哪家开发app好seo优化网站

一. Source 简介

DataStream是Flink的低级API，用于进行数据的实时处理，Flink编程模型分为Source、Transformation、Sink三个部分，如下图所示。

默认Flink提供了大量的内置Source，常见的Source如下：

• 基于文件的Source
• 基于Socket的Source
• 基于集合的Source
• 基于Kafka消息队列的Source

当以上内置Source不能满足业务需要时，可以实现自定义Source。

Flink中有关Source的接口类的继承关系如下：

• SourceFunction：单并行度Source的基类
• RichSourceFunction：单并行度增强型Source的基类
• ParallelSourceFunction：多并行度Source的基类
• RichParallelSourceFunction：多并行度增强型Source的基类

二. 自定义单并行度Source

自定义单并行度的source需要实现SourceFunction接口。

代码实现：

MySource.java

package flink.basic.source;import org.apache.flink.streaming.api.functions.source.SourceFunction;
import java.util.Random;public class MySource implements SourceFunction<String> {boolean running = true;@Overridepublic void run(SourceContext<String> ctx) throws Exception {Random random = new Random();while (running) {// "Num"加上0~100的随机数生成一个字符串ctx.collect("Num: " + random.nextInt(100));Thread.sleep(1000);}}@Overridepublic void cancel() {running = false;}
}

SourceDemo.java

package flink.basic.source;import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;public class SourceDemo {public static void main(String[] args) throws Exception {StreamExecutionEnvironment env= StreamExecutionEnvironment.getExecutionEnvironment();DataStreamSource<String> source = env.addSource(new MySource());source.print();env.execute("source_demo");}
}

运行结果：

5> Num: 62
6> Num: 91
7> Num: 13
8> Num: 53

三. 自定义多并行度Source

自定义多并行度的source需要实现ParallelSourceFunction接口。

代码实现：

MyParallelSource.java

package flink.basic.source;import org.apache.flink.streaming.api.functions.source.ParallelSourceFunction;
import java.util.Random;public class MyParallelSource implements ParallelSourceFunction<String> {boolean running = true;@Overridepublic void run(SourceContext<String> ctx) throws Exception {Random random = new Random();while (running) {ctx.collect("Num: " + random.nextInt(100));Thread.sleep(1000);}}@Overridepublic void cancel() {running = false;}
}

SourceDemo.java

package flink.basic.source;import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;public class SourceDemo {public static void main(String[] args) throws Exception {StreamExecutionEnvironment env= StreamExecutionEnvironment.getExecutionEnvironment();DataStreamSource<String> source = env.addSource(new MyParallelSource());source.print();env.execute("source_demo");}
}

运行结果：

7> Num: 43
8> Num: 30
1> Num: 92
2> Num: 50
5> Num: 39
6> Num: 6
4> Num: 20
3> Num: 2

四. 自定义单并行度增强型Source

增强型Source额外提供了open和close方法，可以用于自定义Source的初始化和清理工作。单并行度增强型Source需要实现RichSourceFunction接口。下面演示实现读取mysql表的单并行度Source。

在mysql中创建student表，并插入三条数据。

create table student (id int primary key,name varchar(50),age int
);insert into student values(1, "name1", 20),(2, "name2", 30), (3, "name3", 15);

实现代码

Student.java

package flink.basic.source;public class Student {private int id;private String name;private int age;public Student(int id, String name, int age) {this.id = id;this.name = name;this.age = age;}public Student() {}public int getId() {return id;}public void setId(int id) {this.id = id;}public String getName() {return name;}public void setName(String name) {this.name = name;}public int getAge() {return age;}public void setAge(int age) {this.age = age;}@Overridepublic String toString() {return "Student{" +"id=" + id +", name='" + name + '\'' +", age=" + age +'}';}
}

MysqlSource.java

package flink.basic.source;import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.functions.source.RichSourceFunction;import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.Statement;public class MysqlSource extends RichSourceFunction<Student> {Connection conn;Statement stmt;@Overridepublic void open(Configuration parameters) throws Exception {Class.forName("com.mysql.cj.jdbc.Driver");String url = "jdbc:mysql://192.168.47.130:3306/test";String user = "root";String password = "root";conn = DriverManager.getConnection(url,user,password);stmt = conn.createStatement();}@Overridepublic void run(SourceContext<Student> ctx) throws Exception {ResultSet rs = stmt.executeQuery("select * from student");while (rs.next()) {int id = rs.getInt("id");String name = rs.getString("name");int age = rs.getInt("age");ctx.collect(new Student(id, name, age));}rs.close();}@Overridepublic void cancel() {}@Overridepublic void close() throws Exception {stmt.close();conn.close();}
}

SourceDemo.java

package flink.basic.source;import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;public class SourceDemo {public static void main(String[] args) throws Exception {StreamExecutionEnvironment env= StreamExecutionEnvironment.getExecutionEnvironment();// 添加mysql SourceDataStreamSource<Student> source = env.addSource(new MysqlSource());source.print();env.execute("source_demo");}
}

运行结果：

1> Student{id=3, name='name3', age=15}
8> Student{id=2, name='name2', age=30}
7> Student{id=1, name='name1', age=20}