normalize.py 文件源码

def materialize_attr_values(a: np.ndarray) -> np.ndarray:
    scalar = False
    if np.isscalar(a):
        scalar = True
        a = np.array([a])
    result: np.ndarray = None
    if np.issubdtype(a.dtype, np.string_):
        # First ensure that what we load is valid ascii (i.e. ignore anything outside 7-bit range)
        temp = np.array([x.decode('ascii', 'ignore') for x in a])
        # Then unescape XML entities and convert to unicode
        result = np.array([html.unescape(x) for x in temp.astype(str)], dtype=np.str_)
    elif np.issubdtype(a.dtype, np.str_) or np.issubdtype(a.dtype, np.unicode_):
        result = np.array(a.astype(str), dtype=np.str_)
    else:
        result = a
    if scalar:
        return result[0]
    else:
        return result