Java UTF from toUTF8ByteArray(String s)

Description

convert the platform dependent string characters to UTF8 which can also be done by calling the java String method getBytes("UTF-8"),but I hope to do it from the ground up.

License

Apache License

Declaration

private static byte[] toUTF8ByteArray(String s) 

Method Source Code

//package com.java2s;
//License from project: Apache License 

public class Main {
    /** convert the platform dependent string characters to UTF8 which can 
      * also be done by calling the java String method getBytes("UTF-8"),but I
      * hope to do it from the ground up.
      *//*w  w  w .j  a  va  2 s.co m*/

    private static byte[] toUTF8ByteArray(String s) {
        int ichar;
        byte buffer[] = new byte[3 * (s.length())];
        byte hold[];
        int index = 0;
        int count = 0; //count the actual bytes in the
                       //buffer array          

        for (int i = 0; i < s.length(); i++) {
            ichar = (int) s.charAt(i);

            //determine the bytes for a specific character
            if ((ichar >= 0x0080) & (ichar <= 0x07FF)) {
                buffer[index++] = (byte) ((6 << 5) | ((ichar >> 6) & 31));
                buffer[index++] = (byte) ((2 << 6) | (ichar & 63));
                count += 2;
            }

            //determine the bytes for a specific character
            else if ((ichar >= 0x0800) & (ichar <= 0x0FFFF)) {
                buffer[index++] = (byte) ((14 << 4) | ((ichar >> 12) & 15));
                buffer[index++] = (byte) ((2 << 6) | ((ichar >> 6) & 63));
                buffer[index++] = (byte) ((2 << 6) | (ichar & 63));
                count += 3;
            }

            //determine the bytes for a specific character
            else if ((ichar >= 0x0000) & (ichar <= 0x007F)) {
                buffer[index++] = (byte) ((0 << 7) | (ichar & 127));
                count += 1;
            }

            //longer than 16 bit Unicode is not supported
            else
                throw new RuntimeException("Unsupported encoding character length!\n");
        }
        hold = new byte[count];
        System.arraycopy(buffer, 0, hold, 0, count); //trim to size
        return hold;
    }
}

Related

1. toUTF8(String oldStr)
2. toUtf8(String s)
3. toUTF8(String s, String encoding)
4. toUTF8(String str)
5. toUtf8(String texto)
6. toUtf8ByteArray(String source)
7. toUTF8FromLatin1(byte[] outputBuffer, String string)
8. toUTF8k(String in)
9. toUtf8String(String source)