed.feed_url.should == "http://aws.typepad.com/aws/atom.xml"
     end
-
+    
     it "should parse the prev atom:link" do
       @feed.prev_page.should == "http://aws.typepad.com/aws/atom.xml?page=1"
     end
@@ -47,7 +55,7 @@ describe Feedzirra::Atom do
     it "should parse the last atom:link" do
       @feed.last_page.should == "http://aws.typepad.com/aws/atom.xml?page=5"
     end
-
+    
     it "should parse entries" do
       @feed.entries.size.should == 10
     end