Spark Streaming实时流处理笔记（5）—— Kafka API 编程

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u012292754/article/details/84828815

1 新建 Maven工程

pom文件

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.myspark.com</groupId>
  <artifactId>sparktrain</artifactId>
  <version>1.0</version>
  <inceptionYear>2008</inceptionYear>
  <properties>
    <scala.version>2.11.12</scala.version>
    <kafka.version>0.9.0.0</kafka.version>
  </properties>

  <repositories>
    <repository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </repository>
  </repositories>

  <pluginRepositories>
    <pluginRepository>
      <id>scala-tools.org</id>
      <name>Scala-Tools Maven2 Repository</name>
      <url>http://scala-tools.org/repo-releases</url>
    </pluginRepository>
  </pluginRepositories>

  <dependencies>
    <dependency>
      <groupId>org.scala-lang</groupId>
      <artifactId>scala-library</artifactId>
      <version>${scala.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.kafka</groupId>
      <artifactId>kafka_2.11</artifactId>
      <version>${kafka.version}</version>
    </dependency>


  </dependencies>

  <build>
    <sourceDirectory>src/main/scala</sourceDirectory>
    <testSourceDirectory>src/test/scala</testSourceDirectory>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <executions>
          <execution>
            <goals>
              <goal>compile</goal>
              <goal>testCompile</goal>
            </goals>
          </execution>
        </executions>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
          <args>
            <arg>-target:jvm-1.5</arg>
          </args>
        </configuration>
      </plugin>
      <plugin>
        <groupId>org.apache.maven.plugins</groupId>
        <artifactId>maven-eclipse-plugin</artifactId>
        <configuration>
          <downloadSources>true</downloadSources>
          <buildcommands>
            <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
          </buildcommands>
          <additionalProjectnatures>
            <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
          </additionalProjectnatures>
          <classpathContainers>
            <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
            <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
          </classpathContainers>
        </configuration>
      </plugin>
    </plugins>
  </build>
  <reporting>
    <plugins>
      <plugin>
        <groupId>org.scala-tools</groupId>
        <artifactId>maven-scala-plugin</artifactId>
        <configuration>
          <scalaVersion>${scala.version}</scalaVersion>
        </configuration>
      </plugin>
    </plugins>
  </reporting>
</project>

2 生产者源码

1. KafkaProperties.java

package com.myspark.kafka;

/*
 *
 * Kafka 配置文件
 * */
public class KafkaProperties {

    public static final String ZK = "192.168.30.131:2181";

    public static final String TOPIC = "hello_topic";

    public static final String BROKER_LIST = "192.168.30.131:9092";


}

2. KafkaProducer.java

package com.myspark.kafka;

import kafka.javaapi.producer.Producer;
import kafka.producer.KeyedMessage;
import kafka.producer.ProducerConfig;

import java.util.Properties;

public class KafkaProducer extends Thread {

    private String topic;

    private Producer<Integer, String> producer;

    public KafkaProducer(String topic) {
        this.topic = topic;

        Properties properties = new Properties();
        properties.put("metadata.broker.list", KafkaProperties.BROKER_LIST);
        properties.put("serializer.class", "kafka.serializer.StringEncoder");
        /*
         * The number of acknowledgments the producer requires the leader to have received before considering a request complete.
         * This controls the durability of the messages sent by the producer.
         *
         * request.required.acks = 0 - means the producer will not wait for any acknowledgement from the leader.
         * request.required.acks = 1 - means the leader will write the message to its local log and immediately acknowledge
         * request.required.acks = -1 - means the leader will wait for acknowledgement from all in-sync replicas before acknowledging the write
         */
        properties.put("request.required.acks", "1");

        producer = new Producer<Integer, String>(new ProducerConfig(properties));
    }

    @Override
    public void run() {
        int messageNo = 1;
        while (true) {
            String message = "message_" + messageNo;
            producer.send(new KeyedMessage<Integer, String>(topic, message));
            System.out.println("Sent: " + message);

            messageNo++;
            try{
                Thread.sleep(2000);
            }catch (Exception e){
                e.printStackTrace();
            }
        }
    }
}

3. KafkaClientApp.java

package com.myspark.kafka;
/*
 * Kafka Java API测试
 * */
public class KafkaClientApp {

    public static void main(String[] args) {
        new KafkaProducer(KafkaProperties.TOPIC).start();
    }

}

测试
先启动 zookeeper,然后启动 kafka

kafka-server-start.sh $KAFKA_HOME/config/server.properties

[hadoop@node1 ~]$ jps -m
2624 Kafka /home/hadoop/apps/kafka_2.11-0.9.0.0/config/server.properties
2714 Jps -m
1405 QuorumPeerMain /home/hadoop/apps/zookeeper-3.4.5-cdh5.7.0/bin/../conf/zoo.cfg
[hadoop@node1 ~]$ 

启动消费者

kafka-console-consumer.sh --zookeeper node1:2181 --topic hello_topic

然后启动 KafkaClientApp

3 消费者

1. KafkaProperties.java

package com.myspark.kafka;
/*
 *
 * Kafka 配置文件
 * */
public class KafkaProperties {
    public static final String ZK = "192.168.30.131:2181";
    public static final String TOPIC = "hello_topic";
    public static final String BROKER_LIST = "192.168.30.131:9092";
    public static final String GROUP_ID = "test_group1";
}

2. KafkaConsumer.java

package com.myspark.kafka;

import kafka.consumer.Consumer;
import kafka.consumer.ConsumerConfig;
import kafka.consumer.ConsumerIterator;
import kafka.consumer.KafkaStream;
import kafka.javaapi.consumer.ConsumerConnector;

import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;

public class KafkaConsumer extends Thread {
    private String topic;
    public KafkaConsumer(String topic) {
        this.topic = topic;
    }
    private ConsumerConnector createConnector() {

        Properties properties = new Properties();
        properties.put("zookeeper.connect", KafkaProperties.ZK);
        properties.put("group.id",KafkaProperties.GROUP_ID);

        return Consumer.createJavaConsumerConnector(new ConsumerConfig(properties));
    }
    @Override
    public void run() {
        ConsumerConnector consumer = createConnector();
        Map<String, Integer> topicCountMap = new HashMap<String, Integer>();
        topicCountMap.put(topic, 1);

        //String : topic
        //第二个参数:数据流
        Map<String, List<KafkaStream<byte[], byte[]>>> messageStream = consumer.createMessageStreams(topicCountMap);

        KafkaStream<byte[], byte[]> stream = messageStream.get(topic).get(0); //获取每次接收到的数据

        ConsumerIterator<byte[], byte[]> iterator = stream.iterator();

        while(iterator.hasNext()){
           String message = new String(iterator.next().message());
            System.out.println("receive: "+message);
        }

    }
}

3. KafkaClientApp.java

package com.myspark.kafka;

/*
 * Kafka Java API测试
 * */
public class KafkaClientApp {
    public static void main(String[] args) {
        new KafkaProducer(KafkaProperties.TOPIC).start();
        new KafkaConsumer(KafkaProperties.TOPIC).start();
    }

}