HADOOP java客户端的使用

一、一般操作

package hdfs;

import java.io.FileNotFoundException;
import java.io.IOException;
import java.net.URI;
import java.util.Iterator;
import java.util.Map.Entry;

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.LocatedFileStatus;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.RemoteIterator;
import org.junit.Before;
import org.junit.Test;
/**
 * 
 * 客户端去操作hdfs时，是有一个用户身份的
 * 默认情况下，hdfs客户端api会从jvm中获取一个参数来作为自己的用户身份：-DHADOOP_USER_NAME=hadoop
 * 也可以在构造客户端fs对象时，通过参数传递进去
 * @author
 *
 */
public class HdfsClientDemo {
	FileSystem fs = null;
	Configuration conf = null;
	@Before
	public void init() throws Exception{
		conf = new Configuration();
		conf.set("fs.defaultFS", "hdfs://vm1:9000");
		conf.set("dfs.replication", "5");
		//拿到一个文件系统操作的客户端实例对象
		fs = FileSystem.get(conf);
		//可以直接传入 uri和用户身份
		fs = FileSystem.get(new URI("hdfs://vm1:9000"),conf,"hadoop");
	}

	/**
	 * 上传文件
	 * @throws Exception
	 */
	@Test
	public void testUpload() throws Exception {
		fs.copyFromLocalFile(new Path("c:/aa.txt"), new Path("/aa.txt"));
		fs.close();
	}
	
	
	/**
	 * 下载文件
	 * @throws Exception
	 */
	@Test
	public void testDownload() throws Exception {
		fs.copyToLocalFile(new Path("/aa.txt"), new Path("d:/"));
		fs.close();
	}
	
	
	/**
	 * 创建目录
	 * @throws Exception
	 */
	@Test
	public void testMkdir() throws Exception {
		boolean mkdirs = fs.mkdirs(new Path("/testmkdir/aaa/bbb"));
		System.out.println(mkdirs);
	}
	
	/**
	 * 删除目录
	 * @throws Exception
	 */
	@Test
	public void testDelete() throws Exception {
		boolean flag = fs.delete(new Path("/testmkdir/aaa"), true);
		System.out.println(flag);
	}
	
	/**
	 * 递归所有文件
	 * @throws Exception
	 */
	@Test
	public void testLs() throws Exception {
		RemoteIterator<LocatedFileStatus> listFiles = fs.listFiles(new Path("/"), true);
		while(listFiles.hasNext()){
			LocatedFileStatus fileStatus = listFiles.next();
			System.out.println("blocksize: " +fileStatus.getBlockSize());
			System.out.println("owner: " +fileStatus.getOwner());
			System.out.println("Replication: " +fileStatus.getReplication());
			System.out.println("Permission: " +fileStatus.getPermission());
			System.out.println("Name: " +fileStatus.getPath().getName());
			System.out.println("------------------");
			BlockLocation[] blockLocations = fileStatus.getBlockLocations();
			for(BlockLocation b:blockLocations){
				System.out.println("块起始偏移量: " +b.getOffset());
				System.out.println("块长度:" + b.getLength());
				//块所在的datanode节点
				String[] datanodes = b.getHosts();
				for(String dn:datanodes){
				System.out.println("datanode:" + dn);
				}
			}
	
		}
		
	}
	
	
}

二、流式操作

package hdfs;

import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.URI;

import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.junit.Before;
import org.junit.Test;


/**
 * 用流的方式来操作hdfs上的文件
 * 可以实现读取指定偏移量范围的数据
 * @author
 *
 */
public class HdfsStreamAccess {
	
	FileSystem fs = null;
	Configuration conf = null;
	
	@Before
	public void init() throws Exception{
		conf = new Configuration();
		//可以直接传入 uri和用户身份
		fs = FileSystem.get(new URI("hdfs://mini1:9000"),conf,"hadoop");
	}
	
	/**
	 * 通过流的方式上传文件到hdfs
	 * @throws Exception
	 */
	@Test
	public void testUpload() throws Exception {
		FSDataOutputStream outputStream = fs.create(new Path("/cc.txt"), true);
		FileInputStream inputStream = new FileInputStream("c:/cc.txt");
		IOUtils.copy(inputStream, outputStream);
	}
	
	/**
	 * 通过流的方式获取hdfs上数据
	 * @throws Exception
	 */
	@Test
	public void testDownLoad() throws Exception {
		FSDataInputStream inputStream = fs.open(new Path("/cc.txt"));
		FileOutputStream outputStream = new FileOutputStream("d:/cc.txt");
		IOUtils.copy(inputStream, outputStream);
	}
	
	/**
	 * 指定偏移量
	 * @throws Exception
	 */
	@Test
	public void testRandomAccess() throws Exception{
		FSDataInputStream inputStream = fs.open(new Path("/cc.txt"));
		inputStream.seek(12);
	        FileOutputStream outputStream = new FileOutputStream("d:/cc2.txt");
		IOUtils.copy(inputStream, outputStream);
	}
	
	/**
	 * 显示hdfs上文件的内容
	 * @throws IOException 
	 * @throws IllegalArgumentException 
	 */
	@Test
	public void testCat() throws IllegalArgumentException, IOException{
		FSDataInputStream in = fs.open(new Path("/cc.txt"));
		IOUtils.copy(in, System.out);
//		IOUtils.copyBytes(in, System.out, 1024);
	}
	
}