simple-rss 2.1.0 → 2.3.0

data/test/base/relation_links_test.rb

@@ -0,0 +1,162 @@
+require "test_helper"
+require "json"
+
+class RelationLinksTest < Test::Unit::TestCase
+  def test_documented_accessor_and_legacy_key_return_the_same_link
+    feed = parse_entry(<<~XML)
+      <link rel="self" href="https://example.com/api/1"/>
+      <link rel="alternate" href="https://example.com/posts/1"/>
+    XML
+    item = feed.first
+
+    assert_equal "https://example.com/posts/1", item.link_alternate
+    assert_equal item.link_alternate, item[:link_alternate]
+    assert_equal item.link_alternate, item[:"link+alternate"]
+    assert_equal "https://example.com/api/1", item.link
+  end
+
+  def test_relations_accept_attribute_order_quotes_whitespace_and_paired_tags
+    item = parse_entry(<<~XML).first
+      <link href = '/posts/1?view=full' title="Article > summary" rel = 'alternate'/>
+      <atom:link xmlns:atom="http://www.w3.org/2005/Atom"
+        rel = "self"
+        href = "https://example.com/api/1"></atom:link>
+      <link href='https://example.com/edit/1' rel='edit'>Edit entry</link>
+      <link rel="replies" type="application/atom+xml" href="/posts/1/replies" />
+    XML
+
+    assert_equal "/posts/1?view=full", item.link_alternate
+    assert_equal "https://example.com/api/1", item.link_self
+    assert_equal "https://example.com/edit/1", item.link_edit
+    assert_equal "/posts/1/replies", item.link_replies
+    %w[alternate self edit replies].each do |relation|
+      assert_equal item[:"link_#{relation}"], item[:"link+#{relation}"]
+    end
+  end
+
+  def test_nested_media_does_not_replace_the_link_href
+    source = File.read(File.join(__dir__, "../data/atom_nested_link.xml"))
+    feed = SimpleRSS.parse(source)
+
+    assert_equal "https://example.com/story", feed.first.link_alternate
+    assert_equal "https://example.com/story", feed.first[:"link+alternate"]
+    assert_equal source, feed.source
+  end
+
+  def test_relations_do_not_borrow_neighboring_attributes_or_content
+    item = parse_entry(<<~XML).first
+      <link href="/unrelated"/>
+      <link rel="self" href="/self"/>
+      <link rel="alternate"><media:thumbnail href="/thumbnail"/></link>
+      <link rel="replies" href="/replies"></link>
+    XML
+
+    assert_equal "/self", item.link_self
+    assert_equal "/replies", item.link_replies
+    assert_nil item.link_alternate
+    assert_nil item[:"link+alternate"]
+    assert_nil item.link_edit
+  end
+
+  def test_relations_ignore_nested_source_content_comments_and_cdata
+    item = parse_entry(<<~XML).first
+      <source xml:base="https://example.com/"><link rel="alternate" href="/source"/></source>
+      <content type="xhtml" xml:base='https://example.com/'><div><link rel="edit" href="/content"/></div></content>
+      <!-- <link rel="self" href="/comment"/> -->
+      <![CDATA[<link rel="replies" href="/cdata"/>]]>
+      <?example <link rel="self" href="/instruction"/> ?>
+      <extension><link rel="replies" href="/extension"/></extension>
+      <link rel="alternate" href="/entry"/>
+    XML
+
+    assert_equal "/entry", item.link_alternate
+    assert_nil item.link_self
+    assert_nil item.link_edit
+    assert_nil item.link_replies
+  end
+
+  def test_relations_match_exact_element_and_attribute_names
+    item = parse_entry(<<~XML).first
+      <linkage rel="alternate" href="/wrong-element"/>
+      <other:link rel="alternate" href="/wrong-namespace"/>
+      <link data-rel="alternate" href="/wrong-attribute"/>
+      <link title="rel='alternate' href='/quoted'" href="/wrong-value"/>
+      <link rel="self" data-href="/wrong-href"/>
+      <link rel="alternate" href="/correct"/>
+    XML
+
+    assert_equal "/correct", item.link_alternate
+    assert_nil item.link_self
+  end
+
+  def test_relations_stay_within_their_entry
+    feed = SimpleRSS.parse <<~XML
+      <feed xmlns="http://www.w3.org/2005/Atom">
+        <title>Separate entries</title>
+        <link rel="edit" href="/feed-edit"/>
+        <entry><title>First</title><link rel="self" href="/first"/></entry>
+        <entry><title>Second</title><link rel="edit" href="/second"/></entry>
+      </feed>
+    XML
+
+    assert_equal "/first", feed.first.link_self
+    assert_nil feed.first.link_edit
+    assert_equal "/second", feed[1].link_edit
+    assert_nil feed[1].link_self
+  end
+
+  def test_first_matching_relation_wins
+    item = parse_entry(<<~XML).first
+      <link rel="alternate" href="/first"/>
+      <link rel="alternate" href="/second"></link>
+    XML
+
+    assert_equal "/first", item.link_alternate
+  end
+
+  def test_relations_preserve_case_insensitive_matching
+    item = parse_entry('<LINK REL="ALTERNATE" HREF="/article"/>').first
+
+    assert_equal "/article", item.link_alternate
+    assert_equal "/article", item[:"link+alternate"]
+  end
+
+  def test_hash_and_json_serialization_include_both_relation_keys
+    feed = parse_entry('<link rel="alternate" href="/article"/>')
+    expected = { title: "Entry", link: "/article", "link+alternate": "/article", link_alternate: "/article" }
+
+    assert_equal expected, feed.first
+    assert_equal expected, feed.to_hash[:items].first
+    assert_equal expected, feed.as_json[:items].first
+    assert_equal expected, JSON.parse(feed.to_json, symbolize_names: true)[:items].first
+  end
+
+  def test_custom_relations_preserve_legacy_keys_and_unrelated_tag_names
+    original_tags = SimpleRSS.item_tags.dup
+    SimpleRSS.item_tags.push(:"link+enclosure", :"custom:label+featured", :"custom:value")
+    item = parse_entry(<<~XML).first
+      <link href="/episode.mp3" rel="enclosure"/>
+      <custom:label rel="featured">Featured</custom:label>
+      <custom:value>Unchanged</custom:value>
+    XML
+
+    assert_equal "/episode.mp3", item.link_enclosure
+    assert_equal "/episode.mp3", item[:"link+enclosure"]
+    assert_equal "Featured", item.custom_label_featured
+    assert_equal "Featured", item[:"custom_label+featured"]
+    assert_equal "Unchanged", item.custom_value
+  ensure
+    SimpleRSS.item_tags.replace(original_tags)
+  end
+
+  private
+
+  def parse_entry(content)
+    SimpleRSS.parse <<~XML
+      <feed xmlns="http://www.w3.org/2005/Atom">
+        <title>Relation links</title>
+        <entry><title>Entry</title>#{content}</entry>
+      </feed>
+    XML
+  end
+end

