cardmagic-simple-rss 1.1

data/install.rb

@@ -0,0 +1,40 @@
+require 'rbconfig'
+require 'find'
+require 'ftools'
+
+include Config
+
+# this was adapted from rdoc's install.rb by ways of Log4r
+
+$sitedir = CONFIG["sitelibdir"]
+unless $sitedir
+  version = CONFIG["MAJOR"] + "." + CONFIG["MINOR"]
+  $libdir = File.join(CONFIG["libdir"], "ruby", version)
+  $sitedir = $:.find {|x| x =~ /site_ruby/ }
+  if !$sitedir
+    $sitedir = File.join($libdir, "site_ruby")
+  elsif $sitedir !~ Regexp.quote(version)
+    $sitedir = File.join($sitedir, version)
+  end
+end
+
+makedirs = %w{ shipping }
+makedirs.each {|f| File::makedirs(File.join($sitedir, *f.split(/\//)))}
+
+Dir.chdir("lib")
+begin
+	require 'rubygems'
+	require 'rake'
+rescue LoadError
+	puts
+	puts "Please install Gem and Rake from http://rubyforge.org/projects/rubygems and http://rubyforge.org/projects/rake"
+	puts
+	exit(-1)
+end
+
+files = FileList["**/*"]
+
+# File::safe_unlink *deprecated.collect{|f| File.join($sitedir, f.split(/\//))}
+files.each {|f| 
+  File::install(f, File.join($sitedir, *f.split(/\//)), 0644, true)
+}

