Hadoop HDFS文件操作的Java代码

1、创建目录

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class MakeDir {
	public static void main(String[] args) throws IOException {
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		Path path = new Path("/user/hadoop/hdfs/xxxx");
		fs.create(path);
		fs.close();
	}
}

2、删除目录

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class DeleteDir {
	public static void main(String[] args) throws IOException {
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		
		Path path = new Path("/user/hadoop/hdfs/xxxx");
		fs.delete(path);
		fs.close();
	}
}

3、写文件

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class WriteFile {
	public static void main(String[] args) throws IOException {
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		Path path = new Path("/user/hadoop/hdfs/xxxx.txt");
		FSDataOutputStream out = fs.create(path);
		out.writeUTF("da jia hao,cai shi zhen de hao!");
		fs.close();
	}
}

4、读文件

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class ReadFile {
	public static void main(String[] args) throws IOException {
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		Path path = new Path("/user/hadoop/hdfs/xxxx.txt");
		
		if(fs.exists(path)){
			FSDataInputStream is = fs.open(path);
			FileStatus status = fs.getFileStatus(path);
			byte[] buffer = new byte[Integer.parseInt(String.valueOf(status.getLen()))];
			is.readFully(0, buffer);
			is.close();
            fs.close();
            System.out.println(buffer.toString());
		}
	}
}

5、上传本地文件到HDFS

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class CopyFromLocalFile {

	public static void main(String[] args) throws IOException {
		
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		Path src = new Path("/home/hadoop/xxxx.txt");
		Path dst = new Path("/user/hadoop/hdfs/");
		fs.copyFromLocalFile(src, dst);
		fs.close();
	}
}

6、删除文件

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class DeleteFile {

	public static void main(String[] args) throws IOException {
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		
		Path path = new Path("/user/hadoop/hdfs/xxxx.txt");
		fs.delete(path);
		fs.close();
	}
}

7、获取给定目录下的所有子目录以及子文件

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class GetAllChildFile {
	static Configuration conf = new Configuration();
	
	
	public static void main(String[] args)throws IOException {
		FileSystem fs = FileSystem.get(conf);
		Path path = new Path("/user/hadoop");
		getFile(path,fs);
		//fs.close();
	}
	
	public static void getFile(Path path,FileSystem fs) throws IOException {
		
		FileStatus[] fileStatus = fs.listStatus(path);
		for(int i=0;i<fileStatus.length;i++){
			if(fileStatus[i].isDir()){
				Path p = new Path(fileStatus[i].getPath().toString());
				getFile(p,fs);
			}else{
				System.out.println(fileStatus[i].getPath().toString());
			}
		}
	}

}

8、查找某个文件在HDFS集群的位置

import java.io.IOException;
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.hdfs.DistributedFileSystem;
import org.apache.hadoop.hdfs.protocol.DatanodeInfo;

public class FindFile {
	
	public static void main(String[] args) throws IOException {	
		getFileLocal();
	}
	
	/**
	 * 查找某个文件在HDFS集群的位置
	 * @Title:  
	 * @Description: 
	 * @param 
	 * @return 
	 * @throws
	 */
	public static void getFileLocal() throws IOException{
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);
		Path path = new Path("/user/hadoop/hdfs/xxxx.txt");
		
		FileStatus status = fs.getFileStatus(path);
		BlockLocation[] locations = fs.getFileBlockLocations(status, 0, status.getLen());
		
		int length = locations.length;
		for(int i=0;i<length;i++){
			String[] hosts = locations[i].getHosts();
			System.out.println("block_" + i + "_location:" + hosts[i]);
		}
	}
	
}

9、HDFS集群上所有节点名称信息

package com.hadoop.file;

import java.io.IOException;
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.hdfs.DistributedFileSystem;
import org.apache.hadoop.hdfs.protocol.DatanodeInfo;

public class FindFile {
	
	public static void main(String[] args) throws IOException {	
		getHDFSNode();
	}
	
	/**
	 * HDFS集群上所有节点名称信息
	 * @Title:  
	 * @Description: 
	 * @param 
	 * @return 
	 * @throws
	 */
	public static void getHDFSNode() throws IOException{
		Configuration conf = new Configuration();
		FileSystem fs = FileSystem.get(conf);

		DistributedFileSystem  dfs = (DistributedFileSystem)fs;
		DatanodeInfo[] dataNodeStats = dfs.getDataNodeStats();
		
		for(int i=0;i<dataNodeStats.length;i++){
			System.out.println("DataNode_" + i + "_Node:" + dataNodeStats[i].getHostName());
		}
		
	}
	
	
}

伪分布环境下操作FileSystem时候会出现异常：　　

Java代码如下：

    FileSystem fs = FileSystem.get(conf); 
    in = fs.open(new Path("hdfs://localhost:9000/wzqSearchEngine/crawl/inject_in")); 

抛出异常如下：

    Exception in thread "main" java.lang.IllegalArgumentException: Wrong FS: hdfs://localhost:9000/wzqSearchEngine/crawl/inject_in, expected: file:/// 
        at org.apache.hadoop.fs.FileSystem.checkPath(FileSystem.java:310) 
        at org.apache.hadoop.fs.RawLocalFileSystem.pathToFile(RawLocalFileSystem.java:47) 
        at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:357) 
        at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:245) 
        at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSInputChecker.<init>(ChecksumFileSystem.java:125) 
        at org.apache.hadoop.fs.ChecksumFileSystem.open(ChecksumFileSystem.java:283) 
        at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:356) 
        at com.netease.hadoop.HDFSCatWithAPI.main(HDFSCatWithAPI.java:23) 

解决方案：
将hadoop的core-site.xml和hdfs-site.xml放到当前工程下（Eclipse工作目录的bin文件夹下面）即可。

总结：

因为是访问远程的HDFS 需要通过URI来获得FileSystem。