SparkSQL 自定义函数UDF实战应用

package sparkSql

import org.apache.spark.sql.SparkSession

/**
 * @Author yqq
 * @Date 2021/12/14 14:12
 * @Version 1.0
 */
object SparkSQLUDF {
  def main(args: Array[String]): Unit = {
    val session = SparkSession.builder().master("local").appName("test01").getOrCreate()
    val list: List[String] = List[String]("科比", "詹姆斯", "杜兰特", "霍华德")
    import session.implicits._
    val frame = list.toDF("name")
    frame.createTempView("t")

    /**
     * 自定义nameLength函数，计算name长度
     */
    session.udf.register("nameLength",(n:String)=>{
      n.length()
    })
    session.sql(
      """
        |select name,nameLength(name) as nl from t order by nl desc
        |""".stripMargin).show()
  }
}