feedzirra 0.2.0.rc2 → 0.2.1

data/.travis.yml

@@ -3,7 +3,6 @@ rvm:
   - 1.8.7
   - 1.9.2
   - 1.9.3
+  - 2.0.0
   - rbx-18mode
   - rbx-19mode
-notifications:
-  irc: "irc.freenode.org#feedzirra"

data/Gemfile

@@ -1,10 +1,9 @@
-source :rubygems
+source 'https://rubygems.org/'
 
 gemspec
 
 group :development, :test do
   gem 'rake'
   gem 'guard-rspec'
-  gem 'growl', :require => false
   gem 'simplecov', :require => false, :platforms => :mri_19
 end

data/Guardfile

@@ -1,4 +1,4 @@
-guard 'rspec', :rvm => ['1.9.3@feedzirra', 'rbx-head@feedzirra'] do
+guard 'rspec' do
   watch(%r{^spec/.+_spec\.rb$})
   watch(%r{^lib/(.+)\.rb$})     { |m| "spec/#{m[1]}_spec.rb" }
   watch('spec/spec_helper.rb')  { "spec" }

data/HISTORY.md

@@ -1,3 +1,9 @@
+# HEAD
+* Use `Time.parse_safely` in `Feed.last_modified_from_header` [[#129](https://github.com/pauldix/feedzirra/pull/129)].
+* Added image to the RSS Entry Parser [[#103](https://github.com/pauldix/feedzirra/pull/103)].
+* Compatibility fixes for Ruby 2.0 [[#136](https://github.com/pauldix/feedzirra/pull/136)].
+* Remove gorillib dependency [[#113](https://github.com/pauldix/feedzirra/pull/113)].
+
 # 0.2.0.rc2
 * Bump sax-machine to `v0.2.0.rc1`, fixes encoding issues [[#76](https://github.com/pauldix/feedzirra/issues/76)].
 

data/feedzirra.gemspec

@@ -6,12 +6,11 @@ Gem::Specification.new do |s|
   s.version = Feedzirra::VERSION
 
   s.authors  = ['Paul Dix', 'Julien Kirch', "Ezekiel Templin"]
-  s.date     = Date.today
   s.email    = 'feedzirra@googlegroups.com'
   s.homepage = 'http://github.com/pauldix/feedzirra'
 
   s.summary     = 'A feed fetching and parsing library'
-  s.description = 'A feed fetching and parsing library that treats the internet like Godzilla treats Japan: it dominates and eats all.'
+  s.description = 'A library designed to retrieve and parse feeds as quickly as possible'
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
@@ -19,11 +18,10 @@ Gem::Specification.new do |s|
   
   s.platform = Gem::Platform::RUBY
 
-  s.add_dependency 'nokogiri',          '~> 1.5.3'
-  s.add_dependency 'sax-machine',       '~> 0.2.0.rc1'
-  s.add_dependency 'curb',              '~> 0.8.0'
+  s.add_dependency 'nokogiri',          '~> 1.6.0'
+  s.add_dependency 'sax-machine',       '~> 0.2.1'
+  s.add_dependency 'curb',              '~> 0.8.1'
   s.add_dependency 'loofah',            '~> 1.2.1'
-  s.add_dependency 'gorillib',          '~> 0.1.9'
 
-  s.add_development_dependency 'rspec', '~> 2.10.0'
+  s.add_development_dependency 'rspec', '~> 2.13.0'
 end

data/lib/feedzirra.rb

@@ -3,7 +3,6 @@ require 'curb'
 require 'sax-machine'
 require 'loofah'
 require 'uri'
-require 'gorillib/datetime/parse'
 
 require 'feedzirra/core_ext'
 require 'feedzirra/version'

data/lib/feedzirra/core_ext.rb

@@ -1,3 +1,3 @@
-Dir["#{File.dirname(__FILE__)}/core_ext/*.rb"].sort.each do |path|
-  require "feedzirra/core_ext/#{File.basename(path, '.rb')}"
-end
+require "feedzirra/core_ext/time"
+require "feedzirra/core_ext/date"
+require "feedzirra/core_ext/string"

data/lib/feedzirra/core_ext/time.rb

@@ -0,0 +1,29 @@
+require "time"
+require "date"
+
+class Time
+  # Parse a time string and convert it to UTC without raising errors.
+  # Parses a flattened 14-digit time (YYYYmmddHHMMMSS) as UTC.
+  #
+  # === Parameters
+  # [dt<String or Time>] Time definition to be parsed.
+  #
+  # === Returns
+  # A Time instance in UTC or nil if there were errors while parsing.
+  def self.parse_safely(dt)
+    if dt
+      case
+      when dt.is_a?(Time)
+        dt.utc
+      when dt.respond_to?(:empty?) && dt.empty?
+        nil
+      when dt.to_s =~ /\A\d{14}\z/
+        parse("#{dt.to_s}Z", true)
+      else
+        parse(dt.to_s, true).utc
+      end
+    end
+  rescue StandardError
+    nil
+  end unless method_defined?(:parse_safely)
+end

data/lib/feedzirra/feed.rb

@@ -44,7 +44,7 @@ module Feedzirra
     # === Returns
     # A array of class names.
     def self.feed_classes
-      @feed_classes ||= [Feedzirra::Parser::RSSFeedBurner, Feedzirra::Parser::RSS, Feedzirra::Parser::GoogleDocsAtom, Feedzirra::Parser::AtomFeedBurner, Feedzirra::Parser::Atom, Feedzirra::Parser::ITunesRSS]
+      @feed_classes ||= [Feedzirra::Parser::RSSFeedBurner, Feedzirra::Parser::GoogleDocsAtom, Feedzirra::Parser::AtomFeedBurner, Feedzirra::Parser::Atom, Feedzirra::Parser::ITunesRSS, Feedzirra::Parser::RSS]
     end
     
     # Makes all registered feeds types look for the passed in element to parse.
@@ -247,7 +247,7 @@ module Feedzirra
       end
     
       multi.perform
-      responses.is_a?(Array)? responses.values : responses.values.first
+      feeds.is_a?(Array) ? responses : responses.values.first
     end
     
     # An abstraction for adding a feed by URL to the passed Curb::multi stack.
@@ -292,7 +292,19 @@ module Feedzirra
             options[:on_failure].call(url, c.response_code, c.header_str, c.body_str) if options.has_key?(:on_failure)
           end
         end
-        
+
+        #
+        # trigger on_failure for 404s
+        #
+        curl.on_complete do |c|
+          add_url_to_multi(multi, url_queue.shift, url_queue, responses, options) unless url_queue.empty?
+          responses[url] = c.response_code
+
+          if c.response_code == 404 && options.has_key?(:on_failure)
+            options[:on_failure].call(url, c.response_code, c.header_str, c.body_str)
+          end
+        end
+
         curl.on_failure do |c, err|
           add_url_to_multi(multi, url_queue.shift, url_queue, responses, options) unless url_queue.empty?
           responses[url] = c.response_code
@@ -376,7 +388,7 @@ module Feedzirra
     # A Time object of the last modified date or nil if it cannot be found in the headers.
     def self.last_modified_from_header(header)
       header =~ /.*Last-Modified:\s(.*)\r/
-      Time.parse($1) if $1
+      Time.parse_safely($1) if $1
     end
   end
 end

data/lib/feedzirra/feed_entry_utilities.rb

@@ -41,6 +41,7 @@ module Feedzirra
       self.author.sanitize! if self.author
       self.summary.sanitize! if self.summary
       self.content.sanitize! if self.content
+      self.image.sanitize! if self.image
     end
 
     alias_method :last_modified, :published

data/lib/feedzirra/feed_utilities.rb

@@ -29,9 +29,9 @@ module Feedzirra
       self.entries.unshift(*self.new_entries)
 
       @updated = false
+
       UPDATABLE_ATTRIBUTES.each do |name|
-        updated = update_attribute(feed, name)
-        @updated ||= updated
+        @updated ||= update_attribute(feed, name)
       end
     end
 
@@ -40,6 +40,9 @@ module Feedzirra
 
       if old_value != new_value
         send("#{name}=", new_value)
+        true
+      else
+        false
       end
     end
 
@@ -54,19 +57,19 @@ module Feedzirra
       # it's to get around the fact that not all feeds have a published date.
       # however, they're always ordered with the newest one first.
       # So we go through the entries just parsed and insert each one as a new entry
-      # until we get to one that has the same url as the the newest for the feed
+      # until we get to one that has the same id as the the newest for the feed
       return feed.entries if self.entries.length == 0
       latest_entry = self.entries.first
       found_new_entries = []
       feed.entries.each do |entry|
-        break if entry.url == latest_entry.url
+        break if entry.id == latest_entry.id
         found_new_entries << entry
       end
       found_new_entries
     end
 
     def existing_entry?(test_entry)
-      entries.any? { |entry| entry.url == test_entry.url }
+      entries.any? { |entry| entry.id == test_entry.id }
     end
   end
-end
+end

data/lib/feedzirra/parser/atom_entry.rb

@@ -11,6 +11,10 @@ module Feedzirra
       element :name, :as => :author
       element :content
       element :summary
+
+      element :"media:content", :as => :image, :value => :url
+      element :enclosure, :as => :image, :value => :href
+
       element :published
       element :id, :as => :entry_id
       element :created, :as => :published

