feedjira 3.0.0.beta1 → 3.2.0

data/spec/feedjira/parser/google_docs_atom_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 module Feedjira

data/spec/feedjira/parser/itunes_rss_item_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 describe Feedjira::Parser::ITunesRSSItem do
@@ -25,7 +27,7 @@ describe Feedjira::Parser::ITunesRSSItem do
   end
 
   it "should parse the summary" do
-    summary = "This week we talk about salt and pepper shakers, comparing and contrasting pour rates, construction materials, and overall aesthetics. Come and join the party!" # rubocop:disable Metrics/LineLength
+    summary = "This week we talk about salt and pepper shakers, comparing and contrasting pour rates, construction materials, and overall aesthetics. Come and join the party!"
     expect(@item.itunes_summary).to eq summary
   end
 

data/spec/feedjira/parser/itunes_rss_owner_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 describe Feedjira::Parser::ITunesRSSOwner do

data/spec/feedjira/parser/itunes_rss_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 module Feedjira
@@ -7,12 +9,12 @@ module Feedjira
         expect(ITunesRSS).to 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 # rubocop:disable Metrics/LineLength
+      it "should return true for an itunes RSS feed with spaces between attribute names, equals sign, and values" do
         expect(ITunesRSS).to be_able_to_parse(sample_itunes_feed_with_spaces)
       end
 
-      it "should return true for an itunes RSS feed with single-quoted attributes" do # rubocop:disable Metrics/LineLength
-        expect(ITunesRSS).to be_able_to_parse(sample_itunes_feed_with_single_quotes)  # rubocop:disable Metrics/LineLength
+      it "should return true for an itunes RSS feed with single-quoted attributes" do
+        expect(ITunesRSS).to be_able_to_parse(sample_itunes_feed_with_single_quotes)
       end
 
       it "should return fase for an atom feed" do
@@ -74,7 +76,7 @@ module Feedjira
       end
 
       it "should parse the image description" do
-        description = "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" # rubocop:disable Metrics/LineLength
+        description = "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"
         expect(@feed.image.description).to eq description
       end
 
@@ -85,14 +87,14 @@ module Feedjira
           "TV & Film",
           "Arts",
           "Design",
-          "Food",
+          "Food"
         ]
 
         expect(@feed.itunes_category_paths).to eq [
-          %w(Technology Gadgets),
+          %w[Technology Gadgets],
           ["TV & Film"],
-          %w(Arts Design),
-          %w(Arts Food),
+          %w[Arts Design],
+          %w[Arts Food]
         ]
       end
 
@@ -101,7 +103,7 @@ module Feedjira
       end
 
       it "should parse the summary" do
-        summary = "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" # rubocop:disable Metrics/LineLength
+        summary = "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"
         expect(@feed.itunes_summary).to eq summary
       end
 

data/spec/feedjira/parser/json_feed_item_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 describe Feedjira::Parser::JSONFeedItem do
@@ -21,7 +23,7 @@ describe Feedjira::Parser::JSONFeedItem do
   end
 
   it "should parse the content" do
-    content = "<p>On Wednesday night I know where I’ll be — playing keyboard for a few songs at the James Dempsey and the Breakpoints concert benefitting App Camp for Girls.</p>\n\n<p><a href=\"https://www.classy.org/events/-/e126329\">You should get tickets</a>. It’s a fun time for a great cause.</p>\n\n<p>Bonus: James writes about how <a href=\"http://jamesdempsey.net/2017/06/02/wwdc-in-san-jose-full-circle/\">this concert is full circle for him</a>. It’s a special night.</p>" # rubocop:disable Metrics/LineLength
+    content = "<p>On Wednesday night I know where I’ll be — playing keyboard for a few songs at the James Dempsey and the Breakpoints concert benefitting App Camp for Girls.</p>\n\n<p><a href=\"https://www.classy.org/events/-/e126329\">You should get tickets</a>. It’s a fun time for a great cause.</p>\n\n<p>Bonus: James writes about how <a href=\"http://jamesdempsey.net/2017/06/02/wwdc-in-san-jose-full-circle/\">this concert is full circle for him</a>. It’s a special night.</p>"
     expect(@entry.content).to eq content
   end
 
