feedjira 2.2.0 → 3.1.2

data/spec/feedjira/parser/rss_feed_burner_spec.rb

@@ -1,62 +1,66 @@
-require 'spec_helper'
+# frozen_string_literal: true
 
-module Feedjira::Parser
-  describe '#will_parse?' do
-    it 'should return true for a feedburner rss feed' do
-      expect(RSSFeedBurner).to be_able_to_parse sample_rss_feed_burner_feed
-    end
+require "spec_helper"
 
-    it 'should return false for a regular RSS feed' do
-      expect(RSSFeedBurner).to_not be_able_to_parse sample_rss_feed
-    end
+module Feedjira
+  module Parser
+    describe "#will_parse?" do
+      it "should return true for a feedburner rss feed" do
+        expect(RSSFeedBurner).to be_able_to_parse sample_rss_feed_burner_feed
+      end
 
-    it 'should return false for a feedburner atom feed' do
-      expect(RSSFeedBurner).to_not be_able_to_parse sample_feedburner_atom_feed
-    end
+      it "should return false for a regular RSS feed" do
+        expect(RSSFeedBurner).to_not be_able_to_parse sample_rss_feed
+      end
 
-    it 'should return false for an rdf feed' do
-      expect(RSSFeedBurner).to_not be_able_to_parse sample_rdf_feed
-    end
+      it "should return false for a feedburner atom feed" do
+        expect(RSSFeedBurner).to_not be_able_to_parse sample_feedburner_atom_feed
+      end
 
-    it 'should return false for a regular atom feed' do
-      expect(RSSFeedBurner).to_not be_able_to_parse sample_atom_feed
-    end
-  end
+      it "should return false for an rdf feed" do
+        expect(RSSFeedBurner).to_not be_able_to_parse sample_rdf_feed
+      end
 
-  describe 'parsing' do
-    before(:each) do
-      @feed = RSSFeedBurner.parse(sample_rss_feed_burner_feed)
+      it "should return false for a regular atom feed" do
+        expect(RSSFeedBurner).to_not be_able_to_parse sample_atom_feed
+      end
     end
 
-    it 'should parse the title' do
-      expect(@feed.title).to eq 'TechCrunch'
-    end
+    describe "parsing" do
+      before(:each) do
+        @feed = RSSFeedBurner.parse(sample_rss_feed_burner_feed)
+      end
 
-    it 'should parse the description' do
-      description = 'TechCrunch is a group-edited blog that profiles the companies, products and events defining and transforming the new web.' # rubocop:disable Metrics/LineLength
-      expect(@feed.description).to eq description
-    end
+      it "should parse the title" do
+        expect(@feed.title).to eq "TechCrunch"
+      end
 
-    it 'should parse the url' do
-      expect(@feed.url).to eq 'http://techcrunch.com'
-    end
+      it "should parse the description" do
+        description = "TechCrunch is a group-edited blog that profiles the companies, products and events defining and transforming the new web."
+        expect(@feed.description).to eq description
+      end
 
-    it 'should parse the last build date' do
-      expect(@feed.last_built).to eq 'Wed, 02 Nov 2011 17:29:59 +0000'
-    end
+      it "should parse the url" do
+        expect(@feed.url).to eq "http://techcrunch.com"
+      end
 
-    it 'should parse the hub urls' do
-      expect(@feed.hubs.count).to eq 2
-      expect(@feed.hubs.first).to eq 'http://pubsubhubbub.appspot.com/'
-    end
+      it "should parse the last build date" do
+        expect(@feed.last_built).to eq "Wed, 02 Nov 2011 17:29:59 +0000"
+      end
 
-    it 'should provide an accessor for the feed_url' do
-      expect(@feed).to respond_to :feed_url
-      expect(@feed).to respond_to :feed_url=
-    end
+      it "should parse the hub urls" do
+        expect(@feed.hubs.count).to eq 2
+        expect(@feed.hubs.first).to eq "http://pubsubhubbub.appspot.com/"
+      end
+
+      it "should provide an accessor for the feed_url" do
+        expect(@feed).to respond_to :feed_url
+        expect(@feed).to respond_to :feed_url=
+      end
 