data/lib/simple-rss.rb

@@ -0,0 +1,135 @@
+require 'cgi'
+require 'time'
+
+class SimpleRSS
+  VERSION = "1.1"
+  
+	attr_reader :items, :source
+	alias :entries :items
+
+	@@feed_tags = [
+		:id,
+		:title, :subtitle, :link,
+		:description, 
+		:author, :webMaster, :managingEditor, :contributor,
+		:pubDate, :lastBuildDate, :updated, :'dc:date',
+		:generator, :language, :docs, :cloud,
+		:ttl, :skipHours, :skipDays,
+		:image, :logo, :icon, :rating,
+		:rights, :copyright,
+		:textInput, :'feedburner:browserFriendly',
+		:'itunes:author', :'itunes:category'
+	]
+
+	@@item_tags = [
+		:id,
+		:title, :link,
+		:author, :contributor,
+		:description, :summary, :content, :'content:encoded', :comments,
+		:pubDate, :published, :updated, :expirationDate, :modified, :'dc:date',
+		:category, :guid,
+		:'trackback:ping', :'trackback:about',
+		:'dc:creator', :'dc:title', :'dc:subject', :'dc:rights', :'dc:publisher'
+	]
+
+	def initialize(source)
+		@source = source.respond_to?(:read) ? source.read : source.to_s
+		@items = Array.new
+
+		parse
+	end
+
+	def channel() self end
+	alias :feed :channel
+
+	class << self
+		def feed_tags
+			@@feed_tags
+		end
+		def feed_tags=(ft)
+			@@feed_tags = ft
+		end
+
+		def item_tags
+			@@item_tags
+		end
+		def item_tags=(it)
+			@@item_tags = it
+		end
+
+		# The strict attribute is for compatibility with Ruby's standard RSS parser
+		def parse(source, do_validate=true, ignore_unknown_element=true, parser_class=false)
+			new source
+		end
+	end
+
+	private
+
+	def parse
+	  raise SimpleRSSError, "Poorly formatted feed" unless @source =~ %r{<(channel|feed).*?>.*?</(channel|feed)>}mi
+	  
+		# Feed's title and link
+		feed_content = $1 if @source =~ %r{(.*?)<(rss:|atom:)?(item|entry).*?>.*?</(rss:|atom:)?(item|entry)>}mi
+		
+		@@feed_tags.each do |tag|
+			if feed_content && feed_content =~ %r{<(rss:|atom:)?#{tag}(.*?)>(.*?)</(rss:|atom:)?#{tag}>}mi
+				nil
+			elsif feed_content && feed_content =~ %r{<(rss:|atom:)?#{tag}(.*?)\/\s*>}mi
+				nil
+			elsif @source =~ %r{<(rss:|atom:)?#{tag}(.*?)>(.*?)</(rss:|atom:)?#{tag}>}mi
+				nil
+			elsif @source =~ %r{<(rss:|atom:)?#{tag}(.*?)\/\s*>}mi
+				nil
+			end
+			
+			if $2 || $3
+        tag_cleaned = clean_tag(tag)
+        eval %{ @#{ tag_cleaned } = clean_content(tag, $2, $3) }
+        self.class.class_eval %{ attr_reader :#{ tag_cleaned } }
+			end
+		end
+
+		# RSS items' title, link, and description
+		@source.scan( %r{<(rss:|atom:)?(item|entry)([\s][^>]*)?>(.*?)</(rss:|atom:)?(item|entry)>}mi ) do |match|
+			item = Hash.new
+			@@item_tags.each do |tag|
+				if match[3] =~ %r{<(rss:|atom:)?#{tag}(.*?)>(.*?)</(rss:|atom:)?#{tag}>}mi
+					nil
+				elsif match[3] =~ %r{<(rss:|atom:)?#{tag}(.*?)/\s*>}mi
+					nil
+				end
+				item[clean_tag(tag)] = clean_content(tag, $2, $3) if $2 || $3
+			end
+			def item.method_missing(name, *args) self[name] end
+			@items << item
+		end
+
+	end
+
+	def clean_content(tag, attrs, content)
+		content = content.to_s
+		case tag
+			when :pubDate, :lastBuildDate, :published, :updated, :expirationDate, :modified, :'dc:date'
+				Time.parse(content) rescue unescape(content)
+			when :author, :contributor, :skipHours, :skipDays
+				unescape(content.gsub(/<.*?>/,''))
+			else
+				content.empty? && "#{attrs} " =~ /href=['"]?([^'"]*)['" ]/mi ? $1.strip : unescape(content)
+		end
+	end
+
+	def clean_tag(tag)
+		tag.to_s.gsub(':','_').intern
+	end
+	
+  def unescape(content)
+  	if content =~ /([^-_.!~*'()a-zA-Z\d;\/?:@&=+$,\[\]]%)/n then
+  		CGI.unescape(content).gsub(/(<!\[CDATA\[|\]\]>)/,'').strip
+  	else
+  		content
+  	end
+  end
+end
+
+class SimpleRSSError < StandardError
+end

data/simple-rss.gemspec

@@ -0,0 +1,12 @@
+Gem::Specification.new do |s|
+  s.name = "simple-rss"
+  s.version = "1.1"
+  s.date = "2008-07-15"
+  s.summary = "A simple, flexible, extensible, and liberal RSS and Atom reader for Ruby. It is designed to be backwards compatible with the standard RSS parser, but will never do RSS generation."
+  s.email = "lucas@rufy.com"
+  s.homepage = "http://github.com/cardmagic/simple-rss"
+  s.description = "A simple, flexible, extensible, and liberal RSS and Atom reader for Ruby. It is designed to be backwards compatible with the standard RSS parser, but will never do RSS generation."
+  s.has_rdoc = true
+  s.authors = ["Lucas Carlson"]
+  s.files = ["install.rb", "lib", "lib/simple-rss.rb", "LICENSE", "Rakefile", "README", "simple-rss.gemspec", "test", "test/base", "test/base/base_test.rb", "test/data", "test/data/atom.xml", "test/data/not-rss.xml", "test/data/rss09.rdf", "test/data/rss20.xml", "test/test_helper.rb"]
+end

data/test/base/base_test.rb

@@ -0,0 +1,51 @@
+require File.dirname(__FILE__) + '/../test_helper'
+class BaseTest < Test::Unit::TestCase
+	def setup
+		@rss09 = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/rss09.rdf'), true
+		@rss20 = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/rss20.xml'), false
+		@atom = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/atom.xml')
+	end
+	
+	def test_channel
+		assert_equal @rss09, @rss09.channel
+		assert_equal @rss20, @rss20.channel
+		assert_equal @atom, @atom.feed
+	end
+	
+	def test_items
+		assert_kind_of Array, @rss09.items
+		assert_kind_of Array, @rss20.items
+		assert_kind_of Array, @atom.entries
+	end
+	
+	def test_rss09
+		assert_equal 10, @rss09.items.size
+		assert_equal "Slashdot", @rss09.title
+		assert_equal "http://slashdot.org/", @rss09.channel.link
+		assert_equal "http://books.slashdot.org/article.pl?sid=05/08/29/1319236&amp;from=rss", @rss09.items.first.link
+		assert_equal "http://books.slashdot.org/article.pl?sid=05/08/29/1319236&amp;from=rss", @rss09.items.first[:link]
+    assert_equal Time.parse("Wed Aug 24 13:33:34 UTC 2005"), @rss20.items.first.pubDate
+    assert_equal Time.parse("Fri Sep 09 02:52:31 PDT 2005"), @rss09.channel.dc_date
+	end
+
+	def test_rss20
+		assert_equal 10, @rss20.items.size
+		assert_equal "Technoblog", @rss20.title
+		assert_equal "http://tech.rufy.com", @rss20.channel.link
+		assert_equal "http://feeds.feedburner.com/rufytech?m=68", @rss20.items.first.link
+		assert_equal "http://feeds.feedburner.com/rufytech?m=68", @rss20.items.first[:link]
+		assert_equal "This is an XML content feed. It is intended to be viewed in a newsreader or syndicated to another site.", @rss20.channel.feedburner_browserFriendly
+	end
+	
+	def test_atom
+		assert_equal 1, @atom.entries.size
+		assert_equal "dive into mark", @atom.title
+		assert_equal "http://example.org/", @atom.feed.link
+		assert_equal "http://example.org/2005/04/02/atom", @atom.entries.first.link
+		assert_equal "http://example.org/2005/04/02/atom", @atom.entries.first[:link]
+	end
+	
+	def test_bad_feed
+	  assert_raise(SimpleRSSError) { SimpleRSS.parse(open(File.dirname(__FILE__) + '/../data/not-rss.xml')) }
+	end
+end

data/test/data/atom.xml

@@ -0,0 +1,45 @@
+<?xml version="1.0" encoding="utf-8"?>
+<feed xmlns="http://www.w3.org/2005/Atom">
+  <rss:title type="text">dive into mark</title>
+  <subtitle type="html">
+    A &lt;em&gt;lot&lt;/em&gt; of effort
+    went into making this effortless
+  </subtitle>
+  <updated>2005-07-31T12:29:29Z</updated>
+  <id>tag:example.org,2003:3</id>
+  <link rel="alternate" type="text/html" 
+   hreflang="en" href="http://example.org/"/>
+  <link rel="self" type="application/atom+xml" 
+   href="http://example.org/feed.atom"/>
+  <rights>Copyright (c) 2003, Mark Pilgrim</rights>
+  <generator uri="http://www.example.com/" version="1.0">
+    Example Toolkit
+  </generator>
+  <entry>
+    <title>Atom draft-07 snapshot</title>
+    <link rel="alternate" type="text/html" 
+     href="http://example.org/2005/04/02/atom"/>
+    <link rel="enclosure" type="audio/mpeg" length="1337"
+     href="http://example.org/audio/ph34r_my_podcast.mp3"/>
+    <id>tag:example.org,2003:3.2397</id>
+    <updated>2005-07-31T12:29:29Z</updated>
+    <published>2003-12-13T08:29:29-04:00</published>
+    <author>
+      <name>Mark Pilgrim</name>
+      <uri>http://example.org/</uri>
+      <email>f8dy@example.com</email>
+    </author>
+    <contributor>
+      <name>Sam Ruby</name>
+    </contributor>
+    <contributor>
+      <name>Joe Gregorio</name>
+    </contributor>
+    <content type="xhtml" xml:lang="en" 
+     xml:base="http://diveintomark.org/">
+      <div xmlns="http://www.w3.org/1999/xhtml">
+        <p><i>[Update: The Atom draft is finished.]</i></p>
+      </div>
+    </content>
+  </entry>
+</feed>

