FlinkCDC初体验

大数据002024-08-18 13:03

1、pom依赖

XML 复制代码 
<?xml version="1.0" encoding="UTF-8"?>

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <groupId>org.example</groupId>
  <artifactId>Flink1.17.2</artifactId>
  <version>1.0-SNAPSHOT</version>

  <name>Flink1.17.2</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>

    <repositories>
        <repository>
            <id>oss.sonatype.org-snapshot</id>
            <name>OSS Sonatype Snapshot Repository</name>
            <url>http://oss.sonatype.org/content/repositories/snapshots</url>
            <releases>
                <enabled>false</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
        </repository>
        <repository>
            <id>apache.snapshots</id>
            <name>Apache Development Snapshot Repository</name>
            <url>https://repository.apache.org/content/repositories/snapshots/</url>
            <releases>
                <enabled>false</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
        </repository>
    </repositories>
  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <scala.version>2.12.7</scala.version>
    <scala.binary.version>2.12</scala.binary.version>
    <flink.version>1.17.2</flink.version>
    <java.version>1.8</java.version>
    <maven.compiler.source>1.8</maven.compiler.source>
    <maven.compiler.target>1.8</maven.compiler.target>
  </properties>

  <dependencies>
<!--    <dependency>-->
<!--      <groupId>com.alibaba.flink</groupId>-->
<!--      <artifactId>datahub-connector</artifactId>-->
<!--      <version>0.1-SNAPSHOT</version>-->
<!--      <classifier>jar-with-dependencies</classifier>-->
<!--    </dependency>-->
<!--     https://mvnrepository.com/artifact/com.alibaba.ververica/ververica-connector-datahub -->
        <dependency>
          <groupId>com.alibaba.ververica</groupId>
          <artifactId>ververica-connector-datahub</artifactId>
          <version>1.17-vvr-8.0.8</version>
            <scope>provided</scope>
        </dependency>
      <!-- https://mvnrepository.com/artifact/com.alibaba.ververica/ververica-connector-common -->
      <dependency>
          <groupId>com.alibaba.ververica</groupId>
          <artifactId>ververica-connector-common</artifactId>
          <version>1.17-vvr-8.0.8</version>
          <scope>provided</scope>
      </dependency>
      <dependency>
          <groupId>com.alibaba.ververica</groupId>
          <artifactId>ververica-connector-continuous-odps</artifactId>
          <version>1.17-vvr-8.0.8</version>
          <scope>provided</scope>
      </dependency>
      <dependency>
          <groupId>org.apache.flink</groupId>
          <artifactId>flink-connector-base</artifactId>
          <version>${flink.version}</version>
<!--          <scope>provided</scope>-->
      </dependency>

    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-core -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-core</artifactId>
      <version>${flink.version}</version>
<!--        <scope>provided</scope>-->
    </dependency>
    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-java -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-java</artifactId>
      <version>${flink.version}</version>
<!--        <scope>provided</scope>-->
    </dependency>
      <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-clients -->
      <dependency>
          <groupId>org.apache.flink</groupId>
          <artifactId>flink-clients</artifactId>
          <version>${flink.version}</version>
<!--          <scope>provided</scope>-->
      </dependency>

    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-java -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-streaming-java</artifactId>
      <version>${flink.version}</version>
<!--            <scope>provided</scope>-->
    </dependency>
    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-runtime -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-runtime</artifactId>
      <version>${flink.version}</version>
<!--            <scope>provided</scope>-->
    </dependency>
    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-table-common -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-table-common</artifactId>
      <version>${flink.version}</version>
<!--      <scope>provided</scope>-->
    </dependency>
    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-table-api-java-bridge -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-table-api-java-bridge</artifactId>
      <version>${flink.version}</version>
<!--      <scope>provided</scope>-->
    </dependency>
    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-table-planner -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-table-planner_2.12</artifactId>
      <version>${flink.version}</version>
<!--      <scope>test</scope>-->
    </dependency>

    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-connector-hive -->
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-connector-hive_2.12</artifactId>
      <version>${flink.version}</version>
      <scope>provided</scope>
    </dependency>

    <dependency>
      <groupId>org.scala-lang</groupId>
      <artifactId>scala-library</artifactId>
      <version>2.12.7</version>
<!--            <scope>provided</scope>-->
    </dependency>
    <!-- https://mvnrepository.com/artifact/org.projectlombok/lombok -->
    <dependency>
      <groupId>org.projectlombok</groupId>
      <artifactId>lombok</artifactId>
      <version>1.18.34</version>
      <!--      <scope>provided</scope>-->
    </dependency>
    <dependency>
      <groupId>mysql</groupId>
      <artifactId>mysql-connector-java</artifactId>
      <version>8.0.23</version>
        <scope>provided</scope>
    </dependency>
      <!-- https://mvnrepository.com/artifact/com.ververica/flink-connector-debezium -->
      <dependency>
          <groupId>com.ververica</groupId>
          <artifactId>flink-connector-debezium</artifactId>
          <version>2.2.0</version>
<!--          <scope>provided</scope>-->
      </dependency>

    <dependency>
      <groupId>com.ververica</groupId>
      <artifactId>flink-connector-mysql-cdc</artifactId>
      <version>2.2.0</version>
<!--      <scope>provided</scope>-->
    </dependency>
    <dependency>
          <groupId>com.ververica</groupId>
          <artifactId>flink-sql-connector-mysql-cdc</artifactId>
          <version>2.2.0</version>
<!--          <scope>provided</scope>-->
      </dependency>


  </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.1</version>
                <configuration>
                    <source>${java.version}</source>
                    <target>${java.version}</target>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.2.4</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <finalName>${project.artifactId}-${project.version}-flink-fat-jar</finalName>
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass>com.tbea.cdc.FlinkCDCStreamExample</mainClass> <!-- 指定你的主类，例如 org.example.MyFlinkJob -->
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

2、FlinkCDC-SQL

java 复制代码 
package com.tbea.cdc;

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;
import org.apache.flink.table.api.*;

public class FlinkCDCSqlExample {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);

        // 创建HiveCatalog
//        String name            = "myhive";
//        String defaultDatabase = "mydatabase";
//        String hiveConfDir      = "/path/to/your/hive/conf"; // 替换为你的Hive配置文件夹路径
//        HiveCatalog hiveCatalog = new HiveCatalog(name, defaultDatabase, hiveConfDir);
//        tableEnv.registerCatalog("myhive", hiveCatalog);
//
//        // 设置HiveCatalog为当前catalog
//        tableEnv.useCatalog("myhive");


        // 注册MySQL表
        String sourceDDL = "CREATE TABLE source_table (" +
                " id INT," +
                " name STRING," +
                " age INT," +
                " addr STRING ,"+
                " create_time timestamp,"+
                " PRIMARY KEY (id) NOT ENFORCED" +
                ") WITH (" +
                " 'connector' = 'mysql-cdc'," +
                " 'hostname' = '192.168.140.1'," + // 替换为你的MySQL主机名
                " 'port' = '3306'," +
                " 'username' = 'flink'," + // 替换为你的MySQL用户名
                " 'password' = 'flink'," + // 替换为你的MySQL密码
                " 'database-name' = 'flinkcdc'," + // 替换为你的数据库名
                " 'table-name' = 'user_info'," + // 替换为你的表名
                //                " 'scan.startup.timestamp-millis' = '1000',"+
                " 'scan.incremental.snapshot.enabled' = 'true',"+
                " 'scan.incremental.snapshot.chunk.size' = '8096'," +
                " 'scan.startup.mode' = 'latest-offset'," +
                " 'debezium.snapshot.mode'= 'latest',"+
                " 'scan.newly-added-table.enabled' = 'true'"+
//                " 'debezium.skipped.operations'='d'" +
                ")";

        tableEnv.executeSql(sourceDDL);

        // 查询并打印数据
        TableResult result = tableEnv.executeSql("SELECT id,name,age,addr,create_time FROM source_table");

        result.print();
        env.execute();
    }
}

运行结果：

3、FlinkCDC-DataStream

java 复制代码 
package com.tbea.cdc;

import com.ververica.cdc.connectors.mysql.source.MySqlSource;
import com.ververica.cdc.connectors.mysql.table.StartupOptions;
import com.ververica.cdc.debezium.JsonDebeziumDeserializationSchema;
import com.ververica.cdc.debezium.StringDebeziumDeserializationSchema;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.restartstrategy.RestartStrategies;
import org.apache.flink.api.common.time.Time;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

public class FlinkCDCStreamExample {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        MySqlSource<String> mySqlSource = MySqlSource.<String>builder()
                .hostname("192.168.140.1")
                .port(3306)
                // 设置捕获的数据库
                .databaseList("flinkcdc")
                // 设置捕获的表 [product, user, address]
                .tableList("flinkcdc.*")
                .username("flink")
                .password("flink")
                .deserializer(new JsonDebeziumDeserializationSchema()) // 将 SourceRecord 转换为 JSON 字符串
                // 启用扫描新添加的表功能
                .scanNewlyAddedTableEnabled(true)
                .startupOptions(StartupOptions.latest())
                .build();
        // 你的业务代码
        // 设置 3s 的 checkpoint 间隔
        env.setParallelism(1);
        env.setRestartStrategy(RestartStrategies.failureRateRestart(1, Time.seconds(3L),Time.seconds(5L)));
        env.enableCheckpointing(3000);

        DataStreamSource<String> dataStreamSource = env.fromSource(mySqlSource, WatermarkStrategy.noWatermarks(), "Mysql-Source");
        dataStreamSource.print();


        env.execute("Print MySQL Snapshot + Binlog");
    }
}

运行结果：

java 复制代码 
{"before":null,"after":{"id":22,"name":"杨延昭","age":45,"addr":"辽宁","create_time":1723798965000},"source":{"version":"1.5.4.Final","connector":"mysql","name":"mysql_binlog_source","ts_ms":1723770167000,"snapshot":"false","db":"flinkcdc","sequence":null,"table":"user_info","server_id":1,"gtid":null,"file":"YANGYINGCHUN-bin.000004","pos":8640,"row":0,"thread":null,"query":null},"op":"c","ts_ms":1723770167469,"transaction":null}

{"before":{"id":17,"name":"储熊","age":28,"addr":"张北","create_time":null},"after":{"id":17,"name":"储熊","age":28,"addr":"张北","create_time":1723798410000},"source":{"version":"1.5.4.Final","connector":"mysql","name":"mysql_binlog_source","ts_ms":1723769613000,"snapshot":"false","db":"flinkcdc","sequence":null,"table":"user_info","server_id":1,"gtid":null,"file":"YANGYINGCHUN-bin.000004","pos":6540,"row":0,"thread":null,"query":null},"op":"u","ts_ms":1723769613737,"transaction":null}

{"before":{"id":8,"name":"赵刚","age":33,"addr":"延安","create_time":1724230872000},"after":null,"source":{"version":"1.5.4.Final","connector":"mysql","name":"mysql_binlog_source","ts_ms":1723770354000,"snapshot":"false","db":"flinkcdc","sequence":null,"table":"user_info","server_id":1,"gtid":null,"file":"YANGYINGCHUN-bin.000004","pos":8968,"row":0,"thread":null,"query":null},"op":"d","ts_ms":1723770354642,"transaction":null}
相关推荐
老周聊架构1 小时前
聊聊Flink：Flink的状态管理
大数据·flink
ssxueyi19 小时前
如何查看flink错误信息
大数据·flink
core5121 天前
flink SQL实现mysql source sink
mysql·flink·jdbc·source·cdc·sink·mysql-cdc
天冬忘忧1 天前
Flink调优----资源配置调优与状态及Checkpoint调优
大数据·flink
Ekine2 天前
【Flink-scala】DataStream编程模型之状态编程
大数据·flink·scala
别这么骄傲4 天前
使用Flinkcdc 采集mysql数据
大数据·数据库·flink
core5124 天前
flink实现复杂kafka数据读取
大数据·flink·kafka·cdc
xyz20114 天前
Flink State面试题和参考答案-（下）
flink·状态模式
ssxueyi5 天前
Flink CDC 读取oracle库数据性能优化
大数据·oracle·性能优化·flink
ssxueyi5 天前
Flink SQL保留关键字
大数据·sql·flink·保留关键字
热门推荐
01〔AI 绘画〕Stable Diffusion 之 解决绘制多人或面部很小的人物时面部崩坏问题 篇02YOLOv8训练好模型后，追加轮数继续训练、或者提前终止训练，缩减训练轮数03玄机平台应急响应—webshell查杀04SQL 主从数据库实时备份05HCIA-datacom数通题库和录播视频资料06Docker 夺命连环 15 问07VSCode插件 —— Cody AI （免费AI助手！）08校验 GPT-4 真实性的三个经典问题：快速区分 GPT-3.5 与 GPT-4，并提供免费测试网站09(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明10组基轨迹建模 GBTM的介绍与实现（Stata 或 R）