mirror of
https://github.com/thewesker/twitter_ebooks.git
synced 2025-12-20 04:11:08 -05:00
19 lines
367 B
Ruby
Executable File
19 lines
367 B
Ruby
Executable File
#!/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
|