Java 한글 Encoding

한글 포함한 문자열을 바이트 단위로 잘라야 하는 경우 아래 코드사용

new String("문자열".getBytes("EUC-KR"), start, end, "EUC-KR")

Source

public class TestMain { public static void main(String[] args) throws Exception { System.out.println("START"); System.out.println("-----------------------------------------"); test("한글입니다"); test("AB영어입니"); System.out.println("-----------------------------------------"); System.out.println("END"); } private static void test(String line) throws Exception { String tab = "    "; System.out.println(); System.out.println(line); System.out.println(tab + "line.getBytes().length                              : " + line.getBytes().length); System.out.println(tab + "line.getBytes(\"EUC-KR\").length                      : " + line.getBytes("EUC-KR").length); System.out.println(tab + "new String(line.getBytes(), 0, 2)                   : " + (new String(line.getBytes(), 0, 2))); System.out.println(tab + "new String(line.getBytes(\"EUC-KR\"), 0, 2, \"EUC-KR\") : " + (new String(line.getBytes("EUC-KR"), 0, 2, "EUC-KR"))); } }

Console

START ----------------------------------------- 한글입니다     line.getBytes().length                              : 15     line.getBytes("EUC-KR").length                      : 10     new String(line.getBytes(), 0, 2)                   : �     new String(line.getBytes("EUC-KR"), 0, 2, "EUC-KR") : 한 AB영어입니     line.getBytes().length                              : 14     line.getBytes("EUC-KR").length                      : 10     new String(line.getBytes(), 0, 2)                   : AB     new String(line.getBytes("EUC-KR"), 0, 2, "EUC-KR") : AB ----------------------------------------- END