HyukjinKwon commented on a change in pull request #29234:
URL: https://github.com/apache/spark/pull/29234#discussion_r461401131
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/util/SchemaUtils.scala
##########
@@ -42,7 +44,27 @@ private[spark] object SchemaUtils {
*/
def checkSchemaColumnNameDuplication(
schema: StructType, colType: String, caseSensitiveAnalysis: Boolean =
false): Unit = {
- checkColumnNameDuplication(schema.map(_.name), colType,
caseSensitiveAnalysis)
+ val queue = new Queue[StructType]()
+ queue.enqueue(schema)
+ do {
+ val struct = queue.dequeue()
+ checkColumnNameDuplication(struct.map(_.name), colType,
caseSensitiveAnalysis)
+ val nestedStructs = struct.map(_.dataType).collect { case st: StructType
=> st }
+ queue.enqueue(nestedStructs: _*)
+ } while (queue.nonEmpty)
Review comment:
Should we just do this in a recursive way? I think the performance here
doesn't matter, and we usually does that.
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/util/SchemaUtils.scala
##########
@@ -42,7 +44,27 @@ private[spark] object SchemaUtils {
*/
def checkSchemaColumnNameDuplication(
schema: StructType, colType: String, caseSensitiveAnalysis: Boolean =
false): Unit = {
- checkColumnNameDuplication(schema.map(_.name), colType,
caseSensitiveAnalysis)
+ val queue = new Queue[StructType]()
+ queue.enqueue(schema)
+ do {
+ val struct = queue.dequeue()
+ checkColumnNameDuplication(struct.map(_.name), colType,
caseSensitiveAnalysis)
+ val nestedStructs = struct.map(_.dataType).collect { case st: StructType
=> st }
+ queue.enqueue(nestedStructs: _*)
+ } while (queue.nonEmpty)
Review comment:
Should we just do this in a recursive way? I think the performance here
doesn't matter, and we usually do that.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
