【实战-08】flink 消费kafka自定义序列化

目的

让从kafka消费出来的数据,直接就转换成我们的对象

mvn pom

<!--
Licensed to the Apache Software Foundation (ASF) under one
or more contributor license agreements.  See the NOTICE file
distributed with this work for additional information
regarding copyright ownership.  The ASF licenses this file
to you under the Apache License, Version 2.0 (the
"License"); you may not use this file except in compliance
with the License.  You may obtain a copy of the License at

  http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing,
software distributed under the License is distributed on an
"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
KIND, either express or implied.  See the License for the
specific language governing permissions and limitations
under the License.
-->
<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.boke</groupId>
	<artifactId>Flink1.7.1</artifactId>
	<version>1.0-SNAPSHOT</version>
	<packaging>jar</packaging>

	<name>Flink Quickstart Job</name>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<flink.version>1.17.1</flink.version>
		<target.java.version>1.8</target.java.version>
		<scala.binary.version>2.12</scala.binary.version>
		<maven.compiler.source>${target.java.version}</maven.compiler.source>
		<maven.compiler.target>${target.java.version}</maven.compiler.target>
		<log4j.version>2.17.1</log4j.version>
	</properties>

	<repositories>
		<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>

	<dependencies>
		<!-- Apache Flink dependencies -->
		<!-- These dependencies are provided, because they should not be packaged into the JAR file. -->
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-java</artifactId>
			<version>${flink.version}</version>
<!--			<scope>provided</scope>-->
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-clients</artifactId>
			<version>${flink.version}</version>
<!--			<scope>provided</scope>-->
		</dependency>
		<!-- table 环境依赖【connectors 和 formats 和driver】 https://nightlies.apache.org/flink/flink-docs-release-1.17/docs/dev/configuration/overview/		-->
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kafka</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-table-api-java</artifactId>
			<version>${flink.version}</version>
<!--			<scope>provided</scope>-->
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-table-api-java-bridge</artifactId>
			<version>${flink.version}</version>
<!--			<scope>provided</scope>-->
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-jdbc</artifactId>
			<version>3.1.0-1.17</version>
		</dependency>
		<dependency>
			<groupId>mysql</groupId>
			<artifactId>mysql-connector-java</artifactId>
			<version>8.0.18</version>
		</dependency>
		<!--idea 运行比西甲这个否则报错:【 Make sure a planner module is on the classpath】-->
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-table-planner-loader</artifactId>
			<version>${flink.version}</version>
			<!--			<scope>provided</scope>-->
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-table-runtime</artifactId>
			<version>${flink.version}</version>
			<!--			<scope>provided</scope>-->
		</dependency>
		<!--第三方的包-->
		<dependency>
			<groupId>com.alibaba</groupId>
			<artifactId>fastjson</artifactId>
			<version>1.2.83</version>
		</dependency>
		<!-- Add connector dependencies here. They must be in the default scope (compile). -->

		<!-- Example:

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

		<!-- Add logging framework, to produce console output when running in the IDE. -->
		<!-- These dependencies are excluded from the application JAR by default. -->
		<dependency>
			<groupId>org.apache.logging.log4j</groupId>
			<artifactId>log4j-slf4j-impl</artifactId>
			<version>${log4j.version}</version>
			<scope>runtime</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.logging.log4j</groupId>
			<artifactId>log4j-api</artifactId>
			<version>${log4j.version}</version>
			<scope>runtime</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.logging.log4j</groupId>
			<artifactId>log4j-core</artifactId>
			<version>${log4j.version}</version>
			<scope>runtime</scope>
		</dependency>
	</dependencies>

	<build>
		<plugins>

			<!-- Java Compiler -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.1</version>
				<configuration>
					<source>${target.java.version}</source>
					<target>${target.java.version}</target>
				</configuration>
			</plugin>

