thoughtafter-simple-rss 1.2.3.1

data/Rakefile

@@ -0,0 +1,212 @@
+require 'rubygems'
+require 'rake'
+require 'rake/testtask'
+require 'rake/rdoctask'
+require 'rake/gempackagetask'
+require 'rake/contrib/rubyforgepublisher'
+require File.dirname(__FILE__) + '/lib/simple-rss'
+
+PKG_VERSION = SimpleRSS::VERSION
+PKG_NAME = "simple-rss"
+PKG_FILE_NAME = "#{PKG_NAME}-#{PKG_VERSION}"
+RUBY_FORGE_PROJECT = "simple-rss"
+RUBY_FORGE_USER = ENV['RUBY_FORGE_USER'] || "cardmagic"
+RELEASE_NAME = "#{PKG_NAME}-#{PKG_VERSION}"
+
+PKG_FILES = FileList[
+    "lib/*", "bin/*", "test/**/*", "[A-Z]*", "Rakefile", "html/**/*"
+]
+
+desc "Default Task"
+task :default => [ :test ]
+
+# Run the unit tests
+desc "Run all unit tests"
+Rake::TestTask.new("test") { |t|
+  t.libs << "lib"
+  t.pattern = 'test/*/*_test.rb'
+  t.verbose = true
+}
+
+# Make a console, useful when working on tests
+desc "Generate a test console"
+task :console do
+   verbose( false ) { sh "irb -I lib/ -r 'simple-rss'" }
+end
+
+# Genereate the RDoc documentation
+desc "Create documentation"
+Rake::RDocTask.new("doc") { |rdoc|
+  rdoc.title = "Simple RSS - A Flexible RSS and Atom reader for Ruby"
+  rdoc.rdoc_dir = 'html'
+  rdoc.rdoc_files.include('README')
+  rdoc.rdoc_files.include('lib/*.rb')
+}
+
+# Genereate the package
+spec = Gem::Specification.new do |s|
+
+  #### Basic information.
+
+  s.name = 'simple-rss'
+  s.version = PKG_VERSION
+  s.summary = <<-EOF
+   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.
+  EOF
+  s.description = <<-EOF
+   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.
+  EOF
+
+  #### Which files are to be included in this gem?  Everything!  (Except CVS directories.)
+
+  s.files = PKG_FILES
+
+  #### Load-time details: library and application (you will need one or both).
+
+  s.require_path = 'lib'
+
+  #### Documentation and testing.
+
+  s.has_rdoc = true
+
+  #### Author and project details.
+
+  s.author = "Lucas Carlson"
+  s.email = "lucas@rufy.com"
+  s.homepage = "http://simple-rss.rubyforge.org/"
+end
+
+Rake::GemPackageTask.new(spec) do |pkg|
+  pkg.need_zip = true
+  pkg.need_tar = true
+end
+
+desc "Report code statistics (KLOCs, etc) from the application"
+task :stats do
+  require 'code_statistics'
+  CodeStatistics.new(
+    ["Library", "lib"],
+    ["Units", "test"]
+  ).to_s
+end
+
+desc "Publish new documentation"
+task :publish do
+    Rake::RubyForgePublisher.new('simple-rss', 'cardmagic').upload
+end
+
+
+desc "Publish the release files to RubyForge."
+task :upload => [:package] do
+  files = ["gem", "tar.gz", "zip"].map { |ext| "pkg/#{PKG_FILE_NAME}.#{ext}" }
+
+  if RUBY_FORGE_PROJECT then
+      require 'net/http'
+      require 'open-uri'
+
+      project_uri = "http://rubyforge.org/projects/#{RUBY_FORGE_PROJECT}/"
+      project_data = open(project_uri) { |data| data.read }
+      group_id = project_data[/[?&]group_id=(\d+)/, 1]
+      raise "Couldn't get group id" unless group_id
+
+      # This echos password to shell which is a bit sucky
+      if ENV["RUBY_FORGE_PASSWORD"]
+          password = ENV["RUBY_FORGE_PASSWORD"]
+      else
+          print "#{RUBY_FORGE_USER}@rubyforge.org's password: "
+          password = STDIN.gets.chomp
+      end
+
+      login_response = Net::HTTP.start("rubyforge.org", 80) do |http|
+          data = [
