We start by exploring a simple Hadoop job with Mapper only. The Mapper outputs only keys starting with A.

MapperOnlyHadoopJob.java

import java.io.IOException;
 
import org.apache.hadoop.conf.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.*;
import org.apache.hadoop.mapreduce.lib.output.*;
import org.apache.hadoop.util.*;
 
public class MapperOnlyHadoopJob extends Configured implements Tool {
  // Mapper
  public static class TheMapper extends Mapper<Text, Text, Text, Text>{
    public void setup(Context context) {
    }
 
    public void map(Text key, Text value, Context context) throws IOException, InterruptedException {
      if (key.getLength() > 0 && Character.toUpperCase(key.charAt(0)) == 'A') {
        context.write(key, value);
      }
    }
 
    public void cleanup(Context context) {
    } 
  }
 
  // Job configuration
  public int run(String[] args) throws Exception {
    if (args.length < 2) {
      System.err.printf("Usage: %s.jar in-path out-path", this.getClass().getName());
      return 1;
    }
 
    Job job = new Job(getConf(), this.getClass().getName());
 
    job.setJarByClass(this.getClass());
    job.setMapperClass(TheMapper.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
 
    job.setInputFormatClass(KeyValueTextInputFormat.class);
 
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
 
    return job.waitForCompletion(true) ? 0 : 1;
  }
 
  // Main method
  public static void main(String[] args) throws Exception {
    int res = ToolRunner.run(new MapperOnlyHadoopJob(), args);
 
    System.exit(res);
  }
}