data/test/data/atom_categories.xml

@@ -0,0 +1,23 @@
+<feed xmlns="http://www.w3.org/2005/Atom" xmlns:topics="http://www.w3.org/2005/Atom">
+  <title>Atom categories</title>
+  <entry>
+    <title>Ruby news</title>
+    <category label="Human label" scheme="https://example.com/topics" term="ruby"/>
+    <category
+      scheme = 'https://example.com/topics'
+      term = 'rails'
+      label = 'Framework'>Ignored element content</category>
+    <topics:category term="Ruby &amp; RSS"/>
+    <category term="ruby"/>
+  </entry>
+  <entry>
+    <title>No usable terms</title>
+    <category label="Label only">Not a term</category>
+    <category term="" label="Empty"/>
+    <category term=" &#32; " label="Whitespace"/>
+  </entry>
+  <entry>
+    <title>Other news</title>
+    <category term="sports"/>
+  </entry>
+</feed>

data/test/data/atom_nested_link.xml

@@ -0,0 +1,13 @@
+<feed xmlns="http://www.w3.org/2005/Atom" xmlns:media="http://search.yahoo.com/mrss/">
+  <title>Nested link media</title>
+  <entry>
+    <title>Story</title>
+    <link href="https://example.com/story" rel="alternate" title="story" type="text/html">
+      <media:content>
+        <media:thumbnail height="60" url="https://example.com/thumbnail.jpg" width="106">
+          <img alt="Thumbnail" src="https://example.com/thumbnail.jpg"/>
+        </media:thumbnail>
+      </media:content>
+    </link>
+  </entry>
+</feed>

