Crockford base 32 implementation (lower case version)

CrockfordBase32.php

/**
 * Crockford base32 encoding implementation (useable with random_bytes())
 * see: https://www.crockford.com/base32.html.
 */
class CrockfordBase32
{
    const BITS_5_RIGHT = 31;

    const CHARS = '0123456789abcdefghjkmnpqrstvwxyz'; // lower-case

    public function sanitize(string $input)
    {
        $lower = strtolower($input);
        $cleaning = preg_replace('/o/', '0', $lower);
        $cleaning = preg_replace('/[il]/', '1', $cleaning);

        return preg_replace('/[^' . self::CHARS . ']/', '', $cleaning);
    }

    public function encode($data, $padRight = false)
    {
        $dataSize = strlen($data);
        $res = '';
        $remainder = 0;
        $remainderSize = 0;

        for ($i = 0; $i < $dataSize; ++$i) {
            $b = ord($data[$i]);
            $remainder = ($remainder << 8) | $b;
            $remainderSize += 8;
            while ($remainderSize > 4) {
                $remainderSize -= 5;
                $c = $remainder & (self::BITS_5_RIGHT << $remainderSize);
                $c >>= $remainderSize;
                $res .= static::CHARS[$c];
            }
        }
        if ($remainderSize > 0) {
            // remainderSize < 5:
            $remainder <<= (5 - $remainderSize);
            $c = $remainder & self::BITS_5_RIGHT;
            $res .= static::CHARS[$c];
        }
        if ($padRight) {
            $padSize = (8 - ceil(($dataSize % 5) * 8 / 5)) % 8;
            $res .= str_repeat('=', $padSize);
        }

        return $res;
    }

    public function decode($data)
    {
        $data = rtrim($data, "=\x20\t\n\r\0\x0B");
        $dataSize = strlen($data);
        $buf = 0;
        $bufSize = 0;
        $res = '';
        $charMap = array_flip(str_split(static::CHARS)); // char=>value map
        $charMap += array_flip(str_split(strtoupper(static::CHARS))); // add upper-case alternatives

        for ($i = 0; $i < $dataSize; ++$i) {
            $c = $data[$i];
            $b = $charMap[$c];
            $buf = ($buf << 5) | $b;
            $bufSize += 5;
            if ($bufSize > 7) {
                $bufSize -= 8;
                $b = ($buf & (0xff << $bufSize)) >> $bufSize;
                $res .= chr($b);
            }
        }

        return $res;
    }
}

ExampleCreateRandomCode.php

$encoder = new CrockfordBase32();
$eightCharCode = $encoder->encode(random_bytes(5));

I don't see the sanitize function being used anywhere. How is it supposed to be used?

Thanks for the gist btw.

Hey @CGAsierPaz it's to sanatize user input. if user had to input a Crockford code.

it turns o into 0 and il into 1 (because these characters are not used on purpose for readability/typo's).
and then removes all other characters.

I see.

Thanks for the answer!