flink入门代码演示(Java)

引入坐标：

		<dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.10.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>1.10.1</version>
        </dependency>

WordCount：懂得都懂

1. 从txt文件中获取数据

public class WordCount {
    public static void main(String[] args) throws Exception {
        //1. 创建环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        String path = "E:\\bs\\flinkjava\\src\\main\\resources\\a.txt";
        //获取数据源
        DataSet<String> source = env.readTextFile(path);
        //对数据进行处理
        DataSet<Tuple2<String,Integer>> result = source.flatMap(new MyFlatMapper())
                .groupBy(0)
                .sum(1);
        //打印输出
        result.print();
    }
    //实现FlatMapFunction接口，重写flatMap方法
    public static class MyFlatMapper implements FlatMapFunction<String, Tuple2<String,Integer>> {
        @Override
        public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
            String[] words = s.split(" ");
            for (String word : words) {
                collector.collect(new Tuple2<>(word,1));
            }
        }
    }
}

结果：

2. 从数据流中获取数据：

public class StreamWC {
    public static void main(String[] args) throws Exception {
        //创建环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        /*String path = "E:\bs\flinkjava\src\main\resources\a.txt";
        DataStreamSource<String> source = env.readTextFile(path);*/

        //用parameter tool工具从程序启动参数中提取配置项
        ParameterTool parameterTool = ParameterTool.fromArgs(args);
        String host = parameterTool.get("host");
        Integer port = parameterTool.getInt("port");
        
        DataStreamSource<String> source = env.socketTextStream(host, port);
        DataStream<Tuple2<String, Integer>> resultStream = source.flatMap(new WordCount.MyFlatMapper())
                .keyBy(0).sum(1);
        //打印输出
        resultStream.print();
        //执行
        env.execute();

    }

    public static class MyFlatMapper implements FlatMapFunction<String, Tuple2<String, Integer>> {
        @Override
        public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
            String[] words = s.split(" ");
            for (String word : words) {
                collector.collect(new Tuple2<>(word, 1));
            }
        }
    }
}

实验结果：

总结：
类似简单ETL，
首先构造环境，然后配置获取数据源的方式(E)，接着使用转换方法(T)，最后输出(L)。