MapReduce(一)

wordcount

mapreduce的阶段
MAP 分区 排序 规约 分组 Reduce

map

package com.example;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.nio.file.Path;
import java.util.HashMap;
import java.util.Map;

/* k1     v1
 * 0      hello,world
 * 11     hello,HDFS
 * -----------------------
 * k2     v2
 * hello   1
 * world   1
 * hello   1
 */

public class jobMapper extends Mapper<LongWritable, Text,Text,LongWritable> {
    Text k=new Text();
    LongWritable v=new LongWritable(1);

    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] line = value.toString().split(" ");

        for (String s : line) {
            k.set(s);
            context.write(k,v);
        }

    }
}

reduce

package com.example;

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

import java.awt.*;
import java.io.IOException;
import java.util.Iterator;

/*
 * k2     v2
 * hello   1
 * world   1
 * hello   1
 * -------------------
 */
public class jobReduce extends Reducer<Text, LongWritable,Text,LongWritable> {
    protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
        //Long sum=0L;
        //for (LongWritable value : values) {
        //    sum+=value.get();
        //}
        //context.write(key,new LongWritable(sum));
        System.out.println("========================================");
        System.out.println("KEY: "+key);
        while (values.iterator().hasNext()) {
            System.out.println("value: "+values.iterator().next());
        }
        System.out.println("========================================");

    }
}

jobmain

package com.example;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;

public class jobMain extends Configured implements Tool {
    public int run(String[] strings) throws Exception {
        Job job = Job.getInstance(super.getConf(),"xxxxxx");
        job.setJarByClass(jobMain.class);

        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("/tmp/README.txt"));
        job.setMapperClass(jobMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        //分区 排序 规约 分组

        // job.addCacheFile(new Path("/tmp/xxx").toUri());  //将hdfs文件(精确到文件) 缓存到NM 本地

        //job.setNumReduceTasks(0);
        job.setReducerClass(jobReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        //设置输出类
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("/tmp/out1"));
        boolean b = job.waitForCompletion(true);
        return b?0:1;
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        int run = ToolRunner.run(conf,new jobMain(), args);
        System.out.println(run);
    }


}