amrishlal commented on code in PR #8978:
URL: https://github.com/apache/hudi/pull/8978#discussion_r1240446113
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieSparkSqlWriter.scala:
##########
@@ -254,11 +254,26 @@ object HoodieSparkSqlWriter {
val (writeResult, writeClient: SparkRDDWriteClient[_]) =
operation match {
- case WriteOperationType.DELETE =>
+ case WriteOperationType.DELETE | WriteOperationType.DELETE_PREPPED =>
val genericRecords = HoodieSparkUtils.createRdd(df,
avroRecordName, avroRecordNamespace)
// Convert to RDD[HoodieKey]
- val keyGenerator =
HoodieSparkKeyGeneratorFactory.createKeyGenerator(new
TypedProperties(hoodieConfig.getProps))
- val hoodieKeysToDelete = genericRecords.map(gr =>
keyGenerator.getKey(gr)).toJavaRDD()
+ val isPrepped =
hoodieConfig.getBooleanOrDefault(DATASOURCE_WRITE_PREPPED_KEY, false)
+ val keyGenerator: Option[BaseKeyGenerator] = if (isPrepped) {
+ None
+ } else {
+ Some(HoodieSparkKeyGeneratorFactory.createKeyGenerator(new
TypedProperties(hoodieConfig.getProps))
+ .asInstanceOf[BaseKeyGenerator])
+ }
+
+ var validatePreppedRecord = true
Review Comment:
Replaced map with mapPartitions to avoid multiple calls to validate function.
--
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]
