feedzirra 0.2.1 → 0.2.2

data/lib/feedzirra/parser/rss_entry.rb

@@ -8,7 +8,7 @@ module Feedzirra
 
       element :title
       element :link, :as => :url
-      
+
       element :"dc:creator", :as => :author
       element :author, :as => :author
       element :"content:encoded", :as => :content
@@ -16,19 +16,20 @@ module Feedzirra
 
       element :"media:content", :as => :image, :value => :url
       element :enclosure, :as => :image, :value => :url
-      
+
       element :pubDate, :as => :published
       element :pubdate, :as => :published
       element :"dc:date", :as => :published
       element :"dc:Date", :as => :published
       element :"dcterms:created", :as => :published
-      
-      
+
+
       element :"dcterms:modified", :as => :updated
       element :issued, :as => :published
       elements :category, :as => :categories
-      
-      element :guid, :as => :entry_id     
+
+      element :guid, :as => :entry_id
+      element :"dc:identifier", :as => :entry_id
     end
 
   end

data/lib/feedzirra/parser/rss_feed_burner.rb

@@ -19,4 +19,4 @@ module Feedzirra
 
   end
 
-end
+end

data/lib/feedzirra/parser/rss_feed_burner_entry.rb

@@ -35,7 +35,7 @@ module Feedzirra
         def url
           @url || @link
         end
-      
+
     end
 
   end

data/lib/feedzirra/parser.rb

@@ -4,7 +4,7 @@ module Feedzirra
     autoload :RSSEntry,           'feedzirra/parser/rss_entry'
     autoload :RSSFeedBurner,      'feedzirra/parser/rss_feed_burner'
     autoload :RSSFeedBurnerEntry, 'feedzirra/parser/rss_feed_burner_entry'
-    
+
     autoload :ITunesRSS,      'feedzirra/parser/itunes_rss'
     autoload :ITunesRSSItem,  'feedzirra/parser/itunes_rss_item'
     autoload :ITunesRSSOwner, 'feedzirra/parser/itunes_rss_owner'

data/lib/feedzirra/version.rb

@@ -1,3 +1,3 @@
 module Feedzirra
-  VERSION = '0.2.1'
+  VERSION = '0.2.2'
 end

data/lib/feedzirra.rb

@@ -12,6 +12,6 @@ module Feedzirra
   autoload :FeedUtilities,      'feedzirra/feed_utilities'
   autoload :Feed,               'feedzirra/feed'
   autoload :Parser,             'feedzirra/parser'
-  
+
   class NoParserAvailable < StandardError; end
 end

data/spec/benchmarks/feed_benchmarks.rb

@@ -44,14 +44,14 @@ benchmark do |t|
 #      puts res.slice(0, 500)
     end
   end
-  
+
   require 'rfuzz/session'
-  include RFuzz 
+  include RFuzz
   t.report("rfuzz") do
     GET_COUNT.times do
       http = HttpClient.new("www.pauldix.net", 80)
       response = http.get("/")
-      if response.http_status != "200" 
+      if response.http_status != "200"
         puts "***** #{response.http_status}"
       else
 #        puts response.http_status
@@ -59,7 +59,7 @@ benchmark do |t|
       end
     end
   end
-  
+
   require 'eventmachine'
   t.report("eventmachine") do
     counter = GET_COUNT
@@ -76,8 +76,8 @@ benchmark do |t|
       end
     end
   end
-  
-  
+
+
   require 'curl-multi'
   t.report("curl multi") do
     multi = Curl::Multi.new
@@ -95,4 +95,4 @@ benchmark do |t|
 
     multi.select([], []) while multi.size > 0
   end
-end
+end

data/spec/benchmarks/feedzirra_benchmarks.rb

@@ -10,7 +10,7 @@ iterations = 10
 urls = File.readlines(File.dirname(__FILE__) + "/../sample_feeds/successful_feed_urls.txt").slice(0, 20)
 puts "benchmarks on #{urls.size} feeds"
 puts "************************************"
-benchmark do |t|    
+benchmark do |t|
   t.report("feedzirra") do
     iterations.times do
       Feedzirra::Feed.fetch_and_parse(urls, :on_success => lambda { |url, feed| $stdout.print '.'; $stdout.flush })

