flink经典实战案例

一、java版flink-wordcount-离线计算版

1.1maven构建flink，加入依赖

     
        org.apache.flink
        flink-java
        ${flink.version}
        
     
     
        org.apache.flink
        flink-clients_${scala.version}
        ${flink.version}
     
     

1.2 java实现flink wordCount的代码编写

1.2.1代码编写

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.tuple.Tuple2;
import org.apache.flink.core.fs.FileSystem.WriteMode;
import org.apache.flink.util.Collector;

/**
* Flink实现离线数据DataSet版本的WordCount经典案例
*
*
*/
public class FlinkWordCount4DataSet {
    public static void main(String[] args) throws Exception {
        // 创建Flink的代码执行离线数据流上下文环境变量
        ExecutionEnvironment env = ExecutionEnvironment
                .getExecutionEnvironment();
        // 定义从本地文件系统当中文件路径
        String filePath = "";
        if (args == null || args.length == 0) {
            filePath = "D:\\temp\\input.txt";
        } else {
            filePath = args[0];
        }
        // 获取输入文件对应的DataSet对象
        DataSet inputLineDataSet = env.readTextFile(filePath);

        // 对数据集进行多个算子处理，按空白符号分词展开，并转换成(word, 1)二元组进行统计
        DataSet> resultSet = inputLineDataSet
                .flatMap(
                        new FlatMapFunction>()