+              "login=1",
+              "form_loginname=#{RUBY_FORGE_USER}",
+              "form_pw=#{password}"
+          ].join("&")
+          http.post("/account/login.php", data)
+      end
+
+      cookie = login_response["set-cookie"]
+      raise "Login failed" unless cookie
+      headers = { "Cookie" => cookie }
+
+      release_uri = "http://rubyforge.org/frs/admin/?group_id=#{group_id}"
+      release_data = open(release_uri, headers) { |data| data.read }
+      package_id = release_data[/[?&]package_id=(\d+)/, 1]
+      raise "Couldn't get package id" unless package_id
+
+      first_file = true
+      release_id = ""
+
+      files.each do |filename|
+          basename  = File.basename(filename)
+          file_ext  = File.extname(filename)
+          file_data = File.open(filename, "rb") { |file| file.read }
+
+          puts "Releasing #{basename}..."
+
+          release_response = Net::HTTP.start("rubyforge.org", 80) do |http|
+              release_date = Time.now.strftime("%Y-%m-%d %H:%M")
+              type_map = {
+                  ".zip"    => "3000",
+                  ".tgz"    => "3110",
+                  ".gz"     => "3110",
+                  ".gem"    => "1400"
+              }; type_map.default = "9999"
+              type = type_map[file_ext]
+              boundary = "rubyqMY6QN9bp6e4kS21H4y0zxcvoor"
+
+              query_hash = if first_file then
+                {
+                  "group_id" => group_id,
+                  "package_id" => package_id,
+                  "release_name" => RELEASE_NAME,
+                  "release_date" => release_date,
+                  "type_id" => type,
+                  "processor_id" => "8000", # Any
+                  "release_notes" => "",
+                  "release_changes" => "",
+                  "preformatted" => "1",
+                  "submit" => "1"
+                }
+              else
+                {
+                  "group_id" => group_id,
+                  "release_id" => release_id,
+                  "package_id" => package_id,
+                  "step2" => "1",
+                  "type_id" => type,
+                  "processor_id" => "8000", # Any
+                  "submit" => "Add This File"
+                }
+              end
+
+              query = "?" + query_hash.map do |(name, value)|
+                  [name, URI.encode(value)].join("=")
+              end.join("&")
+
+              data = [
+                  "--" + boundary,
+                  "Content-Disposition: form-data; name=\"userfile\"; filename=\"#{basename}\"",
+                  "Content-Type: application/octet-stream",
+                  "Content-Transfer-Encoding: binary",
+                  "", file_data, ""
+                  ].join("\x0D\x0A")
+
+              release_headers = headers.merge(
+                  "Content-Type" => "multipart/form-data; boundary=#{boundary}"
+              )
+
+              target = first_file ? "/frs/admin/qrs.php" : "/frs/admin/editrelease.php"
+              http.post(target + query, data, release_headers)
+          end
+
+          if first_file then
+              release_id = release_response.body[/release_id=(\d+)/, 1]
+              raise("Couldn't get release id") unless release_id
+          end
+
+          first_file = false
+      end
+  end
+end

