busk-ruby-readability 1.0.0 → 1.0.1

data/lib/readability.rb

@@ -6,7 +6,7 @@ module Readability
     TEXT_LENGTH_THRESHOLD = 25
     RETRY_LENGTH = 250
 
-    attr_accessor :options, :html
+    attr_accessor :options, :html, :best_candidate
 
     def initialize(input, options = {})
       @input = input
@@ -83,17 +83,18 @@ module Readability
     end
 
     def select_best_candidate(candidates)
-      sorted_candidates = candidates.values.sort { |a, b| b[:content_score] <=> a[:content_score] }
+      @best_candidate ||= begin 
+        sorted_candidates = candidates.values.sort { |a, b| b[:content_score] <=> a[:content_score] }
 
-      debug("Top 5 canidates:")
-      sorted_candidates[0...5].each do |candidate|
-        debug("Candidate #{candidate[:elem].name}##{candidate[:elem][:id]}.#{candidate[:elem][:class]} with score #{candidate[:content_score]}")
-      end
-
-      best_candidate = sorted_candidates.first || { :elem => @html.css("body").first, :content_score => 0 }
-      debug("Best candidate #{best_candidate[:elem].name}##{best_candidate[:elem][:id]}.#{best_candidate[:elem][:class]} with score #{best_candidate[:content_score]}")
+        debug("Top 5 candidates:")
+        sorted_candidates[0...5].each do |candidate|
+          debug("Candidate #{candidate[:elem].andand.name}##{candidate[:elem][:id]}.#{candidate[:elem][:class]} with score #{candidate[:content_score]}")
+        end
 
-      best_candidate
+        best_candidate = sorted_candidates.first || { :elem => @html.css("body").first, :content_score => 0 }
+        #debug("Best candidate #{best_candidate[:elem].andand.name} with score #{best_candidate[:content_score]}")
+        best_candidate
+      end
     end
 
     def get_link_density(elem)
@@ -281,7 +282,8 @@ module Readability
           el.attributes.each { |a, x| el.delete(a) unless @options[:attributes] && @options[:attributes].include?(a.to_s) }
           # Otherwise, replace the element with its contents
         else
-          el.swap(el.text)
+          # keep getting whiny nils with nokogiri
+          el.swap(el.text) rescue nil
         end
 
       end

metadata

@@ -1,7 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: busk-ruby-readability
 version: !ruby/object:Gem::Version 
-  version: 1.0.0
+  hash: 21
+  prerelease: false
+  segments: 
+  - 1
+  - 0
+  - 1
+  version: 1.0.1
 platform: ruby
 authors: []
 
@@ -9,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-09-16 00:00:00 -03:00
+date: 2010-09-20 00:00:00 -03:00
 default_executable: 
 dependencies: []
 
@@ -33,21 +39,27 @@ rdoc_options: []
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.5
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: A rewrite of original ruby-readability