data/test/data/not-rss.xml

@@ -0,0 +1,8 @@
+<html>
+  <head>
+    <title>This ain't RSS!</title>
+  </head>
+  <body>
+    No, this is HTML, not RSS.
+  </body>
+</html>

data/test/data/rss09.rdf

@@ -0,0 +1,79 @@
+<?xml version="1.0" encoding="ISO-8859-1"?>
+
+<rdf:RDF
+xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+xmlns:dc="http://purl.org/dc/elements/1.1/"
+xmlns="http://my.netscape.com/rdf/simple/0.9/">
+
+<channel>
+<title>Slashdot</title>
+<link>http://slashdot.org/</link>
+<description>News for nerds, stuff that matters</description>
+<dc:date>2005-09-09T02:52:31-07:00</dc:date>
+</channel>
+
+<image>
+<title>Slashdot</title>
+<url>http://images.slashdot.org/topics/topicslashdot.gif</url>
+<link>http://slashdot.org/</link>
+</image>
+
+<item>
+<title>JBoss - A Developer's Notebook</title>
+<link>http://books.slashdot.org/article.pl?sid=05/08/29/1319236&amp;from=rss</link>
+<dc:date>2005-09-09T02:52:31-07:00</dc:date>
+</item>
+
+<item>
+<title>Apple Hedges Its Bet on New Intel Chips</title>
+<link>http://hardware.slashdot.org/article.pl?sid=05/08/29/1314219&amp;from=rss</link>
+</item>
+
+<item>
+<title>Beowulf Pioneer Lured From Cal Tech to LSU</title>
+<link>http://slashdot.org/article.pl?sid=05/08/29/1035240&amp;from=rss</link>
+</item>
+
+<item>
+<title>Google Talk Claims Openness, Lacks S2S Support</title>
+<link>http://it.slashdot.org/article.pl?sid=05/08/29/1022242&amp;from=rss</link>
+</item>
+
+<item>
+<title>The End of the Bar Code</title>
+<link>http://slashdot.org/article.pl?sid=05/08/29/1020220&amp;from=rss</link>
+</item>
+
+<item>
+<title>2.6.13 Linux Kernel Released</title>
+<link>http://linux.slashdot.org/article.pl?sid=05/08/29/0334205&amp;from=rss</link>
+</item>
+
+<item>
+<title>HOWTO: The Anti-Printer</title>
+<link>http://hardware.slashdot.org/article.pl?sid=05/08/29/1016204&amp;from=rss</link>
+</item>
+
+<item>
+<title>OSDL Skeptical Of Joint Study with Microsoft</title>
+<link>http://linux.slashdot.org/article.pl?sid=05/08/29/0625224&amp;from=rss</link>
+</item>
+
+<item>
+<title>New Mad Cow Test on the Horizon?</title>
+<link>http://science.slashdot.org/article.pl?sid=05/08/29/0619259&amp;from=rss</link>
+</item>
+
+<item>
+<title>Coffee A Health Drink?</title>
+<link>http://science.slashdot.org/article.pl?sid=05/08/29/0342207&amp;from=rss</link>
+</item>
+
+<textinput>
+<title>Search Slashdot</title>
+<description>Search Slashdot stories</description>
+<name>query</name>
+<link>http://slashdot.org/search.pl</link>
+</textinput>
+
+</rdf:RDF>