环境

• storm 1.2.1
• kafka 0.10.2.2
• eclipse

maven依赖

<dependencies>
        <dependency>
            <groupId>org.apache.storm</groupId>
            <artifactId>storm-core</artifactId>
            <version>1.2.1</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-resources-plugin</artifactId>
        <version>2.6</version>
        </dependency>
        <dependency>
            <groupId>org.apache.storm</groupId>
            <artifactId>storm-kafka-client</artifactId>
            <version>1.2.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka-clients</artifactId>
            <version>0.10.2.1</version>
        </dependency>
  </dependencies>
        <build>
    <plugins>
    <plugin>
        <artifactId>maven-assembly-plugin</artifactId>
        <version>2.4</version>
        <executions>
          <execution>
            <id>make-assembly</id>
            <phase>package</phase>
            <goals>
              <goal>single</goal>
            </goals>
            <configuration>
              <descriptorRefs>
                <descriptorRef>jar-with-dependencies</descriptorRef>
              </descriptorRefs>
              <archive>
                <manifest>
                  <mainClass></mainClass>
                </manifest>
              </archive>
            </configuration>
          </execution>
        </executions>
      </plugin>
      <plugin>
        <artifactId>maven-compiler-plugin</artifactId>
        <version>3.1</version>
        <executions>
          <execution>
            <id>default-compile</id>
            <phase>compile</phase>
            <goals>
              <goal>compile</goal>
            </goals>
            <configuration>
              <source>1.8</source>
              <target>1.8</target>
              <encoding>UTF-8</encoding>
            </configuration>
          </execution>
          <execution>
            <id>default-testCompile</id>
            <phase>test-compile</phase>
            <goals>
              <goal>testCompile</goal>
            </goals>
            <configuration>
              <source>1.8</source>
              <target>1.8</target>
              <encoding>UTF-8</encoding>
            </configuration>
          </execution>
        </executions>
        <configuration>
          <source>1.8</source>
          <target>1.8</target>
          <encoding>UTF-8</encoding>
        </configuration>
      </plugin>
  </plugins>
  </build>

Storm写入到kafka：Kafka producer

Properties props = new Properties();
        props.put("bootstrap.servers", "10.11.6.52:9092");
        props.put("acks", "1");
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");

        KafkaBolt bolt = new KafkaBolt()
                .withProducerProperties(props)
                .withTopicSelector(new DefaultTopicSelector("tokafkatest"))
                .withTupleToKafkaMapper(new FieldNameBasedTupleToKafkaMapper());
        builder.setBolt("forwardToKafka", bolt, 1).shuffleGrouping("spout");

注意

1. topic需要先在kafka中提前创建好
2. bootstrap.servers只用填写集群中部分kafka地址就行
3. 这里使用FieldNameBasedTupleToKafkaMapper（），那么这里spout的输出声明应该是"key", "message"，或者使用FieldNameBasedTupleToKafkaMapper（“AA”，“BB”），AABB为自定义域声明

Storm从kafka中读取：Kafka Consumer

builder.setSpout("kafka_spout", new KafkaSpout<>(KafkaSpoutConfig.builder("10.11.6.52:9092","tokafkatest").build()), 1);

注意

1. 下游收到的信息含有"topic","partition","offset","key","value"，其中key，value，topic是String类型，offset是Long类型。
2. 默认使用的是UNCOMMITTED_EARLIEST (默认值) spout 会从每个partition的最后一次提交的offset开始读取. 如果offset不存在或者过期, 则会依照 EARLIEST进行读取。
   其他读取类型还有：

• EARLIEST ：无论之前的消费情况如何,spout会从每个kafka partition能找到的最早的offset开始的读取
• LATEST ：无论之前的消费情况如何,spout会从每个kafka partition当前最新的offset开始的读取
• UNCOMMITTED_LATEST：spout 会从每个partition的最后一次提交的offset开始读取, 如果offset不存在或者过期, 则会依照 LATEST进行读取

多个topic使用

final TopologyBuilder tp = new TopologyBuilder();

