The realization of writing wordcount program code by MapReduce

MapReduce Classic case Code (wordcount) takes classic wordcount as an example to implement word counting package com.fwmagic.mapreduce;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Job;import org.apache.hadoop.mapreduce.Mapper;import org.apache.hadoop.mapreduce.Reducer through custom mapper and reducer. Import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import java.io.IOException / * MapReduce word Statistics * / public class WordCountDemo {/ * Custom Mapper inheritance: org.apache.hadoop.mapreduce.Mapper Implement the map method * / public static class WordCountMapper extends Mapper {@ Override protected void map (LongWritable key, Text value, Mapper.Context context) throws IOException, InterruptedException {String [] words = value.toString () .split ("") For (String word: words) {context.write (new Text (word), new IntWritable (1)) }} / * Custom Reducer inheritance: org.apache.hadoop.mapreduce.Reducer, implement reduce method * / public static class WordCountReducer extends Reducer {@ Override protected void reduce (Text key, Iterable values, Reducer.Context context) throws IOException, InterruptedException {int count = 0 For (IntWritable writable: values) {count + = writable.get ();} context.write (key, new IntWritable (count)) }} / * job startup class, set parameters and submit job * @ param args * @ throws Exception * / public static void main (String [] args) throws Exception {Configuration conf = new Configuration (); Job job = Job.getInstance (conf); job.setJarByClass (WordCountDemo.class); job.setMapperClass (WordCountMapper.class); job.setReducerClass (WordCountReducer.class) in the cluster Job.setMapOutputKeyClass (Text.class); job.setMapOutputValueClass (IntWritable.class); job.setOutputKeyClass (Text.class); job.setOutputValueClass (IntWritable.class); FileInputFormat.setInputPaths (job, new Path ("/ wordcount/input")); FileOutputFormat.setOutputPath (job, new Path ("/ wordcount/output")); boolean b = job.waitForCompletion (true); System.exit (b? 0: 1) }} data content under the / wordcount/input directory in the cluster

Package the project and execute the jobhadoop jar fwmagic-wordcount.jar execution to output the results