[大数据]Flink中的算子

批处理算子

import org.apache.flink.api.common.functions.RichMapFunction
import org.apache.flink.api.common.operators.Order
import org.apache.flink.api.java.aggregation.Aggregations
import org.apache.flink.api.scala.ExecutionEnvironment
import org.apache.flink.api.scala._
import org.apache.flink.streaming.api.scala.DataStream
object Transform_Batch_Demo {
def main(args: Array[String]): Unit = {
    //创建批处理程序入口
    val env: ExecutionEnvironment = ExecutionEnvironment.getExecutionEnvironment

    //map算子
    val data: DataSet[Int] = env.fromCollection(List(1,2,3,4,5))
    //将每个元素扩大10倍
    val result: DataSet[Int] = data.map(_*10)
    //打印输出
    result.print()
    
    //flatMap算子
    val listDataSet: DataSet[String] = env.fromCollection(List("hadoop spark","hive mysql","hbase kafka"))
    //按照分隔符进行分割
    val result: DataSet[String] = listDataSet.flatMap(_.split(" "))
    //打印输出
    result.print()

    /

开通VIP 解锁文章