Method test_trie_split

tests/utils/test_tokenization_utils.py:229–235

(self)

        self.assertEqual(trie.data, {"H": {"e": {"l": {"l": {"o": {"": 1, " ": {"友": {"達": {"": 1}}}}}}}}})

    def test_trie_split(self):
        trie = Trie()
        self.assertEqual(trie.split("[CLS] This is a extra_id_100"), ["[CLS] This is a extra_id_100"])
        trie.add("[CLS]")
        trie.add("extra_id_1")
        trie.add("extra_id_100")
        self.assertEqual(trie.split("[CLS] This is a extra_id_100"), ["[CLS]", " This is a ", "extra_id_100"])

    def test_trie_single(self):
        trie = Trie()