data/test/data/discovery.html

@@ -0,0 +1,28 @@
+<!doctype html>
+<HTML>
+<HEAD>
+  <meta charset=utf-8>
+  <base HREF='../syndication/'>
+  <link title='News &amp; updates' href='news.xml?edition=1&amp;lang=en#items' TYPE='Application/RSS+XML; charset=UTF-8' REL='ALTERNATE'>
+  <LINK REL="alternate feed" TYPE=application/atom+xml HREF="atom.xml" title="Atom">
+  <link rel=alternate type=application/feed+json href=feed.json title='JSON Feed'>
+  <link rel=alternate type=application/json href=legacy.json />
+  <link rel=alternate type=application/rdf+xml href=feed.rdf>
+  <link rel=alternate type=application/rss+xml href='news.xml?edition=1&amp;lang=en#duplicate' title='Duplicate'>
+  <link rel=alternate type=application/rss+xml href='news.xml?edition=2&amp;lang=en'>
+  <base href='https://ignored.example.com/'>
+  <link rel=stylesheet type=application/rss+xml href=wrong.xml>
+  <link rel=alternate type=text/css href=wrong.css>
+  <link rel=alternate type=application/rss+xml>
+  <!-- <link rel=alternate type=application/rss+xml href=comment.xml> -->
+  <script>var html = '<link rel=alternate type=application/rss+xml href=script.xml>';</script>
+  <style>.example::before { content: '<link rel=alternate type=application/rss+xml href=style.xml>'; }</style>
+  <template><base href='https://wrong.example.com/'><link rel=alternate type=application/rss+xml href=template.xml></template>
+  <noscript><link rel=alternate type=application/rss+xml href=noscript.xml></noscript>
+</HEAD>
+<BODY>
+  <article><link rel=alternate type=application/rss+xml href=body.xml></article>
+  <p>&lt;link rel=alternate type=application/rss+xml href=text.xml&gt;</p>
+  <a href=guessed-feed.xml>Feed</a>
+</BODY>
+</HTML>

data/test/data/json_feed_1.json

@@ -0,0 +1,75 @@
+{
+  "version": "https://jsonfeed.org/version/1",
+  "title": "Example",
+  "description": "A feed of examples",
+  "home_page_url": "https://example.com/",
+  "feed_url": "https://example.com/feed.json",
+  "icon": "https://example.com/icon.png",
+  "favicon": "https://example.com/favicon.png",
+  "expired": true,
+  "next_url": "https://example.com/older.json",
+  "user_comment": "Subscribe with a feed reader.",
+  "hubs": [
+    {
+      "type": "WebSub",
+      "url": "https://example.com/hub"
+    }
+  ],
+  "_publisher": {
+    "enabled": true,
+    "sequence": [
+      1,
+      2
+    ]
+  },
+  "items": [
+    {
+      "id": "opaque:%2F:001",
+      "title": "Ruby & feeds",
+      "url": "https://example.com/blog/article?one=1&two=2",
+      "external_url": "https://example.org/original",
+      "content_html": "<p>Full &amp; complete.</p>",
+      "content_text": "Full & complete.",
+      "summary": "A summary.",
+      "date_published": "2026-09-12T10:00:00Z",
+      "date_modified": "2026-09-13T11:00:00Z",
+      "image": "https://example.com/image.png",
+      "banner_image": "https://example.com/banner.png",
+      "tags": [
+        "ruby",
+        "feeds",
+        "ruby",
+        " "
+      ],
+      "attachments": [
+        {
+          "url": "https://example.com/audio/one.mp3",
+          "mime_type": "audio/mpeg",
+          "title": "Episode",
+          "size_in_bytes": 1234,
+          "duration_in_seconds": 62.5,
+          "_codec": {
+            "lossless": false
+          }
+        },
+        {
+          "url": "https://example.com/images/two.png",
+          "mime_type": "image/png",
+          "title": "Cover",
+          "size_in_bytes": 4321
+        }
+      ],
+      "_extension": {
+        "value": "original"
+      }
+    }
+  ],
+  "author": {
+    "name": "Example Editor",
+    "url": "https://example.com/editor",
+    "avatar": "https://example.com/avatar.png",
+    "_profile": {
+      "role": "editor"
+    }
+  }
+}

