Direct Grouping

2021SC@SDUSC

使用方法（步骤）：

1.上游在prepare方法保存下游bolt的taskId列表

public class SentenceDirectBolt extends BaseRichBolt {
 
    private static final Logger LOGGER = LoggerFactory.getLogger(SentenceDirectBolt.class);
 
    private OutputCollector collector;
 
    private List<Integer> taskIds;
 
    private int numCounterTasks;
 
    public void prepare(Map config, TopologyContext context, OutputCollector collector) {
        this.collector = collector;
        //NOTE 1 这里要取到下游的bolt的taskId，用于emitDirect时指定taskId
        this.taskIds = context.getComponentTasks("count-bolt");
        this.numCounterTasks = taskIds.size();
    }
    //......
}

2.上游在declareOutputFields使用declareStream声明streamId

public class SentenceDirectBolt extends BaseRichBolt {
    //......
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
        declarer.declare(new Fields("word"));
        //NOTE 2 这里要通过declareStream声明direct stream，并指定streamId
        declarer.declareStream("directStreamDemo1",true,new Fields("word"));
        declarer.declareStream("directStreamDemo2",true,new Fields("word"));
    }
}

3.上游采用emitDirect指定下游taskId及streamId

public class SentenceDirectBolt extends BaseRichBolt {
    //......
    public void execute(Tuple tuple) {
        String sentence = tuple.getStringByField("sentence");
        String[] words = sentence.split(" ");
        for(String word : words){
            int targetTaskId = getWordCountTaskId(word);
            LOGGER.info("word:{} choose taskId:{}",word,targetTaskId);
            // NOTE 3 这里指定发送给下游bolt的哪个taskId，同时指定streamId
            if(targetTaskId % 2 == 0){
                this.collector.emitDirect(targetTaskId,"directStreamDemo1",new Values(word));
            }else{
                this.collector.emitDirect(targetTaskId,"directStreamDemo2",new Values(word));
            }
        }
        this.collector.ack(tuple);
    }
}

4.下游使用directGrouping连接上游bolt及streamId

    @Test
    public void testDirectGrouping() throws InvalidTopologyException, AuthorizationException, AlreadyAliveException {
        TopologyBuilder builder = new TopologyBuilder();
 
        builder.setSpout("sentence-spout", new SentenceSpout());
        // SentenceSpout --> SplitSentenceBolt
        builder.setBolt("split-bolt", new SentenceDirectBolt()).shuffleGrouping("sentence-spout");
        // SplitSentenceBolt --> WordCountBolt
        //NOTE 4这里要指定上游的bolt以及要处理的streamId
        builder.setBolt("count-bolt", new WordCountBolt(),5).directGrouping("split-bolt","directStreamDemo1");
        // WordCountBolt --> ReportBolt
        builder.setBolt("report-bolt", new ReportBolt()).globalGrouping("count-bolt");
 
        submitRemote(builder);
    }

总结：

由上游的producer直接指定下游哪个task去接收它发射出来的tuple。下游使用directGrouping连接上游同时指定要消费的streamId，上游在prepare的时候保存下游的taskId列表，然后在declareOutputFields的时候使用declareStream来声明streamId，最后在execute方法里头使用emitDirect(int taskId, String streamId, List<Object> tuple)方法指定了下游的taskId以及要发送到的streamId