panbingkun commented on code in PR #44665:
URL: https://github.com/apache/spark/pull/44665#discussion_r1519252452
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/csvExpressions.scala:
##########
@@ -260,16 +263,36 @@ case class StructsToCsv(
child = child,
timeZoneId = None)
+ override def checkInputDataTypes(): TypeCheckResult = {
+ child.dataType match {
+ case schema: StructType if schema.map(_.dataType).forall(
+ dt => supportDataType(dt)) => TypeCheckSuccess
+ case _: StructType => DataTypeMismatch(errorSubClass =
"TO_CSV_COMPLEX_TYPE")
+ case _ => DataTypeMismatch(
+ errorSubClass = "UNEXPECTED_INPUT_TYPE",
+ messageParameters = Map(
+ "paramIndex" -> ordinalNumber(0),
+ "requiredType" -> toSQLType(StructType),
+ "inputSql" -> toSQLExpr(child),
+ "inputType" -> toSQLType(child.dataType)
+ )
+ )
+ }
+ }
+
+ @tailrec
+ private def supportDataType(dataType: DataType): Boolean = dataType match {
+ case _: VariantType | BinaryType => false
Review Comment:
Because `these types` cannot be `read back` through `from_csv`,
I have added related tests in UT `CsvFunctionsSuite`.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