-    it 'should parse entries' do
-      expect(@feed.entries.size).to eq 20
+      it "should parse entries" do
+        expect(@feed.entries.size).to eq 20
+      end
     end
   end
 end

data/spec/feedjira/parser/rss_spec.rb

@@ -1,89 +1,91 @@
-require 'spec_helper'
+# frozen_string_literal: true
+
+require "spec_helper"
 
 describe Feedjira::Parser::RSS do
-  describe '#will_parse?' do
-    it 'should return true for an RSS feed' do
+  describe "#will_parse?" do
+    it "should return true for an RSS feed" do
       expect(Feedjira::Parser::RSS).to be_able_to_parse(sample_rss_feed)
     end
 
-    it 'should return false for an atom feed' do
+    it "should return false for an atom feed" do
       expect(Feedjira::Parser::RSS).to_not be_able_to_parse(sample_atom_feed)
     end
 
-    it 'should return false for an rss feedburner feed' do
+    it "should return false for an rss feedburner feed" do
       able = Feedjira::Parser::RSS.able_to_parse? sample_rss_feed_burner_feed
       expect(able).to eq false
     end
   end
 
-  describe 'parsing' do
+  describe "parsing" do
     before(:each) do
       @feed = Feedjira::Parser::RSS.parse(sample_rss_feed)
     end
 
-    it 'should parse the version' do
-      expect(@feed.version).to eq '2.0'
+    it "should parse the version" do
+      expect(@feed.version).to eq "2.0"
     end
 
-    it 'should parse the title' do
-      expect(@feed.title).to eq 'Tender Lovemaking'
+    it "should parse the title" do
+      expect(@feed.title).to eq "Tender Lovemaking"
     end
 
-    it 'should parse the description' do
-      expect(@feed.description).to eq 'The act of making love, tenderly.'
+    it "should parse the description" do
+      expect(@feed.description).to eq "The act of making love, tenderly."
     end
 
-    it 'should parse the url' do
-      expect(@feed.url).to eq 'http://tenderlovemaking.com'
+    it "should parse the url" do
+      expect(@feed.url).to eq "http://tenderlovemaking.com"
     end
 
-    it 'should parse the ttl' do
-      expect(@feed.ttl).to eq '60'
+    it "should parse the ttl" do
+      expect(@feed.ttl).to eq "60"
     end
 
-    it 'should parse the last build date' do
-      expect(@feed.last_built).to eq 'Sat, 07 Sep 2002 09:42:31 GMT'
+    it "should parse the last build date" do
+      expect(@feed.last_built).to eq "Sat, 07 Sep 2002 09:42:31 GMT"
     end
 
-    it 'should parse the hub urls' do
+    it "should parse the hub urls" do
       expect(@feed.hubs.count).to eq 1
-      expect(@feed.hubs.first).to eq 'http://pubsubhubbub.appspot.com/'
+      expect(@feed.hubs.first).to eq "http://pubsubhubbub.appspot.com/"
     end
 
-    it 'should provide an accessor for the feed_url' do
+    it "should provide an accessor for the feed_url" do
       expect(@feed).to respond_to :feed_url
       expect(@feed).to respond_to :feed_url=
     end
 
-    it 'should parse the language' do
-      expect(@feed.language).to eq 'en'
+    it "should parse the language" do
+      expect(@feed.language).to eq "en"
     end
 
-    it 'should parse the image url' do
-      expect(@feed.image.url).to eq 'https://tenderlovemaking.com/images/header-logo-text-trimmed.png'
+    it "should parse the image url" do
+      expect(@feed.image.url).to eq "https://tenderlovemaking.com/images/header-logo-text-trimmed.png"
     end
 
