hadoop_wordcount_1027

MyMap

package s26;

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;


public class MyMap extends Mapper<LongWritable,Text,Text,IntWritable> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //super.map(key, value, context);
        Text result = new Text();
        IntWritable one = new IntWritable(1);

        String line = value.toString();
        String[] words = line.split("	");

        for (String w:words) {
            result.set(w);
            context.write(result,one);
        }

    }
}

MyRed

package s26;

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

import java.io.IOException;

public class MyRed extends Reducer<Text,IntWritable,Text,IntWritable> {

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

    }
}

MyJob

package s26;

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.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class MyJob {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        //1.conf
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://master:9000");

        //2.job
        Job job = Job.getInstance(conf);
        // jar-package
        job.setJarByClass(MyJob.class);
        //
        job.setMapperClass(MyMap.class);
        //
        job.setReducerClass(MyRed.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Integer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //3.io
        Path pin = new Path("/sjw");
        Path pout = new Path("/out");
        //
        FileSystem fs = FileSystem.get(conf);
        if(fs.exists(pout)){
            fs.delete(pout,true);
        }
        FileInputFormat.setInputPaths(job,pin);
        FileOutputFormat.setOutputPath(job,pout);

        //4.run
        job.waitForCompletion(true);


    }
}