编码问题

最新推荐文章于 2024-01-12 17:12:41 发布

xiao123456789jia

最新推荐文章于 2024-01-12 17:12:41 发布

阅读量233

点赞数

分类专栏： jsp 文章标签：编码

本文链接：https://blog.csdn.net/xiao123456789jia/article/details/51834109

版权

jsp 专栏收录该内容

2 篇文章 0 订阅

订阅专栏

/**
 * Function:
 *
 * @version 1.0
 *          Date: 2016/7/5
 *          Time: 16:52
 * @author: XJ
 */
public class CharsetTest {

    /**
     * 不同的编码获取的字节数组是不同的
     * @throws UnsupportedEncodingException
     */
    @Test
    public void DifferentEncode() throws UnsupportedEncodingException {
        byte[] b1 = "你好  案发时发生发的是分散：；的说方面的撒发生 。的说法。；‘‘bi".getBytes("utf-8");
        System.out.println(Arrays.toString(b1));
        String utf = new String(b1, 0, b1.length, "utf-8");
        System.out.println(utf);

        byte[] b2 = "你好  案发时发生发的是分散：；的说方面的撒发生 。的说法。；‘‘bi".getBytes("iso8859-1");
        System.out.println(Arrays.toString(b2));
        String iso = new String(b2, 0, b2.length, "iso8859-1");
        System.out.println(iso);

        byte[] b3 = "你好  案发时发生发的是分散：；的说方面的撒发生 。的说法。；‘‘bi".getBytes("GBK");
        System.out.println(Arrays.toString(b3));
        String gbk = new String(b3, 0, b3.length, "GBK");
        System.out.println(gbk);
    }

    /**
     * 利用 iso8859-1 作为中间编码 防止乱码
     * 注意：如果直接将utf-8的编码用GBK解析的话可能导致生成的byte[]与之前的byte[]不同，从而导致最后转为utf-8的时候出现乱码
     * @throws UnsupportedEncodingException
     */
    @Test
    public void UserISOAsMiddleware() throws UnsupportedEncodingException {
        byte[] b1 = "你好  案发时发生发的是分散：；的说方面的撒发生 。的说法。；‘‘bi".getBytes("utf-8");
        System.out.println(Arrays.toString(b1));

//        byte[] b2 = new String(b1, 0, b1.length, "GBK").getBytes("GBK");
//        System.out.println(Arrays.toString(b2));
//        System.out.println(new String(b2, 0, b2.length, "GBK"));

        byte[] b2 = new String(b1, 0, b1.length, "iso8859-1").getBytes("iso8859-1");
        System.out.println(Arrays.toString(b2));
        System.out.println(new String(b2, 0, b2.length, "iso8859-1"));

        byte[] b3 = new String(b2, 0, b2.length, "utf-8").getBytes("utf-8");
        System.out.println(Arrays.toString(b3));
        System.out.println(new String(b3, 0, b3.length, "utf-8"));
    }
}