data/lib/feedzirra/parser/atom_feed_burner_entry.rb

@@ -12,6 +12,10 @@ module Feedzirra
       element :"feedburner:origLink", :as => :url
       element :summary
       element :content
+
+      element :"media:content", :as => :image, :value => :url
+      element :enclosure, :as => :image, :value => :href
+
       element :published
       element :id, :as => :entry_id
       element :issued, :as => :published

data/lib/feedzirra/parser/rss_entry.rb

@@ -13,6 +13,9 @@ module Feedzirra
       element :author, :as => :author
       element :"content:encoded", :as => :content
       element :description, :as => :summary
+
+      element :"media:content", :as => :image, :value => :url
+      element :enclosure, :as => :image, :value => :url
       
       element :pubDate, :as => :published
       element :pubdate, :as => :published
@@ -25,8 +28,7 @@ module Feedzirra
       element :issued, :as => :published
       elements :category, :as => :categories
       
-      element :guid, :as => :entry_id
-      
+      element :guid, :as => :entry_id     
     end
 
   end

data/lib/feedzirra/parser/rss_feed_burner_entry.rb

@@ -16,6 +16,9 @@ module Feedzirra
         element :"content:encoded", :as => :content
         element :description, :as => :summary
 
+        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

data/lib/feedzirra/version.rb

@@ -1,3 +1,3 @@
 module Feedzirra
-  VERSION = '0.2.0.rc2'
+  VERSION = '0.2.1'
 end

data/spec/feedzirra/feed_spec.rb

@@ -68,14 +68,10 @@ describe Feedzirra::Feed do
         feed.entries.size.should == 5
       end      
 
-      it "should parse an itunes feed as a standard RSS feed" do
+      it "should parse an itunes feed" do
         feed = Feedzirra::Feed.parse(sample_itunes_feed)
         feed.title.should == "All About Everything"
         feed.entries.first.published.should == Time.parse_safely("Wed, 15 Jun 2005 19:00:00 GMT")
-        
-        # Since the commit 621957879, iTunes feeds will be parsed as standard RSS, so this
-        # entry should now not have a method for itunes_author.
-        feed.entries.first.should_not respond_to(:itunes_author)
         feed.entries.size.should == 3
       end
     end
@@ -122,7 +118,7 @@ describe Feedzirra::Feed do
     end
 
     it "should return a Feedzirra::Parser::RSS object for an itunes feed" do
-      Feedzirra::Feed.determine_feed_parser_for_xml(sample_itunes_feed).should == Feedzirra::Parser::RSS
+      Feedzirra::Feed.determine_feed_parser_for_xml(sample_itunes_feed).should == Feedzirra::Parser::ITunesRSS
     end
 
   end
@@ -373,17 +369,17 @@ describe Feedzirra::Feed do
 
       describe 'on failure' do
         before(:each) do
-          @headers = "HTTP/1.0 404 Not Found\r\nDate: Thu, 29 Jan 2009 03:55:24 GMT\r\nServer: Apache\r\nX-FB-Host: chi-write6\r\nLast-Modified: Wed, 28 Jan 2009 04:10:32 GMT\r\n"
-          @body = 'Page could not be found.'
+          @headers = "HTTP/1.0 500 Something Bad\r\nDate: Thu, 29 Jan 2009 03:55:24 GMT\r\nServer: Apache\r\nX-FB-Host: chi-write6\r\nLast-Modified: Wed, 28 Jan 2009 04:10:32 GMT\r\n"
+          @body = 'Sorry, something broke'
 
-          @easy_curl.stub!(:response_code).and_return(404)
+          @easy_curl.stub!(:response_code).and_return(500)
           @easy_curl.stub!(:header_str).and_return(@headers)
           @easy_curl.stub!(:body_str).and_return(@body)
         end
 
         it 'should call proc if :on_failure option is passed' do
           failure = lambda { |url, feed| }
-          failure.should_receive(:call).with(@paul_feed[:url], 404, @headers, @body)
+          failure.should_receive(:call).with(@paul_feed[:url], 500, @headers, @body)
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, { :on_failure => failure })
           @easy_curl.on_failure.call(@easy_curl)
         end
@@ -393,6 +389,33 @@ describe Feedzirra::Feed do
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], responses, {})
           @easy_curl.on_failure.call(@easy_curl)
 
