2024年最全使用flink的standalone模式同步Kafka的数据到clickhouse(2)，2024年最新2024大数据开发笔试真题

最新推荐文章于 2024-10-07 16:13:47 发布

2401_84615996

最新推荐文章于 2024-10-07 16:13:47 发布

阅读量602

点赞数 26

分类专栏：程序员文章标签：大数据面试学习

本文链接：https://blog.csdn.net/2401_84615996/article/details/138642210

版权

程序员专栏收录该内容

50 篇文章 0 订阅

订阅专栏

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上大数据知识点，真正体系化！

由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新

需要这份系统化资料的朋友，可以戳这里获取

phone_no String

) ENGINE = MergeTree ()
ORDER BY
(appKey, appVersion, deviceId, phone_no);


8.起一个Kafka生产者发送一条消息，然后观察clickhouse对应表里的情况


![](https://img-blog.csdnimg.cn/direct/003aeb55929b4cd0b786ccdc6404ddb2.png)


9.观察clickhouse表里数据的情况


![](https://img-blog.csdnimg.cn/direct/0326778926894a1b9ec10551442ab523.png)


### #代码


1.主程序类

package com.kszx;

import com.alibaba.fastjson.JSON;
import com.kszx.Mail;
import com.kszx.MyClickHouseUtil;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.streaming.api.TimeCharacteristic;
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 java.util.HashMap;
import java.util.Properties;

public class FlinkSinkClickhouse {

public static void main(String[] args) throws Exception {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    env.enableCheckpointing(5000);
    env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

    // source
    String topic = "topic_test2";

    Properties props = new Properties();
    // 设置连接kafka集群的参数
    props.setProperty("bootstrap.servers", "172.xx.xxx.x:9092,172.xx.xxx.x:9092,172.xx.xxx.x:9092");

    // 定义Flink Kafka Consumer
    FlinkKafkaConsumer<String> consumer = new FlinkKafkaConsumer<String>(topic, new SimpleStringSchema(), props);

    consumer.setStartFromGroupOffsets();
    consumer.setStartFromEarliest();    // 设置每次都从头消费

    // 添加source数据流
    DataStreamSource<String> source = env.addSource(consumer);
    source.print("111");
    System.out.println(source);
    SingleOutputStreamOperator<Mail> dataStream = source.map(new MapFunction<String, Mail>() {
        @Override
        public Mail map(String value) throws Exception {
            HashMap<String, String> hashMap = JSON.parseObject(value, HashMap.class);
            // System.out.println(hashMap);
            String appKey = hashMap.get("appKey");
            String appVersion = hashMap.get("appVersion");
            String deviceId = hashMap.get("deviceId");
            String phone_no = hashMap.get("phone_no");
            Mail mail = new Mail(appKey, appVersion, deviceId, phone_no);
            // System.out.println(mail);
            return mail;
        }
    });
    dataStream.print();

    // sink
    String sql = "INSERT INTO testmaxwell1.ods_countlyV2 (appKey, appVersion, deviceId, phone_no) " +
            "VALUES (?, ?, ?, ?)";
    MyClickHouseUtil ckSink = new MyClickHouseUtil(sql);
    dataStream.addSink(ckSink);


    env.execute();
}

}


2.工具类写入clickhouse

package com.kszx;

import com.kszx.Mail;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.functions.sink.RichSinkFunction;
import ru.yandex.clickhouse.ClickHouseConnection;
import ru.yandex.clickhouse.ClickHouseDataSource;
import ru.yandex.clickhouse.settings.ClickHouseProperties;
import ru.yandex.clickhouse.settings.ClickHouseQueryParam;

import java.sql.PreparedStatement;
import java.util.HashMap;
import java.util.Map;

public class MyClickHouseUtil extends RichSinkFunction {
private ClickHouseConnection conn = null;

String sql;

public MyClickHouseUtil(String sql) {
    this.sql = sql;
}

@Override
public void open(Configuration parameters) throws Exception {
    super.open(parameters);
    return ;
}

@Override
public void close() throws Exception {
    super.close();
    if (conn != null)
    {
        conn.close();
    }
}

@Override
public void invoke(Mail mail, Context context) throws Exception {

    String url = "jdbc:clickhouse://172.xx.xxx.xxx:8123/testmaxwell1";
    ClickHouseProperties properties = new ClickHouseProperties();
    properties.setUser("default");
    properties.setPassword("xxxxxx");
    properties.setSessionId("default-session-id2");

    ClickHouseDataSource dataSource = new ClickHouseDataSource(url, properties);
    Map<ClickHouseQueryParam, String> additionalDBParams = new HashMap<>();

    additionalDBParams.put(ClickHouseQueryParam.SESSION_ID, "new-session-id2");

    try {
        conn = dataSource.getConnection();
        PreparedStatement preparedStatement = conn.prepareStatement(sql);
        preparedStatement.setString(1,mail.getAppKey());
        preparedStatement.setString(2, mail.getAppVersion());
        preparedStatement.setString(3, mail.getDeviceId());
        preparedStatement.setString(4, mail.getPhone_no());

        preparedStatement.execute();
    }
    catch (Exception e){
        e.printStackTrace();
    }
}

}


3.表属性类

package com.kszx;

//package com.demo.flink.pojo;

public class Mail {
private String appKey;
private String appVersion;
private String deviceId;
private String phone_no;

public Mail(String appKey, String appVersion, String deviceId, String phone_no) {
    this.appKey = appKey;
    this.appVersion = appVersion;
    this.deviceId = deviceId;
    this.phone_no = phone_no;
}

public String getAppKey() {
    return appKey;
}

public void setAppKey(String appKey) {
    this.appKey = appKey;
}

public String getAppVersion() {
    return appVersion;
}

public void setAppVersion(String appVersion) {
    this.appVersion = appVersion;
}

public String getDeviceId() {
    return deviceId;
}

public void setDeviceId(String deviceId) {
    this.deviceId = deviceId;
}

public String getPhone_no() {
    return phone_no;
}

public void setPhone_no(String phone_no) {
    this.phone_no = phone_no;
}

@Override
public String toString() {
    return "Mail{" +
            "appKey='" + appKey + '\'' +
            ", appVersion='" + appVersion + '\'' +
            ", deviceId='" + deviceId + '\'' +
            ", phone_no='" + phone_no + '\'' +
            '}';
}

public Mail of(String appKey, String appVersion, String deviceId, String phone_no)
{
    return new Mail(appKey, appVersion, deviceId, phone_no);
}

}


4.pom依赖(注意打包在服务器上运行时会和flink的lib目录下的log4j依赖冲突的问题，如果在服务器上执行jar包时依赖冲突报错的话，最好屏幕代码里的依赖，保留flink原版lib下的依赖)

<?xml version="1.0" encoding="UTF-8"?>

4.0.0

<groupId>com.kszx</groupId>
<artifactId>flink1kc</artifactId>
<version>1.0-SNAPSHOT</version>

<properties>
    <maven.compiler.source>8</maven.compiler.source>
    <maven.compiler.target>8</maven.compiler.target>
</properties>

<dependencies>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-java</artifactId>
        <version>1.11.1</version>
    </dependency>

    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-clients_2.11</artifactId>
        <version>1.11.1</version>
    </dependency>

    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-connector-kafka_2.11</artifactId>
        <version>1.11.1</version>
    </dependency>



    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-table-api-java-bridge_2.11</artifactId>
        <version>1.11.1</version>