Flink java 之自定义数据源

0. 创建maven工程

---

<?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>org.daidai</groupId>
    <artifactId>Flink1.13_Java</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>8</source>
                    <target>8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <properties>
        <flink.version>1.13.0</flink.version>
        <java.version>1.8</java.version>
        <scala.binary.version>2.12</scala.binary.version>
        <slf4j.version>1.7.15</slf4j.version>
        <lombok.version>1.18.24</lombok.version>
        <mysql-connector.version>8.0.29</mysql-connector.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>${mysql-connector.version}</version>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>${lombok.version}</version>
        </dependency>
        <!-- 引入 Flink 相关依赖-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <exclusions>
                <exclusion>
                    <artifactId>slf4j-api</artifactId>
                    <groupId>org.slf4j</groupId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <!-- 引入日志管理相关依赖-->
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version>2.14.0</version>
        </dependency>
    </dependencies>

</project>

1. 创建流处理环境

---

package com.daidai.mocksource;

import com.daidai.mocksource.domain.Order;
import com.daidai.mocksource.source.MyOrderSource;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

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

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
      

        env.execute();
    }
}

2. 创建数据源类

---

2.1 定义数据的类型

package com.daidai.mocksource.domain;

import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;

@Data
@AllArgsConstructor
@NoArgsConstructor
public class Order {
    private String id;
    private Integer userId;
    private Integer money;
    private Long createTime;
}

2.2 定义数据源

package com.daidai.mocksource.source;

import com.daidai.mocksource.domain.Order;
import org.apache.flink.streaming.api.functions.source.RichParallelSourceFunction;

import java.util.Random;
import java.util.UUID;

public class MyOrderSource extends RichParallelSourceFunction<Order> {

    boolean flag = true;

    @Override
    public void run(SourceContext<Order> sourceContext) throws Exception {
        Random random = new Random();
        while (flag){
            Thread.sleep(1000);
            String id = UUID.randomUUID().toString();
            int userId = random.nextInt(3);
            int money = random.nextInt(101);
            long createTime = System.currentTimeMillis();
            sourceContext.collect(new Order(id, userId, money, createTime));
        }
    }

    @Override
    public void cancel() {
        flag = false;
    }
}

3. 从自定义数据源加载数据

---

package com.daidai.mocksource;

import com.daidai.mocksource.domain.Order;
import com.daidai.mocksource.source.MyOrderSource;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

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

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<Order> orderDataStreamSource = env.addSource(new MyOrderSource());
        orderDataStreamSource.print();

        env.execute();
    }
}

4. 注意

RichParallelSourceFunction是支持设置多并行度的，关于 RichParallelSourceFunction 与 RichSourceFunction 的区别，前者支持用户设置多并行度，后者不支持通过 setParallelism () 方法设置并行度大于1，默认的并行度为1。