在Flume中,也允许自定义拦截器。但是不同于其他组件,自定义Interceptor的时候,需要再额外覆盖其中的内部接口。
构建Maven工程,导入对应的依赖。
<?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>org.example</groupId>
<artifactId>flume</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.apache.flume</groupId>
<artifactId>flume-ng-core</artifactId>
<version>1.11.0</version>
</dependency>
<dependency>
<groupId>org.apache.flume</groupId>
<artifactId>flume-ng-sdk</artifactId>
<version>1.11.0</version>
</dependency>
<dependency>
<groupId>org.apache.flume</groupId>
<artifactId>flume-ng-configuration</artifactId>
<version>1.11.0</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.8</source>
<target>1.8</target>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
</plugins>
</build>
</project>
自定义类实现Interceptor接口,覆盖其中initialize,intercept和close方法
定义静态内部类,实现Interceptor.Builder内部接口
package com.st;
import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.interceptor.Interceptor;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
/**
* 模拟timestamp Interceptor
*/
public class SelfInterceptor implements Interceptor {
@Override
public void initialize() {
}
//对event对象的处理就放在这个方法中
@Override
public Event intercept(Event event) {
//时间戳在head中,首先获取时间戳
Map<String, String> headers = event.getHeaders();
//判断是否原来制定
if(headers.containsKey("time")||headers.containsKey("timestamp"))
{
//如果制定,直接返回
return event;
}else{
headers.put("timestamp",System.currentTimeMillis()+"");
event.setHeaders(headers);
}
//下面这个例子是过滤掉hello这个字符串
// 获取事件数据
/* String eventData = new String(event.getBody(), StandardCharsets.UTF_8);
// 检查事件数据中是否包含指定字符串
if (eventData.contains("hello")) {
// 如果包含指定字符串,则过滤掉该事件,返回 null
return null;
}*/
return event;
}
@Override
public List<Event> intercept(List<Event> events) {
//处理拦截之后的events
List<Event> interceptedEvents = new ArrayList<>();
for (Event event : events) {
Event interceptedEvent = intercept(event);
if (interceptedEvent != null) {
interceptedEvents.add(interceptedEvent);
}
}
return interceptedEvents;
}
@Override
public void close() {
}
//覆盖内部接口
public static class Builder implements Interceptor.Builder{
//产生要使用的拦截器对象
@Override
public Interceptor build() {
return new SelfInterceptor();
}
@Override
public void configure(Context context) {
}
}
}
打成jar包方法Flume安装目录的lib目录下
编写配置文件selfinterceptor.conf
a1.sources = s1
a1.channels = c1
a1.sinks = k1
a1.sources.s1.type = netcat
a1.sources.s1.bind = m1
a1.sources.s1.port = 9999
# 指定拦截器
a1.sources.s1.interceptors = i1
a1.sources.s1.interceptors.i1.type = com.st.SelfInterceptor$Builder
a1.channels.c1.type = memory
a1.sinks.k1.type = logger
a1.sources.s1.channels = c1
a1.sinks.k1.channel = c1
启动flume
flume-ng agent -c $FLUME_HOME/conf -n a1 -f selfinterceptor.conf -Dflume.root.logger=INFO,console
发送数据nc m1 9999
查看数据,发现有了timestamp