1.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 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.atguigu</groupId>
<artifactId>atguigu-flink-cdc</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<java.version>1.8</java.version>
<maven.compiler.source>${java.version}</maven.compiler.source>
<maven.compiler.target>${java.version}</maven.compiler.target>
<flink.version>1.13.6</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>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java_${scala.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-runtime-web_${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>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-json</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-csv</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.68</version>
</dependency>
<!--如果保存检查点到hdfs上,需要引入此依赖-->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<version>1.18.20</version>
<scope>provided</scope><!--注解工具, 仅仅在 javac 编译的时候有用-->
</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>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>1.7.25</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-to-slf4j</artifactId>
<version>2.14.0</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-planner-blink_${scala.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-scala_${scala.version}</artifactId>
<version>${flink.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>com.ververica</groupId>
<artifactId>flink-connector-mysql-cdc</artifactId>
<!-- The dependency is available only for stable releases, SNAPSHOT dependency need build by yourself. -->
<version>2.2.1</version>
</dependency>
<!--phoenix相关依赖-->
<dependency>
<groupId>org.apache.phoenix</groupId>
<artifactId>phoenix-core</artifactId>
<version>5.0.0-HBase-2.0</version>
<exclusions>
<exclusion>
<groupId>org.glassfish</groupId>
<artifactId>javax.el</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>30.1-jre</version>
</dependency>
<dependency>
<groupId>com.google.protobuf</groupId>
<artifactId>protobuf-java</artifactId>
<version>2.5.0</version>
</dependency>
<!--phoenix相关依赖-->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>druid</artifactId>
<version>1.1.16</version>
</dependency>
<dependency>
<groupId>commons-beanutils</groupId>
<artifactId>commons-beanutils</artifactId>
<version>1.9.3</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-jdbc_${scala.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>com.janeluo</groupId>
<artifactId>ikanalyzer</artifactId>
<version>2012_u6</version>
</dependency>
<!-- https://mvnrepository.com/artifact/com.clickhouse/clickhouse-jdbc -->
<dependency>
<groupId>com.clickhouse</groupId>
<artifactId>clickhouse-jdbc</artifactId>
<version>0.3.2-patch11</version>
<exclusions>
<exclusion>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
</exclusion>
<exclusion>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.httpcomponents/httpclient -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5</version>
</dependency>
<dependency>
<groupId>redis.clients</groupId>
<artifactId>jedis</artifactId>
<version>3.3.0</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>3.1.1</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<artifactSet>
<excludes>
<exclude>com.google.code.findbugs:jsr305</exclude>
<exclude>org.slf4j:*</exclude>
<exclude>log4j:*</exclude>
<exclude>org.apache.hadoop:*</exclude>
</excludes>
</artifactSet>
<filters>
<filter>
<!-- Do not copy the signatures in the META-INF folder.Otherwise, this might cause SecurityExceptions when using the JAR. -->
<!-- 打包时不复制META-INF下的签名文件,避免报非法签名文件的SecurityExceptions异常-->
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
<transformers combine.children="append">
<!-- The service transformer is needed to merge META-INF/services files -->
<!-- connector和format依赖的工厂类打包时会相互覆盖,需要使用ServicesResourceTransformer解决-->
<transformer
implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
2.主代碼(不用自定義序列化器)
import com.ververica.cdc.connectors.mysql.source.MySqlSource;
import com.ververica.cdc.connectors.mysql.table.StartupOptions;
import com.ververica.cdc.debezium.DebeziumSourceFunction;
import com.ververica.cdc.debezium.JsonDebeziumDeserializationSchema;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.restartstrategy.RestartStrategies;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.runtime.state.hashmap.HashMapStateBackend;
import org.apache.flink.streaming.api.CheckpointingMode;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.CheckpointConfig;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer;
import java.util.Properties;
public class FlinkCDC {
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.setInteger("rest.port",3335);
String ckAndGroupIdAndJobName = "test4";
//1.创建执行环境
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment(conf);
// env.setParallelism(1);
//2.Flink-CDC将读取binlog的位置信息以状态的方式保存在CK,如果想要做到断点续传,需要从Checkpoint或者Savepoint启动程序
//2.1 开启Checkpoint,每隔5秒钟做一次CK
env.enableCheckpointing(5000L);
//2.2 指定CK的一致性语义
env.getCheckpointConfig().setCheckpointingMode(CheckpointingMode.EXACTLY_ONCE);
//2.3 设置任务关闭的时候保留最后一次CK数据
env.getCheckpointConfig().setExternalizedCheckpointCleanup(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);
//2.4 指定从CK自动重启策略
env.setRestartStrategy(RestartStrategies.fixedDelayRestart(3, 2000L));
//2.5 设置状态后端
env.setStateBackend(new HashMapStateBackend());
// 3. 设置 checkpoint 的存储路径
env.getCheckpointConfig().setCheckpointStorage("hdfs://hadoop104:8020/ck/" + ckAndGroupIdAndJobName);
//2.6 设置访问HDFS的用户名
System.setProperty("HADOOP_USER_NAME", "sarah");
//3.创建Flink-MySQL-CDC的Source
//initial (default): Performs an initial snapshot on the monitored database tables upon first startup, and continue to read the latest binlog.
//latest-offset: Never to perform snapshot on the monitored database tables upon first startup, just read from the end of the binlog which means only have the changes since the connector was started.
//timestamp: Never to perform snapshot on the monitored database tables upon first startup, and directly read binlog from the specified timestamp. The consumer will traverse the binlog from the beginning and ignore change events whose timestamp is smaller than the specified timestamp.
//specific-offset: Never to perform snapshot on the monitored database tables upon first startup, and directly read binlog from the specified offset.
MySqlSource<String> mySqlSource = MySqlSource.<String>builder()
.hostname("hadoop102")
.port(3306)
.username("root")
.password("mivbAs7Awc")
.databaseList("gmall_config")
.tableList("gmall_config.table_process")//可选配置项,如果不指定该参数,则会读取上一个配置下的所有表的数据,注意:指定的时候需要使用"db.table"的方式
.serverTimeZone("Asia/Shanghai")
.deserializer(new JsonDebeziumDeserializationSchema()) // converts SourceRecord to JSON String
.build();
DataStreamSource<String> mysqlSourceDS = env.fromSource(mySqlSource, WatermarkStrategy.noWatermarks(), "MysqlSource");
//使用CDC Source从MySQL读取数据
mysqlSourceDS.addSink(getKafkaProducer("hadoop102:9092")).name(ckAndGroupIdAndJobName).uid(ckAndGroupIdAndJobName+"uid2");;
//打印数据并将数据写入 Kafka
mysqlSourceDS.print();
//启动任务
env.execute("FlinkCDC");
}
//kafka 生产者
public static FlinkKafkaProducer<String> getKafkaProducer(String brokers) {
return new FlinkKafkaProducer<String>("hadoop102:9092", "xwq", new SimpleStringSchema());
}
}