Contents

#!/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

Version data entries

33 entries across 33 versions & 1 rubygems

Version	Path
twitter_ebooks-2.3.2	test/tokenize.rb
twitter_ebooks-2.3.1	test/tokenize.rb
twitter_ebooks-2.3.0	test/tokenize.rb
twitter_ebooks-2.2.9	test/tokenize.rb
twitter_ebooks-2.2.8	test/tokenize.rb
twitter_ebooks-2.2.7	test/tokenize.rb
twitter_ebooks-2.2.6	test/tokenize.rb
twitter_ebooks-2.2.5	test/tokenize.rb
twitter_ebooks-2.2.4	test/tokenize.rb
twitter_ebooks-2.2.3	test/tokenize.rb
twitter_ebooks-2.2.2	test/tokenize.rb
twitter_ebooks-2.2.1	test/tokenize.rb
twitter_ebooks-2.2.0	test/tokenize.rb
twitter_ebooks-2.1.9	test/tokenize.rb
twitter_ebooks-2.1.8	test/tokenize.rb
twitter_ebooks-2.1.7	test/tokenize.rb
twitter_ebooks-2.1.6	test/tokenize.rb
twitter_ebooks-2.1.5	test/tokenize.rb
twitter_ebooks-2.1.4	test/tokenize.rb
twitter_ebooks-2.1.3	test/tokenize.rb