feed-normalizer 1.4.0 → 1.5.0

data/History.txt

@@ -1,3 +1,13 @@
+1.5.0
+ * Add support for new fields:
+   * Atom 0.3: issued is now available through entry.date_published.
+   * RSS: feed.skip_hours, feed.skip_days, feed.ttl [joshpeek]
+   * All: entry.last_updated, this is an alias to entry.date_published for RSS.
+ * Rewrite relative links in content [joshpeek]
+ * Handle CDATA sections consistently across all formats. [sam.lown]
+ * Prevent SimpleRSS from doing its own escaping. [reported by: paul.stadig, lionel.bouton]
+ * Reparse Time classes [reported by: sam.lown]
+
 1.4.0
 
  * Support content:encoded. Accessible via Entry#content.

data/Rakefile

@@ -1,11 +1,11 @@
 require 'hoe'
 
-Hoe.new("feed-normalizer", "1.4.0") do |s|
+Hoe.new("feed-normalizer", "1.5.0") do |s|
   s.author = "Andrew A. Smith"
   s.email = "andy@tinnedfruit.org"
   s.url = "http://feed-normalizer.rubyforge.org/"
   s.summary = "Extensible Ruby wrapper for Atom and RSS parsers"
-  s.description = s.paragraphs_of('Readme.txt', 1..2).join("\n\n")
+  s.description = s.paragraphs_of('README.txt', 1..2).join("\n\n")
   s.changes = s.paragraphs_of('History.txt', 0..1).join("\n\n")
   s.extra_deps << ["simple-rss", ">= 1.1"]
   s.extra_deps << ["hpricot", ">= 0.6"]

data/lib/html-cleaner.rb

@@ -1,3 +1,4 @@
+require 'rubygems'
 require 'hpricot'
 require 'cgi'
 
@@ -99,10 +100,10 @@ module FeedNormalizer
         doc = Hpricot(str, :xhtml_strict => true)
         doc = subtree(doc, :body)
 
-        out = ""
+        out = []
         doc.traverse_text {|t| out << add_entities(t.to_html)}
 
-        return out
+        return out.join
       end
 
       # Returns true if the given string contains a suspicious URL,

data/lib/parsers/rss.rb

@@ -42,7 +42,8 @@ module FeedNormalizer
         :copyright => :copyright,
         :authors => :managingEditor,
         :last_updated => [:lastBuildDate, :pubDate, :dc_date],
-        :id => :guid
+        :id => :guid,
+        :ttl => :ttl
       }
 
       # make two passes, to catch all possible root elements
@@ -51,6 +52,8 @@ module FeedNormalizer
 
       # custom channel elements
       feed.image = rss.image ? rss.image.url : nil
+      feed.skip_hours = skip(rss, :skipHours)
+      feed.skip_days = skip(rss, :skipDays)
 
       # item elements
       item_mapping = {
@@ -59,7 +62,8 @@ module FeedNormalizer
         :description => :description,
         :content => [:content_encoded, :description],
         :title => :title,
-        :authors => [:author, :dc_creator]
+        :authors => [:author, :dc_creator],
+        :last_updated => [:pubDate, :dc_date] # This is effectively an alias for date_published for this parser.
       }
 
       rss.items.each do |rss_item|
@@ -79,6 +83,14 @@ module FeedNormalizer
       feed
     end
 
+    def self.skip(parser, attribute)
+      attributes = case attribute
+        when :skipHours: :hours
+        when :skipDays: :days
+      end
+      channel = parser.channel
+      channel.respond_to?(attribute) && channel.send(attribute).send(attributes).map { |e| e.content }
+    end
+
   end
 end
-

data/lib/parsers/simple-rss.rb

@@ -1,5 +1,42 @@
 require 'simple-rss'
 
