def test_full_tokenizer(self): vocab_tokens = [ "<unk>", "[CLS]", "[SEP]", "want", "unwanted", "wa", "un", "running", "," ] with open("/tmp/transfo_xl_tokenizer_test.txt", "w", encoding='utf-8') as vocab_writer: vocab_writer.write("".join([x + "\n" for x in vocab_tokens])) vocab_file = vocab_writer.name tokenizer = TransfoXLTokenizer(vocab_file=vocab_file, lower_case=True) tokenizer.build_vocab() os.remove(vocab_file) tokens = tokenizer.tokenize(u"<unk> UNwanted , running") self.assertListEqual(tokens, ["<unk>", "unwanted", ",", "running"]) self.assertListEqual( tokenizer.convert_tokens_to_ids(tokens), [0, 4, 8, 7]) vocab_file = tokenizer.save_vocabulary(vocab_path="/tmp/") tokenizer.from_pretrained(vocab_file) os.remove(vocab_file) tokens = tokenizer.tokenize(u"<unk> UNwanted , running") self.assertListEqual(tokens, ["<unk>", "unwanted", ",", "running"]) self.assertListEqual( tokenizer.convert_tokens_to_ids(tokens), [0, 4, 8, 7])
def test_full_tokenizer_lower(self): tokenizer = TransfoXLTokenizer(lower_case=True) self.assertListEqual( tokenizer.tokenize(u" \tHeLLo!how \n Are yoU? "), ["hello", "!", "how", "are", "you", "?"]) self.assertListEqual(tokenizer.tokenize(u"H\u00E9llo"), ["hello"])
def test_full_tokenizer_no_lower(self): tokenizer = TransfoXLTokenizer(lower_case=False) self.assertListEqual( tokenizer.tokenize(u" \tHeLLo ! how \n Are yoU ? "), ["HeLLo", "!", "how", "Are", "yoU", "?"])