surrogateescape.py 文件源码

def replace_surrogate_encode(mystring):
    """
    Returns a (unicode) string, not the more logical bytes, because the codecs
    register_error functionality expects this.
    """
    decoded = []
    for ch in mystring:
        # if utils.PY3:
        #     code = ch
        # else:
        code = ord(ch)

        # The following magic comes from Py3.3's Python/codecs.c file:
        if not 0xD800 <= code <= 0xDCFF:
            # Not a surrogate. Fail with the original exception.
            raise exc
        # mybytes = [0xe0 | (code >> 12),
        #            0x80 | ((code >> 6) & 0x3f),
        #            0x80 | (code & 0x3f)]
        # Is this a good idea?
        if 0xDC00 <= code <= 0xDC7F:
            decoded.append(_unichr(code - 0xDC00))
        elif code <= 0xDCFF:
            decoded.append(_unichr(code - 0xDC00))
        else:
            raise NotASurrogateError
    return str().join(decoded)