基于flink滑动窗口的api使用

上篇：基于flink常用4种滚动窗口api的使用

两种api的使用

1、NoKeyedProcessingTime滑动窗口

不分组，按照ProcessingTime划分为滑动窗口，然后调用reduce对窗口内的数据进行聚合

新api【TumblingAlignedProcessingTimeWindows】 

直接代码

import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.datastream.AllWindowedStream;
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.windowing.assigners.SlidingProcessingTimeWindows;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.api.windowing.windows.TimeWindow;
/**
 * 滑动窗口--【无界流】
 * 新api【TumblingAlignedProcessingTimeWindows】
 * 案例需求：当时间触发后，才会生成新的窗口，这里的需求是当5秒钟过去后会生成一个新的窗口进行聚合
 */
public class ProcessingTimeSlidingWindowAllDemo {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.createLocalEnvironmentWithWebUI(new Configuration());
        // env.setStreamTimeCharacteristic(TimeCharacteristic.ProcessingTime);  //老api

        DataStreamSource<String> lines = env.socketTextStream("Master", 8888);

        //将字符串转为数字【lamber表达式】
        //本地执行，执行并行度为4，所以调用map返回的DataStream的并行度为4
        SingleOutputStreamOperator<Integer> nums = lines.map(Integer::parseInt);

        //  AllWindowedStream<Integer, TimeWindow> windowed = nums.timeWindowAll(Time.seconds(30), Time.seconds(10));
        AllWindowedStream<Integer, TimeWindow> windowed = nums.windowAll(SlidingProcessingTimeWindows.of(Time.seconds(30), Time.seconds(10)));

        windowed.sum(0).print();


        env.execute();


    }
}

打印输出，在8888窗口输入10个1，让其滑动测试如下：

查看job： http://localhost:8081/#/job/cbb14bd6e7fe7f13febaa057f3807e5d/overview

---

2、KeyedProcessingTime滑动窗口

先keybey，再划分ProcessingTime的滑动窗口

 直接代码

import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.datastream.WindowedStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.assigners.SlidingProcessingTimeWindows;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.api.windowing.windows.TimeWindow;
/**
 * KeyedProcessingTime滑动窗口--【无界流】
 */
public class ProcessingTimeSlidingWindowDemo {
    public static void main(String [] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.createLocalEnvironmentWithWebUI(new Configuration());


        DataStreamSource<String> lines = env.socketTextStream("Master", 8888);

        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndCount = lines.map(new MapFunction<String, Tuple2<String, Integer>>() {


            @Override
            public Tuple2<String, Integer> map(String value) throws Exception {
                String[] fields = value.split(",");
                return Tuple2.of(fields[0], Integer.parseInt(fields[1]));
            }
        });

        //调用keyBy
        KeyedStream<Tuple2<String, Integer>, String> keyed = wordAndCount.keyBy(t -> t.f0);
        //NoKeyed window：不调用keyBy，然后调用windowAll方法，传入windowAssinger
        //Keyed window：先调用keyBy，然后调用windowAll方法，传入windowAssinger
        /**
         * 第一个参数：窗口的长度时间
         * 第二个参数：滑动时间
         * 说明：
         * （1）滑动的间隔时间与参数滑动的步长可以设置一样，如：Time.seconds(30),Time.seconds(30).--->变成滚动窗口
         * （2）滑动的间隔时间<参数滑动的步长,如：Time.seconds(30),Time.seconds(60).也是可以，但是会少算一些数据
         */
        WindowedStream<Tuple2<String, Integer>, String, TimeWindow> windowed = keyed.window(SlidingProcessingTimeWindows.of(Time.seconds(30),Time.seconds(10)));

        windowed.sum(1).print();

        env.execute();


    }
}

在nc -lk的的命令下，输入的数字信息测试： 

查看job：http://localhost:8081/#/job/24a41ae174fa92c5872f40b49ff35f02/overview