Flume 自定义Source、Sink和Interceptor

1. 自定义source
http://archive.cloudera.com/cdh5/cdh/5/flume-ng-1.6.0-cdh5.15.1/FlumeDeveloperGuide.html#source 


一个简单的自定义source

package com.wxx.bigdata.hadoop.mapreduce.flume;

import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.EventDeliveryException;
import org.apache.flume.PollableSource;
import org.apache.flume.conf.Configurable;
import org.apache.flume.event.SimpleEvent;
import org.apache.flume.source.AbstractSource;

/**
 * 自定义flume的数据源
 */
public class CustomerSource extends AbstractSource implements Configurable, PollableSource {
    private String prefix;
    private String suffix;

    /**
     * 处理event
     * @return
     * @throws EventDeliveryException
     */
    @Override
    public Status process() throws EventDeliveryException {
        Status status = null;
        try {
            for(int i = 1; i <= 100; i++){
                SimpleEvent simpleEvent = new SimpleEvent();
                simpleEvent.setBody((prefix + i + suffix).getBytes());
                // 不需要关注事务，processEvent()方法中，由channel去处理
                getChannelProcessor().processEvent(simpleEvent);
            }

            status = Status.READY;
        } catch (Exception e) {
            e.printStackTrace();
            status = Status.BACKOFF;
        } finally {

        }
        try {
            Thread.sleep(5000);
        } catch (InterruptedException e) {
            e.printStackTrace();
        }
        //返回状态的结果
        return status;
    }

    @Override
    public long getBackOffSleepIncrement() {
        return 0;
    }

    @Override
    public long getMaxBackOffSleepInterval() {
        return 0;
    }

    /**
     * 获取agent传入的信息
     * @param context
     */
    @Override
    public void configure(Context context) {

        this.prefix = context.getString("prefix", "ruozedata");
        this.suffix = context.getString("suffix");

    }
}

打jar包上传到/home/hadoop/app/apache-flume-1.6.0-cdh5.15.1-bin/lib
启动脚本

flume-ng agent \
--name a1 \
--conf-file /home/hadoop/script/flume/customer/customer_source.conf \
--conf  $FLUME_HOME/conf \
-Dflume.root.logger=INFO,console

结果如下图

mysql自定义Source请参考： https://github.com/keedio/flume-ng-sql-source
2. 自定义Sink
官网地址如下
http://archive.cloudera.com/cdh5/cdh/5/flume-ng-1.6.0-cdh5.15.1/FlumeDeveloperGuide.html#sink

代码如下

package com.wxx.bigdata.hadoop.mapreduce.flume;

import org.apache.flume.*;
import org.apache.flume.conf.Configurable;
import org.apache.flume.sink.AbstractSink;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;


/**
 *
 */
public class CustomerSink extends AbstractSink implements Configurable {
    private static final Logger logger = LoggerFactory.getLogger(CustomerSink.class);
    private String prefix;
    private String suffix;
    @Override
    public Status process() throws EventDeliveryException {

        Status status = null;
        Channel channel = getChannel();
        Transaction transaction = channel.getTransaction();
        transaction.begin();
        try {
            Event event ;
            while (true){
                event = channel.take();
                if(event != null){
                    break;
                }
            }
            String body = new String(event.getBody());
            logger.info(prefix + body + suffix);
            transaction.commit();
            status = Status.READY;
        }catch (Exception e){
            transaction.rollback();
            status = Status.BACKOFF;
        }finally {
            transaction.close();
        }



        return status;
    }

    @Override
    public void configure(Context context) {
        this.prefix = context.getString("prefix", "customer");
        this.suffix = context.getString("suffix");

    }
}

将文件打成jar包上传到$FLUME_HOME/lib
Flmue配置文件为
 

#定义agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

#定义source
a1.sources.r1.type = netcat
a1.sources.r1.bind = hadoop000
a1.sources.r1.port = 44444

#定义channnel
a1.channels.c1.type = memory

#定义sink
a1.sinks.k1.type = com.wxx.bigdata.hadoop.mapreduce.flume.CustomerSink
a1.sinks.k1.prefix = TEST
a1.sinks.k1.suffix = 2019