+# Monkey patches for outstanding issues logged in the simple-rss project.
+#   * Add support for issued time field:
+#     http://rubyforge.org/tracker/index.php?func=detail&aid=13980&group_id=893&atid=3517
+#   * The '+' symbol is lost when escaping fields.
+#     http://rubyforge.org/tracker/index.php?func=detail&aid=10852&group_id=893&atid=3517
+#
+class SimpleRSS
+  @@item_tags << :issued
+
+  undef clean_content
+  def clean_content(tag, attrs, content)
+    content = content.to_s
+    case tag
+      when :pubDate, :lastBuildDate, :published, :updated, :expirationDate, :modified, :'dc:date', :issued
+        Time.parse(content) rescue unescape(content)
+      when :author, :contributor, :skipHours, :skipDays
+        unescape(content.gsub(/<.*?>/,''))
+      else
+        content.empty? && "#{attrs} " =~ /href=['"]?([^'"]*)['" ]/mi ? $1.strip : unescape(content)
+    end
+  end
+
+  undef unescape
+  def unescape(s)
+   if s =~ /^(<!\[CDATA\[|\]\]>)/
+     # Raw HTML is inside the CDATA, so just remove the CDATA wrapper.
+     s.gsub(/(<!\[CDATA\[|\]\]>)/,'').strip
+   elsif s =~ /[<>]/
+     # Already looks like HTML.
+     s
+   else
+     # Make it HTML.
+     FeedNormalizer::HtmlCleaner.unescapeHTML(s)
+   end
+ end
+end
+
 module FeedNormalizer
 
   # The SimpleRSS parser can handle both RSS and Atom feeds.
@@ -38,7 +75,8 @@ module FeedNormalizer
         :copyright => [:copyright, :rights],
         :authors => [:author, :webMaster, :managingEditor, :contributor],
         :urls => :link,
-        :description => [:description, :subtitle]
+        :description => [:description, :subtitle],
+        :ttl => :ttl
       }
 
       map_functions!(feed_mapping, atomrss, feed)
@@ -50,13 +88,14 @@ module FeedNormalizer
 
       # entry elements
       entry_mapping = {
-        :date_published => [:pubDate, :published, :dc_date],
+        :date_published => [:pubDate, :published, :dc_date, :issued],
         :urls => :link,
         :description => [:description, :summary],
         :content => [:content, :content_encoded, :description],
         :title => :title,
         :authors => [:author, :contributor, :dc_creator],
-        :categories => :category
+        :categories => :category,
+        :last_updated => [:updated, :dc_date, :pubDate]
       }
 
       atomrss.entries.each do |atomrss_entry|
@@ -76,7 +115,7 @@ module FeedNormalizer
     def self.image(parser)
       if parser.respond_to?(:image) && parser.image
         if parser.image =~ /<url>/ # RSS image contains an <url> spec
-          parser.image.scan(/<url>(.*)<\/url>/).to_s
+          parser.image.scan(/<url>(.*?)<\/url>/).to_s
         else
           parser.image # Atom contains just the url
         end

data/lib/structures.rb

@@ -115,13 +115,55 @@ module FeedNormalizer
     end
   end
 
+  module TimeFix
+    # Reparse any Time instances, due to RSS::Parser's redefinition of
+    # certain aspects of the Time class that creates unexpected behaviour
+    # when extending the Time class, as some common third party libraries do.
+    # See http://code.google.com/p/feed-normalizer/issues/detail?id=13.
+    def reparse(obj)
+      @parsed ||= false
+
+      return obj if @parsed
+
+      if obj.is_a?(Time)
+        @parsed = true
+        Time.at(obj) rescue obj
+      end
+    end
+  end
+
+  module RewriteRelativeLinks
+    def rewrite_relative_links(text, url)
+      if host = url_host(url)
+        text.to_s.gsub(/(href|src)=('|")\//, '\1=\2http://' + host + '/')
+      else
+        text
+      end
+    end
+
+    private
+      def url_host(url)
+        URI.parse(url).host rescue nil
+      end
+  end
+
 
   # Represents a feed item entry.
+  # Available fields are:
+  #  * content
+  #  * description
+  #  * title
+  #  * date_published
+  #  * urls / url
+  #  * id
+  #  * authors / author
+  #  * copyright
+  #  * categories
   class Entry
-    include Singular, ElementEquality, ElementCleaner
+    include Singular, ElementEquality, ElementCleaner, TimeFix, RewriteRelativeLinks
 
     HTML_ELEMENTS = [:content, :description, :title]
-    SIMPLE_ELEMENTS = [:date_published, :urls, :id, :authors, :copyright, :categories]
+    SIMPLE_ELEMENTS = [:date_published, :urls, :id, :authors, :copyright, :categories, :last_updated]
     BLENDED_ELEMENTS = []
 
