普通事务ITransactionalSpout实例之按天统计数据

1、普通事务Spout

/**
 * 普通事务Spout
 */
public class MyTxSpout implements ITransactionalSpout<MyMata>{

	
	private static final long serialVersionUID = 1L;
	
	
	/**
	 * 数据源
	 */
	Map<Long, String> dbMap  = null;
	public MyTxSpout()
	{
		Random random = new Random();
		dbMap = new HashMap<Long, String> ();
		String[] hosts = { "www.taobao.com" };
		String[] session_id = { "ABYH6Y4V4SCVXTG6DPB4VH9U123", "XXYH6YCGFJYERTT834R52FDXV9U34", "BBYH61456FGHHJ7JL89RG5VV9UYU7",
				"CYYH6Y2345GHI899OFG4V9U567", "VVVYH6Y4V4SFXZ56JIPDPB4V678" };
		String[] time = { "2014-01-07 08:40:50", "2014-01-07 08:40:51", "2014-01-07 08:40:52", "2014-01-07 08:40:53", 
				"2014-01-07 09:40:49", "2014-01-07 10:40:49", "2014-01-07 11:40:49", "2014-01-07 12:40:49" };
		
		for (long i = 0; i < 100; i++) {
			dbMap.put(i,hosts[0]+"\t"+session_id[random.nextInt(5)]+"\t"+time[random.nextInt(8)]);
		}
	}
	
	

	public void declareOutputFields(OutputFieldsDeclarer declarer) {
		declarer.declare(new Fields("tx","log"));
	}

	public Map<String, Object> getComponentConfiguration() {
		return null;
	}

	public org.apache.storm.transactional.ITransactionalSpout.Coordinator<MyMata> getCoordinator(Map conf,
			TopologyContext context) {
		/**
		 * 发射该metadata（事务tuple）到“batch emit”流
		 */
		return new MyCoordinator();
	}

	public org.apache.storm.transactional.ITransactionalSpout.Emitter<MyMata> getEmitter(Map conf,
			TopologyContext context) {
		/**
		 * 逐个发射实际batch的tuple
		 */
		return new MyEmitter(dbMap);
	}

}

2、事务Spout创建一个新的事务（元数据）metadata
  2、1元数据定义

public class MyMata implements Serializable{

	/**
	 * metadata(元数据)中包含当前事务可以从哪个point进行重放数据，存放在zookeeper中的，spout可以通过Kryo从zookeeper中序列化和反序列化该元数据。 
	 */
	private static final long serialVersionUID = 1L;
	
	private long beginPoint ;//事务开始位置

	private int num ;//batch 的tuple个数
	@Override
	public String toString() {
		return getBeginPoint()+"----"+getNum();
	}
	
	public long getBeginPoint() {
		return beginPoint;
	}

	public void setBeginPoint(long beginPoint) {
		this.beginPoint = beginPoint;
	}

	public int getNum() {
		return num;
	}

	public void setNum(int num) {
		this.num = num;
	}
	
	
}

2、2 获得（元数据）metadata，逐个发射实际batch的tuple

public class MyEmitter implements ITransactionalSpout.Emitter<MyMata> {

	Map<Long, String> dbMap = null;

	public MyEmitter(Map<Long, String> dbMap) {
		this.dbMap = dbMap;
	}

	//逐个发射实际batch的tuple
	public void emitBatch(TransactionAttempt tx, MyMata coordinatorMeta, BatchOutputCollector collector) {

		long beginPoint = coordinatorMeta.getBeginPoint();// 从上一个批次获得开始位置

		int num = coordinatorMeta.getNum();// 从批次中获取批次数量

		for (long i = beginPoint; i < num + beginPoint; i++) {
			if (dbMap.get(i) == null) {
				continue;
			}
			collector.emit(new Values(tx, dbMap.get(i)));
		}

	}

	public void cleanupBefore(BigInteger txid) {

	}

	public void close() {

	}

}

------------------------spout与上篇相同-----------------------------------------

3、按天统计数据事务Bolt，会从Emitter接收数据处理，处理完成，提交给finishBatch方法处理。

public class MyDailyBatchBolt implements IBatchBolt<TransactionAttempt> {

	/**
	 * 按天统计数据
	 */
	private static final long serialVersionUID = 1L;
	Map<String, Integer> countMap = new HashMap<String, Integer>();
	BatchOutputCollector collector ;
	Integer count = null;
	String today = null;
	TransactionAttempt tx = null;
	@Override
	public void execute(Tuple tuple) {
		// TODO Auto-generated method stub
		String log = tuple.getString(1);
		tx = (TransactionAttempt)tuple.getValue(0);
		if (log != null && log.split("\\t").length >=3 ) {
			today = DateFmt.getCountDate(log.split("\\t")[2], DateFmt.date_short) ;
			count = countMap.get(today);
			if(count == null)
			{
				count = 0;
			}
			count ++ ;
			
			countMap.put(today, count);
		}
	}

	@Override
	public void finishBatch() {
		collector.emit(new Values(tx,today,count));
	}

