feed_ninja 0.0.3 → 0.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e232c6d96bcbdfda50a9985ab6430c2275dc1608
-  data.tar.gz: 2a0d5f1d965290ba077c0bb7eceb176d47a53f55
+  metadata.gz: 33efbad5fc0d64ded0e3319aca0f866180264cf6
+  data.tar.gz: aa93bcb5af9786308807831e3494d2148aa783e4
 SHA512:
-  metadata.gz: 0d3c349beea7ef6835ff680fbc5974f569f2e260fffbc42c55a6b61874a5a5236bc4a1bc6a14311341a2a80982048901daac31e42e0f24a87c25bfeeeb0bc9ab
-  data.tar.gz: 75e0af1da786f34fcd13c7969c7500c49b00299dcc5d76a1a9ed995bf716d4f5fa858aee035bf584d6b30dbdab1baab5369e7039f52edaa268ca25090593c731
+  metadata.gz: e4f48c89a57c342f0c7c4689ba519c73cf4f23a1bfc4d389157506a10453278328688e7cbf2b9e4964b9d1f5a6fc872e2e52bbbfc2887b0ae4e7dce2324acc01
+  data.tar.gz: 8717dfcd4f7e361a0df1641420480003849ccbafe523971d078ab250d7156aaaddb5baa5c437e3ce4bb98e07528810592e4065b057ff0b112d147464099f42d9

data/lib/feed_ninja/atomish.rb

@@ -4,10 +4,10 @@ class AtomIshWriter
     @entries = []
   end
 
-  def new_entry
+  def new_entry(index)
     item = Entry.new
     item = yield item
-    @entries << item;
+    @entries[index] = item
   end
 
   def to_s

data/lib/feed_ninja/feed_ninja.rb

@@ -2,14 +2,14 @@ require 'rss'
 require 'open-uri'
 require 'nokogiri'
 require 'time'
+require 'thread'
+require 'thwait'
 
 class FeedNinja
   attr_accessor :uri, :picture_xpath, :text_xpath, :title_regex, :limit
-  attr_accessor :extractor
 
   def initialize
-    @limit = 2
-    @extractor = Extractor.new
+    @limit = 4
     @writer = AtomIshWriter.new
     @ninja_prefix = "N! "
   end
@@ -43,32 +43,33 @@ class FeedNinja
     if title_regex
       items = items.select { |item| title_regex =~ item.title }
     end
-    items.first(@limit).each do |item|
-
-      #TODO add multithreading here; be sure to use multiple extractor instances
-      process_item item, doc.feed_type
+    threads = []
+    items.first(@limit).each_with_index do |item, index|
+      threads << Thread.new { process_item(item, doc.feed_type, index) }
     end
+    ThreadsWait.all_waits(*threads)
   end
 
-  def process_item original, feed_type
-    @writer.new_entry do |entry|
+  def process_item(original, feed_type, index)
+    @writer.new_entry(index) do |entry|
+      extractor = Extractor.new
       case feed_type
       when "atom"
         entry.title = original.title.content
         entry.link = original.link.href
         entry.updated = original.updated
         entry.id = original.id
-        @extractor.fetch original.link.href
+        extractor.fetch original.link.href
       when "rss"
         entry.title = original.title
         entry.link = original.link
         entry.updated = original.pubDate ? original.pubDate.xmlschema : DateTime.now.to_s
         entry.id = entry.link
-        @extractor.fetch original.link
+        extractor.fetch original.link
       end
 
-      entry.images = @extractor.extract_images @picture_xpath
-      entry.summary = @extractor.extract_xml @text_xpath
+      entry.images = extractor.extract_images @picture_xpath
+      entry.summary = extractor.extract_xml @text_xpath
 
       entry #it's kind of fishy to explicitly have to return the entry here...
     end

data/lib/feed_ninja.rb

@@ -6,7 +6,6 @@ def get (url, &block)
   ninja = FeedNinja.new
   ninja.instance_eval(&block)
   ninja.fetch(url)
-
-  puts "Content-type: application/atom+xml\n"
+  puts "Content-type: application/atom+xml\n\n"
   puts ninja.to_s
 end

data/spec/atomish_spec.rb

@@ -8,7 +8,7 @@ describe AtomIshWriter do
     writer.link = 'http://example.com/atom'
     writer.updated = DateTime.now.to_s
 
-    writer.new_entry do |entry|
+    writer.new_entry(0) do |entry|
       entry = Entry.new
       entry.title = "title"
       entry.link = "http://example.com/one"
@@ -18,7 +18,7 @@ describe AtomIshWriter do
       entry.updated = DateTime.now.to_s
     end
 
-    writer.new_entry do |entry|
+    writer.new_entry(1) do |entry|
       entry = Entry.new
       entry.title = "title"
       entry.link = "http://example.com/two"

data/spec/feed_ninja_spec.rb

@@ -4,25 +4,23 @@ require 'feed_ninja'
 describe FeedNinja do
   before :each do
     @ninja = FeedNinja.new
-    @extractor = double()
-    @ninja.extractor = @extractor
-    @extractor.stub(:extract_images)
-    @extractor.stub(:extract_xml)
+    #Extractor.stub(:extract_images => [])
+    #Extractor.stub(:extract_xml => "")
   end
 
   it 'should read an atom feed' do
-    @extractor.should_receive(:fetch).twice
+    Extractor.should_receive(:new).exactly(3).times
     @ninja.fetch 'spec/feeds/atom.xml'
   end
 
   it 'should read an RSS feed' do
-    @extractor.should_receive(:fetch).twice
+    Extractor.should_receive(:new).exactly(3).times
     @ninja.fetch 'spec/feeds/rss.xml'
   end
 
   it 'should not read more than the given limit' do
     @ninja.limit = 1
-    @extractor.should_receive(:fetch).once
+    Extractor.should_receive(:new).once
     @ninja.fetch 'spec/feeds/rss.xml'
   end
 end

data/spec/feeds/atom.xml

@@ -25,4 +25,11 @@
     <summary>summary_two</summary>
   </entry>
 
+  <entry>
+    <title>three</title>
+    <link href="http://example.com/three"/>
+    <id>3</id>
+    <updated>2007-07-13T18:30:02Z</updated>
+    <summary>summary_three</summary>
+  </entry>
 </feed>

data/spec/feeds/rss.xml

@@ -15,5 +15,10 @@
     <link>http://example.com/two</link>
     <description>description_two</description>
   </item>
+  <item>
+    <title>three</title>
+    <link>http://example.com/three</link>
+    <description>description_three</description>
+  </item>
 </channel>
 </rss>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: feed_ninja
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors:
 - Daniel Latzer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-02-06 00:00:00.000000000 Z
+date: 2014-02-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec