Hadoop大数据单词统计

编写WordCount数单词程序

0x00启动hadoop集群

shell脚本编写：

vim start

#!/bin/bash
/opt/hadoop-2.6.0-cdh5.6.0/sbin/start-all.sh

给脚本加权限

chmod 777 start

执行脚本

./start

0x01新建文件夹并编写程序

创建文件夹

mkdir -p /opt/test2/com/hellohadoop/

单词计数Mapper类

vim TokenizerMapper.java

package com.hellohadoop;

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class TokenizerMapper extends Mapper<LongWritable,Text,Text,IntWritable>{
   
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    public void map(LongWritable key,Text value,Context context) throws
        IOException, InterruptedException {