qiu2011.py 文件源码

def __call__(self, token_tuple, terms):
        """
        Input:
            token_tuple : Token or tuple of Token objects
            terms       : term or iterable of terms to match

        Output:
            Returns None if no match is found.
            Returns the first matched in case many of them show the same
            similarity ratio.
        """
        if not hasattr(terms, '__iter__'):
            terms = [terms]
        if not isinstance(token_tuple, tuple):
            token_tuple = (token_tuple,)
        try:
            token_tuple = tuple(self.key(token) for token in token_tuple)
        except Exception:  # as e
            token_tuple = tuple(str(token) for token in token_tuple)

        best_term = None
        best_ratio = 0

        for term in terms:
            ratio = max([Levenshtein.ratio(unicode(" ".join(token_tuple)),
                                           unicode(" ".join(term_i)))*100
                         for term_i in term])
            if ratio >= self.match and ratio > best_ratio:
                best_term = term
                best_ratio = ratio

        return best_term


# ------- UTIL FUNCTIONS ------------------------------------------------------