分布式wordcount Reduce阶段

package com.ws.wordcount;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.HashMap;

public class WordCountReduce {
    public static void main(String[] args) throws IOException {
        run("0");
    }
    public static void run (String reduceId) throws IOException {
        System.setProperty("HADOOP_USER_NAME","root");
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS","hdfs://dream1:9000");
        FileSystem fs = FileSystem.get(conf);
        RemoteIterator<LocatedFileStatus> filemetas = fs.listFiles(new Path("/wordcount/mapout/"), false);
        if(!fs.exists(new Path("/wordcount/reduceout"))){
            fs.mkdirs(new Path("/wordcount/reduceout/"));
        }
        FSDataInputStream in;
        BufferedReader br;
        String name;
        String line;
        HashMap<String, Integer> resultmap = new HashMap<>();
        while (filemetas.hasNext()){
            name = filemetas.next().getPath().getName();
            if(name.split("\\.")[0].endsWith(reduceId)){
               in = fs.open(new Path("/wordcount/mapout/" + name));
               br = new BufferedReader(new InputStreamReader(in));
               while ((line=br.readLine()) != null){
                   for (String word : line.split("\001")) {
                     resultmap.put(word,resultmap.getOrDefault(word,0)+1);
                   }
               }
            }
        }
        FSDataOutputStream out = fs.create(new Path("/wordcount/reduceout/reduce"+reduceId+".txt"));
        for (String key : resultmap.keySet()) {
            out.write((key+"有"+resultmap.get(key)+"个\n").getBytes());
        }
    }
}

 

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值