Flink 1.16.0 无界数据流 wordCount示例

环境

JDK1.8

新建maven工程

引入依赖

<dependencies>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java</artifactId>
            <version>1.16.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients</artifactId>
            <version>1.16.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-runtime</artifactId>
            <version>1.16.0</version>
        </dependency>

    </dependencies>
    

代码示例

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

        DataStreamSource<String> boundedStream = env.socketTextStream("bigdata.dianblog.com", 7777);
        SingleOutputStreamOperator<Tuple2<String, Long>> wordAndOneTuple = boundedStream.flatMap((String line, Collector<Tuple2<String, Long>> collector) -> {

            String[] words = line.split(" ");
            for (String word : words) {
                collector.collect(Tuple2.of(word, 1L));
            }

        }).returns(Types.TUPLE(Types.STRING, Types.LONG));


        KeyedStream<Tuple2<String, Long>, String> wordAndOneKeyedStream = wordAndOneTuple.keyBy(data -> data.f0);


        SingleOutputStreamOperator<Tuple2<String, Long>> sum = wordAndOneKeyedStream.sum(1);

        sum.print();

        env.execute();

    }