jeffrafter-feedzirra 0.0.4

data/spec/feedzirra/feed_utilities_spec.rb

@@ -0,0 +1,149 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+
+describe Feedzirra::FeedUtilities do
+  before(:each) do
+    @klass = Class.new do
+      include Feedzirra::FeedUtilities
+    end
+  end
+
+  describe "instance methods" do
+    it "should provide an updated? accessor" do
+      feed = @klass.new
+      feed.should_not be_updated
+      feed.updated = true
+      feed.should be_updated
+    end
+    
+    it "should provide a new_entries accessor" do
+      feed = @klass.new
+      feed.new_entries.should == []
+      feed.new_entries = [:foo]
+      feed.new_entries.should == [:foo]
+    end
+    
+    it "should provide an etag accessor" do
+      feed = @klass.new
+      feed.etag = "foo"
+      feed.etag.should == "foo"
+    end
+    
+    it "should provide a last_modified accessor" do
+      feed = @klass.new
+      time = Time.now
+      feed.last_modified = time
+      feed.last_modified.should == time
+    end
+    
+    it "should return new_entries? as true when entries are put into new_entries" do
+      feed = @klass.new
+      feed.new_entries << :foo
+      feed.should have_new_entries
+    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
+      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
+      entry.published = Time.now.to_s
+      feed.entries << entry
+      feed.entries << Feedzirra::AtomEntry.new
+      feed.last_modified.should == entry.published
+    end
+  end
+  
+  describe "#update_from_feed" do
+    describe "updating feed attributes" 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.title    = "A title"
+        @feed.url      = "http://pauldix.net"
+        @feed.feed_url = "http://feeds.feedburner.com/PaulDixExplainsNothing"
+        @feed.updated  = false
+        @updated_feed = @feed.dup
+      end
+    
+      it "should update the title if changed" do
+        @updated_feed.title = "new title"
+        @feed.update_from_feed(@updated_feed)
+        @feed.title.should == @updated_feed.title
+        @feed.should be_updated
+      end
+    
+      it "should not update the title if the same" do
+        @feed.update_from_feed(@updated_feed)
+        @feed.should_not be_updated      
+      end
+    
+      it "should update the feed_url if changed" do
+        @updated_feed.feed_url = "a new feed url"
+        @feed.update_from_feed(@updated_feed)
+        @feed.feed_url.should == @updated_feed.feed_url
+        @feed.should be_updated
+      end
+    
+      it "should not update the feed_url if the same" do
+        @feed.update_from_feed(@updated_feed)
+        @feed.should_not be_updated
+      end
+    
+      it "should update the url if changed" do
+        @updated_feed.url = "a new url"
+        @feed.update_from_feed(@updated_feed)
+        @feed.url.should == @updated_feed.url
+      end
+    
+      it "should not update the url if not changed" do
+        @feed.update_from_feed(@updated_feed)
+        @feed.should_not be_updated
+      end
+    end
+    
+    describe "updating entries" 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.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.url = "http://pauldix.net/old.html"
+        @old_entry.published = Time.now.to_s
+        @new_entry = Feedzirra::AtomEntry.new
+        @new_entry.url = "http://pauldix.net/new.html"
+        @new_entry.published = (Time.now + 10).to_s  
+        @feed.entries << @old_entry
+        @updated_feed.entries << @new_entry
+        @updated_feed.entries << @old_entry
+      end
+      
+      it "should update last-modified from the latest entry date" do
+        @feed.update_from_feed(@updated_feed)
+        @feed.last_modified.should == @new_entry.published
+      end
+      
+      it "should put new entries into new_entries" do
+        @feed.update_from_feed(@updated_feed)
+        @feed.new_entries.should == [@new_entry]
+      end
+      
+      it "should also put new entries into the entries collection" do
+        @feed.update_from_feed(@updated_feed)
+        @feed.entries.should include(@new_entry)
+        @feed.entries.should include(@old_entry)
+      end
+    end
+  end
+end