			<!-- We use the maven-shade plugin to create a fat jar that contains all necessary dependencies. -->
			<!-- Change the value of <mainClass>...</mainClass> if your program entry point changes. -->
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-shade-plugin</artifactId>
				<version>3.1.1</version>
				<executions>
					<!-- Run shade goal on package phase -->
					<execution>
						<phase>package</phase>
						<goals>
							<goal>shade</goal>
						</goals>
						<configuration>
							<createDependencyReducedPom>false</createDependencyReducedPom>
							<artifactSet>
								<excludes>
									<exclude>org.apache.flink:flink-shaded-force-shading</exclude>
									<exclude>com.google.code.findbugs:jsr305</exclude>
									<exclude>org.slf4j:*</exclude>
									<exclude>org.apache.logging.log4j:*</exclude>
								</excludes>
							</artifactSet>
							<filters>
								<filter>
									<!-- Do not copy the signatures in the META-INF folder.
									Otherwise, this might cause SecurityExceptions when using the JAR. -->
									<artifact>*:*</artifact>
									<excludes>
										<exclude>META-INF/*.SF</exclude>
										<exclude>META-INF/*.DSA</exclude>
										<exclude>META-INF/*.RSA</exclude>
									</excludes>
								</filter>
							</filters>
							<transformers>
								<transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
								<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
									<mainClass>com.boke.DataStreamJob</mainClass>
								</transformer>
							</transformers>
						</configuration>
					</execution>
				</executions>
			</plugin>
		</plugins>

		<pluginManagement>
			<plugins>

				<!-- This improves the out-of-the-box experience in Eclipse by resolving some warnings. -->
				<plugin>
					<groupId>org.eclipse.m2e</groupId>
					<artifactId>lifecycle-mapping</artifactId>
					<version>1.0.0</version>
					<configuration>
						<lifecycleMappingMetadata>
							<pluginExecutions>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-shade-plugin</artifactId>
										<versionRange>[3.1.1,)</versionRange>
										<goals>
											<goal>shade</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
								<pluginExecution>
									<pluginExecutionFilter>
										<groupId>org.apache.maven.plugins</groupId>
										<artifactId>maven-compiler-plugin</artifactId>
										<versionRange>[3.1,)</versionRange>
										<goals>
											<goal>testCompile</goal>
											<goal>compile</goal>
										</goals>
									</pluginExecutionFilter>
									<action>
										<ignore/>
									</action>
								</pluginExecution>
							</pluginExecutions>
						</lifecycleMappingMetadata>
					</configuration>
				</plugin>
			</plugins>
		</pluginManagement>
	</build>
</project>

核心代码

package com.boke.kafka;

import com.alibaba.fastjson.JSONObject;

public class Student {
    public String name;
    public Integer age;

    public Student(String name, Integer age) {
        this.name = name;
        this.age = age;
    }

    public static Student fromJson(String s){
        JSONObject jsonObject = JSONObject.parseObject(s);
        String name = jsonObject.getString("name");
        Integer age = jsonObject.getInteger("age");
        return new Student(name,age);
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }

    public Integer getAge() {
        return age;
    }

    public void setAge(Integer age) {
        this.age = age;
    }
}



//下面是main主函数
package com.boke.kafka;

import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.typeinfo.TypeHint;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.connector.kafka.source.KafkaSource;
import org.apache.flink.connector.kafka.source.enumerator.initializer.OffsetsInitializer;
import org.apache.flink.connector.kafka.source.reader.deserializer.KafkaRecordDeserializationSchema;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.KafkaDeserializationSchema;
import org.apache.kafka.clients.consumer.ConsumerRecord;

import java.nio.charset.StandardCharsets;

public class kafkaSource {
    public static void main(String[] args) {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        KafkaSource<Student> source = KafkaSource.<Student>builder()
                .setBootstrapServers("brokers")
                .setTopics("input-topic")
                .setGroupId("my-group")
                .setStartingOffsets(OffsetsInitializer.earliest())//【无论如何都从最早开始消费】
//                .setStartingOffsets(OffsetsInitializer.latest())//【无论如何都从最新开始消费】
//                .setStartingOffsets(OffsetsInitializer.committedOffsets(OffsetResetStrategy.EARLIEST))//【groupid 存在offset 则从offset消费,否则从最早开始消费】
//                .setStartingOffsets(OffsetsInitializer.committedOffsets(OffsetResetStrategy.LATEST))//【groupid 存在offset 则从offset消费,否则从最新开始消费】