-    it 'should parse the image title' do
-      expect(@feed.image.title).to eq 'Tender Lovemaking'
+    it "should parse the image title" do
+      expect(@feed.image.title).to eq "Tender Lovemaking"
     end
 
-    it 'should parse the image link' do
-      expect(@feed.image.link).to eq 'http://tenderlovemaking.com'
+    it "should parse the image link" do
+      expect(@feed.image.link).to eq "http://tenderlovemaking.com"
     end
 
-    it 'should parse the image width' do
-      expect(@feed.image.width).to eq '766'
+    it "should parse the image width" do
+      expect(@feed.image.width).to eq "766"
     end
 
-    it 'should parse the image height' do
-      expect(@feed.image.height).to eq '138'
+    it "should parse the image height" do
+      expect(@feed.image.height).to eq "138"
     end
 
-    it 'should parse the image description' do
-      expect(@feed.image.description).to eq 'The act of making love, tenderly.'
+    it "should parse the image description" do
+      expect(@feed.image.description).to eq "The act of making love, tenderly."
     end
 
-    it 'should parse entries' do
+    it "should parse entries" do
       expect(@feed.entries.size).to eq 10
     end
   end

data/spec/feedjira/preprocessor_spec.rb

@@ -1,8 +1,10 @@
-require 'spec_helper'
+# frozen_string_literal: true
+
+require "spec_helper"
 
 describe Feedjira::Preprocessor do
-  it 'returns the xml as parsed by Nokogiri' do
-    xml = '<xml></xml>'
+  it "returns the xml as parsed by Nokogiri" do
+    xml = "<xml></xml>"
     doc = Nokogiri::XML(xml).remove_namespaces!
     processor = Feedjira::Preprocessor.new xml
     escaped = processor.to_xml
@@ -10,7 +12,7 @@ describe Feedjira::Preprocessor do
     expect(escaped).to eq doc.to_xml
   end
 
-  it 'escapes markup in xhtml content' do
+  it "escapes markup in xhtml content" do
     processor = Feedjira::Preprocessor.new sample_atom_xhtml_feed
     escaped = processor.to_xml
     escaped_parts = escaped.split "\n"
@@ -20,10 +22,10 @@ describe Feedjira::Preprocessor do
     expect(escaped_parts[26]).to match(/&lt;p&gt;$/) # content
   end
 
-  it 'leaves escaped html within pre tag' do
-    processor = Feedjira::Preprocessor.new(sample_atom_xhtml_with_escpaed_html_in_pre_tag_feed) # rubocop:disable Metrics/LineLength
+  it "leaves escaped html within pre tag" do
+    processor = Feedjira::Preprocessor.new(sample_atom_xhtml_with_escpaed_html_in_pre_tag_feed)
     escaped = processor.to_xml
-    expected_pre_tag = '        &lt;pre&gt;&amp;lt;b&amp;gt;test&amp;lt;b&amp;gt;&lt;/pre&gt;' # rubocop:disable Metrics/LineLength
+    expected_pre_tag = "        &lt;pre&gt;&amp;lt;b&amp;gt;test&amp;lt;b&amp;gt;&lt;/pre&gt;"
     expect(escaped.split("\n")[7]).to eq(expected_pre_tag)
   end
 end

