Flume自定义Sink、Source

1.Source

自己造一些数据传输到Source中去

public class source extends AbstractSource implements Configurable, PollableSource {
//定义数据传入的前缀跟后缀
    private String prefix;
    private String suffix;

    @Override
    public Status process() throws EventDeliveryException {
        Status status = null;
        try{

            for(int i = 1;i<100;i++){
                SimpleEvent event = new SimpleEvent();
                //设置数据
                event.setBody((prefix+i+suffix).getBytes());
                //发送body到ChannelProcess
                getChannelProcessor().processEvent(event);

            }
            //返回状态的结果
            status = Status.READY;
        }catch (Exception e){
            //显示报错信息
            e.printStackTrace();
            status = Status.BACKOFF;

        }finally {

        }
        return status;
    }

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

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

    @Override
    public void configure(Context context) {
    //不定义前缀，默认使用“ruozedata”
        this.prefix=context.getString("prefix","ruozedata");
        this.suffix=context.getString("suffix");
    }
}

自定义Source配置文件

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

        # 定义Source
        a1.sources.r1.type =com.ruozedata.bigdata.flume.source
        a1.sources.r1.suffix = ---ruozedata001

        # 定义Channel
        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

2.Sink

接受从Channel来的数据，并打印出来或者存储到HDFS中

public class sink extends AbstractSink implements Configurable {
    private static final Logger logger= LoggerFactory.getLogger(sink.class);
    private String prefix;
    private String suffix;
    @Override
    public Status process() throws EventDeliveryException {
        Status status = null;
        //获取channel数据
        Channel channel = getChannel();
        //获取事务
        Transaction transaction = channel.getTransaction();
        //开启事务
        transaction.begin();
        try{
            Event event=null;
            //需要判断event是否为空,不然测试时候报错
            while(true){ //一直等待
                event = channel.take();
                if(event != null){ //event拿到数据时候，继续往下执行
                    break;
                }
            }
            String body=new String(event.getBody());
            logger.info(prefix+body+suffix);
            transaction.commit();
            status = Status.READY;
        }catch (Exception e){
            //回滚事务
            transaction.rollback();
            status = Status.BACKOFF;
        }finally {

        }
        return status;
    }

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

    }
}

自定义Sink配置文件

# 指定Agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1
 
# 指定source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 5678
 
# 指定sink
a1.sinks.k1.type = com.ruozedata.bigdata.flume.sink
a1.sinks.k1.suffix = -JUMP
 
# 指定channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
 
# 定义配置关系
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1