dejankrak-db commented on code in PR #59305:
URL: https://github.com/apache/spark/pull/59305#discussion_r4277600603
##########
sql/api/src/main/scala/org/apache/spark/sql/types/DataType.scala:
##########
@@ -344,6 +345,16 @@ object DataType {
TimestampNTZNanosType(p)
}
case "timestamp_ltz" => TimestampType
+ case FILE_TYPE(mode) =>
+ // Bare `"file"` resolves differently depending on context: inside a
StructField it is
+ // an external file, which is also what a schema written without any
metadata means; in a
+ // standalone parse (top-level `fromJson` or recursion outside any
StructField) it has no
+ // mode yet, as when a UDF's return type is serialized as a bare
`"file"`.
Review Comment:
Note: commits I mentioned earlier in this thread were squashed. The current
commit is 9c76b11358a, and the comment above is updated to match it.
##########
sql/api/src/main/scala/org/apache/spark/sql/types/StructField.scala:
##########
@@ -77,7 +77,8 @@ case class StructField(
}
private[sql] def dataTypeJsonValue: JValue = {
- if (stringCollationMetadata.isEmpty &&
charVarcharCollationMetadata.isEmpty) {
+ if (stringCollationMetadata.isEmpty &&
charVarcharCollationMetadata.isEmpty &&
+ !dataType.existsRecursively(_.isInstanceOf[FileType])) {
Review Comment:
Note: commits I mentioned earlier in this thread were squashed. The current
commit is 9c76b11358a, and the comment above is updated to match it.
--
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]
