Function _unquote_impl

Lib/urllib/parse.py:795–822

(string: bytes | bytearray | str)

    return bytes(_unquote_impl(string))

def _unquote_impl(string: bytes | bytearray | str) -> bytes | bytearray:
    # Note: strings are encoded as UTF-8. This is only an issue if it contains
    # unescaped non-ASCII characters, which URIs should not.
    if not string:
        # Is it a string-like object?
        string.split
        return b''
    if isinstance(string, str):
        string = string.encode('utf-8')
    bits = string.split(b'%')
    if len(bits) == 1:
        return string
    res = bytearray(bits[0])
    append = res.extend
    # Delay the initialization of the table to not waste memory
    # if the function is never called
    global _hextobyte
    if _hextobyte is None:
        _hextobyte = {(a + b).encode(): bytes.fromhex(a + b)
                      for a in _hexdig for b in _hexdig}
    for item in bits[1:]:
        try:
            append(_hextobyte[item[:2]])
            append(item[2:])
        except KeyError:
            append(b'%')
            append(item)
    return res

_asciire = re.compile('([\x00-\x7f]+)')