example hadoop

main.java

package com.mycompany.emr;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
import org.apache.hadoop.mapreduce.lib.db.DBInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.log4j.Logger;

import com.mycompany.emr.model.EmployeeRecord;

public class Main {
  
	private static String JOB_NAME = "DB WordCount";
	private static String MYSQL_DRIVER = "com.mysql.jdbc.Driver";
	private static String DB_NAME = "jdbc:mysql://localhost/company";
	private static String DB_USER = {your_db_username};
	private static String DB_PASS = {your_db_password};
    private static String TABLE_NAME = "employee";
    private static String PRIMARY_ID = "id";
	
    public static void main( String[] args ) throws Exception {
    	
    	Configuration conf = new Configuration();
    	
        Job job = new Job(conf, JOB_NAME);
        job.setJarByClass(Map.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        
        job.setInputFormatClass(DBInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        
        DBConfiguration.configureDB(job.getConfiguration(), MYSQL_DRIVER, DB_NAME, DB_USER, DB_PASS);
        
        String [] fields = { "id", "title" };      
        DBInputFormat.setInput(job, SerializableBookMetadata.class, TABLE_NAME, null , PRIMARY_ID, fields);
        
        FileOutputFormat.setOutputPath(job, new Path(args[0]));
        
        System.exit(job.waitForCompletion(true)? 0 : 1);
    }
}