Flink入门示例（Word Count，数据来源为Socket）

最新推荐文章于 2024-08-06 10:35:08 发布

Simple-395

最新推荐文章于 2024-08-06 10:35:08 发布

阅读量610

点赞数

本文链接：https://blog.csdn.net/lpw_cn/article/details/114573562

版权

大数据-实时专栏收录该内容

6 篇文章 1 订阅

订阅专栏

以下演示一个简单的Flink Word Count程序。

数据来源为Socket，端口9999。

基于Flink 1.11。

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;

public class WindowWordCount {

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

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        DataStream<Tuple2<String, Integer>> dataStream = env
                .socketTextStream("localhost", 9999)
                .flatMap(new Splitter())
                .keyBy(value -> value.f0).timeWindow(Time.seconds(5)).sum(1);

        dataStream.print();

        env.execute("Window WordCount");
    }

    public static class Splitter implements FlatMapFunction<String, Tuple2<String, Integer>> {
        @Override
        public void flatMap(String sentence, Collector<Tuple2<String, Integer>> out) {
            for (String word : sentence.split(" ")) {
                out.collect(new Tuple2<>(word, 1));
            }
        }
    }
}