0基础学习PyFlink——时间滑动窗口（Sliding Time Windows）

from typing import Iterable
import time
from pyflink.common import Types, Time
from pyflink.datastream import StreamExecutionEnvironment, RuntimeExecutionMode, WindowFunction
from pyflink.datastream.window import  TimeWindow, SlidingProcessingTimeWindows
   
class SumWindowFunction(WindowFunction[tuple, tuple, str, TimeWindow]):
    def apply(self, key: str, window: TimeWindow, inputs: Iterable[tuple]):
        print(*inputs, window)
        return [(key,  len([e for e in inputs]))]


word_count_data = [("A",2),("A",1),("A",4),("A",3),("A",6),("A",5),("A",7),("A",8),("A",9),("A",10),
                   ("A",11),("A",12),("A",13),("A",14),("A",15),("A",16),("A",17),("A",18),("A",19),("A",20)]

def word_count():
    env = StreamExecutionEnvironment.get_execution_environment()
    env.set_runtime_mode(RuntimeExecutionMode.STREAMING)
    # write all the data to one file
    env.set_parallelism(1)

    source_type_info = Types.TUPLE([Types.STRING(), Types.INT()])
    # define the source
    # mappging
    source = env.from_collection(word_count_data, source_type_info)
    # source.print()

    # keying
    keyed=source.key_by(lambda i: i[0]) 
    
    # reducing
    reduced=keyed.window(SlidingProcessingTimeWindows.of(Time.milliseconds(2), Time.milliseconds(1))) \
                    .apply(SumWindowFunction(),
                        Types.TUPLE([Types.STRING(), Types.INT()]))
        
    # # define the sink
    reduced.print()

    # submit for execution
    env.execute()

if __name__ == '__main__':
    word_count()