【极数系列】Flink集成KafkaSink &amp；实时输出数据（11）(1)

最新推荐文章于 2024-05-21 09:52:18 发布

2401_84160361

最新推荐文章于 2024-05-21 09:52:18 发布

阅读量176

点赞数 3

分类专栏：程序员文章标签： flink 大数据

本文链接：https://blog.csdn.net/2401_84160361/article/details/138272695

版权

程序员专栏收录该内容

186 篇文章 0 订阅

订阅专栏

范围	指标	用户变量	描述	类型
算子	currentSendTime	n/a	发送最近一条数据的耗时。该指标反映最后一条数据的瞬时值。	Gauge

06 项目源码实战

6.1 包结构

在这里插入图片描述

6.2 pom.xml依赖

<?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.xsy</groupId>
    <artifactId>aurora_flink_connector_kafka</artifactId>
    <version>1.0-SNAPSHOT</version>

    <!--属性设置-->
    <properties>
        <!--java_JDK版本-->
        <java.version>11</java.version>
        <!--maven打包插件-->
        <maven.plugin.version>3.8.1</maven.plugin.version>
        <!--编译编码UTF-8-->
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <!--输出报告编码UTF-8-->
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <!--json数据格式处理工具-->
        <fastjson.version>1.2.75</fastjson.version>
        <!--log4j版本-->
        <log4j.version>2.17.1</log4j.version>
        <!--flink版本-->
        <flink.version>1.18.0</flink.version>
        <!--scala版本-->
        <scala.binary.version>2.11</scala.binary.version>
    </properties>

    <!--通用依赖-->
    <dependencies>

        <!-- json -->
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>${fastjson.version}</version>
        </dependency>

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

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>

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


        <!--================================集成外部依赖==========================================-->
        <!--集成日志框架 start-->
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-slf4j-impl</artifactId>
            <version>${log4j.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-api</artifactId>
            <version>${log4j.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>${log4j.version}</version>
        </dependency>

        <!--集成日志框架 end-->

        <!--kafka依赖 start-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka</artifactId>
            <version>3.0.2-1.18</version>
        </dependency>
        <!--kafka依赖 end-->

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-base</artifactId>
            <version>1.18.0</version>
        </dependency>
    </dependencies>

    <!--编译打包-->
    <build>
        <finalName>${project.name}</finalName>
        <!--资源文件打包-->
        <resources>
            <resource>
                <directory>src/main/resources</directory>
            </resource>
            <resource>
                <directory>src/main/java</directory>
                <includes>
                    <include>**/*.xml</include>
                </includes>
            </resource>
        </resources>

        <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>org.apache.flink:force-shading</exclude>
                                    <exclude>org.google.code.flindbugs:jar305</exclude>
                                    <exclude>org.slf4j:*</exclude>
                                    <excluder>org.apache.logging.log4j:*</excluder>
                                </excludes>
                            </artifactSet>
                            <filters>
                                <filter>
                                    <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.ManifestResourceTransformer">
                                    <mainClass>org.aurora.KafkaStreamingJob</mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>

        <!--插件统一管理-->
        <pluginManagement>
            <plugins>
                <!--maven打包插件-->
                <plugin>
                    <groupId>org.springframework.boot</groupId>
                    <artifactId>spring-boot-maven-plugin</artifactId>
                    <version>${spring.boot.version}</version>
                    <configuration>
                        <fork>true</fork>
                        <finalName>${project.build.finalName}</finalName>
                    </configuration>
                    <executions>
                        <execution>
                            <goals>
                                <goal>repackage</goal>
                            </goals>
                        </execution>
                    </executions>
                </plugin>

                <!--编译打包插件-->
                <plugin>
                    <artifactId>maven-compiler-plugin</artifactId>
                    <version>${maven.plugin.version}</version>
                    <configuration>
                        <source>${java.version}</source>
                        <target>${java.version}</target>
                        <encoding>UTF-8</encoding>
                        <compilerArgs>
                            <arg>-parameters</arg>
                        </compilerArgs>
                    </configuration>
                </plugin>
            </plugins>
        </pluginManagement>
    </build>

    <!--配置Maven项目中需要使用的远程仓库-->
    <repositories>
        <repository>
            <id>aliyun-repos</id>
            <url>https://maven.aliyun.com/nexus/content/groups/public/</url>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </repository>
    </repositories>

    <!--用来配置maven插件的远程仓库-->
    <pluginRepositories>
        <pluginRepository>
            <id>aliyun-plugin</id>
            <url>https://maven.aliyun.com/nexus/content/groups/public/</url>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </pluginRepository>
    </pluginRepositories>

</project>

6.3 配置文件

（1）application.properties

#kafka集群地址
kafka.bootstrapServers=localhost:9092
#kafka主题
kafka.topic=topic_a
#kafka消费者组
kafka.group=aurora_group

（2）log4j2.properties

rootLogger.level=INFO
rootLogger.appenderRef.console.ref=ConsoleAppender
appender.console.name=ConsoleAppender
appender.console.type=CONSOLE
appender.console.layout.type=PatternLayout
appender.console.layout.pattern=%d{HH:mm:ss,SSS} %-5p %-60c %x - %m%n
log.file=D:\\tmprootLogger.level=INFO
rootLogger.appenderRef.console.ref=ConsoleAppender
appender.console.name=ConsoleAppender
appender.console.type=CONSOLE
appender.console.layout.type=PatternLayout
appender.console.layout.pattern=%d{HH:mm:ss,SSS} %-5p %-60c %x - %m%n
log.file=D:\\tmp

6.4 创建sink作业

package com.aurora;

import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.connector.base.DeliveryGuarantee;
import org.apache.flink.connector.kafka.sink.KafkaRecordSerializationSchema;
import org.apache.flink.connector.kafka.sink.KafkaSink;
import org.apache.flink.connector.kafka.source.KafkaSource;
import org.apache.flink.connector.kafka.source.KafkaSourceBuilder;
import org.apache.flink.connector.kafka.source.enumerator.initializer.OffsetsInitializer;
import org.apache.flink.runtime.state.StateBackend;
import org.apache.flink.runtime.state.filesystem.FsStateBackend;
import org.apache.flink.streaming.api.CheckpointingMode;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.CheckpointConfig;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.ArrayList;

/**
 * @author 浅夏的猫
 * @description kafka 连接器使用demo作业
 * @datetime 22:21 2024/2/1
 */
public class KafkaSinkStreamingJob {

    private static final Logger logger = LoggerFactory.getLogger(KafkaSinkStreamingJob.class);

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

        //===============1.获取参数==============================
        //定义文件路径


![img](https://img-blog.csdnimg.cn/img_convert/48447483a70474aae74c6da3fd42b290.png)
![img](https://img-blog.csdnimg.cn/img_convert/9bc89b0916c55def4873982a964ddaf7.png)
![img](https://img-blog.csdnimg.cn/img_convert/bc9e7074e68db218d29d34a466f01786.png)

**既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上大数据知识点，真正体系化！**

**由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新**

**[需要这份系统化资料的朋友，可以戳这里获取](https://bbs.csdn.net/topics/618545628)**

存中...(img-thbseNft-1714275138539)]
[外链图片转存中...(img-I1ZVInSd-1714275138540)]
[外链图片转存中...(img-i4zz0uaP-1714275138540)]

**既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上大数据知识点，真正体系化！**

**由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新**

**[需要这份系统化资料的朋友，可以戳这里获取](https://bbs.csdn.net/topics/618545628)**