flink教程实现hello word!

flink的代码层面数据处理 流程
addSource（读取数据）->类型为dataStream做一些业务处理（核心部分在这里），好比java的stream的一些API操作->addSink(输出数据)

1.四种读取方式-从集合中、从kafka中、从文件中、自定义

上代码

pom.xml

<?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 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>2.6.6</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>me</groupId>
    <artifactId>flink</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>flink</name>
    <description>Demo project for Spring Boot</description>
    <properties>
        <java.version>1.8</java.version>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <flink.version>1.12.1</flink.version>
        <scala.binary.version>2.12</scala.binary.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <!-- kafka -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <!-- 打包时跳过测试 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <configuration>
                    <skip>true</skip>
                </configuration>
            </plugin>
            <!--springboot打包-->
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
            </plugin>
        </plugins>
    </build>

</project>

package me.flink;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.serialization.SerializationSchema;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.client.program.StreamContextEnvironment;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer;
import org.apache.flink.util.Collector;

import java.util.Properties;

/**
 * @author slmeng
 * @date 2022-4-19 14:41
 * Description:
 */


public class StreamWordCount {

    public static void main(String[] args) throws Exception {

        // 创建流处理执行环境
        StreamExecutionEnvironment env = StreamContextEnvironment.getExecutionEnvironment();
        // 设置并行度1
        env.setParallelism(1);

        Properties properties = new Properties();
        properties.setProperty("bootstrap.servers", "192.168.5.42:9092");
        // 下面这些次要参数
        properties.setProperty("group.id", "consumer-group");
        properties.setProperty("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        properties.setProperty("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        properties.setProperty("auto.offset.reset", "latest");

        // flink添加外部数据源
        DataStream<String> dataStream = env.addSource(new FlinkKafkaConsumer<String>("topic2", new SimpleStringSchema(),properties));

        // 基于数据流进行转换计算 做一些业务操作
        DataStream<String> flatMapStream = dataStream.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String value, Collector<String> out) throws Exception {
                String[] fields = value.split(",");
                for(String field:fields){
                // 收集器输出
                    out.collect(field);
                }
            }
        });

        flatMapStream.print();
        // 将数据写入Kafka
        flatMapStream.addSink( new FlinkKafkaProducer<String>("192.168.5.42:9092", "topic1", new SimpleStringSchema()));

        // 执行任务
        env.execute();
    }

}