jashmenn-feedzirra 0.1.3

data/spec/feedzirra/parser/itunes_rss_owner_spec.rb

@@ -0,0 +1,18 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedzirra::Parser::ITunesRSSOwner 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 ITunesRssOwner
+    @owner = Feedzirra::Parser::ITunesRSS.parse(sample_itunes_feed).itunes_owners.first
+  end
+  
+  it "should parse the name" do
+    @owner.name.should == "John Doe"
+  end
+  
+  it "should parse the email" do
+    @owner.email.should == "john.doe@example.com"
+  end  
+
+end

data/spec/feedzirra/parser/itunes_rss_spec.rb

@@ -0,0 +1,54 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedzirra::Parser::ITunesRSS do
+  describe "#will_parse?" do
+    it "should return true for an itunes RSS feed" do
+      Feedzirra::Parser::ITunesRSS.should be_able_to_parse(sample_itunes_feed)
+    end
+
+    it "should return fase for an atom feed" do
+      Feedzirra::Parser::ITunesRSS.should_not be_able_to_parse(sample_atom_feed)
+    end
+    
+    it "should return false for an rss feedburner feed" do
+      Feedzirra::Parser::ITunesRSS.should_not be_able_to_parse(sample_rss_feed_burner_feed)
+    end
+  end
+
+  describe "parsing" do
+    before(:each) do
+      @feed = Feedzirra::Parser::ITunesRSS.parse(sample_itunes_feed)
+    end
+    
+    it "should parse the subtitle" do
+      @feed.itunes_subtitle.should == "A show about everything"
+    end
+    
+    it "should parse the author" do
+      @feed.itunes_author.should == "John Doe"
+    end
+    
+    it "should parse an owner" do
+      @feed.itunes_owners.size.should == 1
+    end
+    
+    it "should parse an image" do
+      @feed.itunes_image.should == "http://example.com/podcasts/everything/AllAboutEverything.jpg"
+    end
+    
+    it "should parse categories" do
+      @feed.itunes_categories.size == 3
+      @feed.itunes_categories[0] == "Technology"
+      @feed.itunes_categories[1] == "Gadgets"
+      @feed.itunes_categories[2] == "TV & Film"
+    end
+
+    it "should parse the summary" do
+      @feed.itunes_summary.should == "All About Everything is a show about everything. Each week we dive into any subject known to man and talk about it as much as we can. Look for our Podcast in the iTunes Music Store"
+    end
+    
+    it "should parse entries" do
+      @feed.entries.size.should == 3
+    end
+  end
+end

data/spec/feedzirra/parser/rss_entry_spec.rb

@@ -0,0 +1,85 @@
+# coding: utf-8
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedzirra::Parser::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::Parser::RSS.parse(sample_rss_feed).entries.first
+  end
+
+  after(:each) do
+    # We change the title in one or more specs to test []=
+    if @entry.title != "Nokogiri’s Slop Feature"
+      @entry.title = Feedzirra::Parser::RSS.parse(sample_rss_feed).entries.first.title
+    end
+  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
+
+  it "should parse the guid as id" do
+    @entry.id.should == "http://tenderlovemaking.com/?p=198"
+  end
+
+  it "should support each" do
+    @entry.respond_to? :each
+  end
+
+  it "should be able to list out all fields with each" do
+    all_fields = []
+    @entry.each do |field, value|
+      all_fields << field
+    end
+    all_fields.sort == ['author', 'categories', 'content', 'id', 'published', 'summary', 'title', 'url']
+  end
+
+  it "should be able to list out all values with each" do
+    title_value = ''
+    @entry.each do |field, value|
+      title_value = value if field == 'title'
+    end
+    title_value.should == "Nokogiri’s Slop Feature"
+  end
+
+  it "should support checking if a field exists in the entry" do
+    @entry.include?('title') && @entry.include?('author')
+  end
+
+  it "should allow access to fields with hash syntax" do
+    @entry['title'] == @entry.title
+    @entry['title'].should == "Nokogiri’s Slop Feature"
+    @entry['author'] == @entry.author
+    @entry['author'].should == "Aaron Patterson"
+  end
+
+  it "should allow setting field values with hash syntax" do
+    @entry['title'] = "Foobar"
+    @entry.title.should == "Foobar"
+  end
+end

