Storm集成Kafka編程模型

時間 2019-12-09

標籤 storm 集成 kafka 編程模型欄目 Storm 简体版

原文原文鏈接

原創文章，轉載請註明：轉載自http://www.cnblogs.com/tovin/p/3974417.htmlhtml

本文主要介紹如何在Storm編程實現與Kafka的集成node

　　1、實現模型git

　　　數據流程：github

　　　　一、Kafka Producter生成topic1主題的消息　apache

　　　　二、Storm中有個Topology，包含了KafkaSpout、SenqueceBolt、KafkaBolt三個組件。其中KafkaSpout訂閱了topic1主題消息，而後發送編程

　　　　　　給SenqueceBolt加工處理，最後數據由KafkaBolt生成topic2主題消息發送給Kafkamaven

　　　　三、Kafka Consumer負責消費topic2主題的消息ide

　　2、Topology實現測試

　　　　一、建立maven工程，配置pom.xmlui

　　　　　　須要依賴storm-core、kafka_2.十、storm-kafka三個包

  <dependencies>  
      <dependency>
           <groupId>org.apache.storm</groupId>
             <artifactId>storm-core</artifactId>
             <version>0.9.2-incubating</version>
             <scope>provided</scope> 
       </dependency>
   
    <dependency>
        <groupId>org.apache.kafka</groupId>
        <artifactId>kafka_2.10</artifactId>
        <version>0.8.1.1</version>
        <exclusions>
            <exclusion>
                <groupId>org.apache.zookeeper</groupId>
                <artifactId>zookeeper</artifactId>
            </exclusion>
            <exclusion>
                <groupId>log4j</groupId>
                <artifactId>log4j</artifactId>
            </exclusion>
        </exclusions>
    </dependency>
       
        <dependency>  
          <groupId>org.apache.storm</groupId>  
         <artifactId>storm-kafka</artifactId>  
          <version>0.9.2-incubating</version>  
    </dependency>  
  </dependencies>
  
  <build>
    <plugins>
      <plugin>
        <artifactId>maven-assembly-plugin</artifactId>
        <version>2.4</version>
        <configuration>
          <descriptorRefs>
            <descriptorRef>jar-with-dependencies</descriptorRef>
          </descriptorRefs>
        </configuration>
        <executions>
          <execution>
            <id>make-assembly</id> 
            <phase>package</phase>
            <goals>
              <goal>single</goal>
            </goals>
          </execution>
        </executions>
      </plugin>
    </plugins>
  </build>

　　　　二、KafkaSpout

　　　　　　KafkaSpout是Storm中自帶的Spout，源碼在https://github.com/apache/incubator-storm/tree/master/external

　　　　　　使用KafkaSpout時須要子集實現Scheme接口，它主要負責從消息流中解析出須要的數據

public class MessageScheme implements Scheme { 
    
    /* (non-Javadoc)
     * @see backtype.storm.spout.Scheme#deserialize(byte[])
     */
    public List<Object> deserialize(byte[] ser) {
        try {
            String msg = new String(ser, "UTF-8"); 
            return new Values(msg);
        } catch (UnsupportedEncodingException e) {  
         
        }
        return null;
    }
    
    
    /* (non-Javadoc)
     * @see backtype.storm.spout.Scheme#getOutputFields()
     */
    public Fields getOutputFields() {
        // TODO Auto-generated method stub
        return new Fields("msg");  
    }  
}

　　　　三、SenqueceBolt

　　　　　　　SenqueceBolt實現很簡單，在接收的spout的消息前面加上「I‘m」　

public class SenqueceBolt extends BaseBasicBolt{
    
    /* (non-Javadoc)
     * @see backtype.storm.topology.IBasicBolt#execute(backtype.storm.tuple.Tuple, backtype.storm.topology.BasicOutputCollector)
     */
    public void execute(Tuple input, BasicOutputCollector collector) {
        // TODO Auto-generated method stub
         String word = (String) input.getValue(0);  
         String out = "I'm " + word +  "!";  
         System.out.println("out=" + out);
         collector.emit(new Values(out));
    }
    
    /* (non-Javadoc)
     * @see backtype.storm.topology.IComponent#declareOutputFields(backtype.storm.topology.OutputFieldsDeclarer)
     */
    public void declareOutputFields(OutputFieldsDeclarer declarer) {
        declarer.declare(new Fields("message"));
    }
}

　　　　四、KafkaBolt

　　　　　　KafkaBolt是Storm中自帶的Bolt，負責向Kafka發送主題消息

　　　　五、Topology

public class StormKafkaTopo {   
    public static void main(String[] args) throws Exception { 
　　　　 // 配置Zookeeper地址
        BrokerHosts brokerHosts = new ZkHosts("node04:2181,node05:2181,node06:2181");
        // 配置Kafka訂閱的Topic，以及zookeeper中數據節點目錄和名字
        SpoutConfig spoutConfig = new SpoutConfig(brokerHosts, "topic1", "/zkkafkaspout" , "kafkaspout");
       
　　　　 // 配置KafkaBolt中的kafka.broker.properties
        Config conf = new Config();  
        Map<String, String> map = new HashMap<String, String>(); 
　　　　 // 配置Kafka broker地址   
        map.put("metadata.broker.list", "node04:9092");
        // serializer.class爲消息的序列化類
        map.put("serializer.class", "kafka.serializer.StringEncoder");
        conf.put("kafka.broker.properties", map);
　　　　// 配置KafkaBolt生成的topic
        conf.put("topic", "topic2");
        
        spoutConfig.scheme = new SchemeAsMultiScheme(new MessageScheme());  
        TopologyBuilder builder = new TopologyBuilder();   
        builder.setSpout("spout", new KafkaSpout(spoutConfig));  
        builder.setBolt("bolt", new SenqueceBolt()).shuffleGrouping("spout"); 
        builder.setBolt("kafkabolt", new KafkaBolt<String, Integer>()).shuffleGrouping("bolt");        

        if (args != null && args.length > 0) {  
            conf.setNumWorkers(3);  
            StormSubmitter.submitTopology(args[0], conf, builder.createTopology());  
        } else {  
  
            LocalCluster cluster = new LocalCluster();  
            cluster.submitTopology("Topo", conf, builder.createTopology());  
            Utils.sleep(100000);  
            cluster.killTopology("Topo");  
            cluster.shutdown();  
        }  
    }  
}