[大数据]flink-wordcount-批处理版-java版

代码

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.operators.AggregateOperator;
import org.apache.flink.api.java.operators.DataSource;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;


public class WordCount {
    public static void main(String[] args) throws Exception{
        ExecutionEnvironment executionEnvironment = ExecutionEnvironment.getExecutionEnvironment();
        executionEnvironment.setParallelism(1);
        DataSet<String> dataSource = executionEnvironment.readTextFile("***\\src\\main\\resources\\hello.txt");
        AggregateOperator<Tuple2<String, Integer>> resultDataSet = dataSource.flatMap(new MyFlatMapFunction()).groupBy(0).sum(1);
        resultDataSet.print();
    }
    public static class MyFlatMapFunction implements FlatMapFunction<String, Tuple2<String, Integer>> {
        @Override
        public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
            String[] values = s.split(" ");
            for (String value: values) {
                collector.collect(new Tuple2(value,1));
            }

        }
    }
}

数据格式：

输出：

若要排序，可将代码改为：

SortPartitionOperator<Tuple2<String, Integer>> resultDataSet =
                dataSource.flatMap(new MyFlatMapFunction()).groupBy(0).sum(1).sortPartition(1, Order.DESCENDING);

结果：