Java-based HDFS API Tutorial

In this tutorial I show how to use Java to interact with your Hadoop Distributed File System (HDFS) using libHDFS.

This Java program creates a file named hadoop.txt, writes a short message into it, then reads it back and prints it to the screen. If the file already existed, it is deleted first.

  import java.io.File;
  import java.io.IOException;

  //Import LibHDFS Packages
  import org.apache.hadoop.conf.Configuration;
  import org.apache.hadoop.fs.FileSystem;
  import org.apache.hadoop.fs.FSDataInputStream;
  import org.apache.hadoop.fs.FSDataOutputStream;
  import org.apache.hadoop.fs.Path;

  // Create Class
  public class HDFSExample {
   public static final String FileName = "hadoop.txt";
   public static final String message = "My First Hadoop API call!\n";

   public static void main (String [] args) throws IOException {
     //Initialize new default Hadoop Configuration
     Configuration conf = new Configuration();
     //Initialize new abstract Hadoop FileSystem
     FileSystem fs = FileSystem.get(conf);
     //Specify File Path of Hadoop File System
     Path filenamePath = new Path(theFilename);

     try {
       //Check if file doesn't exist
       if (fs.exists(filenamePath)) {
         // if file exist, remove file first
         fs.delete(filenamePath);
      }
       //Write Configuration to File
       FSDataOutputStream out = fs.create(filenamePath);
       out.writeUTF(message);
       out.close();

       //Open Config file to read
       FSDataInputStream in = fs.open(filenamePath);
       String messageIn = in.readUTF();
       System.out.print(messageIn);
       in.close();
     } catch (IOException ioe) {
       System.err.println("IOException during operation: " + ioe.toString());
       System.exit(1);
     }
  }
 }

For more Information:

Complete JavaDoc for the HDFS API is provided at http://wiki.apache.org/hadoop/LibHDFS