data/install.rb

@@ -0,0 +1,40 @@
+require 'rbconfig'
+require 'find'
+require 'fileutils'
+
+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 +1,162 @@
+require 'cgi'
+require 'time'
+
+class SimpleRSS
+  VERSION = "1.2.3"
+  
+	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, :'link+alternate', :'link+self', :'link+edit', :'link+replies',
+		: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',
+		:'feedburner:origLink',
+		:'media:content#url', :'media:content#type', :'media:content#height', :'media:content#width',
+		:'media:title', :'media:thumbnail#url', :'media:thumbnail#height', :'media:thumbnail#width',
+		:'media:credit', :'media:credit#role',
+		:'media:category', :'media:category#scheme'
+	]
+
+	def initialize(source, options={})
+		@source = source.respond_to?(:read) ? source.read : source.to_s
+		@items = Array.new
+    @options = Hash.new.update(options)
+    
+		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, options={})
+			new source, options
+		end
+	end
+
+	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)
+        instance_variable_set("@#{ tag_cleaned }", clean_content(tag, $2, $3))
+        self.class.send(: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 tag.to_s.include?("+")
+			    tag_data = tag.to_s.split("+")
+			    tag = tag_data[0]
+			    rel = tag_data[1]
+			    
+  				if match[3] =~ %r{<(rss:|atom:)?#{tag}(.*?)rel=['"]#{rel}['"](.*?)>(.*?)</(rss:|atom:)?#{tag}>}mi
+            nil
+  				elsif match[3] =~ %r{<(rss:|atom:)?#{tag}(.*?)rel=['"]#{rel}['"](.*?)/\s*>}mi
+  				  nil
+  				end
+  				item[clean_tag("#{tag}+#{rel}")] = clean_content(tag, $3, $4) if $3 || $4
+  			elsif tag.to_s.include?("#")
+			    tag_data = tag.to_s.split("#")
+			    tag = tag_data[0]
+			    attrib = tag_data[1]
+  				if match[3] =~ %r{<(rss:|atom:)?#{tag}(.*?)#{attrib}=['"](.*?)['"](.*?)>(.*?)</(rss:|atom:)?#{tag}>}mi
+            nil
+  				elsif match[3] =~ %r{<(rss:|atom:)?#{tag}(.*?)#{attrib}=['"](.*?)['"](.*?)/\s*>}mi
+  				  nil
+  				end
+  				item[clean_tag("#{tag}_#{attrib}")] = clean_content(tag, attrib, $3) if $3
+		    else
+  				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
+			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 ? $1.strip : unescape(content)
+		end
+	end
+
+	def clean_tag(tag)
+		tag.to_s.gsub(':','_').intern
+	end
+	
+  def unescape(content)
+  	if content =~ /([^-_.!~*'()a-zA-Z\d;\/?:@&=+$,\[\]]%)/u then
+  		CGI.unescape(content).gsub(/(<!\[CDATA\[|\]\]>)/u,'').strip
+  	else
+  		content.gsub(/(<!\[CDATA\[|\]\]>)/u,'').strip
+  	end
+  end
+end
+
+class SimpleRSSError < StandardError
+end

data/simple-rss.gemspec

@@ -0,0 +1,13 @@
+Gem::Specification.new do |s|
+  s.name = "thoughtafter-simple-rss"
+  s.version = "1.2.3.1"
+  s.date = "2011-01-07"
+  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.markdown", "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"]
+  s.rubyforge_project = 'simple-rss'
+end

data/test/base/base_test.rb

@@ -0,0 +1,72 @@
+require File.dirname(__FILE__) + '/../test_helper'
+class BaseTest < Test::Unit::TestCase
+	def setup
+		@rss09 = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/rss09.rdf')
+		@rss20 = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/rss20.xml')
+		@media_rss = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/media_rss.xml')
+		@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_media_rss
+		assert_equal 20, @media_rss.items.size
+		assert_equal "Uploads from herval", @media_rss.title
+		assert_equal "http://www.flickr.com/photos/herval/", @media_rss.channel.link
+		assert_equal "http://www.flickr.com/photos/herval/4671960608/", @media_rss.items.first.link
+		assert_equal "http://www.flickr.com/photos/herval/4671960608/", @media_rss.items.first[:link]
+		assert_equal "http://farm5.static.flickr.com/4040/4671960608_10cb945d5c_o.jpg", @media_rss.items.first.media_content_url
+		assert_equal "image/jpeg", @media_rss.items.first.media_content_type
+		assert_equal "3168", @media_rss.items.first.media_content_height
+		assert_equal "4752", @media_rss.items.first.media_content_width
+		assert_equal "Woof?", @media_rss.items.first.media_title
+		assert_equal "http://farm5.static.flickr.com/4040/4671960608_954d2297bc_s.jpg", @media_rss.items.first.media_thumbnail_url
+		assert_equal "75", @media_rss.items.first.media_thumbnail_height
+		assert_equal "75", @media_rss.items.first.media_thumbnail_width
+		assert_equal "herval", @media_rss.items.first.media_credit
+		assert_equal "photographer", @media_rss.items.first.media_credit_role
+		assert_equal "pets frodo", @media_rss.items.first.media_category
+		assert_equal "urn:flickr:tags", @media_rss.items.first.media_category_scheme
+	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