Flume ---自定义interceptor ----自定义source ---自定义sink

自定义interceptor

1.创建一个maven项目，并引入以下依赖。

<dependency>
    <groupId>org.apache.flume</groupId>
    <artifactId>flume-ng-core</artifactId>
    <version>1.7.0</version>
</dependency>

2.定义CustomInterceptor类并实现Interceptor接口。

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

import java.util.List;

public class CustomInterceptor implements Interceptor {


    @Override
    public void initialize() {

    }

    @Override
    public Event intercept(Event event) {

        byte[] body = event.getBody();
        if (body[0] < 'z' && body[0] > 'a') {
            event.getHeaders().put("type", "letter");
        } else if (body[0] > '0' && body[0] < '9') {
            event.getHeaders().put("type", "number");
        }
        return event;

    }

    @Override
    public List<Event> intercept(List<Event> events) {
        for (Event event : events) {
            intercept(event);
        }
        return events;
    }

    @Override
    public void close() {

    }

    public static class Builder implements Interceptor.Builder {

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

        @Override
        public void configure(Context context) {
        }
    }
}

1.继承接口：org.apache.flume.interceptor.Interceptor
2.实现接口中的4个抽象方法：初始化 initialize()、单个事件拦截 intercept(Event event)、批量事件拦截 intercept(List events)、关闭io流 close()
3.创建一个静态内部类Builder，并实现接口implements Interceptor.Builder。

3.编辑flume配置文件
为bigdata02上的Flume1配置1个netcat source，1个sink group（2个avro sink），并配置相应的ChannelSelector和interceptor。

# Name the components on this agent
a1.sources = r1
a1.sinks = k1 k2
a1.channels = c1 c2

# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = com.bigdata.flume.interceptor.CustomInterceptor$Builder
a1.sources.r1.selector.type = multiplexing
a1.sources.r1.selector.header = type
a1.sources.r1.selector.mapping.letter = c1
a1.sources.r1.selector.mapping.number = c2
# Describe the sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = bigdata03
a1.sinks.k1.port = 4141

a1.sinks.k2.type=avro
a1.sinks.k2.hostname = bigdata04
a1.sinks.k2.port = 4242

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 10000
a1.channels.c1.transactionCapacity = 1000

# Use a channel which buffers events in memory
a1.channels.c2.type = memory
a1.channels.c2.capacity = 10000
a1.channels.c2.transactionCapacity = 1000


# Bind the source and sink to the channel
a1.sources.r1.channels = c1 c2
a1.sinks.k1.channel = c1
a1.sinks.k2.channel = c2

为bigdata03上的Flume4配置一个avro source和一个logger sink。

a1.sources = r1
a1.sinks = k1
a1.channels = c1

a1.sources.r1.type = avro
a1.sources.r1.bind = bigdata03
a1.sources.r1.port = 4141

a1.sinks.k1.type = logger

a1.channels.c1.type = memory
a1.channels.c1.capacity = 10000
a1.channels.c1.transactionCapacity = 10000

a1.sinks.k1.channel = c1
a1.sources.r1.channels = c1

为bigdata04上的Flume3配置一个avro source和一个logger sink。

a1.sources = r1
a1.sinks = k1
a1.channels = c1

a1.sources.r1.type = avro
a1.sources.r1.bind = bigdata04
a1.sources.r1.port = 4242

a1.sinks.k1.type = logger

a1.channels.c1.type = memory
a1.channels.c1.capacity = 10000
a1.channels.c1.transactionCapacity = 1000

a1.sinks.k1.channel = c1
a1.sources.r1.channels = c1

4.分别在bigdata02，bigdata03，bigdata04上启动flume进程，注意先后顺序。
5.在bigdata02使用netcat向localhost:44444发送字母和数字。
6.观察bigdata03和bigdata04打印的日志。

自定义source

导入pom依赖

<dependencies>
    <dependency>
        <groupId>org.apache.flume</groupId>
        <artifactId>flume-ng-core</artifactId>
        <version>1.7.0</version>
</dependency>
</dependencies>

import org.apache.flume.Context;
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;

import java.util.HashMap;

 public class MySource extends AbstractSource implements Configurable, PollableSource {

    //定义配置文件将来要读取的字段
    private Long delay;
    private String field;

    //初始化配置信息
    @Override
    public void configure(Context context) {
        delay = context.getLong("delay");
        field = context.getString("field", "Hello!");
    }

    @Override
    public Status process() throws EventDeliveryException {

        try {
            //创建事件头信息
            HashMap<String, String> hearderMap = new HashMap<>();
            //创建事件
            SimpleEvent event = new SimpleEvent();
            //循环封装事件
            for (int i = 0; i < 5; i++) {
                //给事件设置头信息
                event.setHeaders(hearderMap);
                //给事件设置内容
                event.setBody((field + i).getBytes());
                //将事件写入channel
                getChannelProcessor().processEvent(event);
                Thread.sleep(delay);
            }
        } catch (Exception e) {
            e.printStackTrace();
            return Status.BACKOFF;
        }
        return Status.READY;
    }

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

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

测试
1.打包
将写好的代码打包，并放到flume的lib目录（/opt/module/flume）下。
2.配置文件

# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = com.bigdata.MySource
a1.sources.r1.delay = 1000
#a1.sources.r1.field = hadoop

# Describe the sink
a1.sinks.k1.type = logger

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 10000
a1.channels.c1.transactionCapacity = 1000

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

3.开启任务

[hadoop@bigdata02 flume]$ pwd
/opt/module/flume
[hadoop@bigdata02 flume]$ bin/flume-ng agent -c conf/ -f job/mysource.conf -n a1 -Dflume.root.logger=INFO,console

自定义sink

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 MySink extends AbstractSink implements Configurable {

    //创建Logger对象
    private static final Logger LOG = LoggerFactory.getLogger(AbstractSink.class);

    private String prefix;
    private String suffix;

    @Override
    public Status process() throws EventDeliveryException {

        //声明返回值状态信息
        Status status;

        //获取当前Sink绑定的Channel
        Channel ch = getChannel();

        //获取事务
        Transaction txn = ch.getTransaction();

        //声明事件
        Event event;

        //开启事务
        txn.begin();

        //读取Channel中的事件，直到读取到事件结束循环
        while (true) {
            event = ch.take();
            if (event != null) {
                break;
            }
        }
        try {
            //处理事件（打印）
            LOG.info(prefix + new String(event.getBody()) + suffix);

            //事务提交
            txn.commit();
            status = Status.READY;
        } catch (Exception e) {

            //遇到异常，事务回滚
            txn.rollback();
            status = Status.BACKOFF;
        } finally {

            //关闭事务
            txn.close();
        }
        return status;
    }

    @Override
    public void configure(Context context) {

        //读取配置文件内容，有默认值
        prefix = context.getString("prefix", "hello:");

        //读取配置文件内容，无默认值
        suffix = context.getString("suffix");
    }
}

1.打包
将写好的代码打包，并放到flume的lib目录（/opt/module/flume）下。
2.配置文件

# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444

# Describe the sink
a1.sinks.k1.type = com.bigdata.MySink
#a1.sinks.k1.prefix = hadoop:
a1.sinks.k1.suffix = :hadoop

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 10000
a1.channels.c1.transactionCapacity = 1000

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

3.开启任务

[hadoop@bigdata02 flume]$ bin/flume-ng agent -c conf/ -f job/mysink.conf -n a1 -Dflume.root.logger=INFO,console
[hadoop@bigdata02 ~]$ nc localhost 44444
hello
OK
hadoop
OK