flink小试牛刀（java版本）-实现wordCount

导语：flink是一款优秀的批处理和流处理的大数据计算引擎，本文将通过flink的java api实现wordCount.

环境准备：idea, maven

实验：
1、maven 内容：

<!--        flink-->
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-core -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-core</artifactId>
            <version>1.13.0</version>
        </dependency>


        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-java -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>1.13.1</version>
<!--            <scope>provided</scope>-->
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-clients -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.12</artifactId>
            <version>1.13.2</version>
        </dependency>

2、文件准备
hello.txt

3、代码内容

package flinkTest;


// @Time 2021/9/8
// @Author HaiRu,WU


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;

// 批处理word count 实验
public class WordCount {

    public static void main(String[] args) throws Exception {
        // 创建执行环境
        ExecutionEnvironment environment = ExecutionEnvironment.getExecutionEnvironment();

        // 从文件读取数据
        String inputPath = "D:\\IdeaProjects\\Demo01\\src\\main\\resources\\hello.txt";
        DataSource<String> inputDataSet = environment.readTextFile(inputPath);

        //对数据集进行处理, 空格分词展开，转换成（word,1）这样的二元组进行统计

        DataSet<Tuple2<String, Integer>> resultSet =  inputDataSet.flatMap(new MyFlatMapper())
                //按照第一个位置的word分组
                .groupBy(0)
                //将第二个位置的数据求和
                .sum(1);

        //打印输出
        resultSet.print();

    }

    // 自定义类，实现FlatMapFunction接口
    public static class MyFlatMapper implements FlatMapFunction<String, Tuple2<String, Integer> >{

        @Override
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
            // 按照空格进行分词
            String[] words = value.split(" ");
            // 遍历所有word包成二元组
            for (String word:words){
                out.collect(new Tuple2<String, Integer>(word, 1));
            }
        }
    }

}

4、结果展示