JTidy解决中文乱码问题(亲测可用)

Posted 2021-02-02 haoyoung

项目中需要用到jTidy把html格式化为xml文件，以便后续处理，然而在使用jTidy的时候，发现html文档里中文用jTidy转换后会乱码。
经过一阵研究，发现主要是jTidy的inCharEncoding和outCharEncoding需要设置为UTF-8才可以正常读取和写入中文字符。
关键代码只有两行：

        tidy.setInputEncoding("UTF-8");
        tidy.setOutputEncoding("UTF-8");

完整代码如下：

import org.w3c.tidy.Configuration;
import org.w3c.tidy.Tidy;

import java.io.*;

public class Main {

    public static final String WORK_DIR = "D:\data\temp\jTidy\";

    public static final String INPUT_FILE = "input.html";

    public static final String OUTPUT_FILE = "output.xml";

    public static final String ERROR_LOG = "error.log";

    public static void convert(InputStream inputStream, OutputStream outputStream){
        Tidy tidy = new Tidy();
        tidy.setInputEncoding("UTF-8");
        tidy.setOutputEncoding("UTF-8");
        tidy.setWraplen(0);
        try {
            tidy.setErrout(new PrintWriter(new FileWriter(WORK_DIR+ERROR_LOG)));
        } catch (IOException e) {
            e.printStackTrace();
        }
        tidy.parse(inputStream,outputStream);
    }

    public static void main(String args[]){
        InputStream inputStream = null;
        OutputStream outputStream = null;
        try {
            inputStream = new FileInputStream(WORK_DIR+INPUT_FILE);
            outputStream = new FileOutputStream(WORK_DIR+OUTPUT_FILE);
            convert(inputStream,outputStream);
            inputStream.close();
            outputStream.close();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {

        }

    }



}