Java之utf8中文编码转换

 

import org.apache.commons.codec.binary.Hex;
import org.junit.Test;

/**
 * HBASE中文转换
 */
public class CHCode {

    /**
     * 中文转utf8
     */
    @Test
    public void testStr2UTF8() throws Exception {
        String str = "烦";
        char[] chars = Hex.encodeHex(str.getBytes("UTF-8"));
        System.out.println(chars);
    }

    /**
     * utf8转中文
     */
    @Test
    public void testUTF8ToStr() throws Exception {
//        String str = new String(Hex.decodeHex("e783a6e783a6e783a6".toCharArray()), "UTF-8");

        byte[] bytes = Hex.decodeHex("e783a6e783a6e783a6".toCharArray());
        String str = new String(bytes, "UTF-8");

        System.out.println("bytes:" + bytes);
        System.out.println("String:" + str);
    }

    /**
     * HBASE中文转换
     */
    @Test
    public void testHbaseStr() throws Exception {
//        Hbase UTF8编码
        String content = "\\xE7\\x83\\xA6";
        char[] chars = content.toCharArray();
        StringBuffer sb = new StringBuffer();
        for (int i = 2; i < chars.length; i = i + 4) {
//            System.out.println(chars[i]);
            sb.append(chars[i]);
//            System.out.println(chars[i + 1]);
            sb.append(chars[i + 1]);
        }
        System.out.println(sb);
        String ouputStr = new String(Hex.decodeHex(sb.toString().toCharArray()), "UTF-8");
        System.out.println(ouputStr);
    }


}