Flink之状态编程

---

一、按键分区状态（Keyed State）

1.1、值状态（ValueState）

1.1.1、定义

状态中只保存一个“值”（value）。ValueState本身是一个接口，源码中定义如下：

public interface ValueState<T> extends State {
T value() throws IOException;
void update(T value) throws IOException;
}

1.1.2、使用案例

利用ValueState和定时器每10秒输出一次用户的pv量

package com.hpsk.flink.state;

import com.hpsk.flink.beans.Event;
import com.hpsk.flink.source.EventWithWatermarkSource;
import org.apache.flink.api.common.state.ValueState;
import org.apache.flink.api.common.state.ValueStateDescriptor;
import org.apache.flink.configuration.Configuration;
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.KeyedProcessFunction;
import org.apache.flink.util.Collector;
import java.sql.Timestamp;

public class ValueStateDS {
   
    public static void main(String[] args) throws Exception {
   
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);

        DataStreamSource<Event> stream = env.addSource(new EventWithWatermarkSource());

        SingleOutputStreamOperator<String> result = stream.keyBy(t -> t.user)
                .process(new KeyedProcessFunction<String, Event, String>() {
   
                    // 定义两个状态，保存当前 pv 值，以及定时器时间戳
                    private ValueState<Long> valueState;
                    private ValueState<Long> timerTsState;

                    @Override
                    public void open(Configuration parameters) throws Exception {
   
                        valueState = getRuntimeContext().getState(new ValueStateDescriptor<Long>("value-state", Long.class));
                        timerTsState = getRuntimeContext().getState(new ValueStateDescriptor<Long>("timerTs", Long.class));

                    }

                    @Override
                    public void processElement(Event value, Context ctx, Collector<String> collector) throws Exception {
   
                        Long count = valueState.value();
                        if (count == null) {
   
                            valueState.update(1L);
                        } else {
   
                            valueState.update(count + 1);
                        }

                        // 注册定时器
                        if (timerTsState.value() == null) {
   
                            ctx.timerService().registerEventTimeTimer(value.timestamp + 10 * 1000L);
                            timerTsState.update(value.timestamp + 10 * 1000L);
                        }
                    }

                    @Override
                    public void onTimer(long timestamp, OnTimerContext ctx, Collector<String> out) throws Exception {
   
                        out.collect("时间："+new Timestamp(timestamp) + " ->用户："+  ctx.getCurrentKey() + "的pv值为：" + valueState.value());
                        timerTsState.clear();
                    }
                });
        result.print(">>>>");

        env.execute();
    }
}

1.2、列表状态（ListState）

1.2.1、定义

将需要保存的数据，以列表（List）的形式组织起来。在 ListState接口中同样有一个类型参数 T，表示列表中数据的类型。ListState 也提供了一系列的方法来操作状态，使用方式
与一般的 List 非常相似。

1.2.2、使用案例

利用ListState进行实现sql中的join操作

package com.hpsk.flink.state;

import org.apache.flink.api.common.eventtime.SerializableTimestampAssigner;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.state.ListState;
import org.apache.flink.api.common.state.ListStateDescriptor;
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple3;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.co.CoProcessFunction;
import org.apache.flink.util.Collector;

public class ListStateDS {
   
    public static void main(String[] args) throws Exception {
   
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        SingleOutputStreamOperator<Tuple3<String, String, Long>> stream1 = env.fromElements(
                Tuple3.of("a", "stream-1", 1000L),
                Tuple3.of("b", "stream-1", 2000L)
        ).assignTimestampsAndWatermarks(WatermarkStrategy.<Tuple3<String, String, Long>>forMonotonousTimestamps().withTimestampAssigner(