美文网首页
Flink 学习 —— 自定义 Data Source

Flink 学习 —— 自定义 Data Source

作者: 白习习_c942 | 来源:发表于2019-07-25 00:08 被阅读0次

    准备工作

    首先你需要安装好了 FLink 和 Kafka 。
    运行启动 Flink、Zookepeer、Kafka,


    image.png
    image.png
    image.png

    好了,都启动了!

    • maven依赖
    <groupId>com.bai</groupId>
        <artifactId>flink-demo</artifactId>
        <version>1.0-SNAPSHOT</version>
    
        <properties>
            <compiler.version>1.8</compiler.version>
            <flink.version>1.8.0</flink.version>
            <java.version>1.8</java.version>
            <scala.binary.version>2.11</scala.binary.version>
    
            <maven.compiler.source>1.8</maven.compiler.source>
            <maven.compiler.target>1.8</maven.compiler.target>
            <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        </properties>
    
    
        <dependencies>
            <!--flink java-->
            <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>${flink.version}</version>
            </dependency>
            <!--日志-->
            <dependency>
                <groupId>org.slf4j</groupId>
                <artifactId>slf4j-log4j12</artifactId>
                <version>1.7.7</version>
                <scope>runtime</scope>
            </dependency>
            <dependency>
                <groupId>log4j</groupId>
                <artifactId>log4j</artifactId>
                <version>1.2.17</version>
                <scope>runtime</scope>
            </dependency>
            <!--flink kafka connector-->
            <dependency>
                <groupId>org.apache.flink</groupId>
                <artifactId>flink-connector-kafka-0.11_${scala.binary.version}</artifactId>
                <version>${flink.version}</version>
            </dependency>
            <!--alibaba fastjson-->
            <dependency>
                <groupId>com.alibaba</groupId>
                <artifactId>fastjson</artifactId>
                <version>1.2.51</version>
            </dependency>
    
            <dependency>
                <groupId>org.projectlombok</groupId>
                <artifactId>lombok</artifactId>
                <version>1.18.8</version>
            </dependency>
    
        </dependencies>
    
    • 实体类
    package com.baiyu.flink.model;
    
    
    import lombok.*;
    
    import java.util.Map;
    
    /**
     * Desc:
     * auth: baiyu
     */
    @Getter
    @Setter
    @ToString
    @NoArgsConstructor
    @AllArgsConstructor
    public class Metric {
        public String name;
        public long timestamp;
        public Map<String, Object> fields;
        public Map<String, String> tags;
    
    }
    

    往 kafka 中写数据工具类:KafkaUtils.java

    package com.baiyu.flink.utils;
    
    import com.alibaba.fastjson.JSON;
    import com.baiyu.flink.model.Metric;
    import org.apache.kafka.clients.producer.KafkaProducer;
    import org.apache.kafka.clients.producer.ProducerRecord;
    
    import java.util.HashMap;
    import java.util.Map;
    import java.util.Properties;
    
    /**
     * auth: baiyu
     * 往kafka中写数据
     * 可以使用这个main函数进行测试一下
     */
    public class KafkaUtils {
        public static final String broker_list = "localhost:9092";
        public static final String topic = "metric";  // kafka topic,Flink 程序中需要和这个统一
    
        public static void writeToKafka() throws InterruptedException {
            Properties props = new Properties();
            props.put("bootstrap.servers", broker_list);
            props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer"); //key 序列化
            props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer"); //value 序列化
            KafkaProducer producer = new KafkaProducer<String, String>(props);
    
            Metric metric = new Metric();
            metric.setTimestamp(System.currentTimeMillis());
            metric.setName("mem");
            Map<String, String> tags = new HashMap<>();
            Map<String, Object> fields = new HashMap<>();
    
            tags.put("cluster", "baiyu");
            tags.put("host_ip", "10.211.55.2");
    
            fields.put("used_percent", 95d);
            fields.put("max", 27244873d);
            fields.put("used", 17244873d);
            fields.put("init", 27244873d);
    
            metric.setTags(tags);
            metric.setFields(fields);
    
            ProducerRecord record = new ProducerRecord<String, String>(topic, null, null, JSON.toJSONString(metric));
            producer.send(record);
            System.out.println("发送数据=>: " + JSON.toJSONString(metric));
    
            producer.flush();
        }
    
        public static void main(String[] args) throws InterruptedException {
            while (true) {
                Thread.sleep(300);
                writeToKafka();
            }
        }
    }
    

    运行:


    image.png

    如果出现如上图标记的,即代表能够不断的往 kafka 发送数据的。

    FLINK程序

    package com.baiyu.flink;
    
    import org.apache.flink.api.common.serialization.SimpleStringSchema;
    import org.apache.flink.streaming.api.datastream.DataStreamSource;
    import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
    import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer011;
    
    import java.util.Properties;
    
    /**
     * Desc:
     * auth: baiyu
     */
    public class Main {
        public static void main(String[] args) throws Exception {
            final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    
            Properties props = new Properties();
            props.put("bootstrap.servers", "localhost:9092");
            props.put("zookeeper.connect", "localhost:2181");
            props.put("group.id", "metric-group");
            props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");  //key 反序列化
            props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
            props.put("auto.offset.reset", "latest"); //value 反序列化
    
            DataStreamSource<String> dataStreamSource = env.addSource(new FlinkKafkaConsumer011<>(
                    "metric",  //kafka topic
                    new SimpleStringSchema(),  // String 序列化
                    props)).setParallelism(1);
    
            dataStreamSource.print(); //把从 kafka 读取到的数据打印在控制台
    
            env.execute("Flink add data source");
        }
    }
    

    运行起来(刚才发送的程序需要启动状态):


    image.png

    看到没程序,Flink 程序控制台能够源源不断的打印数据呢。

    自定义source

    上面就是 Flink 自带的 Kafka source,那么接下来就模仿着写一个从 MySQL 中读取数据的 Source。
    首先 pom.xml 中添加 MySQL 依赖:

            <dependency>
                <groupId>mysql</groupId>
                <artifactId>mysql-connector-java</artifactId>
                <version>8.0.16</version>
            </dependency>
    

    数据库建表如下:

    DROP TABLE IF EXISTS `Student`;
    CREATE TABLE `Student` (
      `id` int(11) unsigned NOT NULL AUTO_INCREMENT,
      `name` varchar(25) COLLATE utf8_bin DEFAULT NULL,
      `password` varchar(25) COLLATE utf8_bin DEFAULT NULL,
      `age` int(10) DEFAULT NULL,
      PRIMARY KEY (`id`)
    ) ENGINE=InnoDB AUTO_INCREMENT=5 DEFAULT CHARSET=utf8 COLLATE=utf8_bin;
    

    插入数据:

    INSERT INTO `Student` VALUES ('1', 'zhisheng01', '123456', '18'), ('2', 'zhisheng02', '123', '17'), ('3', 'zhisheng03', '1234', '18'), ('4', 'zhisheng04', '12345', '16');
    COMMIT;
    

    新建实体类:Student.java

    package com.baiyu.flink.model;
    
    import lombok.*;
    
    /**
     * Desc:
     * auth: baiyu
     */
    
    @Setter
    @Getter
    @ToString
    @NoArgsConstructor
    @AllArgsConstructor
    public class Student {
        public int id;
        public String name;
        public String password;
        public int age;
    
    }
    

    新建 Source 类 SourceFromMySQL.java,该类继承 RichSourceFunction ,实现里面的 open、close、run、cancel 方法:

    package com.baiyu.flink.source;
    
    import com.baiyu.flink.model.Student;
    import org.apache.flink.configuration.Configuration;
    import org.apache.flink.streaming.api.functions.source.RichSourceFunction;
    import org.apache.flink.streaming.api.functions.source.SourceFunction;
    
    import java.sql.Connection;
    import java.sql.DriverManager;
    import java.sql.PreparedStatement;
    import java.sql.ResultSet;
    
    
    /**
     * Desc:
     * auth: baiyu
     */
    public class SourceFromMySQL extends RichSourceFunction<Student> {
    
        PreparedStatement ps;
        private Connection connection;
    
        /**
         * open() 方法中建立连接,这样不用每次 invoke 的时候都要建立连接和释放连接。
         *
         * @param parameters
         * @throws Exception
         */
        @Override
        public void open(Configuration parameters) throws Exception {
            super.open(parameters);
            connection = getConnection();
            String sql = "select * from Student;";
            ps = this.connection.prepareStatement(sql);
        }
    
        /**
         * 程序执行完毕就可以进行,关闭连接和释放资源的动作了
         *
         * @throws Exception
         */
        @Override
        public void close() throws Exception {
            super.close();
            if (connection != null) { //关闭连接和释放资源
                connection.close();
            }
            if (ps != null) {
                ps.close();
            }
        }
    
        /**
         * DataStream 调用一次 run() 方法用来获取数据
         *
         * @param ctx
         * @throws Exception
         */
        @Override
        public void run(SourceContext<Student> ctx) throws Exception {
            ResultSet resultSet = ps.executeQuery();
            while (resultSet.next()) {
                Student1 student = new Student(
                        resultSet.getInt("id"),
                        resultSet.getString("name").trim(),
                        resultSet.getString("password").trim(),
                        resultSet.getInt("age"));
                ctx.collect(student);
            }
        }
    
        @Override
        public void cancel() {
        }
    
        private static Connection getConnection() {
            Connection con = null;
            try {
                con = DriverManager.getConnection("jdbc:mysql://localhost:3306/baiyu?useUnicode=true&characterEncoding=UTF-8", "user", "root");
            } catch (Exception e) {
                System.out.println("-----------mysql get connection has exception , msg = "+ e.getMessage());
            }
            return con;
        }
    }
    

    Flink 程序:

    package com.baiyu.flink;
    
    import com.baiyu.flink.source.SourceFromMySQL;
    import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
    
    /**
     * Desc:
     * auth: baiyu
     */
    public class FlinkMain {
        public static void main(String[] args) throws Exception {
            final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    
            env.addSource(new SourceFromMySQL()).print();
    
            env.execute("Flink add data sourc");
        }
    }
    

    运行 Flink 程序,控制台日志中可以看见打印的 student 信息。


    image.png
    • RichSourceFunction
      从上面自定义的 Source 可以看到我们继承的就是这个 RichSourceFunction 类,那么来了解一下:
      image.png
      一个抽象类,继承自 AbstractRichFunction。为实现一个 Rich SourceFunction 提供基础能力。该类的子类有三个,两个是抽象类,在此基础上提供了更具体的实现,另一个是 ContinuousFileMonitoringFunction。
      image.png
    • MessageAcknowledgingSourceBase :它针对的是数据源是消息队列的场景并且提供了基于 ID 的应答机制。
    • MultipleIdsMessageAcknowledgingSourceBase : 在 MessageAcknowledgingSourceBase 的基础上针对 ID 应答机制进行了更为细分的处理,支持两种 ID 应答模型:session id 和 unique message id。
    • ContinuousFileMonitoringFunction:这是单个(非并行)监视任务,它接受 FileInputFormat,并且根据 FileProcessingMode 和 FilePathFilter,它负责监视用户提供的路径;决定应该进一步读取和处理哪些文件;创建与这些文件对应的 FileInputSplit 拆分,将它们分配给下游任务以进行进一步处理。

    写在最后

    本文主要讲了下 Flink 使用 Kafka Source 的使用,并提供了一个 demo 教大家如何自定义 Source,从 MySQL 中读取数据,当然你也可以从其他地方读取,实现自己的数据源 source。可能平时工作会比这个更复杂,需要大家灵活应对!

    相关文章

      网友评论

          本文标题:Flink 学习 —— 自定义 Data Source

          本文链接:https://www.haomeiwen.com/subject/eopqrctx.html