Base64.java

public class Base64
{
	public static String encode(byte[] data)
	{
		String encoded = "";
	        String split = "";
	        String tbl = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
	        byte[] data;
	        //try to use the appropriate encoding string, but fallback to default locale
	        try { data = string.getBytes("UTF-8");
	        } catch (Exception ex) { data = string.getBytes(); }
	        //determine how many padding bytes to add to the end
	        int paddingCount = (3 - (data.length % 3)) % 3;
	        //add any necessary padding to the input
	        byte[] padded = new byte[data.length + paddingCount];
	        System.arraycopy(data, 0, padded, 0, data.length);
	        data = padded;
	        //proces 3 bytes at a time, output 4 bytes at a time
	        //worry about CRLF later
	        for (int i = 0; i < data.length; i += 3) {
	        	int j = ((data[i] & 0xff) << 16) + ((data[i + 1] & 0xff) << 8) + (data[i + 2] & 0xff);
	        	encoded = encoded + tbl.charAt((j >> 18) & 0x3f) + tbl.charAt((j >> 12) & 0x3f) + tbl.charAt((j >> 6) & 0x3f) + tbl.charAt(j & 0x3f);
	        }
	        //replace encoded padding nulls with "="
	        encoded = encoded.substring(0, encoded.length() - paddingCount) + "==".substring(0, paddingCount);
	        //split into multiple lines
	        for (int i = 0; i < encoded.length(); i += 76) {
	        	split += encoded.substring(i, Math.min(encoded.length(), i + 76)) + "\r\n";
	        }
	        //trim the new line at the end of the string and return the result
	        return split.trim();
	}

	public static byte[] decode(String data)
	{
		int[] tbl = { 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, -1, -1, 63, 52, 53, 54, 
			55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1, -1,  0,  1,  2, 
			 3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 
			20, 21, 22, 23, 24, 25, -1, -1, -1, -1, -1, -1, 26, 27, 28, 29, 30, 
			31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 
			48, 49, 50, 51, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
			-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 };
			
		byte[] bytes = data.getBytes();
			
		StringBuilder buffer = new StringBuilder();
		for (int i = 0; i < bytes.length; ) {
			int b = 0;
			if (tbl[bytes[i]] != -1) {
				b = (tbl[bytes[i]] & 0xFF) << 18;
			} 
			// skip unknown characters
			else {
				i++;
				continue;
			}
			
			if (i + 1 < bytes.length && tbl[bytes[i+1]] != -1) {
				b = b | ((tbl[bytes[i+1]] & 0xFF) << 12);
			}
			if (i + 2 < bytes.length && tbl[bytes[i+2]] != -1) {
				b = b | ((tbl[bytes[i+2]] & 0xFF) << 6);
			}
			if (i + 3 < bytes.length && tbl[bytes[i+3]] != -1) {
				b = b | (tbl[bytes[i+3]] & 0xFF);
			}
			
			while ((b & 0xFFFFFF) != 0) {
				int c = (b & 0xFF0000) >> 16;
				buffer.append((char)c);
				b <<= 8;
			}
			
			i += 4;
		}
		
		return buffer.toString().getBytes();
	}
}

gendecodetbl.py

# script to generate the reverse lookup table

s = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"

res = [(ord(c), i) for i,c in enumerate(s)]

lookup = dict(res)

f = []
for i in xrange(0,255):
    if lookup.has_key(i):
        n = str(lookup[i])
        if len(n) == 1:
            n = " " + n
        f.append(" " + n)
    else:
        f.append(" " + str(-1))

print len(f)
print ",".join(f)

Hi,
I tried using decoding part of code, but couldn't get working decode, so it decodes:
String stru = "c8SBbHM=";
It returns "sÄ�ls", but it should return "sāls", it is probably some problem with UTF-8.

I also tried to incorporate some conversion from bytes to String but still I'm stuck.

Encoding part is working fine with UTF-8, thank you very much.