data/spec/feedzirra/parser/rss_feed_burner_entry_spec.rb

@@ -0,0 +1,85 @@
+# coding: utf-8
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedzirra::Parser::RSSFeedBurnerEntry 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::Parser::RSSFeedBurner.parse(sample_rss_feed_burner_feed).entries.first
+  end
+
+  after(:each) do
+    # We change the title in one or more specs to test []=
+    if @entry.title != "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M"
+      @entry.title = Feedzirra::Parser::RSS.parse(sample_rss_feed_burner_feed).entries.first.title
+    end
+  end
+
+  it "should parse the title" do
+    @entry.title.should == "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M"
+  end
+
+  it "should parse the original url" do
+    @entry.url.should == "http://techcrunch.com/2011/11/02/angies-list-prices-ipo-at-11-to-13-per-share-valued-at-over-600m/"
+  end
+  
+  it "should parse the author" do
+    @entry.author.should == "Leena Rao"
+  end
+
+  it "should parse the content" do
+    @entry.content.should == sample_rss_feed_burner_entry_content
+  end
+
+  it "should provide a summary" do
+    @entry.summary.should == sample_rss_feed_burner_entry_description
+  end
+
+  it "should parse the published date" do
+    @entry.published.to_s.should == "Wed Nov 02 17:25:27 UTC 2011"
+  end
+
+  it "should parse the categories" do
+    @entry.categories.should == ["TC", "angie\\'s list"]
+  end
+
+  it "should parse the guid as id" do
+    @entry.id.should == "http://techcrunch.com/?p=446154"
+  end
+
+  it "should support each" do
+    @entry.respond_to? :each
+  end
+
+  it "should be able to list out all fields with each" do
+    all_fields = []
+    @entry.each do |field, value|
+      all_fields << field
+    end
+    all_fields.sort == ['author', 'categories', 'content', 'id', 'published', 'summary', 'title', 'url']
+  end
+
+  it "should be able to list out all values with each" do
+    title_value = ''
+    @entry.each do |field, value|
+      title_value = value if field == 'title'
+    end
+    title_value.should == "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M"
+  end
+
+  it "should support checking if a field exists in the entry" do
+    @entry.include?('title') && @entry.include?('author')
+  end
+
+  it "should allow access to fields with hash syntax" do
+    @entry['title'] == @entry.title
+    @entry['title'].should == "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M"
+    @entry['author'] == @entry.author
+    @entry['author'].should == "Leena Rao"
+  end
+
+  it "should allow setting field values with hash syntax" do
+    @entry['title'] = "Foobar"
+    @entry.title.should == "Foobar"
+  end
+end

data/spec/feedzirra/parser/rss_feed_burner_spec.rb

@@ -0,0 +1,52 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedzirra::Parser::RSSFeedBurner do
+  describe "#will_parse?" do
+    it "should return true for a feedburner rss feed" do
+      Feedzirra::Parser::RSSFeedBurner.should be_able_to_parse(sample_rss_feed_burner_feed)
+    end
+    
+    it "should return false for a regular RSS feed" do
+       Feedzirra::Parser::RSSFeedBurner.should_not be_able_to_parse(sample_rss_feed)
+     end
+    
+    it "should return false for a feedburner atom feed" do
+      Feedzirra::Parser::RSSFeedBurner.should_not be_able_to_parse(sample_feedburner_atom_feed)
+    end
+    
+    it "should return false for an rdf feed" do
+      Feedzirra::Parser::RSSFeedBurner.should_not be_able_to_parse(sample_rdf_feed)
+    end
+    
+    it "should return false for a regular atom feed" do
+      Feedzirra::Parser::RSSFeedBurner.should_not be_able_to_parse(sample_atom_feed)
+    end
+  end
+
+  describe "parsing" do
+    before(:each) do
+      @feed = Feedzirra::Parser::RSSFeedBurner.parse(sample_rss_feed_burner_feed)
+    end
+    
+    it "should parse the title" do
+      @feed.title.should == "TechCrunch"
+    end
+
+    it "should parse the description" do
+      @feed.description.should == "TechCrunch is a group-edited blog that profiles the companies, products and events defining and transforming the new web."
+    end
+
+    it "should parse the url" do
+      @feed.url.should == "http://techcrunch.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 == 20
+    end
+  end
+end

