mongodb的自定义source
需求:用flume从mongodb中采集数据然后把数据存到kafka和hdfs中,用于后面的数据分析。
pom.xml
<parent>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-parent</artifactId>
<version>2.1.2.RELEASE</version>
</parent>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<scala.version>2.11.8</scala.version>
<spark.version>2.2.0</spark.version>
<hadoop.version>2.6.5</hadoop.version>
<encoding>UTF-8</encoding>
</properties>
<dependencies>
<!-- spring boot专门操作 各种数据源 -->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-data-mongodb</artifactId>
<optional>true</optional>
</dependency>
<dependency>
<groupId>org.mongodb</groupId>
<artifactId>mongo-java-driver</artifactId>
</dependency>
<dependency>
<groupId>org.apache.flume</groupId>
<artifactId>flume-ng-core</artifactId>
<version>1.7.0</version>
<scope>provided</scope>
</dependency>
</dependencies>
<build>
<pluginManagement>
<plugins>
<!-- 编译java的插件 -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
</plugin>
</plugins>
</pluginManagement>
<plugins>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<executions>
<execution>
<id