data/spec/feedzirra/rdf_entry_spec.rb

@@ -0,0 +1,33 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+
+describe Feedzirra::RDFEntry 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::RDF.parse(sample_rdf_feed).entries.first
+  end
+  
+  it "should parse the title" do
+    @entry.title.should == "Chrome, V8 and Strongtalk"
+  end
+  
+  it "should parse the url" do
+    @entry.url.should == "http://www.avibryant.com/2008/09/chrome-v8-and-s.html"
+  end
+  
+  it "should parse the author" do
+    @entry.author.should == "Avi"
+  end
+  
+  it "should parse the content" do
+    @entry.content.should == sample_rdf_entry_content
+  end
+  
+  it "should provide a summary" do
+    @entry.summary.should == "There's lots to like about Google's new web browser, Chrome, which was released today. When I read the awesome comic strip introduction yesterday, however, the thing that stood out most for me was in very small type: the name Lars..."
+  end
+  
+  it "should parse the published date" do
+    @entry.published.to_s.should == "Tue Sep 02 19:50:07 UTC 2008"
+  end
+end

data/spec/feedzirra/rdf_spec.rb

@@ -0,0 +1,37 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+
+describe Feedzirra::RDF do
+  describe "#will_parse?" do
+    it "should return true for an rdf feed" do
+      Feedzirra::RDF.should be_able_to_parse(sample_rdf_feed)
+    end
+    
+    it "should return false for an atom feed" do
+      Feedzirra::RDF.should_not be_able_to_parse(sample_atom_feed)
+    end
+  end
+  
+  describe "parsing" do
+    before(:each) do
+      @feed = Feedzirra::RDF.parse(sample_rdf_feed)
+    end
+    
+    it "should parse the title" do
+      @feed.title.should == "HREF Considered Harmful"
+    end
+    
+    it "should parse the url" do
+      @feed.url.should == "http://www.avibryant.com/"
+    end
+    
+    # rdf doesn't actually specify the feed_url. This should be set in the fetcher.
+    it "should provide an accessor for the feed_url" do
+      @feed.respond_to?(:feed_url).should == true
+      @feed.respond_to?(:feed_url=).should == true
+    end
+    
+    it "should parse entries" do
+      @feed.entries.size.should == 10
+    end    
+  end
+end

data/spec/feedzirra/rss_entry_spec.rb

@@ -0,0 +1,37 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+
+describe Feedzirra::RSSEntry do
+  before(:each) do
+    # I don't really like doing it this way because these unit test should only rely on RSSEntry,
+    # but this is actually how it should work. You would never just pass entry xml straight to the AtomEnry
+    @entry = Feedzirra::RSS.parse(sample_rss_feed).entries.first
+  end
+  
+  it "should parse the title" do
+    @entry.title.should == "Nokogiri’s Slop Feature"
+  end
+  
+  it "should parse the url" do
+    @entry.url.should == "http://tenderlovemaking.com/2008/12/04/nokogiris-slop-feature/"
+  end
+  
+  it "should parse the author" do
+    @entry.author.should == "Aaron Patterson"
+  end
+  
+  it "should parse the content" do
+    @entry.content.should == sample_rss_entry_content
+  end
+  
+  it "should provide a summary" do
+    @entry.summary.should == "Oops!  When I released nokogiri version 1.0.7, I totally forgot to talk about Nokogiri::Slop() feature that was added.  Why is it called \"slop\"?  It lets you sloppily explore documents.  Basically, it decorates your document with method_missing() that allows you to search your document via method calls.\nGiven this document:\n\ndoc = Nokogiri::Slop(<<-eohtml)\n<html>\n  <body>\n  [...]"
+  end
+  
+  it "should parse the published date" do
+    @entry.published.to_s.should == "Thu Dec 04 17:17:49 UTC 2008"
+  end
+
+  it "should parse the categories" do
+    @entry.categories.should == ['computadora', 'nokogiri', 'rails']
+  end
+end

data/spec/feedzirra/rss_spec.rb

@@ -0,0 +1,41 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+
+describe Feedzirra::RSS do
+  describe "#will_parse?" do
+    it "should return true for an RSS feed" do
+      Feedzirra::RSS.should be_able_to_parse(sample_rss_feed)
+    end
+
+    # this is no longer true. combined rdf and rss into one
+    # it "should return false for an rdf feed" do
+    #   Feedzirra::RSS.should_not be_able_to_parse(sample_rdf_feed)
+    # end
+    
+    it "should return fase for an atom feed" do
+      Feedzirra::RSS.should_not be_able_to_parse(sample_atom_feed)
+    end
+  end
+
+  describe "parsing" do
+    before(:each) do
+      @feed = Feedzirra::RSS.parse(sample_rss_feed)
+    end
+    
+    it "should parse the title" do
+      @feed.title.should == "Tender Lovemaking"
+    end
+    
+    it "should parse the url" do
+      @feed.url.should == "http://tenderlovemaking.com"
+    end
+    
+    it "should provide an accessor for the feed_url" do
+      @feed.respond_to?(:feed_url).should == true
+      @feed.respond_to?(:feed_url=).should == true
+    end
+    
+    it "should parse entries" do
+      @feed.entries.size.should == 10
+    end
+  end
+end

