pauldix-feedzirra 0.0.6 → 0.0.7

data/lib/feedzirra/atom_entry.rb

@@ -19,7 +19,11 @@ module Feedzirra
     element :content
     element :summary
     element :published
+    element :id
     element :created, :as => :published
+    element :issued, :as => :published
+    element :updated
+    element :modified, :as => :updated
     elements :category, :as => :categories, :value => :term
   end
 end

data/lib/feedzirra/atom_feed_burner_entry.rb

@@ -20,6 +20,11 @@ module Feedzirra
     element :summary
     element :content
     element :published
+    element :id
+    element :issued, :as => :published
+    element :created, :as => :published
+    element :updated
+    element :modified, :as => :updated
     elements :category, :as => :categories, :value => :term
   end
 end

data/lib/feedzirra/feed.rb

@@ -153,15 +153,20 @@ module Feedzirra
     # [curl_request<Curl::Easy>] The Curl::Easy response object from the request.
     # === Returns
     # A decoded string of XML.
-    def self.decode_content(curl_request)
-      if curl_request.header_str.match(/Content-Encoding: gzip/)
-        gz =  Zlib::GzipReader.new(StringIO.new(curl_request.body_str))
-        xml = gz.read
-        gz.close
-      elsif curl_request.header_str.match(/Content-Encoding: deflate/)
-        xml = Zlib::Deflate.inflate(curl_request.body_str)
+    def self.decode_content(c)
+      if c.header_str.match(/Content-Encoding: gzip/)
+        begin
+          gz =  Zlib::GzipReader.new(StringIO.new(c.body_str))
+          xml = gz.read
+          gz.close
+        rescue Zlib::GzipFile::Error 
+          # Maybe this is not gzipped?
+          xml = c.body_str
+        end
+      elsif c.header_str.match(/Content-Encoding: deflate/)
+        xml = Zlib::Inflate.inflate(c.body_str)
       else
-        xml = curl_request.body_str
+        xml = c.body_str
       end
 
       xml
@@ -228,7 +233,9 @@ module Feedzirra
             responses[url] = feed
             options[:on_success].call(url, feed) if options.has_key?(:on_success)
           else
-            raise NoParserAvailable.new("Error determining parser for #{url} - #{c.last_effective_url}.")
+            # puts "Error determining parser for #{url} - #{c.last_effective_url}"
+            # raise NoParserAvailable.new("no valid parser for content.") (this would unfirtunately fail the whole 'multi', so it's not really useable)
+            options[:on_failure].call(url, c.response_code, c.header_str, c.body_str) if options.has_key?(:on_failure)
           end
         end
         

data/lib/feedzirra/feed_entry_utilities.rb

@@ -1,13 +1,36 @@
 module Feedzirra
-  module FeedEntryUtilities
-    attr_reader :published
+  module FeedEntryUtilities    
+    def published
+      @published || @updated
+    end
     
     def parse_datetime(string)
-      DateTime.parse(string).feed_utils_to_gm_time
+      begin
+        DateTime.parse(string).feed_utils_to_gm_time
+      rescue
+        puts "DATE CAN'T BE PARSED: #{string}"
+        nil
+      end
+    end
+    
+    ##
+    # Returns the id of the entry or its url if not id is present, as some formats don't support it
+    def id
+      @id || @url
     end
     
+    ##
+    # Writter for published. By default, we keep the "oldest" publish time found.
     def published=(val)
-      @published = parse_datetime(val)
+      parsed = parse_datetime(val)
+      @published = parsed if !@published || parsed < @published
+    end
+    
+    ##
+    # Writter for udapted. By default, we keep the most recenet update time found.
+    def updated=(val)
+      parsed = parse_datetime(val)
+      @updated = parsed if !@updated || parsed > @updated
     end
 
     def sanitize!

data/lib/feedzirra/rss_entry.rb

@@ -22,6 +22,14 @@ module Feedzirra
 
     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 => :id
   end
 end

data/lib/feedzirra.rb

@@ -32,5 +32,5 @@ require 'feedzirra/atom'
 require 'feedzirra/atom_feed_burner'
 
 module Feedzirra
-  VERSION = "0.0.6"
+  VERSION = "0.0.7"
 end

data/spec/feedzirra/atom_entry_spec.rb

@@ -34,4 +34,9 @@ describe Feedzirra::AtomEntry do
   it "should parse the categories" do
     @entry.categories.should == ['Turkey', 'Seattle']
   end
+  
+  it "should parse the updated date" do
+    @entry.updated.to_s.should == "Fri Jan 16 18:21:00 UTC 2009"
+  end
+  
 end

data/spec/feedzirra/feed_spec.rb

@@ -523,7 +523,7 @@ describe Feedzirra::Feed do
       
       it 'should deflate the response body using inflate if the Content-Encoding: is deflate' do
         @curl_easy.stub!(:header_str).and_return('Content-Encoding: deflate')
-        Zlib::Deflate.should_receive(:inflate).with(@curl_easy.body_str)
+        Zlib::Inflate.should_receive(:inflate).with(@curl_easy.body_str)
         Feedzirra::Feed.decode_content(@curl_easy)
       end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: pauldix-feedzirra
 version: !ruby/object:Gem::Version 
-  version: 0.0.6
+  version: 0.0.7
 platform: ruby
 authors: 
 - Paul Dix

data/lib/feedzirra/rdf.rb

@@ -1,23 +0,0 @@
-module Feedzirra
-  # == Summary
-  # Parser for dealing with RDF feeds.
-  #
-  # == Attributes
-  # * title
-  # * feed_url
-  # * url
-  # * entries
-  class RDF
-    include SAXMachine
-    include FeedUtilities
-    element :title
-    element :link, :as => :url
-    elements :item, :as => :entries, :class => RDFEntry
-
-    attr_accessor :feed_url
-    
-    def self.able_to_parse?(xml) #:nodoc:
-      xml =~ /(rdf\:RDF)|(#{Regexp.escape("http://purl.org/rss/1.0")})|(rss version\=\"0\.9.?\")/ || false
-    end
-  end
-end

data/lib/feedzirra/rdf_entry.rb

@@ -1,22 +0,0 @@
-module Feedzirra
-  # == Summary
-  # Parser for dealing with RDF feed entries.
-  #
-  # == Attributes
-  # * title
-  # * url
-  # * author
-  # * content
-  # * summary
-  # * published
-  class RDFEntry
-    include SAXMachine
-    include FeedEntryUtilities
-    element :title
-    element :link, :as => :url
-    element :"dc:creator", :as => :author
-    element :"content:encoded", :as => :content
-    element :description, :as => :summary
-    element :"dc:date", :as => :published
-  end
-end

data/spec/feedzirra/rdf_entry_spec.rb

@@ -1,33 +0,0 @@
-require File.dirname(__FILE__) + '/../spec_helper'
-
-describe Feedzirra::RDFEntry do
-  before(:each) do
-    # I don't really like doing it this way because these unit test should only rely on AtomEntry,
-    # but this is actually how it should work. You would never just pass entry xml straight to the AtomEnry
-    @entry = Feedzirra::RDF.parse(sample_rdf_feed).entries.first
-  end
-  
-  it "should parse the title" do
-    @entry.title.should == "Chrome, V8 and Strongtalk"
-  end
-  
-  it "should parse the url" do
-    @entry.url.should == "http://www.avibryant.com/2008/09/chrome-v8-and-s.html"
-  end
-  
-  it "should parse the author" do
-    @entry.author.should == "Avi"
-  end
-  
-  it "should parse the content" do
-    @entry.content.should == sample_rdf_entry_content
-  end
-  
-  it "should provide a summary" do
-    @entry.summary.should == "There's lots to like about Google's new web browser, Chrome, which was released today. When I read the awesome comic strip introduction yesterday, however, the thing that stood out most for me was in very small type: the name Lars..."
-  end
-  
-  it "should parse the published date" do
-    @entry.published.to_s.should == "Tue Sep 02 19:50:07 UTC 2008"
-  end
-end

data/spec/feedzirra/rdf_spec.rb

@@ -1,37 +0,0 @@
-require File.dirname(__FILE__) + '/../spec_helper'
-
-describe Feedzirra::RDF do
-  describe "#will_parse?" do
-    it "should return true for an rdf feed" do
-      Feedzirra::RDF.should be_able_to_parse(sample_rdf_feed)
-    end
-    
-    it "should return false for an atom feed" do
-      Feedzirra::RDF.should_not be_able_to_parse(sample_atom_feed)
-    end
-  end
-  
-  describe "parsing" do
-    before(:each) do
-      @feed = Feedzirra::RDF.parse(sample_rdf_feed)
-    end
-    
-    it "should parse the title" do
-      @feed.title.should == "HREF Considered Harmful"
-    end
-    
-    it "should parse the url" do
-      @feed.url.should == "http://www.avibryant.com/"
-    end
-    
-    # rdf doesn't actually specify the feed_url. This should be set in the fetcher.
-    it "should provide an accessor for the feed_url" do
-      @feed.respond_to?(:feed_url).should == true
-      @feed.respond_to?(:feed_url=).should == true
-    end
-    
-    it "should parse entries" do
-      @feed.entries.size.should == 10
-    end    
-  end
-end