Flume自定义sink

Sink是完全事务性的。在从Channel 批量删除数据之前，每个Sink用Channel启动一个事务。批量事件一旦成功写出到存储系统或下一个Flume Agent，Sink就利用Channel提交事务。事务一旦被提交，该Channel从自己的内部缓冲区删除事件。

Sink组件目的地包括hdfs、logger、avro、thrift、ipc、file、null、HBase、solr、自定义。官方提供的Sink类型已经很多，但是有时候并不能满足实际开发当中的需求，此时我们就需要根据实际需求自定义某些Sink。
编写的大概流程

代码

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 {
    //定义俩个属性  前后缀
    private String prefix;
    private String subfix;

    /**
     * 获取channel
     * 从channel获取事务及数据
     * 发送数据
     *
     * @return
     * @throws EventDeliveryException
     */
    @Override
    public Status process() throws EventDeliveryException {
        //获取log对象
        Logger logger = LoggerFactory.getLogger(MySink.class);
        //定义返回值
        Status status = null;
        //获取channel
        Channel channel = getChannel();
        //从channel获取事务
        Transaction transaction = channel.getTransaction();
        //开启事务
        transaction.begin();
        try {
            //从channel获取数据
            Event event = channel.take();
            //处理事务
            if (event != null) {
                String body = new String(event.getBody());
                logger.info(prefix+body+subfix);
            }
            //提交事务
            transaction.commit();
            //成功提交修改状态信息
            status = Status.READY;
        } catch (ChannelException e) {
            e.printStackTrace();
            //提交失败，回滚，状态修改
            transaction.rollback();
            status = Status.BACKOFF;
        } finally {
            //关闭
            transaction.close();
        }
        //返回状态信息
        return status;
    }

    @Override
    public void configure(Context context) {
        //读取配置文件，给前后缀赋值
        prefix = context.getString("prefix");
        subfix = context.getString("prefix", "subfix");
    }
}

配置文件

a2.sources = r1
a2.sinks = k1
a2.channels = c1

# Describe/configure the source
a2.sources.r1.type = avro
a2.sources.r1.bind = hadoop102
a2.sources.r1.port = 4141

# Describe the sink
a2.sinks.k1.type = flume.MySink
a2.sinks.k1.prefix = aa
a2.sinks.k1.subfix = bb

# Describe the channel
a2.channels.c1.type = memory
a2.channels.c1.capacity = 1000
a2.channels.c1.transactionCapacity = 100

# Bind the source and sink to the channel
a2.sources.r1.channels = c1
a2.sinks.k1.channel = c1