data/spec/feedjira_spec.rb

@@ -0,0 +1,166 @@
+# frozen_string_literal: true
+
+require "spec_helper"
+
+RSpec.describe Feedjira do
+  describe ".parse" do
+    context "allows the parser to be specified" do
+      it "should parse an rss feed" do
+        parser = Feedjira.parser_for_xml(sample_rss_feed)
+        feed = Feedjira.parse(sample_rss_feed, parser: parser)
+
+        expect(feed.title).to eq "Tender Lovemaking"
+        published = Time.parse_safely "Thu Dec 04 17:17:49 UTC 2008"
+        expect(feed.entries.first.published).to eq published
+        expect(feed.entries.size).to eq 10
+      end
+    end
+
+    context "when there's an available parser" do
+      it "should parse an rdf feed" do
+        feed = Feedjira.parse(sample_rdf_feed)
+        expect(feed.title).to eq "HREF Considered Harmful"
+        published = Time.parse_safely("Tue Sep 02 19:50:07 UTC 2008")
+        expect(feed.entries.first.published).to eq published
+        expect(feed.entries.size).to eq 10
+      end
+
+      it "should parse an rss feed" do
+        feed = Feedjira.parse(sample_rss_feed)
+        expect(feed.title).to eq "Tender Lovemaking"
+        published = Time.parse_safely "Thu Dec 04 17:17:49 UTC 2008"
+        expect(feed.entries.first.published).to eq published
+        expect(feed.entries.size).to eq 10
+      end
+
+      it "should parse an atom feed" do
+        feed = Feedjira.parse(sample_atom_feed)
+        expect(feed.title).to eq "Amazon Web Services Blog"
+        published = Time.parse_safely "Fri Jan 16 18:21:00 UTC 2009"
+        expect(feed.entries.first.published).to eq published
+        expect(feed.entries.size).to eq 10
+      end
+
+      it "should parse an feedburner atom feed" do
+        feed = Feedjira.parse(sample_feedburner_atom_feed)
+        expect(feed.title).to eq "Paul Dix Explains Nothing"
+        published = Time.parse_safely "Thu Jan 22 15:50:22 UTC 2009"
+        expect(feed.entries.first.published).to eq published
+        expect(feed.entries.size).to eq 5
+      end
+
+      it "should parse an itunes feed" do
+        feed = Feedjira.parse(sample_itunes_feed)
+        expect(feed.title).to eq "All About Everything"
+        published = Time.parse_safely "Wed, 15 Jun 2005 19:00:00 GMT"
+        expect(feed.entries.first.published).to eq published
+        expect(feed.entries.size).to eq 3
+      end
+
+      it "with nested dc:identifier it does not overwrite entry_id" do
+        feed = Feedjira.parse(sample_rss_feed_huffpost_ca)
+        expect(feed.title.strip).to eq "HuffPost Canada - Athena2 - All Posts"
+        expect(feed.entries.size).to eq 2
+        expect(feed.entries.first.id).to eq "23246627"
+        expect(feed.entries.last.id.strip).to eq "1"
+      end
+
+      it "does not fail if multiple published dates exist and some are unparseable" do
+        expect(Feedjira.logger).to receive(:warn).twice
+
+        feed = Feedjira.parse(sample_invalid_date_format_feed)
+        expect(feed.title).to eq "Invalid date format feed"
+        published = Time.parse_safely "Mon, 16 Oct 2017 15:10:00 GMT"
+        expect(feed.entries.first.published).to eq published
