Hadoop Mapreduce模板

Mapper

package com.scb.jason.mapper;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;
import java.util.StringTokenizer;

/**
 * Created by Administrator on 2017/7/23.
 */
// Step 1: Map Class
public class WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable> {

    private Text mapOutputkey =  new Text();
    private final static IntWritable mapOutputValue = new IntWritable(1);

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        super.setup(context);
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String lineValue = value.toString();
        StringTokenizer stringTokenizer = new StringTokenizer(lineValue);
        while(stringTokenizer.hasMoreTokens()){
            String wordValue = stringTokenizer.nextToken();
            mapOutputkey.set(wordValue);
            context.write(mapOutputkey,mapOutputValue);
        }
    }

    @Override
    protected void cleanup(Context context) throws IOException, InterruptedException {
        super.cleanup(context);
    }

    @Override
    public void run(Context context) throws IOException, InterruptedException {
        super.run(context);
    }
}

---

Reducer

package com.scb.jason.reducer;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * Created by Administrator on 2017/7/23.
 */
// Step 2: Reduce Class
public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {

    private IntWritable outputValue = new IntWritable();

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        super.setup(context);
    }

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for(IntWritable value:values){
            sum += value.get();
        }
        outputValue.set(sum);
        context.write(key,outputValue);
    }

    @Override
    protected void cleanup(Context context) throws IOException, InterruptedException {
        super.cleanup(context);
    }

    @Override
    public void run(Context context) throws IOException, InterruptedException {
        super.run(context);
    }
}

---

Driver

package com.scb.jason.driver;

import com.scb.jason.mapper.WordCountMapper;
import com.scb.jason.reducer.WordCountReducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;

/**
 * Created by Administrator on 2017/7/17.
 */
public class WordCount extends Configured implements Tool {

    // Step 3: Driver
    public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration configuration = new Configuration();
        FileSystem fs = FileSystem.get(configuration);

        Job job = Job.getInstance(configuration,this.getClass().getSimpleName());
        job.setJarByClass(this.getClass());

        Path input = new Path(args[0]);
        FileInputFormat.addInputPath(job,input);

        job.setMapperClass(WordCountMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setReducerClass(WordCountReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        Path outPath = new Path(args[1]);
        if(fs.exists(outPath)){
            fs.delete(outPath,true);
        }
        FileOutputFormat.setOutputPath(job,outPath);

        boolean isSuccess = job.waitForCompletion(true);
        return isSuccess?1:0;
    }

    public static void main(String[] args) throws Exception {
        int exitCode = ToolRunner.run(new WordCount(),args);
        System.exit(exitCode);
    }

}

---