//默认情况下,spout 消费但未被match到的topic的message的"topic","key"和"value"将发送到"STREAM_1"
ByTopicRecordTranslator<String, String> byTopic = new ByTopicRecordTranslator<>(
    (r) -> new Values(r.topic(), r.key(), r.value()),
    new Fields("topic", "key", "value"), "STREAM_1");
//topic_2 所有的消息的 "key" and "value" 将发送到 "STREAM_2"中
byTopic.forTopic("topic_2", (r) -> new Values(r.key(), r.value()), new Fields("key", "value"), "STREAM_2");

tp.setSpout("kafka_spout", new KafkaSpout<>(KafkaSpoutConfig.builder("127.0.0.1:" + port, "topic_1", "topic_2", "topic_3").build()), 1);
tp.setBolt("bolt", new myBolt()).shuffleGrouping("kafka_spout", "STREAM_1");
tp.setBolt("another", new myOtherBolt()).shuffleGrouping("kafka_spout", "STREAM_2");

通配符 Topics

通配符 topics 将消费所有符合通配符的topics. 在下面的例子中 "topic", "topic_foo" 和 "topic_bar" 适配通配符 "topic.*", 但是 "not_my_topic" 并不适配.

final TopologyBuilder tp = new TopologyBuilder();
tp.setSpout("kafka_spout", new KafkaSpout<>(KafkaSpoutConfig.builder("127.0.0.1:" + port, Pattern.compile("topic.*")).build()), 1);
tp.setBolt("bolt", new myBolt()).shuffleGrouping("kafka_spout");

完整代码

package Topology;

import java.util.Properties;

import org.apache.storm.Config;
import org.apache.storm.LocalCluster;
import org.apache.storm.StormSubmitter;
import org.apache.storm.generated.AlreadyAliveException;
import org.apache.storm.generated.AuthorizationException;
import org.apache.storm.generated.InvalidTopologyException;
import org.apache.storm.kafka.bolt.KafkaBolt;
import org.apache.storm.kafka.bolt.mapper.FieldNameBasedTupleToKafkaMapper;
import org.apache.storm.kafka.bolt.selector.DefaultTopicSelector;
import org.apache.storm.kafka.spout.KafkaSpout;
import org.apache.storm.kafka.spout.KafkaSpoutConfig;
import org.apache.storm.topology.IRichSpout;
import org.apache.storm.topology.TopologyBuilder;
import org.apache.storm.trident.testing.FixedBatchSpout;
import org.apache.storm.tuple.Fields;
import org.apache.storm.tuple.Values;

import Bolts.printbolt;
import Bolts.printbolt2;
import Spouts.NormalSpout;

public class sk {

    public static void main(String[] args) throws Exception {
        // TODO Auto-generated method stub
        TopologyBuilder builder = new TopologyBuilder();
        
        builder.setSpout("spout", new NormalSpout(), 1);
        //set producer properties.
        Properties props = new Properties();
        props.put("bootstrap.servers", "10.11.6.52:9092");
        props.put("acks", "1");
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");

        KafkaBolt bolt = new KafkaBolt()
                .withProducerProperties(props)
                .withTopicSelector(new DefaultTopicSelector("tokafkatest"))
                .withTupleToKafkaMapper(new FieldNameBasedTupleToKafkaMapper());
        builder.setBolt("forwardToKafka", bolt, 1).shuffleGrouping("spout");
        builder.setBolt("printforwardToKafka", new printbolt(), 1).shuffleGrouping("spout");
        
        builder.setSpout("kafka_spout", new KafkaSpout<>(KafkaSpoutConfig.builder("10.11.6.52:9092","tokafkatest").build()), 1);
        builder.setBolt("printFromKafka", new printbolt2(),1).shuffleGrouping("kafka_spout");
        
        Config conf = new Config();
         conf.setDebug(true);
          
          if (args != null && args.length > 0) {
              conf.setNumWorkers(3);

              StormSubmitter.submitTopologyWithProgressBar(args[0], conf, builder.createTopology());
            }
            else {
              conf.setMaxTaskParallelism(3);

              LocalCluster cluster = new LocalCluster();
              cluster.submitTopology("kafkaboltTest", conf, builder.createTopology());

              Thread.sleep(1000000);

              cluster.shutdown();
            }
        
    }

}