     ELEMENTS = HTML_ELEMENTS + SIMPLE_ELEMENTS + BLENDED_ELEMENTS
@@ -132,19 +174,41 @@ module FeedNormalizer
       @urls = []
       @authors = []
       @categories = []
+      @date_published, @content = nil
+    end
+
+    undef date_published
+    def date_published
+      @date_published = reparse(@date_published)
+    end
+
+    undef content
+    def content
+      @content = rewrite_relative_links(@content, url)
     end
 
   end
 
   # Represents the root element of a feed.
+  # Available fields are:
+  #  * title
+  #  * description
+  #  * id
+  #  * last_updated
+  #  * copyright
+  #  * authors / author
+  #  * urls / url
+  #  * image
+  #  * generator
+  #  * items / channel
   class Feed
-    include Singular, ElementEquality, ElementCleaner
+    include Singular, ElementEquality, ElementCleaner, TimeFix
 
     # Elements that can contain HTML fragments.
     HTML_ELEMENTS = [:title, :description]
 
     # Elements that contain 'plain' Strings, with HTML escaped.
-    SIMPLE_ELEMENTS = [:id, :last_updated, :copyright, :authors, :urls, :image, :generator]
+    SIMPLE_ELEMENTS = [:id, :last_updated, :copyright, :authors, :urls, :image, :generator, :ttl, :skip_hours, :skip_days]
 
     # Elements that contain both HTML and escaped HTML.
     BLENDED_ELEMENTS = [:items]
@@ -160,8 +224,16 @@ module FeedNormalizer
       # set up associations (i.e. arrays where needed)
       @urls = []
       @authors = []
+      @skip_hours = []
+      @skip_days = []
       @items = []
       @parser = wrapper.parser.to_s
+      @last_updated = nil
+    end
+
+    undef last_updated
+    def last_updated
+      @last_updated = reparse(@last_updated)
     end
 
     def channel() self end

data/test/data/atom03.xml

@@ -24,7 +24,7 @@
 Kmart has the Levi Strauss Signature Girl’s Low Rise Flare Jean for $10 after $5 instant savings (ends 9/2)
 Slim fit through hip and thigh, with zip-fly with button-through closure. Machine washable 99% Cotton/1% Spandex
 ]]></summary>
-    <content type="text/html" mode="escaped" xml:base="http://www.cheapstingybargains.com/24557/levi-strauss-signature-girls-low-rise-slim-fit-flare-jeans-10/"><![CDATA[<p><a href="http://clickserve.cc-dt.com/link/tplclick?lid=41000000011334249&#038;pubid=21000000000053626" target=_"blank"><img  src="http://images.kmart.com/assets/images/product/productDetail/9990000058546711.jpg" width="150" height="150" border="0" style="float: right; margin: 0px 0px 5px 5px;" /></a><br />
+    <content type="text/html" mode="escaped" xml:base="http://www.cheapstingybargains.com/24557/levi-strauss-signature-girls-low-rise-slim-fit-flare-jeans-10/"><![CDATA[<p><a href="/link/tplclick?lid=41000000011334249&#038;pubid=21000000000053626" target=_"blank"><img  src="/assets/images/product/productDetail/9990000058546711.jpg" width="150" height="150" border="0" style="float: right; margin: 0px 0px 5px 5px;" /></a><br />
 <strong>Kmart has the <a href="http://clickserve.cc-dt.com/link/tplclick?lid=41000000011334249&#038;pubid=21000000000053626" target=_"blank">Levi Strauss Signature Girl&#8217;s Low Rise Flare Jean</a> for $10 after $5 instant savings (ends 9/2)</strong></p>
 <p>Slim fit through hip and thigh, with zip-fly with button-through closure. Machine washable 99% Cotton/1% Spandex</p>
 ]]></content>

data/test/data/atom10.xml

@@ -17,8 +17,8 @@
     <link href="http://habtm.com/articles/2006/08/16/a-forum-on-rails" rel="alternate" type="text/html"/>
     <category term="rails" scheme="http://habtm.com/articles/category/rails" label="rails"/>
     <category term="ruby" scheme="http://habtm.com/articles/category/ruby" label="ruby"/>
-    <summary type="html">&lt;p&gt;Josh Goebel and I took an evening to bang out a little project: &lt;a href="http://beast.caboo.se/"&gt;Beast&lt;/a&gt;.  It&amp;#8217;s our minimal no-fluff Rails forum.  It&amp;#8217;s no beast of an application either, clocking in at 285 LOC and a 1:1.5 test ratio.  &lt;a href="http://svn.techno-weenie.net/projects/beast/"&gt;Check it out&lt;/a&gt;!&lt;/p&gt;</summary>
-    <content type="html">&lt;p&gt;Josh Goebel and I took an evening to bang out a little project: &lt;a href="http://beast.caboo.se/"&gt;Beast&lt;/a&gt;.  It&amp;#8217;s our minimal no-fluff Rails forum.  It&amp;#8217;s no beast of an application either, clocking in at 285 LOC and a 1:1.5 test ratio.  &lt;a href="http://svn.techno-weenie.net/projects/beast/"&gt;Check it out&lt;/a&gt;!&lt;/p&gt;</content>
+    <summary type="html">&lt;plaintext&gt;&lt;p&gt;Josh Goebel and I took an evening to bang out a little project: &lt;a href="http://beast.caboo.se/"&gt;Beast&lt;/a&gt;.  It&amp;#8217;s our minimal no-fluff Rails forum.  It&amp;#8217;s no beast of an application either, clocking in at 285 LOC and a 1:1.5 test ratio.  &lt;a href="http://svn.techno-weenie.net/projects/beast/"&gt;Check it out&lt;/a&gt;!&lt;/p&gt;</summary>
+    <content type="html">&lt;plaintext&gt;&lt;p&gt;Josh Goebel and I took an evening to bang out a little project: &lt;a href="http://beast.caboo.se/"&gt;Beast&lt;/a&gt;.  It&amp;#8217;s our minimal no-fluff Rails forum.  It&amp;#8217;s no beast of an application either, clocking in at 285 LOC and a 1:1.5 test ratio.  &lt;a href="http://svn.techno-weenie.net/projects/beast/"&gt;Check it out&lt;/a&gt;!&lt;/p&gt;</content>
   </entry>
   <entry>
     <author>

data/test/data/rss20.xml

@@ -10,6 +10,17 @@
     <copyright>Copyright: (C) British Broadcasting Corporation, see http://news.bbc.co.uk/1/hi/help/rss/4498287.stm for terms and conditions of reuse</copyright>
     <docs>http://www.bbc.co.uk/syndication/</docs>
     <ttl>15</ttl>
+    <skipHours>
+       <hour>6</hour>
+       <hour>7</hour>
+       <hour>8</hour>
+       <hour>9</hour>
+       <hour>10</hour>
+       <hour>11</hour>
+    </skipHours>
+    <skipDays>
+       <day>Sunday</day>
+    </skipDays>
 
     <image>
       <title>BBC News</title>
@@ -19,7 +30,7 @@
 
     <item>
       <title>Concerns over security software</title>
-      <description>BBC Click investigates free security software and finds out who will protect PCs when Microsoft launches Vista.</description>
+      <description><![CDATA[BBC Click investigates free security software and finds out who will protect PCs when Microsoft launches Vista.]]></description>
       <content:encoded><![CDATA[<p>test1</p>]]></content:encoded>
       <link>http://news.bbc.co.uk/go/rss/-/1/hi/programmes/click_online/5326654.stm</link>
       <guid isPermaLink="false">http://news.bbc.co.uk/1/hi/programmes/click_online/5326654.stm</guid>
@@ -40,7 +51,7 @@
 
     <item>
       <title>MP3 player court order overturned</title>
-      <description>SanDisk puts its MP3 players back on display at a German electronics show after overturning a court injunction.</description>
+      <description>&lt;b&gt;SanDisk&lt;/b&gt; puts its MP3 players back on display at a German electronics show after overturning a court injunction.</description>
       <content:encoded><![CDATA[<p>test3</p>]]></content:encoded>
       <link>http://news.bbc.co.uk/go/rss/-/1/hi/technology/5326660.stm</link>
       <guid isPermaLink="false">http://news.bbc.co.uk/1/hi/technology/5326660.stm</guid>

data/test/data/rss20diff.xml

@@ -10,6 +10,17 @@
     <copyright>Copyright: (C) British Broadcasting Corporation, see http://news.bbc.co.uk/1/hi/help/rss/4498287.stm for terms and conditions of reuse</copyright>
     <docs>http://www.bbc.co.uk/syndication/</docs>
     <ttl>15</ttl>
+    <skipHours>
+       <hour>6</hour>
+       <hour>7</hour>
+       <hour>8</hour>
+       <hour>9</hour>
+       <hour>10</hour>
+       <hour>11</hour>
+    </skipHours>
+    <skipDays>
+       <day>Sunday</day>
+    </skipDays>
 
