processor.rb in pupa-0.0.6

- old
+ new

@@ -15,11 +15,11 @@
     include Helper
 
     class_attribute :tasks
     self.tasks = []
 
-    attr_reader :report
+    attr_reader :report, :client, :options
 
     def_delegators :@logger, :debug, :info, :warn, :error, :fatal
 
     # @param [String] output_dir the directory in which to dump JSON documents
     # @param [String] cache_dir the directory in which to cache HTTP responses
@@ -52,20 +52,20 @@
             params[key] = value.first
           end
         end
       end
 
-      @client.get(url, params).body
+      client.get(url, params).body
     end
 
     # Retrieves and parses a document with a POST request.
     #
     # @param [String] url a URL to an HTML document
     # @param [String,Hash] params query string parameters
     # @return a parsed document
     def post(url, params = {})
-      @client.post(url, params).body
+      client.post(url, params).body
     end
 
     # Adds a scraping task to Pupa.rb.
     #
     # Defines a method whose name is identical to `task_name`. This method
@@ -275,9 +275,11 @@
     #
     # @param [Hash] objects a hash of scraped objects keyed by ID
     # @return [Hash] a mapping from an object ID to the ID of its duplicate
     def build_losers_to_winners_map(objects)
       {}.tap do |map|
+        # We don't need to iterate on the last item in the hash, but skipping
+        # the last item is more effort than running the last item.
         objects.each_with_index do |(id1,object1),index|
           unless map.key?(id1) # Don't search for duplicates of duplicates.
             objects.drop(index + 1).each do |id2,object2|
               if object1 == object2
                 map[id2] = id1