storm实战入门
1、SimpleSpout类继承BaseRichSpout类，用来产生数据并且向topology里面发出消息：tuple。
package com.ljq.helloword;
import java.util.Map;
import java.util.Random;
import backtype.storm.spout.SpoutOutputCollector;
import backtype.storm.task.TopologyContext;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.base.BaseRichSpout;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Values;
/**
* Spout起到和外界沟通的作用，他可以从一个数据库中按照某种规则取数据，也可以从分布式队列中取任务
*
* @author Administrator
*
*/
@SuppressWarnings("serial")
public class SimpleSpout extends BaseRichSpout{
//用来发射数据的工具类
private SpoutOutputCollector collector;
private static String[] info = new String[]{
"comaple\t,12424,44w46,654,12424,44w46,654,",
"lisi\t,435435,6537,12424,44w46,654,",
"lipeng\t,45735,6757,12424,44w46,654,",
"hujintao\t,45735,6757,12424,44w46,654,",
"jiangmin\t,23545,6457,2455,7576,qr44453",
"beijing\t,435435,6537,12424,44w46,654,",
"xiaoming\t,46654,8579,w3675,85877,077998,",
"xiaozhang\t,9789,788,97978,656,345235,09889,",
"ceo\t,46654,8579,w3675,85877,077998,",
"cto\t,46654,8579,w3675,85877,077998,",
"zhansan\t,46654,8579,w3675,85877,077998,"};
Random random=new Random();
/**
* 初始化collector
*/
public void open(Map conf, TopologyContext context, SpoutOutputCollector collector) {
this.collector = collector;
}
/**
* 在SpoutTracker类中被调用，每调用一次就可以向storm集群中发射一条数据（一个tuple元组），该方法会被不停的调用
*/
@Override
public void nextTuple() {
try {
String msg = info[random.nextInt(11)];
// 调用发射方法
collector.emit(new Values(msg));
// 模拟等待100ms
Thread.sleep(100);
} catch (InterruptedException e) {
e.printStackTrace();
}
}
/**
* 定义字段id，该id在简单模式下没有用处，但在按照字段分组的模式下有很大的用处。
* 该declarer变量有很大作用，我们还可以调用declarer.declareStream();来定义stramId，该id可以用来定义更加复杂的流拓扑结构
*/
@Override
public void declareOutputFields(OutputFieldsDeclarer declarer) {
declarer.declare(new Fields("source")); //collector.emit(new Values(msg));参数要对应
}
}package com.ljq.helloword;
import backtype.storm.topology.BasicOutputCollector;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.topology.base.BaseBasicBolt;
import backtype.storm.tuple.Fields;
import backtype.storm.tuple.Tuple;
import backtype.storm.tuple.Values;
/**
* 接收喷发节点(Spout)发送的数据进行简单的处理后，发射出去。
*
* @author Administrator
*
*/
@SuppressWarnings("serial")
public class SimpleBolt extends BaseBasicBolt {
public void execute(Tuple input, BasicOutputCollector collector) {
try {
String msg = input.getString(0);
if (msg != null){
//System.out.println("msg="+msg);
collector.emit(new Values(msg + "msg is processed!"));
}
} catch (Exception e) {
e.printStackTrace();
}
}
public void declareOutputFields(OutputFieldsDeclarer declarer) {
declarer.declare(new Fields("info"));
}
}3、SimpleTopology类包含一个main函数，是Storm程序执行的入口点，包括一个数据喷发节点spout和一个数据处理节点bolt。
package com.ljq.helloword;
import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.StormSubmitter;
import backtype.storm.topology.TopologyBuilder;
/**
* 定义了一个简单的topology，包括一个数据喷发节点spout和一个数据处理节点bolt。
*
* @author Administrator
*
*/
public class SimpleTopology {
public static void main(String[] args) {
try {
// 实例化TopologyBuilder类。
TopologyBuilder topologyBuilder = new TopologyBuilder();
// 设置喷发节点并分配并发数，该并发数将会控制该对象在集群中的线程数。
topologyBuilder.setSpout("SimpleSpout", new SimpleSpout(), 1);
// 设置数据处理节点并分配并发数。指定该节点接收喷发节点的策略为随机方式。
topologyBuilder.setBolt("SimpleBolt", new SimpleBolt(), 3).shuffleGrouping("SimpleSpout");
Config config = new Config();
config.setDebug(true);
if (args != null && args.length > 0) {
config.setNumWorkers(1);
StormSubmitter.submitTopology(args[0], config, topologyBuilder.createTopology());
} else {
// 这里是本地模式下运行的启动代码。
config.setMaxTaskParallelism(1);
LocalCluster cluster = new LocalCluster();
cluster.submitTopology("simple", config, topologyBuilder.createTopology());
}
} catch (Exception e) {
e.printStackTrace();
}
}
}