HadoopHadoop mr wordcount基础

Posted 2020-08-07 junneyang 的博客

1、基本概念

2、Mapper

package com.ares.hadoop.mr.wordcount;

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

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

//Long, String, String, Long --> LongWritable, Text, Text, LongWritable
public class WordCountMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
    private final static LongWritable ONE = new LongWritable(1L) ;
    private Text word = new Text();
    
    @Override
    protected void map(LongWritable key, Text value,
            Mapper<LongWritable, Text, Text, LongWritable>.Context context)
            throws IOException, InterruptedException {
        // TODO Auto-generated method stub
        //super.map(key, value, context);
        StringTokenizer itr = new StringTokenizer(value.toString(), " ");
        while (itr.hasMoreTokens()) {
            //efficiency is not well
            //context.write(new Text(itr.nextToken()), new LongWritable(1L));
            word.set(itr.nextToken());
            context.write(word, ONE);            
        }
    }
}

3、Reducer

package com.ares.hadoop.mr.wordcount;

import java.io.IOException;

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

public class WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable>{
    private LongWritable result = new LongWritable();
    
    @Override
    protected void reduce(Text key, Iterable<LongWritable> vlaues,
            Reducer<Text, LongWritable, Text, LongWritable>.Context context)
            throws IOException, InterruptedException {
        // TODO Auto-generated method stub
        //super.reduce(arg0, arg1, arg2);
        long sum = 0;
        for (LongWritable value : vlaues) {
            sum += value.get();
        }
        result.set(sum);
        context.write(key, result);
    }
}

4、JobRunner

package com.ares.hadoop.mr.wordcount;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.log4j.Logger;

public class MRTest {
    private static final Logger LOGGER = Logger.getLogger(MRTest.class);
    
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        LOGGER.debug("MRTest: MRTest STARTED...");
        
        if (args.length != 2) {
            LOGGER.error("MRTest: ARGUMENTS ERROR");
            System.exit(-1);
        }
        
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        
        // JOB NAME
        job.setJobName("wordcount");
        
        // JOB MAPPER & REDUCER
        job.setJarByClass(MRTest.class);
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        
        // MAP & REDUCE
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        // MAP
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        
        // JOB INPUT & OUTPUT PATH
        //FileInputFormat.addInputPath(job, new Path(args[0]));
        FileInputFormat.setInputPaths(job, args[0]);
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        
        // VERBOSE OUTPUT
        if (job.waitForCompletion(true)) {
            LOGGER.debug("MRTest: MRTest SUCCESSFULLY...");
        } else {
            LOGGER.debug("MRTest: MRTest FAILED...");
        }
        
        LOGGER.debug("MRTest: MRTest COMPLETED...");
    }
}

5、JAR 提交作业 到YARN

hadoop jar wordcount.jar com.ares.hadoop.mr.wordcount.MRTest hdfs://HADOOP-NODE1:9000/word-count/input hdfs://HADOOP-NODE1:9000/word-count/output