storm入门demo测试

组织架构

**

主程序

**

package com.wenglei.storm.demo;

import org.apache.storm.Config;
import org.apache.storm.LocalCluster;
import org.apache.storm.topology.TopologyBuilder;


public class TopologMain {

    public static void main(String[] args) {
        //1. 构建 拓扑关系
        TopologyBuilder builder = new TopologyBuilder();


        builder.setSpout("readFileSpout", new ReadFileSpout());

        builder.setBolt("splitBolt", new SplitBolt()).shuffleGrouping("readFileSpout");

        builder.setBolt("countBolt", new CountBolt()).shuffleGrouping("splitBolt");


        //2.  提交任务 : 2种  1_本地提交  2. 集群提交

        LocalCluster localCluster = new LocalCluster();
        // 参数1: 任务的名称    参数2:  运行的配置  参数3  拓扑图(任务)
        localCluster.submitTopology("wordCount", new Config(), builder.createTopology());

    }
}

数据源

package com.wenglei.storm.demo;

import org.apache.storm.spout.SpoutOutputCollector;
import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.OutputFieldsDeclarer;
import org.apache.storm.topology.base.BaseRichSpout;
import org.apache.storm.tuple.Fields;
import org.apache.storm.tuple.Values;
import java.util.Map;
import java.util.Random;


//读取文件的spout程序
public class ReadFileSpout extends BaseRichSpout{
    //在创建这个 ReadFileSpout对象的时候就会调用这个方法进行初始化
    private SpoutOutputCollector collector;
    // 随机数
    private Random random;
    private String[] users;

    /**
     *
     * @param map 进行对storm配置操作 一般不使用
     * @param topologyContext storm上下文对象，一般不使用
     * @param collector 向下游输出内容对象
     */

    @Override
    public void open(Map map, TopologyContext topologyContext, SpoutOutputCollector collector) {
        this.collector = collector;
        users =new String[]{"1 zhaoliying 18","2 yangmi 19","3 tongliya 20","4 zhangxiulian 24"};
        random = new Random();
    }

    //当任务提交给storm程序后，storm程序会不断的调用
    //nextTuple方法 进行执行  一般在这个方法 循环的读取数据
    @Override
    public void nextTuple() {
            //随机获取一个用户信息
            int i = random.nextInt(users.length);
            String user = users[i];
             collector.emit(new Values(user));
    }

    //数据传输 tuple 看成一个map  本质上是一个list
    @Override
    public void declareOutputFields(OutputFieldsDeclarer outputFieldsDeclarer) {
        outputFieldsDeclarer.declare(new Fields("line"));
    }
}

数据处理的程序

1.数据分割

package com.wenglei.storm.demo;

import org.apache.storm.task.OutputCollector;
import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.OutputFieldsDeclarer;
import org.apache.storm.topology.base.BaseRichBolt;
import org.apache.storm.tuple.Fields;
import org.apache.storm.tuple.Tuple;

import java.util.Arrays;
import java.util.Map;

public class SplitBolt extends BaseRichBolt {
    private OutputCollector outputCollector;


    @Override
    public void prepare(Map map, TopologyContext topologyContext, OutputCollector outputCollector) {
        this.outputCollector=outputCollector;
    }

    @Override
    public void execute(Tuple tuple) {
        //从tuple中获取数据
        String line = tuple.getStringByField("line");
        //切割数据
        String[] words = line.split(" ");
        //获取用户姓名信息，打上 一个标签，向下游传输数据
        outputCollector.emit(Arrays.asList(words[1],1));

    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer outputFieldsDeclarer) {
        outputFieldsDeclarer.declare(new Fields("word","count"));
    }
}

2.数据输出

package com.wenglei.storm.demo;

import org.apache.storm.task.OutputCollector;
import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.OutputFieldsDeclarer;
import org.apache.storm.topology.base.BaseRichBolt;
import org.apache.storm.tuple.Tuple;

import java.util.HashMap;
import java.util.Map;


public class CountBolt extends BaseRichBolt {
    private OutputCollector outputCollector;
    private Map<String,Integer> map = new HashMap<>();

    @Override
    public void prepare(Map map, TopologyContext topologyContext, OutputCollector outputCollector) {
        this.outputCollector=outputCollector;
    }

    @Override
    public void execute(Tuple tuple) {
        //1 从tuple中获取数据
        String word = tuple.getStringByField("word");
        Integer count = tuple.getIntegerByField("count");


        if (map.get(word)!=null){
            Integer wordCount = map.get(word);
            wordCount++;

            map.put(word,wordCount);
        }else {
            map.put(word,count);
        }

        Integer integer = map.get(word);
        System.out.println(word+"   "+integer);
        //System.out.println(map);
    }

    @Override
    public void declareOutputFields(OutputFieldsDeclarer outputFieldsDeclarer) {

    }
}