Typical Hadoop Template

(From the book Hadoop in Action, Code List_4_1 & 4_3)

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class MyNewJob extends Configured implements Tool {

	public static class MapClass extends Mapper<LongWritable, Text, Text, Text> {

		public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

			String[] citation = value.toString().split(",");
			context.write(new Text(citation[1]), new Text(citation[0]));
		}
	}

	public static class Reduce extends Reducer<Text, Text, Text, Text> {

		public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {

			String csv = "";
			for (Text val:values) {
				if (csv.length() > 0) csv += ",";
				csv += val.toString();
			}

			context.write(key, new Text(csv));
		}
	}

	public int run(String[] args) throws Exception {
		Configuration conf = getConf();

		Job job = new Job(conf, "MyJob");
		job.setJarByClass(MyNewJob.class);

		Path in = new Path(args[0]);
		Path out = new Path(args[1]);
		FileInputFormat.setInputPaths(job, in);
		FileOutputFormat.setOutputPath(job, out);

		job.setMapperClass(MapClass.class);
		job.setReducerClass(Reduce.class);

		job.setInputFormatClass(TextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);

		System.exit(job.waitForCompletion(true)?0:1);

		return 0;
	}

	public static void main(String[] args) throws Exception {
		int res = ToolRunner.run(new Configuration(), new MyNewJob(), args);

		System.exit(res);
	}
}

import java.io.IOException;
import java.util.Iterator;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class MyJob extends Configured implements Tool {

	public static class MapClass extends MapReduceBase
		implements Mapper<Text, Text, Text, Text> {

			public void map(Text key, Text value,
					OutputCollector<Text, Text> output,
					Reporter reporter) throws IOException {

				output.collect(value, key);
			}
		}

	public static class Reduce extends MapReduceBase
		implements Reducer<Text, Text, Text, Text> {

			public void reduce(Text key, Iterator<Text> values,
					OutputCollector<Text, Text> output,
					Reporter reporter) throws IOException {

				String csv = "";
				while (values.hasNext()) {
					if (csv.length() > 0) csv += ",";
					csv += values.next().toString();
				}
				output.collect(key, new Text(csv));
			}
		}

	public int run(String[] args) throws Exception {
		Configuration conf = getConf();

		JobConf job = new JobConf(conf, MyJob.class);

		Path in = new Path(args[0]);
		Path out = new Path(args[1]);
		FileInputFormat.setInputPaths(job, in);
		FileOutputFormat.setOutputPath(job, out);

		job.setJobName("MyJob");
		job.setMapperClass(MapClass.class);
		job.setReducerClass(Reduce.class);

		job.setInputFormat(KeyValueTextInputFormat.class);
		job.setOutputFormat(TextOutputFormat.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		job.set("key.value.separator.in.input.line", ",");

		JobClient.runJob(job);

		return 0;
	}

	public static void main(String[] args) throws Exception { 
		int res = ToolRunner.run(new Configuration(), new MyJob(), args);

		System.exit(res);
	}
}