+        expect(feed.entries.size).to eq 2
+      end
+    end
+
+    context "when there's no available parser" do
+      it "raises Feedjira::NoParserAvailable" do
+        expect do
+          Feedjira.parse("I'm an invalid feed")
+        end.to raise_error(Feedjira::NoParserAvailable)
+      end
+    end
+
+    it "should parse an feedburner rss feed" do
+      feed = Feedjira.parse(sample_rss_feed_burner_feed)
+      expect(feed.title).to eq "TechCrunch"
+      published = Time.parse_safely "Wed Nov 02 17:25:27 UTC 2011"
+      expect(feed.entries.first.published).to eq published
+      expect(feed.entries.size).to eq 20
+    end
+
+    it "should parse an RSS feed with an a10 namespace" do
+      feed = Feedjira.parse(sample_rss_feed_with_a10_namespace)
+      expect(feed.url).to eq "http://www.example.com/"
+      expect(feed.entries.first.url).to eq "http://www.example.com/5"
+      expect(feed.entries.first.updated).to eq Time.parse_safely("2020-05-14T10:00:18Z")
+      expect(feed.entries.first.author).to eq "John Doe"
+      expect(feed.entries.size).to eq 5
+    end
+  end
+
+  describe ".parser_for_xml" do
+    it "with Google Docs atom feed it returns the GoogleDocsAtom parser" do
+      xml = sample_google_docs_list_feed
+      actual_parser = Feedjira.parser_for_xml(xml)
+      expect(actual_parser).to eq Feedjira::Parser::GoogleDocsAtom
+    end
+
+    it "with an atom feed it returns the Atom parser" do
+      xml = sample_atom_feed
+      actual_parser = Feedjira.parser_for_xml(xml)
+      expect(actual_parser).to eq Feedjira::Parser::Atom
+    end
+
+    it "with an atom feedburner feed it returns the AtomFeedBurner parser" do
+      xml = sample_feedburner_atom_feed
+      actual_parser = Feedjira.parser_for_xml(xml)
+      expect(actual_parser).to eq Feedjira::Parser::AtomFeedBurner
+    end
+
+    it "with an rdf feed it returns the RSS parser" do
+      xml = sample_rdf_feed
+      actual_parser = Feedjira.parser_for_xml(xml)
+      expect(actual_parser).to eq Feedjira::Parser::RSS
+    end
+
+    it "with an rss feedburner feed it returns the RSSFeedBurner parser" do
+      xml = sample_rss_feed_burner_feed
+      actual_parser = Feedjira.parser_for_xml(xml)
+      expect(actual_parser).to eq Feedjira::Parser::RSSFeedBurner
+    end
+
+    it "with an rss 2.0 feed it returns the RSS parser" do
+      xml = sample_rss_feed
+      actual_parser = Feedjira.parser_for_xml(xml)
+      expect(actual_parser).to eq Feedjira::Parser::RSS
+    end
+
+    it "with an itunes feed it returns the RSS parser" do
+      xml = sample_itunes_feed
+      actual_parser = Feedjira.parser_for_xml(xml)
+      expect(actual_parser).to eq Feedjira::Parser::ITunesRSS
+    end
+
+    context "when parsers are configured" do
+      it "does not use default parsers" do
+        xml = "Atom asdf"
+        new_parser = Class.new do
+          def self.able_to_parse?(_xml)
+            true
+          end
+        end
+
+        Feedjira.configure { |config| config.parsers = [new_parser] }
+
+        parser = Feedjira.parser_for_xml(xml)
+        expect(parser).to eq(new_parser)
+
+        Feedjira.reset_configuration!
+      end
+    end
+  end
+end