data/test/data/json_feed_1_1.json

@@ -0,0 +1,78 @@
+{
+  "version": "https://jsonfeed.org/version/1.1",
+  "title": "Example",
+  "description": "A feed of examples",
+  "home_page_url": "https://example.com/",
+  "feed_url": "https://example.com/feed.json",
+  "icon": "https://example.com/icon.png",
+  "favicon": "https://example.com/favicon.png",
+  "language": "en",
+  "expired": true,
+  "next_url": "https://example.com/older.json",
+  "user_comment": "Subscribe with a feed reader.",
+  "hubs": [
+    {
+      "type": "WebSub",
+      "url": "https://example.com/hub"
+    }
+  ],
+  "authors": [
+    {
+      "name": "Example Editor",
+      "url": "https://example.com/editor",
+      "avatar": "https://example.com/avatar.png",
+      "_profile": {
+        "role": "editor"
+      }
+    }
+  ],
+  "_publisher": {
+    "enabled": true,
+    "sequence": [
+      1,
+      2
+    ]
+  },
+  "items": [
+    {
+      "id": "opaque:%2F:001",
+      "title": "Ruby & feeds",
+      "url": "https://example.com/blog/article?one=1&two=2",
+      "external_url": "https://example.org/original",
+      "content_html": "<p>Full &amp; complete.</p>",
+      "content_text": "Full & complete.",
+      "summary": "A summary.",
+      "date_published": "2026-09-12T10:00:00Z",
+      "date_modified": "2026-09-13T11:00:00Z",
+      "image": "https://example.com/image.png",
+      "banner_image": "https://example.com/banner.png",
+      "tags": [
+        "ruby",
+        "feeds",
+        "ruby",
+        " "
+      ],
+      "attachments": [
+        {
+          "url": "https://example.com/audio/one.mp3",
+          "mime_type": "audio/mpeg",
+          "title": "Episode",
+          "size_in_bytes": 1234,
+          "duration_in_seconds": 62.5,
+          "_codec": {
+            "lossless": false
+          }
+        },
+        {
+          "url": "https://example.com/images/two.png",
+          "mime_type": "image/png",
+          "title": "Cover",
+          "size_in_bytes": 4321
+        }
+      ],
+      "_extension": {
+        "value": "original"
+      }
+    }
+  ]
+}

data/test/data/mixed_dates.xml

@@ -0,0 +1,55 @@
+<rss version="2.0">
+  <channel>
+    <title>Mixed dates</title>
+    <item>
+      <title>Missing first</title>
+    </item>
+    <item>
+      <guid>publication</guid>
+      <title>Publication</title>
+      <pubDate>2026-09-01T00:00:00Z</pubDate>
+      <updated>2026-09-05T00:00:00Z</updated>
+      <published>2026-09-06T00:00:00Z</published>
+    </item>
+    <item>
+      <guid>fractional</guid>
+      <title>Fractional</title>
+      <pubDate>2026-09-03T00:00:00.000000001Z</pubDate>
+    </item>
+    <item>
+      <guid>updated-first</guid>
+      <title>Updated first</title>
+      <pubDate>not-a-date</pubDate>
+      <updated>2026-09-03T00:00:00.000000002Z</updated>
+      <published>2026-09-07T00:00:00Z</published>
+    </item>
+    <item>
+      <guid>published</guid>
+      <title>Published</title>
+      <pubDate></pubDate>
+      <updated>not-a-date</updated>
+      <published>2026-09-02T00:00:00Z</published>
+    </item>
+    <item>
+      <guid>historical</guid>
+      <title>Historical</title>
+      <pubDate>1965-01-01T00:00:00Z</pubDate>
+    </item>
+    <item>
+      <guid>updated-second</guid>
+      <title>Updated second</title>
+      <updated>2026-09-03T01:00:00.000000002+01:00</updated>
+    </item>
+    <item>
+      <guid>blank</guid>
+      <title>Blank</title>
+      <pubDate> </pubDate>
+    </item>
+    <item>
+      <guid>invalid</guid>
+      <title>Invalid</title>
+      <pubDate>not-a-date</pubDate>
+      <updated>not-a-date</updated>
+    </item>
+  </channel>
+</rss>

