package com.sandra.day03;
import com.sandra.bean.Event;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.source.ParallelSourceFunction;
import org.apache.flink.streaming.api.functions.source.SourceFunction;
import java.util.Random;
//自定义Source
public class Flink01_Source_Customer {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(1);
//通过自定义source数据源获取数据
DataStreamSource<Event> streamSource = env.addSource(new MySourceFunction()).setParallelism(2);
streamSource.print();
env.execute();
}
//自定义类实现SourceFunction接口,在里面随机生成Event,默认并行度只能设置为1
// public static class MySourceFunction implements SourceFunction<Event>{
//如果想要实现多并行度,需要实现ParallelSourceFunction接口
public static class MySourceFunction implements ParallelSourceFunction<Event> {
// private Random random = new Random();//如果写在这个位置,多并行度下每个时间段产生的数据是一样的
private Boolean isRunning = true;
/**
* 该方法主要用来生成数据或者获取其他数据库数据,并且在这个方法中通常有一个while循环
* @param ctx 可以利用上下文对象的collect方法将生成或者获取的数据发送至下游
* @throws Exception
*/
@Override
public void run(SourceContext<Event> ctx) throws Exception {
Random random = new Random(); //写在这个位置,多并行度下每个时间段产生的数据是不一样的
String[] users = {"sandra","wuli"};
String[] urls = {"./home","./cart","./flink","./java"};
while (isRunning){
ctx.collect(new Event(users[random.nextInt(users.length)],urls[random.nextInt(urls.length)],System.currentTimeMillis()));
Thread.sleep(500);
}
}
/**
* 因为在run方法中通常有一个while循环,可以通过该方法终止,这个方法不是我们手动调用,是系统内部自动调用
*/
@Override
public void cancel() {
isRunning = false;
}
}
}
Event:
package com.sandra.bean;
import java.sql.Timestamp;
public class Event {
public String user;
public String url;
public Long timestamp;
public Event(){
}
public Event(String user,String url,Long timestamp){
this.user=user;
this.url=url;
this.timestamp=timestamp;
}
@Override
public String toString(){
return "Event{"+
"user='" + user + "'"+
",url='" + url + "'"+
",timestamp='"+new Timestamp(timestamp)+
"'}";
}
}
依赖(带打包插件):
<?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.sandra</groupId>
<artifactId>flink-demo1</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<flink.version>1.13.6</flink.version>
<java.version>1.8</java.version>
<scala.binary.version>2.12</scala.binary.version>
<slf4j.version>1.7.30</slf4j.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-java</artifactId>
<!-- <version>1.13.6</version>-->
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
<!-- <version>1.13.6</version>-->
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients_${scala.binary.version}</artifactId>
<!-- <version>1.13.6</version>-->
<version>${flink.version}</version>
</dependency>
<!-- flink用本地看web ui要加的依赖-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-runtime-web_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-kafka_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>3.2.4</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<artifactSet>
<excludes>
<exclude>com.google.code.findbugs:jsr305</exclude>
<exclude>org.slf4j:*</exclude>
<exclude>log4j:*</exclude>
</excludes>
</artifactSet>
<filters>
<filter>
<!-- Do not copy the signatures in the META-INF folder.
Otherwise, this might cause SecurityExceptions when using the JAR. -->
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
<transformers combine.children="append">
<transformer
implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer">
</transformer>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
结果: