자바 한글 인코딩 변환 / Java Korean Encoding & Decoding

자바 한글 인코딩 변환 샘플

String word = "자바 한글 인코딩 변환 샘플"; // UTF-8 System.out.println("utf-8 -> euc-kr : " + new String(word.getBytes("utf-8"), "euc-kr")); System.out.println("utf-8 -> ksc5601 : " + new String(word.getBytes("utf-8"), "ksc5601")); System.out.println("utf-8 -> x-windows-949 : " + new String(word.getBytes("utf-8"), "x-windows-949")); System.out.println("utf-8 -> iso-8859-1 : " + new String(word.getBytes("utf-8"), "iso-8859-1")); //ISO-8859 System.out.println("iso-8859-1 -> euc-kr : " + new String(word.getBytes("iso-8859-1"), "euc-kr")); System.out.println("iso-8859-1 -> ksc5601 : " + new String(word.getBytes("iso-8859-1"), "ksc5601")); System.out.println("iso-8859-1 -> x-windows-949 : " + new String(word.getBytes("iso-8859-1"), "x-windows-949")); System.out.println("iso-8859-1 -> utf-8 : " + new String(word.getBytes("iso-8859-1"), "utf-8")); // EUC-KR System.out.println("euc-kr -> utf-8 : " + new String(word.getBytes("euc-kr"), "utf-8")); System.out.println("euc-kr -> ksc5601 : " + new String(word.getBytes("euc-kr"), "ksc5601")); System.out.println("euc-kr -> x-windows-949 : " + new String(word.getBytes("euc-kr"), "x-windows-949")); System.out.println("euc-kr -> iso-8859-1 : " + new String(word.getBytes("euc-kr"), "iso-8859-1")); // KSC5601 System.out.println("ksc5601 -> euc-kr : " + new String(word.getBytes("ksc5601"), "euc-kr")); System.out.println("ksc5601 -> utf-8 : " + new String(word.getBytes("ksc5601"), "utf-8")); System.out.println("ksc5601 -> x-windows-949 : " + new String(word.getBytes("ksc5601"), "x-windows-949")); System.out.println("ksc5601 -> iso-8859-1 : " + new String(word.getBytes("ksc5601"), "iso-8859-1")); // x-windows-949 System.out.println("x-windows-949 -> euc-kr : " + new String(word.getBytes("x-windows-949"), "euc-kr")); System.out.println("x-windows-949 -> utf-8 : " + new String(word.getBytes("x-windows-949"), "utf-8")); System.out.println("x-windows-949 -> ksc5601 : " + new String(word.getBytes("x-windows-949"), "ksc5601")); System.out.println("x-windows-949 -> iso-8859-1 : " + new String(word.getBytes("x-windows-949"), "iso-8859-1"));

자바 코드 포인트

package test; public class CodePointTest { public static void main(String args[]){ String sample="한글테스트 test"; for(int i=0;i<sample.length();i++){ System.out.print("["+sample.charAt(i)+"]의 10진수 값 : "+sample.codePointAt(i)); System.out.print(" - 16진수 값 : "+Integer.toHexString(sample.codePointAt(i))); new Character(sample.charAt(i)).toString().getBytes(); System.out.println(); } } }

자바 UTF-8문자열 HEX로 변환

package test; import java.io.UnsupportedEncodingException; public class Utf8Hex { public static void main(String args[]) throws UnsupportedEncodingException{ String str="한글 테스트"; byte[] bytes=str.getBytes("UTF-8"); StringBuffer sb=new StringBuffer(); for(int i=0;i<bytes.length;i++){ sb.append(Integer.toString((bytes[i]&0xff) + 0x100, 16).substring(1)); } System.out.println(sb); } }

Unicode 테스트

package test; import java.io.UnsupportedEncodingException; public class CodePointTest { public static void main(String args[]) throws UnsupportedEncodingException{ String a = "\uAC00\uAC01"; System.out.println(a); byte[] xxx = a.getBytes("UTF-8"); for (byte x : xxx) { System.out.println(Integer.toHexString(x & 0xFF)); } } }

출처 : http://goodcodes.tistory.com/75