KnightChess commented on code in PR #12242:
URL: https://github.com/apache/hudi/pull/12242#discussion_r1841408916
##########
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/payload/ExpressionPayload.scala:
##########
@@ -164,6 +163,34 @@ class ExpressionPayload(@transient record: GenericRecord,
}
}
+ private def doRecordMerge(incomingRecord: GenericRecord,
+ existingRecord: IndexedRecord,
+ schema: Schema,
+ properties: Properties): HOption[IndexedRecord] = {
+ val tablePayloadClass =
properties.getProperty(PAYLOAD_ORIGINAL_AVRO_PAYLOAD)
+ if
(tablePayloadClass.equals(classOf[OverwriteWithLatestAvroPayload].getName)) {
+ HOption.of(incomingRecord)
+ } else if
(tablePayloadClass.equals(classOf[DefaultHoodieRecordPayload].getName)) {
+ if (needUpdatingPersistedRecord(existingRecord, incomingRecord,
properties)) {
+ HOption.of(incomingRecord)
+ } else {
+ HOption.of(existingRecord)
+ }
+ } else {
+ val orderingField = ConfigUtils.getOrderingField(properties)
+ if (StringUtils.isNullOrEmpty(orderingField)) {
+ HOption.of(incomingRecord)
+ } else {
+ val consistentLogicalTimestampEnabled =
properties.getProperty(KeyGeneratorOptions.KEYGENERATOR_CONSISTENT_LOGICAL_TIMESTAMP_ENABLED.key,
+
KeyGeneratorOptions.KEYGENERATOR_CONSISTENT_LOGICAL_TIMESTAMP_ENABLED.defaultValue).toBoolean
+ val incomingRecordPayload =
HoodieRecordUtils.loadPayload(tablePayloadClass, incomingRecord,
Review Comment:
make sence, and I think user should have the flexibility to control their
update requirements, rather than being constrained by any payload or
preCombineKey. This check can be placed in the conditional expression after the
match primary key, but this is already an MIT design issue.
--
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]
