首页 > 其他分享 >Flink设置Source数据源

Flink设置Source数据源

时间:2023-01-09 15:44:25浏览次数:48  
标签:flink 数据源 Flink Source env org apache import TODO

流处理说明

有边界的流bounded stream:批数据

无边界的流unbounded stream:真正的流数据

Source

基于集合

package com.pzb.source;

import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

import java.util.Arrays;

/**
 * Desc 演示DataStream-Source-基于集合
 */
public class SourceDemo01_Collection {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        // 设置自动处理,不设置默认流处理
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        //TODO 1.source
        DataStream<String> ds1 = env.fromElements("hadoop spark flink", "hadoop spark flink");
        DataStream<String> ds2 = env.fromCollection(Arrays.asList("hadoop spark flink", "hadoop spark flink"));
        DataStream<Long> ds3 = env.generateSequence(1, 100);//产生一个从1-100的有序数据	官方认为此方法已过时,建议使用下方的方法
        DataStream<Long> ds4 = env.fromSequence(1, 100);//产生一个从1-100的有序数据

        //TODO 2.transformation

        //TODO 3.sink
        ds1.print();
        ds2.print();
        ds3.print();
        ds4.print();

        //TODO 4.execute
        env.execute();
    }
}

基于文件

package com.pzb.source;

import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

/**
 * Desc 演示DataStream-Source-基于本地/HDFS的文件/文件夹/压缩文件
 */
public class SourceDemo02_File {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        //TODO 1.source
        DataStream<String> ds1 = env.readTextFile("data/input/words.txt");
        DataStream<String> ds2 = env.readTextFile("data/input/dir");// 读取该目录下的所有文件
        DataStream<String> ds3 = env.readTextFile("data/input/wordcount.txt.gz"); // 读取压缩包文件
        DataStream<String> ds4 = env.readTextFile("hdfs://hadoop111:8020/data/input/words.txt");// 读hdfs文件


        //TODO 2.transformation

        //TODO 3.sink
        ds1.print();
        ds2.print();
        ds3.print();

        //TODO 4.execute
        env.execute();
    }
}

基于Socket

package com.pzb.source;

import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
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.util.Collector;

/**
 * Desc 演示DataStream-Source-基于Socket
 */
public class SourceDemo03_Socket {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        //TODO 1.source
        DataStream<String> lines = env.socketTextStream("node1", 9999);// 不管怎么设置socketTextStream并行度,其并行度都为1


        //TODO 2.transformation
        /*SingleOutputStreamOperator<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String value, Collector<String> out) throws Exception {
                String[] arr = value.split(" ");
                for (String word : arr) {
                    out.collect(word);
                }
            }
        });

        words.map(new MapFunction<String, Tuple2<String,Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String value) throws Exception {
                return Tuple2.of(value,1);
            }
        });*/

        //注意:下面的操作将上面的2步合成了1步,直接切割单词并记为1返回
        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = lines.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
                String[] arr = value.split(" ");
                for (String word : arr) {
                    out.collect(Tuple2.of(word, 1));
                }
            }
        });

        SingleOutputStreamOperator<Tuple2<String, Integer>> result = wordAndOne.keyBy(t -> t.f0).sum(1);

        //TODO 3.sink
        result.print();

        //TODO 4.execute
        env.execute();
    }
}

基于Kafka

addSource

首先添加相关依赖

		<dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_2.11</artifactId>
            <version>1.13.6</version>
        </dependency>
package com.peng.kafka_;

import org.apache.flink.api.common.RuntimeExecutionMode;
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;

/**
 * @author 海绵先生
 * @Description TODO Source对接Kafka
 * @date 2022/10/11-17:07
 */
public class KafkaComsumerDemo {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        //TODO 1.source
        //准备kafka连接参数
        Properties props  = new Properties();
        props.setProperty("bootstrap.servers", "hadoop111:9092");//集群地址
        props.setProperty("group.id", "flink");//消费者组id
        props.setProperty("auto.offset.reset","latest");//latest有offset记录从记录位置开始消费,没有记录从最新的/最后的消息开始消费 /earliest有offset记录从记录位置开始消费,没有记录从最早的/最开始的消息开始消费
        props.setProperty("flink.partition-discovery.interval-millis","5000");//会开启一个后台线程每隔5s检测一下Kafka的分区情况,实现动态分区检测
        props.setProperty("enable.auto.commit", "true");//自动提交,设置offset
        props.setProperty("auto.commit.interval.ms", "2000");//自动提交的时间间隔
        //使用连接参数创建FlinkKafkaConsumer/kafkaSource
        FlinkKafkaConsumer<String> kafkaSource = new FlinkKafkaConsumer<String>("flink_kafka", new SimpleStringSchema(), props);// String泛型为当前存储数据的数据类型
        /*
        SimpleStringSchema接口:官方注释说 Very simple serialization schema for strings :非常简单的字符串序列化架构。将数据序列化和反序列化成String类型,默认编码格式为UTF-8。
        */
        
        //使用kafkaSource
        DataStream<String> kafkaDS = env.addSource(kafkaSource);
        

        //TODO 2.transformation

        //TODO 3.sink
        kafkaDS.print();

        //TODO 4.execute
        env.execute();
    }
}

Kafka存储的数据类型是字节数据类型,要想把字节数据类型转换成Java中对应的基本数据类型/类数据类型,需要进行反序列化操作。

自定义反序列化:

package com.peng.kafka_;

import com.alibaba.fastjson.JSON;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.serialization.DeserializationSchema;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
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 cn.hutool.json.JSONUtil;

import java.io.IOException;
import java.util.Properties;

/**
 * @author 海绵先生
 * @Description TODO    实现将Kafka里的Json数据消息转换成所对应的类
 * @date 2022/11/6-11:28
 */
public class Kafka_Sink_Source {
    @Data
    @AllArgsConstructor
    @NoArgsConstructor
    public static class People{
        private int id;
        private String name;
        private int age;
    }
    public static void main(String[] args) throws Exception {
        // env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // TODO sink    自定义生产数据,将数据传送到Kafka
        DataStreamSource<People> peopleDataStreamSource = env.fromElements(new People(1, "zhangsan", 18),
                new People(2, "lisi", 20),
                new People(3, "wangwu", 22));
        Properties sinkProperties = new Properties();
        sinkProperties.setProperty("bootstrap.servers","hadoop111:9092");
        SingleOutputStreamOperator<String> map = peopleDataStreamSource.map(new MapFunction<People, String>() {
            @Override
            public String map(People value) throws Exception {//因为Kafka是识别不了Java里的数据类型的,因此要将其转换成String类型
                // 直接.toString也行,但是为了后面更好的反序列化,所以就转换成了JSONString
                return JSON.toJSONString(value);
            }
        });
        FlinkKafkaProducer<String> sinkKafka = new FlinkKafkaProducer<>("flink_kafka", new SimpleStringSchema(), sinkProperties);
        map.addSink(sinkKafka);

        // TODO source 对接上一步,接收kafka数据
        Properties sourceProperties = new Properties();
        sourceProperties.setProperty("bootstrap.servers","hadoop111:9092");
        sourceProperties.setProperty("group.id", "flink");//消费者组id
        sourceProperties.setProperty("auto.offset.reset","latest");
        sourceProperties.setProperty("flink.partition-discovery.interval-millis","5000");
        sourceProperties.setProperty("enable.auto.commit", "false");//自动提交,设置offset
        sourceProperties.setProperty("auto.commit.interval.ms", "2000");//自动提交的时间间隔
        FlinkKafkaConsumer<People> flink = new FlinkKafkaConsumer<People>("flink_kafka", new DeserializationSchema<People>() {
            @Override
            public TypeInformation<People> getProducedType() {
                // 定义返回的类型
                return TypeInformation.of(People.class);
            }

            @Override
            public People deserialize(byte[] message) throws IOException {
                // 引入import cn.hutool.json.JSONUtil;
                // 将String类型的数据,通过key值转换成对用的class
                return JSONUtil.toBean(new String(message),People.class);
            }

            @Override
            public boolean isEndOfStream(People nextElement) {
                return false;
            }
        },sourceProperties);

        DataStreamSource<People> peopleDataStreamSource1 = env.addSource(flink);

        peopleDataStreamSource1.print("反序列化结果:");// 反序列化结果::2> Kafka_Sink_Source.People(id=1, name=zhangsan, age=18)

        env.execute();
    }

}

这样数据就具有类的操作了

自定义Source-随机订单数据

注意: lombok的使用

Rich代表“富”,它可以获得运行环境的上下文,并拥有一些生命周期的方法

  • open是 Rich Function 的初始化方法,也就是会开启一个算子的生命周期。当一个算子的实际工作方法例如 map()或者 filter()方法被调用之前,open()会首先被调用。所以像文件 IO 的创建,数据库连接的创建,配置文件的读取等等这样一次性的工作,都适合在 open()方法中完成。
  • close()方法,是生命周期中的最后一个调用的方法,类似于解构方法。一般用来做一些清理工作。
  • run()
  • cancel()
  • 并且,每个transform方法都有对应的Rich抽象类

package com.pzb.source;

import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.source.RichParallelSourceFunction;

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

/**
 * Desc 演示DataStream-Source-自定义数据源
 * 需求:
 */
public class SourceDemo04_Customer {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        //TODO 1.source
        DataStream<Order> orderDS = env.addSource(new MyOrderSource()).setParallelism(2);

        //TODO 2.transformation

        //TODO 3.sink
        orderDS.print();

        //TODO 4.execute
        env.execute();
    }
    @Data
    @AllArgsConstructor
    @NoArgsConstructor
    public static class Order{
        private String id;
        private Integer userId;
        private Integer money;
        private Long createTime;
    }
    public static class MyOrderSource extends RichParallelSourceFunction<Order>{//Order为输出的数据类型

        private Boolean flag = true;
        //执行并生成数据
        @Override
        public void run(SourceContext<Order> ctx) throws Exception {//当线程启动时,会自动启动run方法
            Random random = new Random();
            while (flag) {
                //UUID是java.util包里的类,具有自定生成订单的功能
                String oid = UUID.randomUUID().toString();
                int userId = random.nextInt(3);
                int money = random.nextInt(101);
                long createTime = System.currentTimeMillis();
                ctx.collect(new Order(oid,userId,money,createTime));
                Thread.sleep(1000);
            }
        }

        //执行cancel命令的时候执行
        @Override
        public void cancel() {
            flag = false;
        }
    }
}

自定义Source-MySQL

package com.pzb.source;

import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.source.RichParallelSourceFunction;

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.PreparedStatement;
import java.sql.ResultSet;

/**
 * Desc 演示DataStream-Source-自定义数据源-MySQL
 * 需求:
 */
public class SourceDemo05_Customer_MySQL {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        //TODO 1.source
        DataStream<Student> studentDS = env.addSource(new MySQLSource()).setParallelism(1);

        //TODO 2.transformation

        //TODO 3.sink
        studentDS.print();

        //TODO 4.execute
        env.execute();
    }

   /*
   CREATE TABLE `t_student` (
    `id` int(11) NOT NULL AUTO_INCREMENT,
    `name` varchar(255) DEFAULT NULL,
    `age` int(11) DEFAULT NULL,
    PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=7 DEFAULT CHARSET=utf8;

INSERT INTO `t_student` VALUES ('1', 'jack', '18');
INSERT INTO `t_student` VALUES ('2', 'tom', '19');
INSERT INTO `t_student` VALUES ('3', 'rose', '20');
INSERT INTO `t_student` VALUES ('4', 'tom', '19');
INSERT INTO `t_student` VALUES ('5', 'jack', '18');
INSERT INTO `t_student` VALUES ('6', 'rose', '20');
    */

    @Data
    @NoArgsConstructor
    @AllArgsConstructor
    public static class Student {
        private Integer id;
        private String name;
        private Integer age;
    }
    
	// 貌似这些方法都会自动调用???是线程?
    public static class MySQLSource extends RichParallelSourceFunction<Student> {
        private boolean flag = true;
        // 数据库的连接对象
        private Connection conn = null;
        private PreparedStatement ps =null;
        private ResultSet rs  = null;
        //open只执行一次,适合开启资源
        @Override
        public void open(Configuration parameters) throws Exception {
            conn = DriverManager.getConnection("jdbc:mysql://localhost:3306/bigdata", "root", "root");
            String sql = "select id,name,age from t_student";
            ps = conn.prepareStatement(sql);// 执行SQL语句
        }

        //open后会启动run方法
        @Override
        public void run(SourceContext<Student> ctx) throws Exception {
            while (flag) {// 先设置死循环,让程序持续读取数据,调用cancel时,破除死循环
                rs = ps.executeQuery();//executeQuery会把数据库响应的查询结果存放在ResultSet类对象中供我们使用。
                while (rs.next()) {// 遍历Set里的值
                    int id = rs.getInt("id");//根据列标签获取对应的值
                    String name = rs.getString("name");
                    int age  = rs.getInt("age");
                    ctx.collect(new Student(id,name,age));
                }
                Thread.sleep(5000);
            }
        }

        //接收到cancel命令时取消数据生成
        @Override
        public void cancel() {
            flag = false;
        }

        //close里面关闭资源
        @Override
        public void close() throws Exception {
            if(conn != null) conn.close();
            if(ps != null) ps.close();
            if(rs != null) rs.close();

        }
    }

}

标签:flink,数据源,Flink,Source,env,org,apache,import,TODO
From: https://www.cnblogs.com/Mr-Sponge/p/17037250.html

相关文章