使用JavaAPI获取文件信息

package demo;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.Arrays;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.BlockLocation;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.junit.Test;
public class TestMetaData {
    @Test
    public void test1() throws Exception{
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://bigdata11:9000");
        FileSystem client = FileSystem.get(conf);
        FileStatus[] fsList = client.listStatus(new Path("/folder1"));
        for(FileStatus s:fsList) {
            System.out.println("文件还是目录?"+(s.isDirectory()? "目录" : "文件"));
            System.out.println(s.getPath().toString());
        }
    }
    //获取文件的数据块信息
    @Test
    public void test2() throws Exception{
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://bigdata11:9000");
        //创建HDFS的客户端
        FileSystem client = FileSystem.get(conf);
        //获取文件的信息
        FileStatus fs = client.getFileStatus(new Path("/folder1/a.txt"));
        BlockLocation[] blkLocations = client.getFileBlockLocations(fs,0,fs.getLen());
        for(BlockLocation b : blkLocations) {
            //数据块的主机信息：数组，表示同一个数据块的多个副本(冗余)被保存到了不同的主机上
            System.out.println(Arrays.toString(b.getHosts()));
            //获取的数据块的名称
            System.out.println(Arrays.toString(b.getNames()));
        }
    }

}

原文地址：https://www.cnblogs.com/JasonPeng1/p/12547583.html