     <image>
       <title>BBC News</title>

data/test/data/rss20diff_short.xml

@@ -10,6 +10,17 @@
     <copyright>Copyright: (C) British Broadcasting Corporation, see http://news.bbc.co.uk/1/hi/help/rss/4498287.stm for terms and conditions of reuse</copyright>
     <docs>http://www.bbc.co.uk/syndication/</docs>
     <ttl>15</ttl>
+    <skipHours>
+       <hour>6</hour>
+       <hour>7</hour>
+       <hour>8</hour>
+       <hour>9</hour>
+       <hour>10</hour>
+       <hour>11</hour>
+    </skipHours>
+    <skipDays>
+       <day>Sunday</day>
+    </skipDays>
 
     <image>
       <title>BBC News</title>

data/test/test_feednormalizer.rb

@@ -1,4 +1,6 @@
 require 'test/unit'
+$:.unshift(File.dirname(__FILE__))
+$:.unshift(File.dirname(__FILE__) + '/../lib')
 require 'feed-normalizer'
 require 'yaml'
 
@@ -66,8 +68,11 @@ class FeedNormalizerTest < Test::Unit::TestCase
 
     assert_equal "BBC News | Technology | UK Edition", feed.title
     assert_equal ["http://news.bbc.co.uk/go/rss/-/1/hi/technology/default.stm"], feed.urls
+    assert_equal 15, feed.ttl
+    assert_equal [6, 7, 8, 9, 10, 11], feed.skip_hours
+    assert_equal ["Sunday"], feed.skip_days
     assert_equal "MP3 player court order overturned", feed.entries.last.title
-    assert_equal "SanDisk puts its MP3 players back on display at a German electronics show after overturning a court injunction.", feed.entries.last.description
+    assert_equal "<b>SanDisk</b> puts its MP3 players back on display at a German electronics show after overturning a court injunction.", feed.entries.last.description
     assert_match(/test\d/, feed.entries.last.content)
     assert_instance_of Time, feed.entries.last.date_published
   end
@@ -77,6 +82,9 @@ class FeedNormalizerTest < Test::Unit::TestCase
 
     assert_equal "~:caboose", feed.title
     assert_equal "http://habtm.com/xml/atom10/feed.xml", feed.url
+    assert_equal nil, feed.ttl
+    assert_equal [], feed.skip_hours
+    assert_equal [], feed.skip_days
     assert_equal "Starfish - Easy Distribution of Site Maintenance", feed.entries.last.title
     assert_equal "urn:uuid:6c028f36-f87a-4f53-b7e3-1f943d2341f0", feed.entries.last.id
 
@@ -134,9 +142,11 @@ class FeedNormalizerTest < Test::Unit::TestCase
   def test_clean
     feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:atom10])
 
-    assert feed.entries.first.content !~ /\<p\>/
+    assert_match(/<plaintext>/, feed.entries.first.content)
+    assert_match(/<plaintext>/, feed.entries.first.description)
     feed.clean!
-    assert feed.entries.first.content =~ /\<p\>/
+    assert_no_match(/<plaintext>/, feed.entries.first.content)
+    assert_no_match(/<plaintext>/, feed.entries.first.description)
   end
 
   def test_malformed_feed
@@ -145,25 +155,21 @@ class FeedNormalizerTest < Test::Unit::TestCase
 
   def test_dublin_core_date_ruby_rss
     feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rdf10], :force_parser => RubyRssParser, :try_others => false)
-    assert_equal 'RSS::Parser', feed.parser
     assert_instance_of Time, feed.entries.first.date_published
   end
 
   def test_dublin_core_date_simple_rss
     feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rdf10], :force_parser => SimpleRssParser, :try_others => false)
-    assert_equal 'SimpleRSS', feed.parser
     assert_instance_of Time, feed.entries.first.date_published
   end
 
   def test_dublin_core_creator_ruby_rss
     feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rdf10], :force_parser => RubyRssParser, :try_others => false)
-    assert_equal 'RSS::Parser', feed.parser
     assert_equal 'Jeff Hecht', feed.entries.last.author
   end
 
   def test_dublin_core_creator_simple_rss
     feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rdf10], :force_parser => SimpleRssParser, :try_others => false)
-    assert_equal 'SimpleRSS', feed.parser
     assert_equal 'Jeff Hecht', feed.entries.last.author
   end
 