//                .setDeserializer(KafkaRecordDeserializationSchema.of(new KafkaDeserializationSchemaWrapper<>(new SimpleStringSchema())))
//                .setDeserializer(KafkaRecordDeserializationSchema.of(new SimpleStringSchema());
                .setDeserializer(KafkaRecordDeserializationSchema.of(new MyKafkaDeserializationSchema()))
//                .setDeserializer(KafkaRecordDeserializationSchema.valueOnly())
                .build();

        env.fromSource(source, WatermarkStrategy.noWatermarks(), "Kafka Source");
    }
}
class MyKafkaDeserializationSchema implements KafkaDeserializationSchema<Student>{




    @Override
    public boolean isEndOfStream(Student nextElement) {
        return false;
    }

//Deserializes the Kafka record.
//Params:
//record – Kafka record to be deserialized.
//Returns:
//The deserialized message as an object (null if the message cannot be deserialized).
    @Override
    public Student deserialize(ConsumerRecord<byte[], byte[]> record) throws Exception {
        /*
         *自定义kafka反序列化
         *如果数据异常,可以直接返回nulll即可,源码中有一句英文:null if the message cannot be deserialized
         * */
        String topic = record.topic();
        long KafkaTimeStamp = record.timestamp();
        int partitionNum = record.partition();
        String value = new String(record.value(), StandardCharsets.UTF_8);
        return Student.fromJson(value);
    }



    @Override
    public TypeInformation<Student> getProducedType() {
        return TypeInformation.of(new TypeHint<Student>() {});
    }
}

要将FlinkKafka消费的数据反序列化并存入Hive,可以按照以下步骤进行操作: 1. 配置Kafka消费者和Hive连接 首先需要配置FlinkKafka消费者和Hive连接,可以使用Flink提供的Kafka连接器和Hive连接器来实现。具体的配置可以参考Flink官方文档进行设置。 2. 设计反序列化类 根据你从Kafka消费的数据格式,需要设计一个反序列化类来将数据转换为Flink中的对象。例如,如果你从Kafka消费的是JSON格式的数据,可以使用Flink提供的JSON反序列化类进行转换。 3. 定义Hive表结构 在Hive中创建一个表来存储反序列化后的数据。你需要定义表的结构,包括列名、列类型和分区等信息。 4. 编写Flink程序 编写一个Flink程序来消费Kafka中的数据,并将数据反序列化后存入Hive表中。具体的实现可以参考以下代码示例: ```java DataStream<String> dataStream = env.addSource(new FlinkKafkaConsumer<String>( "topic", new SimpleStringSchema(), properties)); DataStream<MyObject> myObjects = dataStream.map(new MapFunction<String, MyObject>() { @Override public MyObject map(String value) throws Exception { ObjectMapper mapper = new ObjectMapper(); return mapper.readValue(value, MyObject.class); } }); HiveCatalog hiveCatalog = new HiveCatalog("myHiveCatalog", "default", "/path/to/hive/conf"); TableSchema schema = new TableSchema( new String[] {"id", "name", "age"}, new TypeInformation<?>[] {Types.STRING, Types.STRING, Types.INT}); HiveTableSink hiveTableSink = new HiveTableSink( "myDatabase.myTable", schema, hiveCatalog, new Configuration(), "myPartition"); myObjects.addSink(hiveTableSink); ``` 其中,`MyObject`是你从Kafka消费的数据反序列化后的对象,`hiveCatalog`是Hive连接器的配置信息,`schema`是Hive表的列信息,`hiveTableSink`是Hive表的输出目的地。 5. 运行Flink程序 配置好Flink程序后,就可以运行程序了。程序会从Kafka消费数据,将数据反序列化后存入Hive表中。 以上就是将FlinkKafka消费数据反序列化存入Hive的步骤和示例代码。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

我先森

鼓励一个吧,哈哈

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值