Storm--kafka集成

版权声明：未经同意，不得转载。 https://blog.csdn.net/qq_36235275/article/details/82155013

Bolt1:

package com.jiangnan.storm.kafka;

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

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

//统计通话次数。
public class WordCounterBolt implements  IRichBolt{
	private static final long serialVersionUID = 1L;
	private OutputCollector collector;
	private Map<String, Integer> countMap;
	@Override
	public void prepare(Map stormConf, TopologyContext context, OutputCollector collector) {
		this.collector = collector;
		countMap = new HashMap<String, Integer>();
	}

	@Override
	public void execute(Tuple input) {
		String word = input.getString(0);
		
		if(countMap.containsKey(word)) {
			countMap.put(word, countMap.get(word)+1);
		}else {
			countMap.put(word, 1);
		}
		//确认元组数据已经处理完毕
		collector.ack(input);
		System.out.println(countMap);
	}

	@Override
	public void cleanup() {
		
	}

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

	@Override
	public Map<String, Object> getComponentConfiguration() {
		// TODO Auto-generated method stub
		return null;
	}

}

Bolt2:

package com.jiangnan.storm.kafka;

import java.util.Map;

import org.apache.storm.task.OutputCollector;
import org.apache.storm.task.TopologyContext;
import org.apache.storm.topology.IRichBolt;
import org.apache.storm.topology.OutputFieldsDeclarer;
import org.apache.storm.tuple.Fields;
import org.apache.storm.tuple.Tuple;
import org.apache.storm.tuple.Values;

//创建数据切分，产生一个一个的单词
public class WordCountSplitBolt implements IRichBolt{
	
	private OutputCollector collector;

	/**
	 * 为bolt提供要执行的环境，初始化bolt
	 */
	@Override
	public void prepare(Map conf, TopologyContext context, OutputCollector collector) {
		this.collector = collector;
		
	}

	//处理输入元组
	@Override
	public void execute(Tuple input) {
		System.out.println(input.getFields());
		//input的字段为[topic, partition, offset, key, value]，对应的value为第4个
		String line = input.getString(4);
		String[] words = line.split(" ");
		for(String word:words) {
			word = word.trim();
			if(!word.isEmpty()) {
				word = word.toLowerCase();
				collector.emit(new Values(word));
			}
		}
		
	}

	//清理工作
	@Override
	public void cleanup() {
		// TODO Auto-generated method stub
		
	}

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

	@Override
	public Map<String, Object> getComponentConfiguration() {
		// TODO Auto-generated method stub
		return null;
	}

}

Spout(main):

package com.jiangnan.storm.kafka;

import org.apache.storm.Config;
import org.apache.storm.LocalCluster;
import org.apache.storm.StormSubmitter;
import org.apache.storm.kafka.spout.KafkaSpout;
import org.apache.storm.kafka.spout.KafkaSpoutConfig;
import org.apache.storm.topology.TopologyBuilder;
import org.apache.storm.tuple.Fields;

public class WordCountApp {

	public static void main(String[] args) throws Exception {
		
		Config conf = new Config();
		conf.setNumWorkers(2);
		conf.setDebug(true);
		//创建拓扑对象
		TopologyBuilder builder = new TopologyBuilder();
		
		String topic = "stormKafka";
		builder.setSpout("kafka_spout", new KafkaSpout<>(KafkaSpoutConfig.builder("master:9092", topic).build()));
		
		
		
		builder.setBolt("wordcount-split-bolt", new WordCountSplitBolt())
			   .shuffleGrouping("kafka_spout");
		
		builder.setBolt("wordcount-counter-bolt", new WordCounterBolt())
		       .fieldsGrouping("wordcount-split-bolt", new Fields("word"));
		
		//LocalCluster cluster = new LocalCluster();
		//cluster.submitTopology("www", conf, builder.createTopology());
		StormSubmitter.submitTopology("wwwwww", conf, builder.createTopology());
	}
}

所需jar包：