def test_basic_tokenizer_no_lower(self):
tokenizer = tokenization.BasicTokenizer(do_lower_case=False)
self.assertAllEqual(
tokenizer.tokenize(u" \tHeLLo!how \n Are yoU? "),
["HeLLo", "!", "how", "Are", "yoU", "?"],
)
def test_basic_tokenizer_lower(self):
tokenizer = tokenization.BasicTokenizer(do_lower_case=True)
self.assertAllEqual(
tokenizer.tokenize(u" \tHeLLo!how \n Are yoU? "),
["hello", "!", "how", "are", "you", "?"])
self.assertAllEqual(tokenizer.tokenize(u"H\u00E9llo"), ["hello"])
def test_chinese(self):
tokenizer = tokenization.BasicTokenizer()
self.assertAllEqual(
tokenizer.tokenize(u"ah\u535A\u63A8zz"),
[u"ah", u"\u535A", u"\u63A8", u"zz"],
)
