FlinkCDC从Mysql数据写入Kafka

环境安装：

　　1.jdk

　　2.Zookeeper

　　3.Kafka

　　4.maven

　　5.开启Mysql的binlog

一、binlog监控Mysql的库

二、编写FlinkCDC程序

1.添加pom文件

<?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 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.lxz</groupId>
    <artifactId>gmall-logger</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>gmall-20210909</name>
    <description>Demo project for Spring Boot</description>

    <properties>
        <java.version>1.8</java.version>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <spring-boot.version>2.4.1</spring-boot.version>
        <maven.compiler.source>${java.version}</maven.compiler.source>
        <maven.compiler.target>${java.version}</maven.compiler.target>
        <flink.version>1.12.0</flink.version>
        <scala.version>2.12</scala.version>
        <hadoop.version>3.1.3</hadoop.version>
    </properties>

    <dependencies>
        <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_${scala.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_${scala.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-cep_${scala.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-json</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.68</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba.ververica</groupId>
            <artifactId>flink-connector-mysql-cdc</artifactId>
            <version>1.2.0</version>
        </dependency>

        <!--如果保存检查点到hdfs上，需要引入此依赖-->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <!--Flink默认使用的是slf4j记录日志，相当于一个日志的接口,我们这里使用log4j作为具体的日志实现-->
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>1.7.25</version>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.25</version>
        </dependency>

        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version>2.14.0</version>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.kafka</groupId>
            <artifactId>spring-kafka</artifactId>
        </dependency>

        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <optional>true</optional>
        </dependency>
    </dependencies>

    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-dependencies</artifactId>
                <version>${spring-boot.version}</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.8.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
                <version>2.3.0.RELEASE</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>repackage</goal>
                        </goals>
                    </execution>
                </executions>
                <configuration>
                    <classifier>boot</classifier>
                    <mainClass>com.lxz.gamll20210909.Gamll20210909Application</mainClass>
                </configuration>
            </plugin>


        </plugins>
    </build>
</project>

2.MykafkaUtil工具类

import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer;
import java.util.Properties;

public class MyKafkaUtil {
    private static String KAFKA_SERVER = "hadoop201:9092,hadoop202:9092,hadoop203:9092";
    private static Properties properties =  new Properties();
    static {
        properties.setProperty("bootstrap.servers",KAFKA_SERVER);
    }
    public static FlinkKafkaProducer<String> getKafkaSink(String topic){
        return new FlinkKafkaProducer<String>(topic,new SimpleStringSchema(),properties);
    }
}

3.FlinkCDC主程序

import com.alibaba.fastjson.JSONObject;
import com.alibaba.ververica.cdc.connectors.mysql.MySQLSource;
import com.alibaba.ververica.cdc.connectors.mysql.table.StartupOptions;
import com.alibaba.ververica.cdc.debezium.DebeziumDeserializationSchema;
import com.alibaba.ververica.cdc.debezium.DebeziumSourceFunction;
import com.lxz.gamll20210909.util.MyKafkaUtil;
import io.debezium.data.Envelope;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
import org.apache.kafka.connect.data.Field;
import org.apache.kafka.connect.data.Schema;
import org.apache.kafka.connect.data.Struct;
import org.apache.kafka.connect.source.SourceRecord;

public class Flink_CDCWithCustomerSchema {

    public static void main(String[] args) throws Exception {

        //1.创建执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);

        //2.创建Flink-MySQL-CDC的Source
        DebeziumSourceFunction<String> mysqlSource = MySQLSource.<String>builder()
                .hostname("hadoop201")
                .port(3306)
                .username("root")
                .password("000000")
                .databaseList("gmall-20210712")
                .startupOptions(StartupOptions.latest())
//                .startupOptions(KafkaOptions.StartupOptions.class)
                .deserializer(new DebeziumDeserializationSchema<String>() {
                    //自定义数据解析器
                    @Override
                    public void deserialize(SourceRecord sourceRecord, Collector<String> collector) throws Exception {

                        //获取主题信息,包含着数据库和表名  mysql_binlog_source.gmall-flink.z_user_info
                        String topic = sourceRecord.topic();
                        String[] arr = topic.split("\\.");
                        String db = arr[1];
                        String tableName = arr[2];

                        //获取操作类型 READ DELETE UPDATE CREATE
                        Envelope.Operation operation = Envelope.operationFor(sourceRecord);

                        //获取值信息并转换为Struct类型
                        Struct value = (Struct) sourceRecord.value();

                        //获取变化后的数据
                        Struct after = value.getStruct("after");

                        //创建JSON对象用于存储数据信息
                        JSONObject data = new JSONObject();
                        if (after != null) {
                            Schema schema = after.schema();
                            for (Field field : schema.fields()) {
                                data.put(field.name(), after.get(field.name()));
                            }
                        }

                        //创建JSON对象用于封装最终返回值数据信息
                        JSONObject result = new JSONObject();
                        result.put("operation", operation.toString().toLowerCase());
                        result.put("data", data);
                        result.put("database", db);
                        result.put("table", tableName);

                        //发送数据至下游
                        collector.collect(result.toJSONString());
                    }

                    @Override
                    public TypeInformation<String> getProducedType() {
                        return TypeInformation.of(String.class);
                    }
                })
                .build();

        //3.使用CDC Source从MySQL读取数据
        DataStreamSource<String> mysqlDS = env.addSource(mysqlSource);

        //4.打印数据
        mysqlDS.addSink(MyKafkaUtil.getKafkaSink("ods_base_db"));

        //5.执行任务
        env.execute();
    }
}

三、结果

1.启动FlinkCDC主程序

2.在服务器上开一个kafka的消费者

bin/kafka-console-consumer.sh --bootstrap-server hadoop201:9092 --topic ods_base_db

3.在Mysql中插入数据看Kafka会不会消费

　　Mysql端

 

 　　Kafka端

 

 成功消费。