SparkSql之UDF编写

数据

{"name":"uzi","age":20}
{"name":"gala","age":22}
{"name":"theshy","age":21}

代码

package com.bfd.sql

import org.apache.spark.SparkConf
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.expressions.{MutableAggregationBuffer, UserDefinedAggregateFunction}
import org.apache.spark.sql.types.{DoubleType, LongType, StructType}

object SparkSQL06_UDF {
  def main(args: Array[String]): Unit = {
    //sparkSQL

    //sparkConf
    val sparkConf = new SparkConf()
      .setMaster("local[*]")
      .setAppName("sparkSql_06")

    //sparkSession
    val spark=
      SparkSession.builder().config(sparkConf).getOrCreate()


    import spark.implicits._

    val frame =
      spark
        .read
        .json("D:\\development\\code\\2021.01\\scala1\\spark_core\\src\\main\\in\\user.json")

    //注册udf
    spark.udf.register("addName",(x:String) => "name:"+x)
    //给表一个名字
    frame.createTempView("student")
    //使用udf查询
    spark.sql("select addName(name) from student").show()

    //释放资源
    spark.stop

  }
}

结果