删除集群中HDFS的所有空文件和空目录

删除集群中HDFS的所有空文件和空目录

package com.zzm.day03;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
/**
 * @Description:
 * 3、删除HDFS集群中的所有空文件和空目录
 * @author: zzm
 * @vision: 1.0
 * @Date: Created in 20:13 2019-09-23
 */
public class DeleteEmpty {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);

        //对根目录下所有的空文件夹和空文件进行删除
        FileStatus[] listStatus = fs.listStatus(new Path("/"));
        for (FileStatus fss : listStatus) {
            if (fss.isDirectory()) {
                //删除空文件夹
                DeleteEmptyDir(fss.getPath());
            } else {
                //删除空文件
                if (fss.getLen() == 0) {
                    fs.delete(fss.getPath(), false);
                }
            }
        }
    }

    //该方法用于删除空的文件夹
    private static void DeleteEmptyDir(Path path) throws Exception {
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);
        FileStatus[] fst = fs.listStatus(path);
        //判断该文件夹是否为空
        if (fst.length == 0) {
            fs.delete(path, false);
        }
    }
}