data/spec/benchmarks/fetching_benchmarks.rb

@@ -10,7 +10,7 @@ iterations = 10
 urls = File.readlines(File.dirname(__FILE__) + "/../sample_feeds/successful_feed_urls.txt").slice(0, 20)
 puts "benchmarks on #{urls.size} feeds"
 puts "************************************"
-benchmark do |t|    
+benchmark do |t|
   t.report("feedzirra open uri") do
     iterations.times do
       urls.each do |url|
@@ -24,5 +24,5 @@ benchmark do |t|
     iterations.times do
       Feedzirra::Feed.fetch_and_parse(urls, :on_success => lambda { |url, feed| $stdout.print '.'; $stdout.flush })
     end
-  end  
-end
+  end
+end

data/spec/benchmarks/parsing_benchmark.rb

@@ -8,7 +8,7 @@ include Benchmark
 iterations = 50
 xml = File.read(File.dirname(__FILE__) + '/../sample_feeds/PaulDixExplainsNothing.xml')
 
-benchmark do |t|    
+benchmark do |t|
   t.report("feedzirra") do
     iterations.times do
       Feedzirra::Feed.parse(xml)

data/spec/benchmarks/updating_benchmarks.rb

@@ -10,24 +10,24 @@ puts "************************************"
 benchmark do |t|
   feeds = {}
   t.report("feedzirra fetch and parse") do
-    feeds = Feedzirra::Feed.fetch_and_parse(urls, 
+    feeds = Feedzirra::Feed.fetch_and_parse(urls,
       :on_success => lambda { |url, feed| $stdout.print '.'; $stdout.flush },
       :on_failure => lambda {|url, response_code, header, body| puts "#{response_code} ERROR on #{url}"})
   end
-  
+
   # curb caches the dns lookups for 60 seconds. to make things fair we have to wait for the cache to expire
   puts "sleeping to wait for dns cache to clear"
   65.times {$stdout.print('.'); sleep(1)}
   puts "done"
-  
+
   updated_feeds = []
   t.report("feedzirra update") do
-    updated_feeds = Feedzirra::Feed.update(feeds.values.reject {|f| f.class == Fixnum}, 
+    updated_feeds = Feedzirra::Feed.update(feeds.values.reject {|f| f.class == Fixnum},
       :on_success => lambda {|feed| $stdout.print '.'; $stdout.flush},
       :on_failure => lambda {|feed, response_code, header, body| puts "#{response_code} ERROR on #{feed.feed_url}"})
   end
-  
+
   updated_feeds.each do |feed|
     puts feed.feed_url if feed.updated?
   end
-end
+end

data/spec/feedzirra/feed_entry_utilities_spec.rb

@@ -6,7 +6,7 @@ describe Feedzirra::FeedUtilities do
       include Feedzirra::FeedEntryUtilities
     end
   end
-  
+
   describe "handling dates" do
     it "should parse an ISO 8601 formatted datetime into Time" do
       time = @klass.new.parse_datetime("2008-02-20T8:05:00-010:00")
@@ -14,26 +14,30 @@ describe Feedzirra::FeedUtilities do
       time.should == Time.parse_safely("Wed Feb 20 18:05:00 UTC 2008")
     end
   end
-  
+
   describe "sanitizing" do
     before(:each) do
       @feed = Feedzirra::Feed.parse(sample_atom_feed)
       @entry = @feed.entries.first
     end
-    
+
+    it "doesn't fail when no elements are defined on includer" do
+      expect { @klass.new.sanitize!  }.to_not raise_error
+    end
+
     it "should provide a sanitized title" do
       new_title = "<script>this is not safe</script>" + @entry.title
       @entry.title = new_title
       @entry.title.sanitize.should == Loofah.scrub_fragment(new_title, :prune).to_s
     end
-    
+
     it "should sanitize content in place" do
       new_content = "<script>" + @entry.content
       @entry.content = new_content.dup
       @entry.content.sanitize!.should == Loofah.scrub_fragment(new_content, :prune).to_s
       @entry.content.should == Loofah.scrub_fragment(new_content, :prune).to_s
     end
-    
+
     it "should sanitize things in place" do
       @entry.title   += "<script>"
       @entry.author  += "<script>"
@@ -42,11 +46,11 @@ describe Feedzirra::FeedUtilities do
       cleaned_title   = Loofah.scrub_fragment(@entry.title, :prune).to_s
       cleaned_author  = Loofah.scrub_fragment(@entry.author, :prune).to_s
       cleaned_content = Loofah.scrub_fragment(@entry.content, :prune).to_s
-      
+
       @entry.sanitize!
       @entry.title.should   == cleaned_title
       @entry.author.should  == cleaned_author
       @entry.content.should == cleaned_content
     end
   end
-end
+end