Strom的Stream_id

在storm的collector中（如SpoutOutputCollector）会发现 collector.emit() 方法最终调用的是

 public List<Integer> emit(String streamId, List<Object> tuple, Object messageId) {
        return this._delegate.emit(streamId, tuple, messageId);
    }

即有3个参数， stremId , tuple , messageId 。 其中tuple和 messageId 比较好理解，tuple是要发送的 List , messageId是事务id 。下面的 代码来探究一下 streamId是什么

下面的代码是一个简单的 WordCount的程序， 只写了一个语句的发送RandomSentenceSpout 和处理语句的SplitSentenceBolt， 处理语句仅仅把收到的tuple打印出来。

public class WorkCountTopologySimple {

    public static class RandomSentenceSpout extends BaseRichSpout {

        SpoutOutputCollector collector;
        Random rand;
        String[] sentences =null;

        public void open(Map map, TopologyContext topologyContext, SpoutOutputCollector spoutOutputCollector) {
            this.collector = spoutOutputCollector;
            rand = new Random();
            sentences = new String[]{ "the cow jumped over the moon", "an apple a day keeps the doctor away", "four score and seven years ago", "snow white and the seven dwarfs", "i am at two with nature" };

        }

        public void declareOutputFields(OutputFieldsDeclarer outputFieldsDeclarer) {
            outputFieldsDeclarer.declare(new Fields("sentence"));
        }

        public void nextTuple() {
            try {
                Thread.sleep(1000);
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
            String sentence = sentences[rand.nextInt(sentences.length)];
           // System.out.println(sentence);
            this.collector.emit(new Values(sentence));
        }
    }

    public static class SplitSentenceBolt extends BaseRichBolt {

        private OutputCollector collector;

        public void prepare(Map map, TopologyContext topologyContext, OutputCollector outputCollector) {
            collector= outputCollector;
        }

        public void execute(Tuple tuple) {
            String sentence = tuple.getStringByField("sentence");
            System.out.println(sentence);
        }

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


    public static void main(String[] args) throws InterruptedException {
        TopologyBuilder builder = new TopologyBuilder();
        builder.setSpout("spout", new RandomSentenceSpout(), 1);
        builder.setBolt("split", new SplitSentenceBolt(), 2).shuffleGrouping("spout");

        Config conf = new Config();
        LocalCluster cluster = new LocalCluster();
        cluster.submitTopology("word-count", conf, builder.createTopology());
        Thread.sleep(60000);
        cluster.shutdown();

    }
}

观察 SpoutOutputCollector的 emit方法， 发现最终调用的方法是

public List<Integer> emit(List<Object> tuple, Object messageId) {
        return this.emit("default", tuple, messageId);
    }

其中default即 streamid ， 由此可推知：默认情况下，Spout发送到下游Bolt的stream-id，以及Bolt发送到下游Bolt或者接收上游Spout/Bolt的stream-id都是default。

下面的代码指定了 streamid

public class WorkCountTopologySimple {

    public static class RandomSentenceSpout extends BaseRichSpout {

        SpoutOutputCollector collector;
        Random rand;
        String[] sentences =null;

        public void open(Map map, TopologyContext topologyContext, SpoutOutputCollector spoutOutputCollector) {
            this.collector = spoutOutputCollector;
            rand = new Random();
            sentences = new String[]{ "A the cow jumped over the moon", "B an apple a day keeps the doctor away", "four score and seven years ago", "snow white and the seven dwarfs", "i am at two with nature" };

        }

        public void declareOutputFields(OutputFieldsDeclarer outputFieldsDeclarer) {
            outputFieldsDeclarer.declare(new Fields("sentence"));
            outputFieldsDeclarer.declareStream("A-split", new Fields("sentence"));

        }

        public void nextTuple() {
            try {
                Thread.sleep(1000);
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
            String sentence = sentences[rand.nextInt(sentences.length)];
            if(sentence.startsWith("A")){
                this.collector.emit("A-split",new Values(sentence));
            }else {
                this.collector.emit(new Values(sentence));
            }

        }
    }

    public static class SplitSentenceBolt extends BaseRichBolt {

        private OutputCollector collector;



        public void prepare(Map map, TopologyContext topologyContext, OutputCollector outputCollector) {
            collector= outputCollector;
        }

        public void execute(Tuple tuple) {
            String sentence = tuple.getStringByField("sentence");
            System.out.println(sentence);
        }

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


    public static void main(String[] args) throws InterruptedException {
        TopologyBuilder builder = new TopologyBuilder();
        builder.setSpout("spout", new RandomSentenceSpout(), 1);
        builder.setBolt("split", new SplitSentenceBolt(), 2).shuffleGrouping("spout","A-split");

        Config conf = new Config();
        LocalCluster cluster = new LocalCluster();
        cluster.submitTopology("word-count", conf, builder.createTopology());
        Thread.sleep(60000);
        cluster.shutdown();

    }
}

观察输出结果，发现只有A开头的语句被发送到 SplitSentenceBolt

结论

当你声明一个bolt的输入流时，你总是以另一个组件的指定流作为输入。如果你想订阅另一个组件的所有流，你必须分别订阅每一个流。InputDeclarer提供了使用默认流ID订阅流的语法糖，调用declarer.shuffleGrouping(“1”)订阅组件“1”上的默认流，作用等同于declarer.shuffleGrouping(“1”, DEFAULT_STREAM_ID)。

emit方法在默认时，发送的stream_id即为default