def __init__(self, vocab_file, do_lower_case=True, vocab_override=None):
super().__init__()
self.vocab_file = vocab_file
self.do_lower_case = do_lower_case
if vocab_override is None:
self.vocab = tokenization.load_vocab(vocab_file)
else:
self.vocab = vocab_override
self.inv_vocab = {v: k for k, v in self.vocab.items()}
self.basic_tokenizer = tokenization.BasicTokenizer(
do_lower_case=do_lower_case)
self.wordpiece_tokenizer = tokenization.WordpieceTokenizer(
vocab=self.vocab)
def test_wordpiece_tokenizer(self):
vocab_tokens = [
"[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un",
"runn", "##ing"
]
vocab = {}
for (i, token) in enumerate(vocab_tokens):
vocab[token] = i
tokenizer = tokenization.WordpieceTokenizer(vocab=vocab)
self.assertAllEqual(tokenizer.tokenize(""), [])
self.assertAllEqual(tokenizer.tokenize("unwanted running"),
["un", "##want", "##ed", "runn", "##ing"])
self.assertAllEqual(tokenizer.tokenize("unwantedX running"),
["[UNK]", "runn", "##ing"])