UTF-8 encode and decode: Difference between revisions

=={{header|Java}}==

{{works with|Java|7+}}

<lang java>import java.util.Formatter;

import java.io.UnsupportedEncodingException;

public class UTF8EncodeDecode {

public static final void main(String[] args) throws UnsupportedEncodingException {

System.out.printf("%-7s %-43s %7s\t%s\t%7s\n", "Char", "Name", "Unicode", "UTF-8 encoded", "Decoded");

for (int codepoint : new int[]{0x0041, 0x00F6, 0x0416, 0x20AC, 0x1D11E}) {

String name = Character.getName(codepoint);

String string = new String(new int[]{codepoint}, 0, 1);

byte[] encoded = string.getBytes("UTF-8");

Formatter formatter = new Formatter();

for (byte b : encoded) {

formatter.format("%02X ", b);

}

String encodedHex = formatter.toString();

int decoded = new String(encoded, "UTF-8").codePointAt(0);

System.out.printf("%-7s %-43s U+%04X\t%-12s\tU+%04X\n", string, name, codepoint, encodedHex, decoded);

}

}

}</lang>

{{out}}

<pre>

Char Name Unicode UTF-8 encoded Decoded

A LATIN CAPITAL LETTER A U+0041 41 U+0041

ö LATIN SMALL LETTER O WITH DIAERESIS U+00F6 C3 B6 U+00F6

Ж CYRILLIC CAPITAL LETTER ZHE U+0416 D0 96 U+0416

€ EURO SIGN U+20AC E2 82 AC U+20AC

𝄞 MUSICAL SYMBOL G CLEF U+1D11E F0 9D 84 9E U+1D11E

</pre>