Вы можете достичь своего результата, определив функцию udf
и передав собранные столбцы структуры *1003* в функцию udf
для s , направляя и заполняя нулевые значения ненулевыми значениями ,( комментарии приведены в коде для объяснения )
import org.apache.spark.sql.functions._
//udf function definition
def sortAndAggUdf = udf((structs: Seq[Row])=>{
//sorting the collected list by timestamp in descending order
val sortedStruct = structs.sortBy(str => str.getAs[Long]("UpdatedtimeStamp"))(Ordering[Long].reverse)
//selecting the first struct and casting to out case class
val first = out(sortedStruct(0).getAs[String]("Name"), sortedStruct(0).getAs[String]("Passport"), sortedStruct(0).getAs[String]("Country"), sortedStruct(0).getAs[String]("License"), sortedStruct(0).getAs[Long]("UpdatedtimeStamp"))
//aggregation for checking nulls and populating first not null value
sortedStruct
.foldLeft(first)((x, y) => {
out(
if(x.Name == null || x.Name.isEmpty) y.getAs[String]("Name") else x.Name,
if(x.Passport == null || x.Passport.isEmpty) y.getAs[String]("Passport") else x.Passport,
if(x.Country == null || x.Country.isEmpty) y.getAs[String]("Country") else x.Country,
if(x.License == null || x.License.isEmpty) y.getAs[String]("License") else x.License,
x.UpdatedtimeStamp)
})
})
//making the rest of the columns as one column and changing the UpdatedtimeStamp column to long for sorting in udf
df.select(col("ID"), struct(col("Name"), col("Passport"), col("Country"), col("License"), unix_timestamp(col("UpdatedtimeStamp"), "MM-dd-yyyy").as("UpdatedtimeStamp")).as("struct"))
//grouping and collecting the structs and passing to udf function for manipulation
.groupBy("ID").agg(sortAndAggUdf(collect_list("struct")).as("struct"))
//separating the aggregated columns to separate columns
.select(col("ID"), col("struct.*"))
//getting the date in correct format
.withColumn("UpdatedtimeStamp", date_format(col("UpdatedtimeStamp").cast("timestamp"), "MM-dd-yyyy"))
.show(false)
, что должно дать вам
+---+----+--------+-------+-------+----------------+
|ID |Name|Passport|Country|License|UpdatedtimeStamp|
+---+----+--------+-------+-------+----------------+
|1 |Shah|12345 |null |ABC |12-02-2018 |
|2 |PJ |null |ANB |a |10-02-2018 |
+---+----+--------+-------+-------+----------------+
и, конечно, необходим класс кейсов
case class out(Name: String, Passport: String, Country: String, License: String, UpdatedtimeStamp: Long)