環境準備

本地Windows環境已安裝Flink 1.9.0版本。

一.準備代碼

1.1 maven準備

配置Flink的依賴

<dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-java</artifactId>
      <version>1.9.0</version>
      <scope>provided</scope>
    </dependency>
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-streaming-java_2.11</artifactId>
      <version>1.9.0</version>
      <scope>provided</scope>
    </dependency>
    <dependency>
      <groupId>org.apache.flink</groupId>
      <artifactId>flink-core</artifactId>
      <version>1.9.0</version>
    </dependency>

1.2 Java代碼準備

還是以大家耳熟能詳的wordCount程序爲例

package com.zqs.study.flink;

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.DataSource;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.util.Collector;

/*
  @author  只是甲
 * @date    2021-08-24
 * @remark  Flink的第一個wordCount程序
 */

public class wordCount {
    public static void main(String[] args) throws Exception{
        //創建執行環境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        //從文件中讀取數據
        String inputPath = "C:\\Users\\Administrator\\IdeaProjects\\FlinkStudy\\src\\main\\java\\com\\zqs\\study\\flink\\hello.txt";
        DataSet<String> inputDataSet = env.readTextFile(inputPath);

        // 對數據集進行處理，按空格分詞展開，轉換成(word, 1)二元組進行統計
        DataSet<Tuple2<String, Integer>> resultSet = inputDataSet.flatMap(new MyFlatMapper())
                .groupBy(0) // 按照第一個位置的word分組
                .sum(1); // 將第二個位置上的數據求和;

        resultSet.print();

        //env.execute();

        //env.execute("Word Count Example");
    }

    //自定義類，實現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 {
            //按空格分詞
            String[] words = value.split(" ");
            //遍歷所有word,包成二元組輸出
            for (String word : words) {
                out.collect(new Tuple2<String, Integer>(word, 1));
            }

        }
    }
}