Github time!

test/keywords.rb

@@ -0,0 +1,18 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require 'twitter_ebooks'
+require 'minitest/autorun'
+require 'benchmark'
+
+module Ebooks
+  class TestKeywords < Minitest::Test
+    corpus = NLP.normalize(File.read(ARGV[0]))
+    puts "Finding and ranking keywords"
+    puts Benchmark.measure {
+      NLP.keywords(corpus).top(50).each do |keyword|
+        puts "#{keyword.text} #{keyword.weight}"
+      end
+    }
+  end
+end

test/tokenize.rb

@@ -0,0 +1,18 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+require 'twitter_ebooks'
+require 'minitest/autorun'
+
+module Ebooks
+  class TestTokenize < Minitest::Test
+    corpus = NLP.normalize(File.read(TEST_CORPUS_PATH))
+    sents = NLP.sentences(corpus).sample(10)
+
+    NLP.sentences(corpus).sample(10).each do |sent|
+      p sent
+      p NLP.tokenize(sent)
+      puts
+    end
+  end
+end