hadoop wordcount程序代码

/**
* @Copyright: Copyright 2007 - 2017 MPR Tech. Co. Ltd. All Rights Reserved.
* @Description:
*
* Modification History:
* Author: lucius.lv
* Version: 1.0.0.0
* Description: (Initialize)
* Reviewer:
* Review Date:
*/
package com.hbase.hbasetest;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCount {

public static class TokenizerMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
                throws IOException, InterruptedException {
            String line=value.toString();
            String [] words=line.split(" ");
            for(String w:words){
                context.write(new Text(w), new IntWritable(1));
            }
        }




}

public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    private IntWritable result = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context)
            throws IOException, InterruptedException {

            int sum = 0;

            for (IntWritable val : values) {

                sum += val.get();

            }
            result.set(sum);

            context.write(key, result);

    }



}

public static void main(String[] args) throws Exception {

    Configuration conf = new Configuration();
    conf.set("fs.defaultFS", "hdfs://172.16.5.125:9000");

    Job job =Job.getInstance(conf);

    job.setJarByClass(WordCount.class);

    job.setMapperClass(TokenizerMapper.class);

    job.setCombinerClass(IntSumReducer.class);

    job.setReducerClass(IntSumReducer.class);

    job.setMapOutputKeyClass(Text.class);

    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputKeyClass(Text.class);

    job.setOutputValueClass(IntWritable.class);

    FileInputFormat.setInputPaths(job, new Path("/test_words.txt"));

    Path output=new Path("/test/output");

    FileSystem fs=FileSystem.get(conf);
    if(fs.exists(output)){
        fs.delete(output,true);
    }
    FileOutputFormat.setOutputPath(job, output);

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

}

}