+          responses.length.should == 1
+          responses[@paul_feed[:url]].should == 500
+        end
+      end
+
+      describe 'on complete for 404s' do
+        before(:each) do
+          @headers = "HTTP/1.0 404 Not Found\r\nDate: Thu, 29 Jan 2009 03:55:24 GMT\r\nServer: Apache\r\nX-FB-Host: chi-write6\r\nLast-Modified: Wed, 28 Jan 2009 04:10:32 GMT\r\n"
+          @body = 'Page could not be found.'
+
+          @easy_curl.stub!(:response_code).and_return(404)
+          @easy_curl.stub!(:header_str).and_return(@headers)
+          @easy_curl.stub!(:body_str).and_return(@body)
+        end
+
+        it 'should call proc if :on_failure option is passed' do
+          complete = lambda { |url| }
+          complete.should_receive(:call).with(@paul_feed[:url], 404, @headers, @body)
+          Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, { :on_failure => complete })
+          @easy_curl.on_complete.call(@easy_curl)
+        end
+        
+        it 'should return the http code in the responses' do
+          responses = {}
+          Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], responses, {})
+          @easy_curl.on_complete.call(@easy_curl)
+
           responses.length.should == 1
           responses[@paul_feed[:url]].should == 404
         end

data/spec/feedzirra/feed_utilities_spec.rb

@@ -146,5 +146,48 @@ describe Feedzirra::FeedUtilities do
         @feed.entries.should include(@old_entry)
       end
     end
+
+    describe "changing the url of an existing entry" do
+      before(:each) do
+        # I'm using the Atom class when I know I should be using a different one. However, this update_from_feed
+        # method would only be called against a feed item.
+        @feed = Feedzirra::Parser::Atom.new
+        @feed.title    = "A title"
+        @feed.url      = "http://pauldix.net"
+        @feed.feed_url = "http://feeds.feedburner.com/PaulDixExplainsNothing"
+        @feed.updated  = false
+        @updated_feed = @feed.dup
+
+        @old_entry = Feedzirra::Parser::AtomEntry.new
+        @old_entry.url = "http://pauldix.net/old.html"
+        @old_entry.published = (Time.now - 10).to_s
+
+        @entry = Feedzirra::Parser::AtomEntry.new
+        @entry.published = (Time.now + 10).to_s
+        @entry.entry_id = "entry_id"
+        @entry.url = "http://pauldix.net/entry.html"
+
+        # only difference is a changed url
+        @entry_changed_url = @entry.dup
+        @entry_changed_url.url = "http://pauldix.net/updated.html"
+
+        # entry with changed url must be first
+        @feed.entries << @entry
+        @feed.entries << @old_entry
+        @updated_feed.entries << @entry_changed_url
+        @updated_feed.entries << @old_entry
+      end
+
+      it "should not put the complete feed into new_entries" do
+        @feed.update_from_feed(@updated_feed)
+
+        @feed.new_entries.should_not include(@entry_changed_url)
+        @feed.new_entries.should_not include(@old_entry)
+
+        # don't return complete feed
+        @feed.new_entries.size.should == 0
+        @feed.new_entries.size.should_not == 2
+      end
+    end
   end
-end
+end

metadata

@@ -1,8 +1,8 @@
 --- !ruby/object:Gem::Specification
 name: feedzirra
 version: !ruby/object:Gem::Version
-  version: 0.2.0.rc2
-  prerelease: 6
+  version: 0.2.1
+  prerelease: 
 platform: ruby
 authors:
 - Paul Dix
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-04 00:00:00.000000000 Z
+date: 2013-10-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -20,7 +20,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 1.5.3
+        version: 1.6.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -28,7 +28,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 1.5.3
+        version: 1.6.0
 - !ruby/object:Gem::Dependency
   name: sax-machine
   requirement: !ruby/object:Gem::Requirement
@@ -36,7 +36,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.2.0.rc1
+        version: 0.2.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -44,7 +44,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.2.0.rc1
+        version: 0.2.1
 - !ruby/object:Gem::Dependency
   name: curb
   requirement: !ruby/object:Gem::Requirement
@@ -52,7 +52,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.8.0
+        version: 0.8.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -60,7 +60,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.8.0
+        version: 0.8.1
 - !ruby/object:Gem::Dependency
   name: loofah
   requirement: !ruby/object:Gem::Requirement
@@ -77,22 +77,6 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: 1.2.1
-- !ruby/object:Gem::Dependency
-  name: gorillib
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 0.1.9
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 0.1.9
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -100,7 +84,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 2.10.0
+        version: 2.13.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -108,9 +92,8 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 2.10.0
-description: ! 'A feed fetching and parsing library that treats the internet like
-  Godzilla treats Japan: it dominates and eats all.'
+        version: 2.13.0
+description: A library designed to retrieve and parse feeds as quickly as possible
 email: feedzirra@googlegroups.com
 executables: []
 extensions: []
@@ -129,6 +112,7 @@ files:
 - lib/feedzirra/core_ext.rb
 - lib/feedzirra/core_ext/date.rb
 - lib/feedzirra/core_ext/string.rb
+- lib/feedzirra/core_ext/time.rb
 - lib/feedzirra/feed.rb
 - lib/feedzirra/feed_entry_utilities.rb
 - lib/feedzirra/feed_utilities.rb
@@ -202,18 +186,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: -1608049973569295975
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
-  - - ! '>'
+  - - ! '>='
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 1.8.23
 signing_key: 
 specification_version: 3
 summary: A feed fetching and parsing library