SpringBoot 实战：SpringBoot整合Flink CDC，实时追踪mysql数据变动

引言

Flink CDC（Flink Change Data Capture）即 Flink 的变更数据捕获技术，是一种基于数据库日志的CDC技术，它实现了一个全增量一体化的数据集成框架。与Flink计算框架相结合，Flink CDC能够高效地实现海量数据的实时集成。其核心功能在于实时监视数据库或数据流中的数据变动，并将这些变动抽取出来，以便进行进一步的处理和分析。借助Flink CDC，用户可以轻松地构建实时数据管道，实时响应和处理数据变动，为实时分析、实时报表和实时决策等场景提供有力支持。

一、MySQL开启Binlog

MySQL开启 BinLong 功能，需要在配置文件中 修改 [mysql]的相关参数（lunux 中 /etc/my.cnf 文件 或windows 的 /my.ini 文件）

[mysqld]
server-id=1
# 设置日志格式为行级格式
binlog-format=Row
# 设置binlog日志文件的前缀
log-bin=mysql-bin
# 指定需要记录二进制日志的数据库
binlog_do_db=testjpa

开启Binlog 后，在需要 为 Flink CDC 配置响应的权限，使其能够正常链接到 MySQL数据库，包括授权 Flink CDC 链接 数据库的用户权限。

mysql> SHOW VARIABLES LIKE 'log_bin';
+---------------+-------+
| Variable_name | Value |
+---------------+-------+
| log_bin | ON |
+---------------+-------+

二、代码示例

创建Spring Boot项目添加依赖

<dependencies>
    <!-- Flink dependency -->
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-java</artifactId>
        <version>1.14.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-streaming-java_2.12</artifactId>
        <version>1.14.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-connector-mysql-cdc</artifactId>
        <version>2.0.0</version>
    </dependency>
    <!-- Spring Boot dependencies -->
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter</artifactId>
    </dependency>
</dependencies>

配置Flink和MySQL CDC

flink:
  checkpoint:
    interval: 10000
  parallelism: 1

spring:
  datasource:
    url: jdbc:mysql://localhost:3306/your_database
    username: your_username
    password: your_password

创建服务类实现实时跟踪

import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
import org.springframework.stereotype.Service;

@Service
public class FlinkCdcService {

    public void startDataStreaming() {
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        final StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);

        // 使用Flink CDC连接MySQL
        String name = "inventory";
        tableEnv.executeSql("CREATE TABLE " + name + " (" +
            " id INT," +
            " name STRING," +
            " description STRING," +
            " weight DECIMAL(10, 3)" +
            ") WITH (" +
            " 'connector' = 'mysql-cdc'," +
            " 'hostname' = 'localhost'," +
            " 'port' = '3306'," +
            " 'username' = 'your_username'," +
            " 'password' = 'your_password'," +
            " 'database-name' = 'your_database'," +
            " 'table-name' = 'your_table'" +
            ")");

        // 查询并打印结果
        DataStream<String> dataStream = tableEnv.sqlQuery("SELECT * FROM " + name).execute().print();

        try {
            env.execute("Flink CDC Demo");
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

配置 SpringBoot 启动类

import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.CommandLineRunner;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;

@SpringBootApplication
public class FlinkCdcApplication implements CommandLineRunner {

    @Autowired
    private FlinkCdcService flinkCdcService;

    public static void main(String[] args) {
        SpringApplication.run(FlinkCdcApplication.class, args);
    }

    @Override
    public void run(String... args) throws Exception {
        flinkCdcService.startDataStreaming();
    }
}