对于单列,UDF的输入类型是该列的dataType,而对于struct列,输入类型是Row,为什么以及如何实现?
import org.apache.spark.sql.types._
import org.apache.spark.sql.Row
val sub_schema = StructType(StructField("col1",ArrayType(IntegerType,false),true) :: StructField("col2",StringType,true)::Nil)
val schema = StructType(StructField("subtable", sub_schema,true) :: Nil)
val data = Seq(Row(Row(Array(1,2),"eb")), Row(Row(Array(3,2,1), "dsf")) )
val rd = sc.parallelize(data)
val df = spark.createDataFrame(rd, schema)
df.printSchema
val u = udf((x:Row) => x, sub_schema)
root
|-- subtable: struct (nullable = true)
| |-- col1: array (nullable = true)
| | |-- element: integer (containsNull = false)
| |-- col2: string (nullable = true)