@@ -44,7 +46,7 @@ describe Feedjira::Parser::JSONFeedItem do
 
     expect(title_value).to eq "James Dempsey and the Breakpoints Benefit App Camp for Girls"
 
-    expected_fields = %w(
+    expected_fields = %w[
       author
       banner_image
       categories
@@ -58,7 +60,7 @@ describe Feedjira::Parser::JSONFeedItem do
       title
       updated
       url
-    )
+    ]
     expect(all_fields).to match_array expected_fields
   end
 

data/spec/feedjira/parser/json_feed_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 module Feedjira

data/spec/feedjira/parser/podlove_chapter_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 describe Feedjira::Parser::PodloveChapter do

data/spec/feedjira/parser/rss_entry_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 describe Feedjira::Parser::RSSEntry do
@@ -35,7 +37,7 @@ describe Feedjira::Parser::RSSEntry do
   end
 
   it "should provide a summary" do
-    summary = "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  [...]" # rubocop:disable Metrics/LineLength
+    summary = "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  [...]"
     expect(@entry.summary).to eq summary
   end
 
@@ -45,7 +47,7 @@ describe Feedjira::Parser::RSSEntry do
   end
 
   it "should parse the categories" do
-    expect(@entry.categories).to eq %w(computadora nokogiri rails)
+    expect(@entry.categories).to eq %w[computadora nokogiri rails]
   end
 
   it "should parse the guid as id" do
@@ -66,7 +68,7 @@ describe Feedjira::Parser::RSSEntry do
 
     expect(title_value).to eq "Nokogiri’s Slop Feature"
 
-    expected_fields = %w(
+    expected_fields = %w[
       author
       categories
       comment_rss
@@ -76,7 +78,7 @@ describe Feedjira::Parser::RSSEntry do
       summary
       title
       url
-    )
+    ]
     expect(all_fields.sort).to eq expected_fields
   end
 
@@ -94,4 +96,24 @@ describe Feedjira::Parser::RSSEntry do
     @entry["title"] = "Foobar"
     expect(@entry.title).to eq "Foobar"
   end
+
+  it "should ignore urls from guids with isPermaLink='false'" do
+    feed = Feedjira.parse(sample_rss_feed_permalinks)
+    expect(feed.entries[0].url).to eq nil
+  end
+
+  it "should get urls from guids with isPermaLink='true'" do
+    feed = Feedjira.parse(sample_rss_feed_permalinks)
+    expect(feed.entries[1].url).to eq "http://example.com/2"
+  end
+
+  it "should get urls from guid where isPermaLink is unspecified" do
+    feed = Feedjira.parse(sample_rss_feed_permalinks)
+    expect(feed.entries[2].url).to eq "http://example.com/3"
+  end
+
+  it "should prefer urls from <link> when both guid and link are specified" do
+    feed = Feedjira.parse(sample_rss_feed_permalinks)
+    expect(feed.entries[3].url).to eq "http://example.com/4"
+  end
 end

data/spec/feedjira/parser/rss_feed_burner_entry_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 describe Feedjira::Parser::RSSFeedBurnerEntry do
@@ -13,19 +15,19 @@ describe Feedjira::Parser::RSSFeedBurnerEntry do
 
   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" # rubocop:disable Metrics/LineLength
+    if @entry.title != "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M"
       feed = Feedjira::Parser::RSS.parse sample_rss_feed_burner_feed
       @entry.title = feed.entries.first.title
     end
   end
 
   it "should parse the title" do
-    title = "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M" # rubocop:disable Metrics/LineLength
+    title = "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M"
     expect(@entry.title).to eq title
   end
 
   it "should parse the original url" do
-    expect(@entry.url).to eq "http://techcrunch.com/2011/11/02/angies-list-prices-ipo-at-11-to-13-per-share-valued-at-over-600m/" # rubocop:disable Metrics/LineLength
+    expect(@entry.url).to eq "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
@@ -66,10 +68,10 @@ describe Feedjira::Parser::RSSFeedBurnerEntry do
       title_value = value if field == "title"
     end
 