data/spec/feedzirra/parser/rss_spec.rb

@@ -0,0 +1,49 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedzirra::Parser::RSS do
+  describe "#will_parse?" do
+    it "should return true for an RSS feed" do
+      Feedzirra::Parser::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 false for an atom feed" do
+      Feedzirra::Parser::RSS.should_not be_able_to_parse(sample_atom_feed)
+    end
+    
+    it "should return false for an rss feedburner feed" do
+      Feedzirra::Parser::RSS.should_not be_able_to_parse(sample_rss_feed_burner_feed)
+    end
+  end
+
+  describe "parsing" do
+    before(:each) do
+      @feed = Feedzirra::Parser::RSS.parse(sample_rss_feed)
+    end
+    
+    it "should parse the title" do
+      @feed.title.should == "Tender Lovemaking"
+    end
+
+    it "should parse the description" do
+      @feed.description.should == "The act of making love, tenderly."
+    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/sample_feeds/run_against_sample.rb

@@ -0,0 +1,20 @@
+require 'rubygems'
+require File.dirname(__FILE__) + "/../../lib/feedzirra.rb"
+
+feed_urls = File.readlines(File.dirname(__FILE__) + "/top5kfeeds.dat").collect {|line| line.split.first}
+
+success = lambda do |url, feed|
+  puts "SUCCESS - #{feed.title} - #{url}"
+end
+
+failed_feeds = []
+failure = lambda do |url, response_code, header, body|
+  failed_feeds << url if response_code == 200
+  puts "*********** FAILED with #{response_code} on #{url}"
+end
+
+Feedzirra::Feed.fetch_and_parse(feed_urls, :on_success => success, :on_failure => failure)
+
+File.open("./failed_urls.txt", "w") do |f|
+  f.write failed_feeds.join("\n")
+end

data/spec/spec_helper.rb

@@ -0,0 +1,78 @@
+require "rubygems"
+require "rspec"
+
+# 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 "feedzirra"
+
+def load_sample(filename)
+  File.read("#{File.dirname(__FILE__)}/sample_feeds/#{filename}")
+end
+
+def sample_atom_feed
+  load_sample("AmazonWebServicesBlog.xml")
+end
+
+def sample_atom_entry_content
+  load_sample("AmazonWebServicesBlogFirstEntryContent.xml")
+end
+
+def sample_itunes_feed
+  load_sample("itunes.xml")
+end
+
+def sample_rdf_feed
+  load_sample("HREFConsideredHarmful.xml")
+end
+
+def sample_rdf_entry_content
+  load_sample("HREFConsideredHarmfulFirstEntry.xml")
+end
+
+def sample_rss_feed_burner_feed
+  load_sample("TechCrunch.xml")
+end
+
+def sample_rss_feed_burner_entry_content
+  load_sample("TechCrunchFirstEntry.xml")
+end
+
+def sample_rss_feed_burner_entry_description
+  load_sample("TechCrunchFirstEntryDescription.xml")
+end
+
+def sample_rss_feed
+  load_sample("TenderLovemaking.xml")
+end
+
+def sample_rss_entry_content
+  load_sample("TenderLovemakingFirstEntry.xml")
+end
+
+def sample_feedburner_atom_feed
+  load_sample("PaulDixExplainsNothing.xml")
+end
+
+def sample_feedburner_atom_entry_content
+  load_sample("PaulDixExplainsNothingFirstEntryContent.xml")
+end
+
+def sample_wfw_feed
+  load_sample("PaulDixExplainsNothingWFW.xml")
+end       
+
+def sample_google_docs_list_feed
+  load_sample("GoogleDocsList.xml")
+end       
+       
+# http://eigenclass.org/hiki/Changes+in+Ruby+1.9#l156
+# Default Time.to_s changed in 1.9, monkeypatching it back
+class Time
+  def to_s
+    strftime("%a %b %d %H:%M:%S %Z %Y")
+  end
+end