#定义配置关系
a1.sinks.k1.channel = c1
a1.sources.r1.channels = c1

启动脚本

flume-ng agent \
--name a1 \
--conf-file /home/hadoop/script/flume/customer/customer_sink.conf \
--conf  $FLUME_HOME/conf \
-Dflume.root.logger=INFO,console

3. 自定义拦截器
a1 的数据经过拦截器处理后，如果body中包含"PEK"，则发送到a2，否则发送到a3
代码如下
 

package com.wxx.bigdata.hadoop.mapreduce.flume;

import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.interceptor.Interceptor;
import org.apache.flume.interceptor.InterceptorBuilderFactory;

import java.util.ArrayList;
import java.util.List;
import java.util.Map;

public class CustomerInterceptor implements Interceptor {

    private List events;
    @Override
    public void initialize() {
        events  = new ArrayList<>();
    }

    @Override
    public Event intercept(Event event) {
        Map headers = event.getHeaders();
        String body = new String(event.getBody());
        if(body.contains("PEK")){
            headers.put("type","PEK");
        }else{
            headers.put("type","OTHER");
        }
        return event;
    }

    @Override
    public List intercept(List list) {
        events.clear();
        for(Event event : list){
            events.add(intercept(event));
        }
        return events;
    }

    @Override
    public void close() {

    }

    public static class Builder implements Interceptor.Builder{

        @Override
        public Interceptor build() {
            return new CustomerInterceptor();
        }

        @Override
        public void configure(Context context) {

        }
    }
}

三个agnet的配置文件如下
 

#定义agent
a1.sources = r1
a1.sinks = k1 k2 
a1.channels = c1 c2

#定义source
a1.sources.r1.type = netcat
a1.sources.r1.bind = hadoop000
a1.sources.r1.port = 44444

#interceptors
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = com.wxx.bigdata.hadoop.mapreduce.flume.CustomerInterceptor$Builder

#定义selector
a1.sources.r1.selector.type = multiplexing
a1.sources.r1.selector.header = type
a1.sources.r1.selector.mapping.PEK = c1
a1.sources.r1.selector.mapping.OTHER = c2


#定义channnel
a1.channels.c1.type = memory
a1.channels.c2.type = memory

#定义sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = hadoop000
a1.sinks.k1.port = 44445

a1.sinks.k2.type = avro
a1.sinks.k2.hostname = hadoop000
a1.sinks.k2.port = 44446


#定义配置关系
a1.sources.r1.channels = c1 c2
a1.sinks.k1.channel = c1
a1.sinks.k2.channel = c2



#定义agent
a2.sources = r1
a2.sinks = k1
a2.channels = c1

#定义source
a2.sources.r1.type = avro
a2.sources.r1.bind = hadoop000
a2.sources.r1.port = 44445

#定义channnel
a2.channels.c1.type = memory

#定义sink
a2.sinks.k1.type = logger

#定义配置关系
a2.sinks.k1.channel = c1
a2.sources.r1.channels = c1


#定义agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

#定义source
a1.sources.r1.type = avro
a1.sources.r1.bind = hadoop000
a1.sources.r1.port = 44446

#定义channnel
a1.channels.c1.type = memory

#定义sink
a1.sinks.k1.type = logger

#定义配置关系
a1.sinks.k1.channel = c1
a1.sources.r1.channels = c1

启动脚本如下

flume-ng agent \
--name a3 \
--conf-file /home/hadoop/script/flume/customer/customer_interceptor03.conf \
--conf  $FLUME_HOME/conf \
-Dflume.root.logger=INFO,console


flume-ng agent \
--name a2 \
--conf-file /home/hadoop/script/flume/customer/customer_interceptor02.conf \
--conf  $FLUME_HOME/conf \
-Dflume.root.logger=INFO,console

flume-ng agent \
--name a1 \
--conf-file /home/hadoop/script/flume/customer/customer_interceptor01.conf \
--conf  $FLUME_HOME/conf \
-Dflume.root.logger=INFO,console

在一个terminal中输入

a2下

a3下