练习 ：Flink 字频统计

xiaoming,english,90
xiaoming,math,80
xiaohong,english,98
xiaohong,math,82

test

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.operators.DataSource;
import org.apache.flink.api.java.operators.FlatMapOperator;
import org.apache.flink.api.java.operators.UnsortedGrouping;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

public class WordCount {
    public static void main(String[] args) {
        System.out.println("字频统计");
        //1 环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        //2 读取文件
        DataSource<String> source = env.readTextFile("src\\main\\resources\\file.txt");
        //3 得到二元组
        FlatMapOperator<String, Tuple2<String, Long>> wordAndOne = source.flatMap(
                (String line, Collector<Tuple2<String, Long>> out) -> {
                    String[] split = line.split(",");
                    for (String s : split) {
                        out.collect(Tuple2.of(s, 1L));
                    }
                }
        ).returns(Types.TUPLE(Types.STRING, Types.LONG));
//        wordAndOne.print("word count");
        //4 分组
        UnsortedGrouping<Tuple2<String, Long>> wordAndOneGroup = wordAndOne.groupBy(0);
        //5 聚合
        AggregateOperator<Tuple2<String, Long>> sum = wordAndOneGroup.sum(1);
        //6 打印
        try {
            sum.print();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}