feedjira 0.9.0

data/spec/feedjira/parser/atom_spec.rb

@@ -0,0 +1,76 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedjira::Parser::Atom do
+  describe "#will_parse?" do
+    it "should return true for an atom feed" do
+      Feedjira::Parser::Atom.should be_able_to_parse(sample_atom_feed)
+    end
+
+    it "should return false for an rdf feed" do
+      Feedjira::Parser::Atom.should_not be_able_to_parse(sample_rdf_feed)
+    end
+
+    it "should return false for an rss feedburner feed" do
+      Feedjira::Parser::Atom.should_not be_able_to_parse(sample_rss_feed_burner_feed)
+    end
+
+    it "should return true for an atom feed that has line breaks in between attributes in the <feed> node" do
+      Feedjira::Parser::Atom.should be_able_to_parse(sample_atom_feed_line_breaks)
+    end
+  end
+
+  describe "parsing" do
+    before(:each) do
+      @feed = Feedjira::Parser::Atom.parse(sample_atom_feed)
+    end
+
+    it "should parse the title" do
+      @feed.title.should == "Amazon Web Services Blog"
+    end
+
+    it "should parse the description" do
+      @feed.description.should == "Amazon Web Services, Products, Tools, and Developer Information..."
+    end
+
+    it "should parse the url" do
+      @feed.url.should == "http://aws.typepad.com/aws/"
+    end
+
+    it "should parse the url even when it doesn't have the type='text/html' attribute" do
+      Feedjira::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
+      Feedjira::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 no hub urls" do
+      @feed.hubs.count.should == 0
+    end
+
+    it "should parse the hub urls" do
+      feed_with_hub = Feedjira::Parser::Atom.parse(load_sample("SamRuby.xml"))
+      feed_with_hub.hubs.count.should == 1
+      feed_with_hub.hubs.first.should == "http://pubsubhubbub.appspot.com/"
+    end
+
+    it "should parse entries" do
+      @feed.entries.size.should == 10
+    end
+  end
+
+  describe "preprocessing" do
+    it "retains markup in xhtml content" do
+      Feedjira::Parser::Atom.preprocess_xml = true
+
+      feed = Feedjira::Parser::Atom.parse sample_atom_xhtml_feed
+      entry = feed.entries.first
+
+      entry.content.should match /\<div/
+    end
+  end
+end

data/spec/feedjira/parser/google_docs_atom_entry_spec.rb

@@ -0,0 +1,22 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedjira::Parser::GoogleDocsAtomEntry do
+  describe 'parsing' do
+    before do
+      @feed = Feedjira::Parser::GoogleDocsAtom.parse(sample_google_docs_list_feed)
+      @entry = @feed.entries.first
+    end
+
+    it 'should have the custom checksum element' do
+      @entry.checksum.should eql '2b01142f7481c7b056c4b410d28f33cf'
+    end
+
+    it 'should have the custom filename element' do
+      @entry.original_filename.should eql "MyFile.pdf"
+    end
+
+    it 'should have the custom suggested filename element' do
+      @entry.suggested_filename.should eql "TaxDocument.pdf"
+    end
+  end
+end

data/spec/feedjira/parser/google_docs_atom_spec.rb

@@ -0,0 +1,31 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedjira::Parser::GoogleDocsAtom do
+  describe '.able_to_parser?' do
+    it 'should return true for Google Docs feed' do
+      Feedjira::Parser::GoogleDocsAtom.should be_able_to_parse(sample_google_docs_list_feed)
+    end
+
+    it 'should not be able to parse another Atom feed' do
+      Feedjira::Parser::GoogleDocsAtom.should_not be_able_to_parse(sample_atom_feed)
+    end
+  end
+
+  describe 'parsing' do
+    before do
+      @feed = Feedjira::Parser::GoogleDocsAtom.parse(sample_google_docs_list_feed)
+    end
+
+    it 'should return a bunch of objects' do
+      @feed.entries.should_not be_empty
+    end
+
+    it 'should populate a title, interhited from the Atom entry' do
+      @feed.title.should_not be_nil
+    end
+
+    it 'should return a bunch of entries of type GoogleDocsAtomEntry' do
+      @feed.entries.first.should be_a Feedjira::Parser::GoogleDocsAtomEntry
+    end
+  end
+end

