truffle-hog 0.0.1 → 0.0.2

data/lib/truffle-hog.rb

@@ -1,12 +1,9 @@
 module TruffleHog
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
   
   def self.parse_feed_urls(html, favor = :all)
-    rss_links  = []
-    atom_links = []
-    
-    rss_links  = (scan_for_tag(html, "a", "rss") + scan_for_tag(html, "link", "rss")).flatten.uniq
-    atom_links = (scan_for_tag(html, "a", "atom") + scan_for_tag(html, "link", "atom")).flatten.uniq
+    rss_links  = scan_for_tag(html, "rss")
+    atom_links = scan_for_tag(html, "atom")
 
     case favor
     when :all
@@ -18,10 +15,24 @@ module TruffleHog
     end
   end
   
-  def self.scan_for_tag(html, tag, type)
-    href_first = html.scan(/<#{tag}.*href\=['"](.*?)['"].*type\=['"]application\/#{type}\+xml['"].*?>/)
-    return href_first unless href_first.empty?
-    
-    html.scan(/<#{tag}.*type\=['"]application\/#{type}\+xml['"].*href=['"](.*?)['"].*?>/)
+  def self.scan_for_tag(html, type)
+    urls(html, "link", type) + urls(html, "a", type)
+  end
+  
+  def self.urls(html, tag, type)
+    tags = html.scan(/(<#{tag}.*?>)/).flatten
+    feed_tags = collect(tags, type)
+    feed_tags.map do |tag|
+      url = tag.match(/.*href=['"](.*?)['"].*/)[1]
+      url =~ /^http.*/ ? url : nil
+    end.compact
+  end
+  
+  def self.collect(tags, type)
+    tags.collect {|t| t if feed?(t, type)}.compact
+  end
+  
+  def self.feed?(html, type)
+    html =~ /.*type=['"]application\/#{type}\+xml['"].*/
   end
 end

data/spec/truffle-hog_spec.rb

@@ -6,10 +6,7 @@ describe "parsing html" do
   end
   
   it "parses all feed urls" do
-    TruffleHog.parse_feed_urls(@html).should == ["http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/rss", 
-                                                 "http://www.pauldix.net/in_head/index.rdf", "http://www.pauldix.net/in_head/rss.xml", 
-                                                 "http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom", 
-                                                 "http://www.pauldix.net/in_head/atom.xml"]
+    TruffleHog.parse_feed_urls(@html).should == ["http://www.pauldix.net/in_head/index.rdf", "http://www.pauldix.net/in_head/rss.xml", "http://feeds.feedburner.com/PaulDixExplainsNothing", "http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/rss", "http://www.pauldix.net/in_head/atom.xml", "http://feeds.feedburner.com/PaulDixExplainsNothing/in_body/atom"]
   end
   
   it "parses rss feeds from the link tags in head" do
@@ -41,4 +38,12 @@ describe "parsing html" do
   
   it "returns atom feeds if rss is favored, but none are found"
   it "returns rss feeds if atom is favored, but none are found"
+  
+  describe "odd regressions" do
+    it "doesn't go into an infinite loop on this input" do
+      input = File.read("#{File.dirname(__FILE__)}/infinite.html")
+      feed_urls = TruffleHog.parse_feed_urls(input)
+      feed_urls.should == ["http://feeds.feedburner.com/cryptload"]
+    end
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: truffle-hog
 version: !ruby/object:Gem::Version 
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors: 
 - Paul Dix