flink测流输出

flink测流输出

目的
给数据打上标签,我们支取其中的某一个或者几个标签作为支流输出,其他的所有的主流可以另外输出,
还能获取迟到的数据

package com._51doit.flink.day06;

import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.tuple.Tuple3;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.ProcessFunction;
import org.apache.flink.util.Collector;
import org.apache.flink.util.OutputTag;
/**
 * 1.将数据整理成Tuple3
 * 2.然后使用侧流输出将数据分类
 */
public class SideOutputsDemo2 {

    public static void main(String[] args) throws Exception {

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

//        view,pid,2020-03-09 11:42:30
//        activity,a10,2020-03-09 11:42:38
//        order,o345,2020-03-09 11:42:38
        DataStreamSource<String> lines = env.socketTextStream("localhost", 8888);

        OutputTag<Tuple3<String, String, String>> viewTag = new OutputTag<Tuple3<String, String, String>>("view-tag") {
        };
        OutputTag<Tuple3<String, String, String>> activityTag = new OutputTag<Tuple3<String, String, String>>("activity-tag") {
        };
        OutputTag<Tuple3<String, String, String>> orderTag = new OutputTag<Tuple3<String, String, String>>("order-tag") {
        };

        //直接调用process方法
        SingleOutputStreamOperator<Tuple3<String, String, String>> tpDataStream = lines.process(new ProcessFunction<String, Tuple3<String, String, String>>() {

            @Override
            public void open(Configuration parameters) throws Exception {
                super.open(parameters);
            }

            @Override
            public void processElement(String input, Context ctx, Collector<Tuple3<String, String, String>> out) throws Exception {

                //1.将字符串转成Tuple2
                String[] fields = input.split(",");
                String type = fields[0];
                String id = fields[1];
                String time = fields[2];
                Tuple3<String, String, String> tp = Tuple3.of(type, id, time);

                //2.对数据打标签
                //将数据打上标签
                if (type.equals("view")) {
                    //输出数据，将数据和标签关联
                    ctx.output(viewTag, tp);  //ctx.output  输出侧流的
                } else if (type.equals("activity")) {
                    ctx.output(activityTag, tp);
                } else {
                    ctx.output(orderTag, tp);
                }
                //输出主流的数据
                out.collect(tp);
            }
        });


        //输出的测流只能通过getSideOutput
        DataStream<Tuple3<String, String, String>> viewDataStream = tpDataStream.getSideOutput(viewTag);

        //分别处理各种类型的数据。
        viewDataStream.print();

        env.execute();

    }
}