-    title = "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M" # rubocop:disable Metrics/LineLength
+    title = "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M"
     expect(title_value).to eq title
 
-    expected_fields = %w(
+    expected_fields = %w[
       author
       categories
       comment_rss
@@ -80,7 +82,7 @@ describe Feedjira::Parser::RSSFeedBurnerEntry do
       summary
       title
       url
-    )
+    ]
     expect(all_fields.sort).to eq expected_fields
   end
 
@@ -91,7 +93,7 @@ describe Feedjira::Parser::RSSFeedBurnerEntry do
 
   it "should allow access to fields with hash syntax" do
     expect(@entry["author"]).to eq "Leena Rao"
-    title = "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M" # rubocop:disable Metrics/LineLength
+    title = "Angie’s List Sets Price Range IPO At $11 To $13 Per Share; Valued At Over $600M"
     expect(@entry["title"]).to eq title
   end
 

data/spec/feedjira/parser/rss_feed_burner_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 module Feedjira
@@ -34,7 +36,7 @@ module Feedjira
       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
+        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
 

data/spec/feedjira/parser/rss_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 describe Feedjira::Parser::RSS do

data/spec/feedjira/preprocessor_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 describe Feedjira::Preprocessor do
@@ -21,9 +23,9 @@ describe Feedjira::Preprocessor do
   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
+    processor = Feedjira::Preprocessor.new(sample_atom_xhtml_with_escpaed_html_in_pre_tag_feed)
     escaped = processor.to_xml
-    expected_pre_tag = "        <pre><b>test<b></pre>" # rubocop:disable Metrics/LineLength
+    expected_pre_tag = "        <pre><b>test<b></pre>"
     expect(escaped.split("\n")[7]).to eq(expected_pre_tag)
   end
 end

data/spec/feedjira_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "spec_helper"
 
 RSpec.describe Feedjira do
@@ -62,6 +64,16 @@ RSpec.describe Feedjira do
         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
@@ -79,6 +91,15 @@ RSpec.describe Feedjira do
       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
@@ -128,7 +149,7 @@ RSpec.describe Feedjira do
       it "does not use default parsers" do
         xml = "Atom asdf"
         new_parser = Class.new do
-          def self.able_to_parse?(_)
+          def self.able_to_parse?(_xml)
             true
           end
         end

data/spec/sample_feeds.rb

@@ -1,8 +1,10 @@
-# rubocop:disable Metrics/LineLength
+# frozen_string_literal: true
 
 module SampleFeeds
   FEEDS = {
     sample_atom_feed: "AmazonWebServicesBlog.xml",
+    sample_atom_simple: "atom_simple_single_entry.xml",
+    sample_atom_simple_link_self: "atom_simple_single_entry_link_self.xml",
     sample_atom_middleman_feed: "FeedjiraBlog.xml",
     sample_atom_xhtml_feed: "pet_atom.xml",
     sample_atom_feed_line_breaks: "AtomFeedWithSpacesAroundEquals.xml",
@@ -21,6 +23,7 @@ module SampleFeeds
     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",
@@ -29,6 +32,9 @@ module SampleFeeds
     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|
@@ -39,5 +45,3 @@ module SampleFeeds
     File.read("#{File.dirname(__FILE__)}/sample_feeds/#{filename}")
   end
 end
-
-# rubocop:enable Metrics/LineLength

data/spec/sample_feeds/InvalidDateFormat.xml

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
+  xmlns:dc="http://purl.org/dc/elements/1.1/">
+
+<channel>
+  <title>Invalid date format feed</title>
+  <link>http://example.com/feed</link>
+  <language>en-US</language>
+  <item>
+    <title>Item 0 with an invalid date</title>
+    <link>http://example.com/item0</link>
+    <pubDate>Mon, 16 Oct 2017 15:10:00 +0000</pubDate>
+    <dc:date>1518478934</dc:date>
+  </item>
+  <item>
+    <title>Item 1 with all valid dates</title>
+    <link>http://example.com/item1</link>
+    <pubDate>Tue, 17 Oct 2017 12:17:00 +0000</pubDate>
+    <dc:date>Tue, 17 Oct 2017 22:17:00 +0000</dc:date>
+  </item>
+</channel>