data/spec/feedjira/parser/itunes_rss_item_spec.rb

@@ -0,0 +1,63 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedjira::Parser::ITunesRSSItem do
+  before(:each) do
+    # I don't really like doing it this way because these unit test should only rely on ITunesRssItem,
+    # but this is actually how it should work. You would never just pass entry xml straight to the ITunesRssItem
+    @item = Feedjira::Parser::ITunesRSS.parse(sample_itunes_feed).entries.first
+  end
+
+  it "should parse the title" do
+    @item.title.should == "Shake Shake Shake Your Spices"
+  end
+
+  it "should parse the author" do
+    @item.itunes_author.should == "John Doe"
+  end
+
+  it "should parse the subtitle" do
+    @item.itunes_subtitle.should == "A short primer on table spices"
+  end
+
+  it "should parse the summary" do
+    @item.itunes_summary.should == "This week we talk about salt and pepper shakers, comparing and contrasting pour rates, construction materials, and overall aesthetics. Come and join the party!"
+  end
+
+  it "should parse the enclosure" do
+    @item.enclosure_length.should == "8727310"
+    @item.enclosure_type.should == "audio/x-m4a"
+    @item.enclosure_url.should == "http://example.com/podcasts/everything/AllAboutEverythingEpisode3.m4a"
+  end
+
+  it "should parse the guid as id" do
+    @item.id.should == "http://example.com/podcasts/archive/aae20050615.m4a"
+  end
+
+  it "should parse the published date" do
+    @item.published.should == Time.parse_safely("Wed Jun 15 19:00:00 UTC 2005")
+  end
+
+  it "should parse the duration" do
+    @item.itunes_duration.should == "7:04"
+  end
+
+  it "should parse the keywords" do
+    @item.itunes_keywords.should == "salt, pepper, shaker, exciting"
+  end
+
+  it "should parse the image" do
+    @item.itunes_image.should == "http://example.com/podcasts/everything/AllAboutEverything.jpg"
+  end
+
+  it "should parse the order" do
+    @item.itunes_order.should eq '12'
+  end
+
+  it "should parse the closed captioned flag" do
+    @item.itunes_closed_captioned.should eq 'yes'
+  end
+
+  it "should parse the encoded content" do
+    @item.content.should == "<p><strong>TOPIC</strong>: Gooseneck Options</p>"
+  end
+end

data/spec/feedjira/parser/itunes_rss_owner_spec.rb

@@ -0,0 +1,18 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedjira::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 = Feedjira::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/feedjira/parser/itunes_rss_spec.rb

@@ -0,0 +1,58 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedjira::Parser::ITunesRSS do
+  describe "#will_parse?" do
+    it "should return true for an itunes RSS feed" do
+      Feedjira::Parser::ITunesRSS.should be_able_to_parse(sample_itunes_feed)
+    end
+
+    it "should return true for an itunes RSS feed with spaces between attribute names, equals sign, and values" do
+      Feedjira::Parser::ITunesRSS.should be_able_to_parse(sample_itunes_feed_with_spaces)
+    end
+
+    it "should return fase for an atom feed" do
+      Feedjira::Parser::ITunesRSS.should_not be_able_to_parse(sample_atom_feed)
+    end
+
+    it "should return false for an rss feedburner feed" do
+      Feedjira::Parser::ITunesRSS.should_not be_able_to_parse(sample_rss_feed_burner_feed)
+    end
+  end
+
+  describe "parsing" do
+    before(:each) do
+      @feed = Feedjira::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/feedjira/parser/rss_entry_spec.rb

@@ -0,0 +1,85 @@
+# coding: utf-8
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedjira::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 = Feedjira::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 = Feedjira::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.should == Time.parse_safely("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/feedjira/parser/rss_feed_burner_entry_spec.rb

@@ -0,0 +1,85 @@
+# coding: utf-8
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedjira::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 = Feedjira::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 = Feedjira::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.should == Time.parse_safely("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