上接：flink1.12.x 创建第一个工程

说明

在 flink1.12.x 中，DataSet不推荐使用了

官方文档：
https://ci.apache.org/projects/flink/flink-docs-release-1.12/dev/batch/

java代码

package top.malaoshi;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

public class Main {
    public static void main(String[] args) throws Exception {
        final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        DataSet<String> ds = env.fromElements(
                "Who's there?",
                "I think I hear them. Stand, ho! Who's there?");

        DataSet<Tuple2<String, Integer>> wordCounts = ds
                .flatMap(new LineSplitter())//拆分、并记为1，每个元素是 (单词,1)
                .groupBy(0)//按照第一个元素（即：单词）分组
                .sum(1);//按照第二个元素聚合

        wordCounts.print();
    }

    public static class LineSplitter implements FlatMapFunction<String, Tuple2<String, Integer>> {
        /**
         *
         * @param line 表示每一行数据
         * @param out  返回的数据
         */
        @Override
        public void flatMap(String line, Collector<Tuple2<String, Integer>> out) {
            for (String word : line.split(" ")) {
                out.collect(new Tuple2<String, Integer>(word, 1));
            }
        }
    }
}

执行结果

(yarn,2)
(hadoop,3)
(flink,2)
(hdfs,1)

原文出处：/show_1IX1yxw3kHh4.html