data/spec/spec.opts

@@ -0,0 +1,2 @@
+--diff
+--color

data/spec/spec_helper.rb

@@ -0,0 +1,50 @@
+require "rubygems"
+require "spec"
+
+# gem install redgreen for colored test output
+begin require "redgreen" unless ENV['TM_CURRENT_LINE']; rescue LoadError; end
+
+path = File.expand_path(File.dirname(__FILE__) + "/../lib/")
+$LOAD_PATH.unshift(path) unless $LOAD_PATH.include?(path)
+
+require "lib/feedzirra"
+
+def sample_atom_feed
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/AmazonWebServicesBlog.xml")
+end
+
+def sample_atom_entry_content
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/AmazonWebServicesBlogFirstEntryContent.xml")
+end
+
+def sample_rdf_feed
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/HREFConsideredHarmful.xml")
+end
+
+def sample_rdf_entry_content
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/HREFConsideredHarmfulFirstEntry.xml")
+end
+
+def sample_rss_feed_burner_feed
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/SamHarrisAuthorPhilosopherEssayistAtheist.xml")
+end
+
+def sample_rss_feed
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/TenderLovemaking.xml")
+end
+
+def sample_rss_entry_content
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/TenderLovemakingFirstEntry.xml")
+end
+
+def sample_feedburner_atom_feed
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/PaulDixExplainsNothing.xml")
+end
+
+def sample_feedburner_atom_entry_content
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/PaulDixExplainsNothingFirstEntryContent.xml")
+end
+
+def sample_google_news_atom_feed
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/GoogleNewsSearch.xml")
+end

metadata

@@ -0,0 +1,139 @@
+--- !ruby/object:Gem::Specification 
+name: jeffrafter-feedzirra
+version: !ruby/object:Gem::Version 
+  version: 0.0.4
+platform: ruby
+authors: 
+- Paul Dix
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-02-19 00:00:00 -08:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">"
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: pauldix-sax-machine
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.0.9
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: taf2-curb
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.2.3
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: builder
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 2.1.2
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: activesupport
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 2.0.0
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: mdalessio-dryopteris
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
+    version: 
+description: 
+email: paul@pauldix.net
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/core_ext/date.rb
+- lib/feedzirra.rb
+- lib/feedzirra/feed.rb
+- lib/feedzirra/atom.rb
+- lib/feedzirra/atom_entry.rb
+- lib/feedzirra/atom_feed_burner.rb
+- lib/feedzirra/atom_feed_burner_entry.rb
+- lib/feedzirra/rdf.rb
+- lib/feedzirra/rdf_entry.rb
+- lib/feedzirra/rss.rb
+- lib/feedzirra/rss_entry.rb
+- lib/feedzirra/feed_utilities.rb
+- lib/feedzirra/feed_entry_utilities.rb
+- README.textile
+- Rakefile
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/feedzirra/feed_spec.rb
+- spec/feedzirra/atom_spec.rb
+- spec/feedzirra/atom_entry_spec.rb
+- spec/feedzirra/atom_feed_burner_spec.rb
+- spec/feedzirra/atom_feed_burner_entry_spec.rb
+- spec/feedzirra/rdf_spec.rb
+- spec/feedzirra/rdf_entry_spec.rb
+- spec/feedzirra/rss_spec.rb
+- spec/feedzirra/rss_entry_spec.rb
+- spec/feedzirra/feed_utilities_spec.rb
+- spec/feedzirra/feed_entry_utilities_spec.rb
+has_rdoc: true
+homepage: http://github.com/pauldix/feedzirra
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 2
+summary: "A feed fetching and parsing library that treats the internet like Godzilla treats Japan: it dominates and eats all."
+test_files: []
+