bhat-vinay commented on code in PR #10272:
URL: https://github.com/apache/hudi/pull/10272#discussion_r1421924315
##########
hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/HoodieDatasetBulkInsertHelper.scala:
##########
@@ -243,21 +238,17 @@ object HoodieDatasetBulkInsertHelper
}
}
- private def dropPartitionColumns(df: DataFrame, config: HoodieWriteConfig):
DataFrame = {
- val partitionPathFields = getPartitionPathFields(config).toSet
- val nestedPartitionPathFields = partitionPathFields.filter(f =>
f.contains('.'))
- if (nestedPartitionPathFields.nonEmpty) {
- logWarning(s"Can not drop nested partition path fields:
$nestedPartitionPathFields")
- }
-
- val partitionPathCols = (partitionPathFields --
nestedPartitionPathFields).toSeq
-
- df.drop(partitionPathCols: _*)
- }
-
private def getPartitionPathFields(config: HoodieWriteConfig): Seq[String] =
{
val keyGeneratorClassName =
config.getString(HoodieWriteConfig.KEYGENERATOR_CLASS_NAME)
val keyGenerator = ReflectionUtils.loadClass(keyGeneratorClassName, new
TypedProperties(config.getProps)).asInstanceOf[BuiltinKeyGenerator]
keyGenerator.getPartitionPathFields.asScala
}
+
+ def getPartitionPathCols(config: HoodieWriteConfig): Seq[String] = {
+ val partitionPathFields = getPartitionPathFields(config).toSet
+ val nestedPartitionPathFields = partitionPathFields.filter(f =>
f.contains('.'))
+
+ return (partitionPathFields -- nestedPartitionPathFields).toSeq
Review Comment:
Preserving the existing
[behaviour](https://github.com/apache/hudi/blob/a7c01f6874b20ebebb24399995ed8e8aba09cb2a/hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/HoodieDatasetBulkInsertHelper.scala#L248).
--
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]
