Flink+Kafka：FlinkKafkaConsumer简单样例

1、创建Maven项目，pom.xml文件如下

代码语言：javascript复制

<?xml version="1.0" encoding="UTF-8"?>
<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/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.example</groupId>
    <artifactId>flinkanaly</artifactId>
    <version>1.0-SNAPSHOT</version>


    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-core -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-core</artifactId>
            <version>1.13.2</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-clients -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.12</artifactId>
            <version>1.13.2</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-runtime-web -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-runtime-web_2.12</artifactId>
            <version>1.13.2</version>

        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-java -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>1.13.2</version>
            <scope>provided</scope>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-connector-kafka -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_2.12</artifactId>
            <version>1.13.2</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.7</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.7</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.7</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
                <version>2.5.4</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>repackage</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

2、Flink作为Kafka的Consumer

代码语言：javascript复制

package com.example;

import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;

import java.util.Properties;

public class Fink_Kafka_Demo {

    public static void main(String[] args) {
        System.out.println("start.....");
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        Properties properties = new Properties();
        properties.setProperty("bootstrap.servers", "node1:9092");
        properties.setProperty("group.id", "test");
        //构建FlinkKafkaConsumer
        FlinkKafkaConsumer<String> myConsumer = new FlinkKafkaConsumer<String>("demo", new SimpleStringSchema(), properties);
        //指定偏移量
        myConsumer.setStartFromLatest();
        DataStream<String> stream = env.addSource(myConsumer);
        env.enableCheckpointing(5000);
        stream.print();
        try {
            env.execute("Fink_Kafka_Demo");
        } catch (Exception e) {
            e.printStackTrace();
        }

    }
}

3、编译jar

mvn clean package

4、执行过程

（1）启动jar

代码语言：javascript复制

[root@node1 jar]# java -jar flinkanaly-1.0-SNAPSHOT.jar 
start.....
log4j:WARN No appenders could be found for logger (org.apache.flink.api.java.ClosureCleaner).
log4j:WARN Please initialize the log4j system properly.
log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.

（2）启动生产者，录入消息

代码语言：javascript复制

[root@node3 kafka-2.8.0]# bin/kafka-console-producer.sh --topic demo --bootstrap-server node1:9092
>Hi
>Flink
>Kafka
>

（3）查看flink程序输出

代码语言：javascript复制

[root@node1 jar]# java -jar flinkanaly-1.0-SNAPSHOT.jar 
start.....
log4j:WARN No appenders could be found for logger (org.apache.flink.api.java.ClosureCleaner).
log4j:WARN Please initialize the log4j system properly.
log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.
3> Hi
4> Flink
3> Kafka

jar flink 大数据

0 人点赞