	@Override
	public void prepare(Map conf, TopologyContext context,
			BatchOutputCollector collector, TransactionAttempt id) {
		// TODO Auto-generated method stub
		this.collector = collector;
		
	}

	@Override
	public void declareOutputFields(OutputFieldsDeclarer declarer) {
		// TODO Auto-generated method stub
		declarer.declare(new Fields("tx","date","count"));
	}

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

}

4、接收统计数据，累加汇总MyDailyCommitterBolt，batch之间强制按照顺序进行提交

public class MyDailyCommitterBolt extends BaseTransactionalBolt implements ICommitter{

	/**
	 * 接收统计数据，累加汇总
	 */
	private static final long serialVersionUID = 1L;
	public static final String GLOBAL_KEY = "GLOBAL_KEY";
	public static Map<String, DbValue> dbMap = new HashMap<String, DbValue>() ;
	
	Map<String, Integer> countMap = new HashMap<String, Integer>();
	TransactionAttempt id ;
	BatchOutputCollector collector;
	String today = null;
	@Override
	public void execute(Tuple tuple) {
		today = tuple.getString(1) ;
		Integer count = tuple.getInteger(2);
		id = (TransactionAttempt)tuple.getValue(0);
		
		if (today !=null && count != null) {
			Integer batchCount = countMap.get(today) ;
			if (batchCount == null) {
				batchCount = 0;
			}
			batchCount += count ;
			countMap.put(today, batchCount);
		}
	}

	@Override
	public void finishBatch() {
		// TODO Auto-generated method stub
		if (countMap.size() > 0) {
			DbValue value = dbMap.get(GLOBAL_KEY);
			DbValue newValue ;
			if (value == null || !value.txid.equals(id.getTransactionId())) {
				//更新数据库
				newValue = new DbValue();
				newValue.txid = id.getTransactionId() ;
				newValue.dateStr = today;
				if (value == null) {
					newValue.count = countMap.get(today) ;
				}else {
					newValue.count = value.count + countMap.get("2014-01-07") ;
				}
				dbMap.put(GLOBAL_KEY, newValue);
			}else
			{
				newValue = value;
			}
		}
		
		System.out.println("total==========================:"+dbMap.get(GLOBAL_KEY).count);
//		collector.emit(tuple)
	}

	@Override
	public void prepare(Map conf, TopologyContext context,
			BatchOutputCollector collector, TransactionAttempt id) {
		// TODO Auto-generated method stub
		this.id = id ;
		this.collector = collector;
	}

	@Override
	public void declareOutputFields(OutputFieldsDeclarer declarer) {
		// TODO Auto-generated method stub

	}
	public static class DbValue
	{
		BigInteger txid;
		int count = 0;
		String dateStr;
	}

}

5、topo类

public class MyDailyTopo {

	/**
	 * @param args
	 */
	public static void main(String[] args) {
		// TODO Auto-generated method stub

		TransactionalTopologyBuilder builder = new TransactionalTopologyBuilder("ttbId","spoutid",new MyTxSpout(),1);
		builder.setBolt("bolt1", new MyDailyBatchBolt(),3).shuffleGrouping("spoutid");
		builder.setBolt("committer", new MyDailyCommitterBolt(),1).shuffleGrouping("bolt1") ;
		
		Config conf = new Config() ;
		conf.setDebug(true);

		if (args.length > 0) {
			try {
				StormSubmitter.submitTopology(args[0], conf, builder.buildTopology());
			} catch (AlreadyAliveException e) {
				e.printStackTrace();
			} catch (InvalidTopologyException e) {
				e.printStackTrace();
			}
		}else {
			LocalCluster localCluster = new LocalCluster();
			localCluster.submitTopology("mytopology", conf, builder.buildTopology());
		}
		
		
		
		
	}

}

6、测试结果

引用

启动一个事务：0----10
total==========================:10
启动一个事务：10----10
total==========================:20
启动一个事务：20----10
total==========================:30