data/test/data/normalized_atom.xml

@@ -0,0 +1,22 @@
+<feed xmlns="http://www.w3.org/2005/Atom" xml:base="https://example.com/blog/">
+  <title>Example feed</title>
+  <entry xml:base="posts/">
+    <id>opaque:%2F:001</id>
+    <title>Ruby &amp; feeds</title>
+    <link rel="self" type="application/atom+xml" href="api/001"/>
+    <link rel="alternate" type="application/pdf" href="article.pdf"/>
+    <link rel="alternate" type="text/html" xml:base="../" href="article?one=1&amp;two=2">
+      <extension href="https://wrong.example.com/"/>
+    </link>
+    <published>2026-09-12T10:00:00Z</published>
+    <updated>2026-09-13T11:00:00Z</updated>
+    <summary type="html">&lt;p&gt;A summary.&lt;/p&gt;</summary>
+    <content type="html">&lt;p&gt;Full &amp;amp; complete.&lt;/p&gt;</content>
+    <category term="ruby" label="Ruby language" scheme="urn:topics"/>
+    <category term="feeds"/>
+    <category term="ruby"/>
+    <category label="Missing term"/>
+    <link rel="enclosure" href="/audio/one.mp3" type="audio/mpeg" length="1234"/>
+    <link rel="enclosure" href="/images/two.png" type="image/png" length="4321"/>
+  </entry>
+</feed>

data/test/data/normalized_rss.xml

@@ -0,0 +1,21 @@
+<rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/"
+     xmlns:atom="http://www.w3.org/2005/Atom" xml:base="https://example.com/blog/">
+  <channel>
+    <title>Example feed</title>
+    <item xml:base="posts/">
+      <guid isPermaLink="false">opaque:%2F:001</guid>
+      <title>Ruby &amp; feeds</title>
+      <link xml:base="../">article?one=1&amp;two=2</link>
+      <pubDate>Sat, 12 Sep 2026 10:00:00 GMT</pubDate>
+      <atom:updated>2026-09-13T11:00:00Z</atom:updated>
+      <description><![CDATA[<p>A summary.</p>]]></description>
+      <content:encoded><![CDATA[<p>Full &amp; complete.</p>]]></content:encoded>
+      <category domain="urn:topics">ruby</category>
+      <category>feeds</category>
+      <category>ruby</category>
+      <category> </category>
+      <enclosure url="/audio/one.mp3" type="audio/mpeg" length="1234"/>
+      <enclosure url="/images/two.png" type="image/png" length="4321"/>
+    </item>
+  </channel>
+</rss>

data/test/data/rss_categories.xml

@@ -0,0 +1,15 @@
+<rss version="2.0">
+  <channel>
+    <title>RSS categories</title>
+    <item>
+      <title>Ruby news</title>
+      <category domain="https://example.com/topics">Technology</category>
+      <category><![CDATA[ Ruby & RSS ]]></category>
+      <category>Technology</category>
+    </item>
+    <item>
+      <title>Other news</title>
+      <category>Sports</category>
+    </item>
+  </channel>
+</rss>

data/test/support/http_server.rb

@@ -0,0 +1,44 @@
+require "socket"
+
+module HTTPServer
+  def wait_for_disconnect(client)
+    client.read
+  rescue Errno::ECONNRESET
+    nil
+  end
+
+  def with_server(responses)
+    server = TCPServer.new("127.0.0.1", 0)
+    base_url = "http://127.0.0.1:#{server.addr[1]}"
+    requests = []
+    worker = Thread.new do
+      responses.each do |response|
+        client = server.accept
+        begin
+          request = []
+          while (line = client.gets)
+            break if line == "\r\n"
+
+            request << line.strip
+          end
+          requests << request
+          if response.respond_to?(:call)
+            response.call(client, request)
+            next
+          end
+          status, headers, body = response
+          response_headers = headers.merge("Content-Length" => body.bytesize.to_s, "Connection" => "close")
+          client.write("HTTP/1.1 #{status} Test\r\n" + response_headers.map { |name, value| "#{name}: #{value}\r\n" }.join + "\r\n" + body)
+        ensure
+          client.close
+        end
+      end
+    end
+    yield base_url, requests
+    worker.value
+  ensure
+    worker&.kill
+    worker&.join
+    server&.close
+  end
+end

data/test/support/replace_method.rb

@@ -0,0 +1,14 @@
+module ReplaceMethod
+  def with_replaced_method(object, name, replacement)
+    own_method = object.singleton_methods(false).include?(name)
+    original = object.method(name)
+    object.define_singleton_method(name) { |*arguments, **keywords, &block| replacement.call(*arguments, **keywords, &block) }
+    yield
+  ensure
+    if own_method
+      object.define_singleton_method(name, original)
+    else
+      object.singleton_class.remove_method(name)
+    end
+  end
+end