Setting replication factor for a file programmatically

I wanted to figure out how to set/change replication factor for a file stored in HDFS, so i built this sample program, which has 3 methods

• read(): This method takes a file path as input and print its content to system console
• write(): This method takes a file path as input and open it for writing. It takes user input and writes that to the HDFS file
• setReplication(): This method takes file path and replication factor as input and sets the replication factor for the given file path

	package com.spnotes.hadoop;
	import org.apache.commons.io.IOUtils;
	import org.apache.hadoop.conf.Configuration;
	import org.apache.hadoop.fs.FileSystem;
	import org.apache.hadoop.fs.Path;
	import org.apache.hadoop.hdfs.DistributedFileSystem;
	import java.io.*;
	import java.net.URI;
	import java.util.Scanner;
	/**
	* Created by user on 7/1/14.
	*/
	public class HelloHDFS {
	public static void main(String[] argv) throws Exception{
	if(argv.length != 2){
	System.out.println("Use HelloHDFS read/write/replicate path");
	System.exit(-1);
	}
	String command = argv[0];
	String filePath = argv[1];
	Configuration conf = new Configuration();
	DistributedFileSystem dfs = (DistributedFileSystem)FileSystem.get(URI.create(filePath),conf);
	HelloHDFS hdfsClient = new HelloHDFS();
	if(command.equals("read")){
	hdfsClient.read(dfs,filePath);
	}else if(command.equals("write")){
	hdfsClient.write(dfs, filePath);
	}else if(command.equals("replicate")){
	hdfsClient.setReplication(dfs,filePath);
	}
	}
	private void read(DistributedFileSystem fs, String path)throws IOException{
	System.out.println("Entering HelloHDFS.read()");
	InputStream in = null;
	try{
	in = fs.open(new Path(path) );
	IOUtils.copy(in, System.out);
	}finally{
	IOUtils.closeQuietly(in);
	}
	System.out.println("Entering HelloHDFS.read()");
	}
	private void write(DistributedFileSystem fs, String filePath)throws IOException{
	System.out.println("Entering HelloHDFS.write()");
	OutputStreamWriter out = null;
	try{
	out = new OutputStreamWriter(fs.create(new Path(filePath)));
	BufferedReader br = new BufferedReader(new InputStreamReader(System.in));
	String line = br.readLine();
	while(line != null){
	if(line.equals("endfile")){
	break;
	}
	line = br.readLine();
	IOUtils.write(line,out);
	}
	}finally{
	out.close();
	}
	System.out.println("Entering HelloHDFS.wite()");
	}
	private void setReplication(DistributedFileSystem dfs, String filePath)throws IOException{
	System.out.println("Entering HelloHDFS.setReplicationFactor()");
	Scanner reader = new Scanner(System.in);
	System.out.println("Enter replication factor:");
	short replicationFactor = reader.nextShort();
	dfs.setReplication(new Path(filePath),replicationFactor);
	System.out.println("Entering HelloHDFS.setReplicationFactor()");
	}
	}

view raw HelloHDFS.java hosted with ❤ by GitHub

Once you build the jar you can execute it by using command like this

java -jar target/HelloHDFS-jar-with-dependencies.jar read <hdfsfile_path>

Ex. In my case i have aesop.txt at hdfs://localhost/user/user/aesop.txt so i can print it by using following command

java -jar target/HelloHDFS-jar-with-dependencies.jar read aesop.txt