Hadoop实现字母计数（自写jar，相比昨天）

最新推荐文章于 2021-12-30 15:37:17 发布

左尔@

最新推荐文章于 2021-12-30 15:37:17 发布

阅读量350

点赞数

本文链接：https://blog.csdn.net/SmionFox/article/details/100561076

版权

本文详细介绍了如何使用Hadoop实现字母计数功能，包括map、reduce和driver三个项目的jar打包过程，参考资料来源于CSDN上的相关文章。

摘要由CSDN通过智能技术生成

三个项目实现jar：

1.map

package com.doit.mr;

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.HashMap;

/**
*map程序逐行读取数据，将每一行数据的起始偏移量做为key，类型是LongWritable，将每一行数据的内容做为value(Text),传给我们写的map
经过map阶段的处理，输出的key是Text ,value是IntWritable
调用的机制
1，谁在调用，map再调用
2，怎么调：是在当前mapreduce过程中，每读取一行数据，调用一次map
*/
public class WordCountMap extends Mapper <LongWritable, Text,Text, IntWritable>{
<输入：LongWritable为key的类型，Text为value的类型>
///<输出：Text，，，，，，，，，，，LntWritable,,,,,,,,,,,,,,>
//输入：前俩个，输出：后两个
    @Override
    ///重写方法
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String word = value.toString();
        String[] words = word.split(" ");
        split：用“  ”分块
        for (String w:words
             ) {
             count++；
           } context.write(new Text(w),new IntWritable(1));}}

2Reduce

package com.doit.mr;

import junit.framework.Test;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class WordCountReduce extends Reducer <Text, IntWritable, Text,IntWritable>{
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values ,Context context) throws IOException, InterruptedException {
        Integer count = 0;
        for (IntWritable v: values
             ) {
            count++;
        }context.write(key ,new IntWritable(count));
    }
}

Driver

package com.doit.mr;

import org.apache.hadoop.conf.Configuration;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

import java.io.FileOutputStream;
import java.io.IOException;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        conf.set("yarn.resorcemanager.hostname","node01");
        conf.set("fs.defutFS","hdfs://node01:9000/");
        Job job = Job.getInstance(conf);
        job.setJarByClass(WordCountDriver.class);
        //设置本次job使用map，reduce
        job.setMapperClass(WordCountMap.class);
        job.setReducerClass(WordCountReduce.class);
        //设置本次map和reduce的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //指定本次job读取数据源时需要的组件：我们的原文件在hdsf中，用TextInputFormat
        job.setInputFormatClass(TextInputFormat.class);
        //制定本次job输出数据需要的组件：我们要输出到hdfs文件中，用TextOutputFormat
        job.setOutputFormatClass(TextOutputFormat.class);
        //设置输入路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
        //提交任务，客户端返回
        job.submit();
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);


    }
}