基于SpringBoot 使用 Flink 收发Kafka消息的示例详解

---
version: '2'

services:
  ZooKeeper:
    image: confluentinc/cp-zookeeper:7.3.0
    hostname: zookeeper
    container_name: zookeeper
    ports:
      - "2181:2181"
    environment:
      ZOOKEEPER_CLIENT_PORT: 2181
      ZOOKEEPER_TICK_TIME: 2000

  broker:
    image: confluentinc/cp-kafka:7.3.0
    hostname: broker
    container_name: broker
    depends_on:
      - zookeeper
    ports:
      - "29092:29092"
    environment:
      KAFKA_BROKER_ID: 1
      KAFKA_ZOOKEEPER_CONNECT: 'zookeeper:2181'
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://broker:9092,PLAINTEXT_HOST://localhost:29092
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 0

    <properties>
        <jdk.version>1.8</jdk.version>
        <Maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <spring-boot.version>2.7.7</spring-boot.version>
        <flink.version>1.16.0</flink.version>
    </properties>
    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-dependencies</artifactId>
                <version>${spring-boot.version}</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter</artifactId>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <optional>true</optional>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
    </dependencies>

@Component
@Slf4j
public class KafkaRunner implements ApplicationRunner
{
    @Override
    public void run(ApplicationArguments args) throws Exception {
        try{

            

            // Set up the streaming execution environment
            final StreamExecutionEnvironment streamEnv
                    = StreamExecutionEnvironment.getExecutionEnvironment();

            

            //Set connection properties to Kafka Cluster
            Properties properties = new Properties();
            properties.setProperty("bootstrap.servers", "localhost:29092");
            properties.setProperty("group.id", "flink.learn.realtime");

            //Setup a Kafka Consumer on Flnk
            FlinkKafkaConsumer<String> kafkaConsumer =
                    new FlinkKafkaConsumer<>
                            ("flink.kafka.streaming.source", //topic
                                    new SimpleStringSchema(), //Schema for data
                                    properties); //connection properties

            //Setup to receive only new messages
            kafkaConsumer.setStartFromLatest();

            //Create the data stream
            DataStream<String> auditTrailStr = streamEnv
                    .addSource(kafkaConsumer);

            //Convert each record to an Object
            DataStream<Tuple2<String, Integer>> userCounts
                    = auditTrailStr
                    .map(new MapFunction<String,Tuple2<String,Integer>>() {

                        @Override
                        public Tuple2<String,Integer> map(String auditStr) {
                            System.out.println("--- Received Record : " + auditStr);
                            AuditTrail at = new AuditTrail(auditStr);
                            return new Tuple2<String,Integer>(at.getUser(),at.getDuration());
                        }
                    })

                    .keyBy(0)  //By user name
                    .reduce((x,y) -> new Tuple2<String,Integer>( x.f0, x.f1 + y.f1));

            //Print User and Durations.
            userCounts.print();

            
            //Start the Kafka Stream generator on a separate thread
            System.out.println("Starting Kafka Data Generator...");
            Thread kafkaThread = new Thread(new KafkaStreamDataGenerator());
            kafkaThread.start();

            // execute the streaming pipeline
            streamEnv.execute("Flink Windowing Example");

        }
        catch(Exception e) {
            e.printStackTrace();
        }
    }
}

        Thread kafkaThread = new Thread(new KafkaStreamDataGenerator());
        kafkaThread.start();