@@ -191,7 +197,7 @@ class FeedNormalizerTest < Test::Unit::TestCase
     feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rss20], :force_parser => SimpleRssParser, :try_others => false)
 
     feed.entries.each_with_index do |e, i|
-      assert_match(/test#{i+1}/, e.content)
+      assert_equal("<p>test#{i+1}</p>", e.content)
     end
   end
 
@@ -199,9 +205,63 @@ class FeedNormalizerTest < Test::Unit::TestCase
     feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rss20], :force_parser => RubyRssParser, :try_others => false)
 
     feed.entries.each_with_index do |e, i|
-      assert_match(/test#{i+1}/, e.content)
+      assert_equal("<p>test#{i+1}</p>", e.content)
     end
   end
 
+  def test_atom_content_contains_pluses
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:atom10], :force_parser => SimpleRssParser, :try_others => false)
+
+    assert_equal 2, feed.entries.last.content.scan(/\+/).size
+  end
+
+  # http://code.google.com/p/feed-normalizer/issues/detail?id=13
+  def test_times_are_reparsed
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rss20], :force_parser => RubyRssParser, :try_others => false)
+
+    Time.class_eval "alias :old_to_s :to_s; def to_s(x=1); old_to_s; end"
+
+    assert_equal "Sat Sep 09 07:57:06 -0700 2006", feed.last_updated.to_s(:foo)
+    assert_equal "Sat Sep 09 05:45:35 -0700 2006", feed.entries.first.date_published.to_s(:foo)
+  end
+
+  def test_atom03_has_issued
+    SimpleRSS.class_eval "@@item_tags.delete(:issued)"
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:atom03], :force_parser => SimpleRssParser, :try_others => false)
+    assert_nil feed.entries.first.date_published
+
+    SimpleRSS.class_eval "@@item_tags << :issued"
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:atom03], :force_parser => SimpleRssParser, :try_others => false)
+    assert_equal "Tue Aug 29 02:31:03 UTC 2006", feed.entries.first.date_published.to_s
+  end
+
+  def test_html_should_be_escaped_by_default
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rss20], :force_parser => RubyRssParser, :try_others => false)
+    assert_match "<b>SanDisk</b>", feed.items.last.description
+
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rss20], :force_parser => SimpleRssParser, :try_others => false)
+    assert_match "<b>SanDisk</b>", feed.items.last.description
+  end
+
+  def test_relative_links_and_images_should_be_rewritten_with_url_base
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:atom03])
+    assert_match '<a href="http://www.cheapstingybargains.com/link/tplclick?lid=41000000011334249&#038;pubid=21000000000053626"' + 
+      ' target=_"blank"><img  src="http://www.cheapstingybargains.com/assets/images/product/productDetail/9990000058546711.jpg"' + 
+      ' width="150" height="150" border="0" style="float: right; margin: 0px 0px 5px 5px;" /></a>',
+      feed.items.first.content
+  end
+
+  def test_last_updated_simple_rss
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:atom10], :force_parser => SimpleRssParser, :try_others => false)
+
+    assert_equal Time.parse("Wed Aug 16 09:59:44 -0700 2006"), feed.entries.first.last_updated
+  end
+
+  def test_last_updated_ruby_rss
+    feed = FeedNormalizer::FeedNormalizer.parse(XML_FILES[:rss20], :force_parser => RubyRssParser, :try_others => false)
+
+    assert_equal feed.entries.first.date_published, feed.entries.first.last_updated
+  end
+
 end
 

metadata

@@ -1,10 +1,10 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.9.2
+rubygems_version: 0.9.4
 specification_version: 1
 name: feed-normalizer
 version: !ruby/object:Gem::Version 
-  version: 1.4.0
-date: 2007-07-10 00:00:00 -07:00
+  version: 1.5.0
+date: 2008-02-05 00:00:00 -08:00
 summary: Extensible Ruby wrapper for Atom and RSS parsers
 require_paths: 
 - lib
@@ -90,5 +90,5 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 1.2.1
+        version: 1.5.0
     version: