Flink Java CDC

概述

CDC Connectors for Apache Flink 是一组用于Apache Flink 的源连接器，使用变更数据捕获 (CDC) 从不同数据库获取变更。用于 Apache Flink 的 CDC 连接器将 Debezium 集成为捕获数据更改的引擎。所以它可以充分发挥 Debezium 的能力。

支持的连接器

支持的 flink

flink cdc version	flink version
1.0.0	1.11.*
1.1.0	1.11.*
1.2.0	1.12.*
1.3.0	1.12.*
1.4.0	1.13.*
2.0.*	1.13.*
2.1.*	1.13.*
2.2.*	1.13.*, 1.14.*

特色

支持读取数据库快照，即使发生故障也能继续读取binlog，一次处理。

DataStream API 的 CDC 连接器，用户可以在单个作业中使用多个数据库和表的更改，而无需部署 Debezium 和 Kafka。

Table/SQL API 的 CDC 连接器，用户可以使用 SQL DDL 创建 CDC 源来监控单个表的更改。

Table SQL API

-- creates a mysql cdc table source
CREATE TABLE mysql_binlog (
 id INT NOT NULL,
 name STRING,
 description STRING,
 weight DECIMAL(10,3),
 PRIMARY KEY(id) NOT ENFORCED
) WITH (
 'connector' = 'mysql-cdc',
 'hostname' = 'localhost',
 'port' = '3306',
 'username' = 'flinkuser',
 'password' = 'flinkpw',
 'database-name' = 'inventory',
 'table-name' = 'products'
);

-- read snapshot and binlog data from mysql, and do some transformation, and show on the client
SELECT id, UPPER(name), description, weight FROM mysql_binlog;

DataStream API

<dependency>
  <groupId>com.ververica</groupId>
  <!-- add the dependency matching your database -->
  <artifactId>flink-connector-mysql-cdc</artifactId>
  <!-- The dependency is available only for stable releases, SNAPSHOT dependency need build by yourself. -->
  <version>2.3-SNAPSHOT</version>
</dependency>

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import com.ververica.cdc.debezium.JsonDebeziumDeserializationSchema;
import com.ververica.cdc.connectors.mysql.source.MySqlSource;

public class MySqlBinlogSourceExample {
  public static void main(String[] args) throws Exception {
    MySqlSource<String> mySqlSource = MySqlSource.<String>builder()
            .hostname("yourHostname")
            .port(yourPort)
            .databaseList("yourDatabaseName") // set captured database
            .tableList("yourDatabaseName.yourTableName") // set captured table
            .username("yourUsername")
            .password("yourPassword")
            .deserializer(new JsonDebeziumDeserializationSchema()) // converts SourceRecord to JSON String
            .build();
    
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    
    // enable checkpoint
    env.enableCheckpointing(3000);
    
    env
      .fromSource(mySqlSource, WatermarkStrategy.noWatermarks(), "MySQL Source")
      // set 4 parallel source tasks
      .setParallelism(4)
      .print().setParallelism(1); // use parallelism 1 for sink to keep message ordering
    
    env.execute("Print MySQL Snapshot + Binlog");
  }
}

数据

{
  "before": {
    "id": 111,
    "name": "scooter",
    "description": "Big 2-wheel scooter",
    "weight": 5.18
  },
  "after": {
    "id": 111,
    "name": "scooter",
    "description": "Big 2-wheel scooter",
    "weight": 5.15
  },
  "source": {...},
  "op": "u",  // the operation type, "u" means this this is an update event 
  "ts_ms": 1589362330904,  // the time at which the connector processed the event
  "transaction": null
}