data/spec/sample_feeds/Permalinks.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0" encoding="utf-8"?>
+<rss version="2.0">
+    <channel>
+        <item>
+            <title>Item 1</title>
+            <guid isPermaLink="false">http://example.com/1</guid>
+        </item>
+        <item>
+            <title>Item 2</title>
+            <guid isPermaLink="true">http://example.com/2</guid>
+        </item>
+        <item>
+            <title>Item 3</title>
+            <guid>http://example.com/3</guid>
+        </item>
+        <item>
+            <title>Item 4</title>
+            <link>http://example.com/4</link>
+            <guid>http://example.com/5</guid>
+        </item>
+    </channel>
+</rss>

data/spec/sample_feeds/a10.xml

@@ -0,0 +1,72 @@
+<?xml version="1.0" encoding="utf-8"?>
+<rss xmlns:a10="http://www.w3.org/2005/Atom" version="2.0">
+  <channel>
+    <title>Some Title</title>
+    <description>Some Description</description>
+    <lastBuildDate>Thu, 14 May 2020 10:00:18 Z</lastBuildDate>
+    <category>Some Category</category>
+    <a10:link href="http://www.example.com/" />
+    <pubDate>Sat, 16 May 2020 08:50:40 GMT</pubDate>
+    <item>
+      <title>Title 5</title>
+      <description>Description 5</description>
+      <pubDate>Thu, 14 May 2020 10:00:18 Z</pubDate>
+      <a10:link href="http://www.example.com/5" />
+      <a10:author>
+        <a10:name>John Doe</a10:name>
+        <a10:uri>http://www.example.com/</a10:uri>
+        <a10:email>john.doe@example.com</a10:email>
+      </a10:author>
+      <a10:updated>2020-05-14T10:00:18Z</a10:updated>
+    </item>
+    <item>
+      <title>Title 4</title>
+      <description>Description 4</description>
+      <pubDate>Wed, 13 May 2020 10:17:57 Z</pubDate>
+      <a10:link href="http://www.example.com/4" />
+      <a10:author>
+        <a10:name>John Doe</a10:name>
+        <a10:uri>http://www.example.com/</a10:uri>
+        <a10:email>john.doe@example.com</a10:email>
+      </a10:author>
+      <a10:updated>2020-05-13T10:17:57Z</a10:updated>
+    </item>
+    <item>
+      <title>Title 3</title>
+      <description>Dfescription 3</description>
+      <pubDate>Tue, 12 May 2020 15:00:00 Z</pubDate>
+      <a10:link href="http://www.example.com/3" />
+      <a10:author>
+        <a10:name>John Doe</a10:name>
+        <a10:uri>http://www.example.com/</a10:uri>
+        <a10:email>john.doe@example.com</a10:email>
+      </a10:author>
+      <a10:updated>2020-05-12T15:00:00Z</a10:updated>
+    </item>
+    <item>
+      <title>Title 2</title>
+      <description>Description 2</description>
+      <pubDate>Tue, 12 May 2020 07:52:36 Z</pubDate>
+      <a10:link href="http://www.example.com/2" />
+      <a10:author>
+        <a10:name>John Doe</a10:name>
+        <a10:uri>http://www.example.com/</a10:uri>
+        <a10:email>john.doe@example.com</a10:email>
+      </a10:author>
+      <a10:updated>2020-05-12T07:52:36Z</a10:updated>
+    </item>
+    <item>
+      <title>Title 1</title>
+      <description>Description 1</description>
+      <pubDate>Thu, 07 May 2020 07:36:53 Z</pubDate>
+      <a10:link href="http://www.example.com/1" />
+      <a10:author>
+        <a10:name>John Doe</a10:name>
+        <a10:uri>http://www.example.com/</a10:uri>
+        <a10:email>john.doe@example.com</a10:email>
+      </a10:author>
+      <a10:updated>2020-05-07T07:36:53Z</a10:updated>
+    </item>
+  </channel>
+</rss>
+