Flink入门WorldCount1

1.1 pom文件

scala版本，flink版本等等结合实际情况

 <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <flink.version>1.12.2</flink.version>
        <scala.binary.version>2.11</scala.binary.version>
        <scala.version>2.11.12</scala.version>
        <slf4j.version>1.7.30</slf4j.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
    </dependencies>

1.2 代码实现

    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.BATCH);
        //数据接入  source
        DataStream<String> sourceDs = env.fromElements("test demo", "hello gc well", "gc test");
        //数据转换   下列写法效果相同
        //写法一
/*
        DataStream<String> processDs = sourceDs.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String lines, Collector<String> collector) throws Exception {
                for (String word : lines.split("\\s+")) {
                    collector.collect(word);
                }
            }
        });
*/
        //写法二  Lambda表达式 需要指定返回类型 （泛型丢失）
        DataStream<String> processDs = sourceDs.flatMap((String lines, Collector<String> collector) ->
                Arrays.stream(lines.split("\\s+")).forEach(collector::collect)
        ).returns(Types.STRING);

        DataStream<Tuple2<String, Integer>> outDs = processDs.map(x -> Tuple2.of(x, 1))
                .returns(Types.TUPLE(Types.STRING, Types.INT))
                .keyBy(x -> x.f0)
                .sum(1);
        //输出到控制台  下列都可以
        outDs.addSink(new PrintSinkFunction<>());
//        outDs.print();

        //调用execute才会真正执行
        env.execute();

    }

1.3 演示