data/spec/sample_feeds.rb

@@ -1,33 +1,38 @@
-# rubocop:disable Metrics/LineLength
+# frozen_string_literal: true
 
 module SampleFeeds
   FEEDS = {
-    sample_atom_feed: 'AmazonWebServicesBlog.xml',
-    sample_atom_middleman_feed: 'FeedjiraBlog.xml',
-    sample_atom_xhtml_feed: 'pet_atom.xml',
-    sample_atom_feed_line_breaks: 'AtomFeedWithSpacesAroundEquals.xml',
-    sample_atom_entry_content: 'AmazonWebServicesBlogFirstEntryContent.xml',
-    sample_itunes_feed: 'itunes.xml',
-    sample_itunes_feed_with_single_quotes: 'ITunesWithSingleQuotedAttributes.xml',
-    sample_itunes_feed_with_spaces: 'ITunesWithSpacesInAttributes.xml',
-    sample_podlove_feed: 'CRE.xml',
-    sample_rdf_feed: 'HREFConsideredHarmful.xml',
-    sample_rdf_entry_content: 'HREFConsideredHarmfulFirstEntry.xml',
-    sample_rss_feed_burner_feed: 'TechCrunch.xml',
-    sample_rss_feed_burner_entry_content: 'TechCrunchFirstEntry.xml',
-    sample_rss_feed_burner_entry_description: 'TechCrunchFirstEntryDescription.xml',
-    sample_rss_feed: 'TenderLovemaking.xml',
-    sample_rss_entry_content: 'TenderLovemakingFirstEntry.xml',
-    sample_feedburner_atom_feed: 'PaulDixExplainsNothing.xml',
-    sample_feedburner_atom_feed_alternate: 'GiantRobotsSmashingIntoOtherGiantRobots.xml',
-    sample_feedburner_atom_entry_content: 'PaulDixExplainsNothingFirstEntryContent.xml',
-    sample_wfw_feed: 'PaulDixExplainsNothingWFW.xml',
-    sample_google_docs_list_feed: 'GoogleDocsList.xml',
-    sample_feed_burner_atom_xhtml_feed: 'FeedBurnerXHTML.xml',
-    sample_duplicate_content_atom_feed: 'DuplicateContentAtomFeed.xml',
-    sample_youtube_atom_feed: 'youtube_atom.xml',
-    sample_atom_xhtml_with_escpaed_html_in_pre_tag_feed: 'AtomEscapedHTMLInPreTag.xml',
-    sample_invalid_date_format_feed: 'InvalidDateFormat.xml'
+    sample_atom_feed: "AmazonWebServicesBlog.xml",
+    sample_atom_middleman_feed: "FeedjiraBlog.xml",
+    sample_atom_xhtml_feed: "pet_atom.xml",
+    sample_atom_feed_line_breaks: "AtomFeedWithSpacesAroundEquals.xml",
+    sample_atom_entry_content: "AmazonWebServicesBlogFirstEntryContent.xml",
+    sample_itunes_feed: "itunes.xml",
+    sample_itunes_feed_with_single_quotes: "ITunesWithSingleQuotedAttributes.xml",
+    sample_itunes_feed_with_spaces: "ITunesWithSpacesInAttributes.xml",
+    sample_podlove_feed: "CRE.xml",
+    sample_rdf_feed: "HREFConsideredHarmful.xml",
+    sample_rdf_entry_content: "HREFConsideredHarmfulFirstEntry.xml",
+    sample_rss_feed_burner_feed: "TechCrunch.xml",
+    sample_rss_feed_burner_entry_content: "TechCrunchFirstEntry.xml",
+    sample_rss_feed_burner_entry_description: "TechCrunchFirstEntryDescription.xml",
+    sample_rss_feed: "TenderLovemaking.xml",
+    sample_rss_entry_content: "TenderLovemakingFirstEntry.xml",
+    sample_feedburner_atom_feed: "PaulDixExplainsNothing.xml",
+    sample_feedburner_atom_feed_alternate: "GiantRobotsSmashingIntoOtherGiantRobots.xml",
+    sample_feedburner_atom_entry_content: "PaulDixExplainsNothingFirstEntryContent.xml",
+    sample_google_alerts_atom_feed: "google_alerts_atom.xml",
+    sample_wfw_feed: "PaulDixExplainsNothingWFW.xml",
+    sample_google_docs_list_feed: "GoogleDocsList.xml",
+    sample_feed_burner_atom_xhtml_feed: "FeedBurnerXHTML.xml",
+    sample_duplicate_content_atom_feed: "DuplicateContentAtomFeed.xml",
+    sample_youtube_atom_feed: "youtube_atom.xml",
+    sample_atom_xhtml_with_escpaed_html_in_pre_tag_feed: "AtomEscapedHTMLInPreTag.xml",
+    sample_json_feed: "json_feed.json",
+    sample_rss_feed_huffpost_ca: "HuffPostCanada.xml",
+    sample_invalid_date_format_feed: "InvalidDateFormat.xml",
+    sample_rss_feed_permalinks: "Permalinks.xml",
+    sample_rss_feed_with_a10_namespace: "a10.xml"
   }.freeze
 
   FEEDS.each do |method, filename|
@@ -38,5 +43,3 @@ module SampleFeeds
     File.read("#{File.dirname(__FILE__)}/sample_feeds/#{filename}")
   end
 end
-
-# rubocop:enable Metrics/LineLength