Hadoop Tutorial - YDN https://developer.yahoo.com/hadoop/tutorial/module4.html
import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; 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.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class test { public static class Map extends Mapper<Object, Text, Text, IntWritable>{ private IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException { String inputValue=value.toString();//input context.write(word, one);//output } } public static class Reduce extends Reducer<Text,IntWritable,Text,Text> { private Text result = new Text("reduce"); public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { for (IntWritable val : values) { val.get();//get number val.toString();//get string val.toString().getBytes();//get byte[] } context.write(key, result); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: <in> <out>"); System.exit(2); } Job job = Job.getInstance(conf, "job name"); job.setJarByClass(test.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }