How to use the underthesea.feature_engineering.text.Text function in underthesea

def test_text_1(self):
        input = u"đi học"
        output = Text(input)
        self.assertTrue(is_unicode(output))

def tokenize(text):
    """
    tokenize text for word segmentation
    :param text: raw text input
    :return: tokenize text
    """
    text = Text(text)
    specials = ["==>", "->", "\.\.\.", ">>"]
    digit = "\d+([\.,_]\d+)+"
    email = "(^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$)"
    web = "^(http[s]?://)?(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+$"
    datetime = [
        "\d{1,2}\/\d{1,2}(\/\d+)?",
        "\d{1,2}-\d{1,2}(-\d+)?",
    ]
    word = "\w+"
    non_word = "[^\w\s]"
    abbreviations = [
        "[A-ZĐ]+\.",
        "Tp\.",
        "Mr\.", "Mrs\.", "Ms\.",
        "Dr\.", "ThS\."
    ]