搭建项目并处理离线数据

pom

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.bygones</groupId>
    <artifactId>learn-flink</artifactId>
    <version>1.0.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>1.10.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>1.10.1</version>
        </dependency>
    </dependencies>
</project>

java & filnk 处理离线数据的代码

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

// batch word count
// 对离线数据集的处理
// DataSet 批处理API
public class WordCount {
    public static void main(String[] args) throws Exception {
        // 创建执行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        // 从文件中读取数据
        String inputPath = "F:\\workspace\\data-process\\flink\\learn-flink\\src\\main\\resources\\batch1.txt";
        // DataSource<String> stringDataSources = env.readTextFile(inputPath);
        DataSet inputDataSet = env.readTextFile(inputPath);

        // 对数据集进行处理，按空格分词展开，转换成(word，1)二元组进行统计
        DataSet<Tuple2<String,Integer>> resultDataSet = inputDataSet.flatMap(new MyFlatMapper()) // MyFlatMapper 返回的是二元组数据(word, 1)
        .groupBy(0) // 0 代表位置
        .sum(1); // 1 代表位置

        // 打印输出
        resultDataSet.print();
    }

    // FlatMapFunction<输入参数的类型, 输出参数的类型>
    // Tuple2<String,Integer> 二元组数据类型,例如(word , 1);
    public static class MyFlatMapper implements FlatMapFunction<String,Tuple2<String,Integer>>{

        // 定义对数据的处理规则

        /***
         * <p>
         *     知识点描述:
         *     Collector 收集器, 将需要返回的数据收集起来
         * </p>
         * @param value 输入的数据
         * @param collector 收集器, 将需要返回的数据收集起来
         * @throws Exception
         */
        public void flatMap(String value, Collector<Tuple2<String, Integer>> collector) throws Exception {
            // 按照空格分词
            String[] words = value.split(" ");
            // 遍历所有word，包成二元组
            for (String word: words) {
                collector.collect(new Tuple2<String, Integer>(word , 1));
            }
        }
    }
}

batch1.txt文件的内容

hello world
hello flink
hello spark
hello scala
how are you
fine thank you
and you