lib/datasets/wikipedia.rb in red-datasets-0.1.4 vs lib/datasets/wikipedia.rb in red-datasets-0.1.5

@@ -1,8 +1,9 @@
 require "rexml/streamlistener"
 require "rexml/parsers/baseparser"
 require "rexml/parsers/streamparser"
+require "time"
 
 require_relative "dataset"
 
 module Datasets
   class Wikipedia < Dataset
@@ -53,14 +54,12 @@
 
     private
     def open_data(&block)
       base_name = "#{@language}wiki-latest-#{type_in_path}.xml.bz2"
       data_path = cache_dir_path + base_name
-      unless data_path.exist?
-        data_url = "https://dumps.wikimedia.org/#{@language}wiki/latest/#{base_name}"
-        download(data_path, data_url)
-      end
+      data_url = "https://dumps.wikimedia.org/#{@language}wiki/latest/#{base_name}"
+      download(data_path, data_url)
 
       extract_bz2(data_path, &block)
     end
 
     def type_in_path
@@ -151,10 +150,10 @@
 
       def text(data)
         @text_stack.last << data
       end
 
-      def cdata(contnet)
+      def cdata(content)
         @text_stack.last << content
       end
 
       private
       def on_page(page)