def test_is_punctuation(self): self.assertTrue(tokenization._is_punctuation(u"-")) self.assertTrue(tokenization._is_punctuation(u"$")) self.assertTrue(tokenization._is_punctuation(u"`")) self.assertTrue(tokenization._is_punctuation(u".")) self.assertFalse(tokenization._is_punctuation(u"A")) self.assertFalse(tokenization._is_punctuation(u" "))
def customize_tokenizer(text, do_lower_case=False): tokenizer = tokenization.BasicTokenizer(do_lower_case=do_lower_case) temp_x = "" text = tokenization.convert_to_unicode(text) for c in text: if tokenizer._is_chinese_char(ord(c)) or tokenization._is_punctuation( c) or tokenization._is_whitespace( c) or tokenization._is_control(c): temp_x += " " + c + " " else: temp_x += c if do_lower_case: temp_x = temp_x.lower() return temp_x.split()
def _is_punctuation(self, char): return bert_tokenization._is_punctuation(char) # pylint: disable=protected-access