예제 #1
0
    def test_small_doc(self):
        # need an instance to call analyze
        koh = Kohlschuetter()

        self.assertEqual((None, []), Kohlschuetter.make_features('<html></html>'))
        self.assertEqual('', koh.analyze('<html></html>'))

        s = '<html> <p>a</p> <div>b</div> </html>'
        features, blocks = Kohlschuetter.make_features(s)
        self.assertTrue(features is None)
        self.block_output_tokens(blocks, [['a'], ['b']])
        self.assertEqual('a b', koh.analyze(s))