viirya commented on a change in pull request #32747:
URL: https://github.com/apache/spark/pull/32747#discussion_r655127351
##########
File path:
external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReaderAdmin.scala
##########
@@ -208,25 +205,47 @@ private[kafka010] class KafkaOffsetReaderAdmin(
val listOffsetsParams = tps.asScala.map { tp =>
tp -> OffsetSpec.forTimestamp(timestamp)
}.toMap.asJava
- admin.listOffsets(listOffsetsParams,
listOffsetsOptions).all().get().asScala.map {
- case (tp, offsetSpec) =>
- if (failsOnNoMatchingOffset) {
- assert(offsetSpec.offset() != OffsetFetchResponse.INVALID_OFFSET,
"No offset " +
- s"matched from request of topic-partition $tp and timestamp " +
- s"$timestamp.")
- }
- if (offsetSpec.offset() == OffsetFetchResponse.INVALID_OFFSET) {
- tp -> KafkaOffsetRangeLimit.LATEST
- } else {
- tp -> offsetSpec.offset()
- }
- }.toMap
+ readTimestampOffsets(
+ admin.listOffsets(listOffsetsParams,
listOffsetsOptions).all().get().asScala.toMap,
+ isStartingOffsets,
+ strategyOnNoMatchStartingOffset,
+ _ => timestamp
+ )
}
fetchSpecificOffsets0(fnAssertParametersWithPartitions,
fnRetrievePartitionOffsets)
}
+ private def readTimestampOffsets(
+ tpToOffsetMap: Map[TopicPartition,
ListOffsetsResult.ListOffsetsResultInfo],
+ isStartingOffsets: Boolean,
+ strategyOnNoMatchStartingOffset: StrategyOnNoMatchStartingOffset.Value,
+ partitionTimestampFn: TopicPartition => Long): Map[TopicPartition, Long]
= {
+
+ tpToOffsetMap.map { case (tp, offsetSpec) =>
+ val offset = if (offsetSpec.offset() ==
OffsetFetchResponse.INVALID_OFFSET) {
+ if (isStartingOffsets) {
+ strategyOnNoMatchStartingOffset match {
+ case StrategyOnNoMatchStartingOffset.ERROR =>
+ throw new IllegalArgumentException("No offset " +
+ s"matched from request of topic-partition $tp and timestamp " +
+ s"${partitionTimestampFn(tp)}.")
+
+ case StrategyOnNoMatchStartingOffset.LATEST =>
+ KafkaOffsetRangeLimit.LATEST
+ }
Review comment:
Looks like this checks the strategy for each start offsets per batch?
I'm a bit confused. Isn't the `startingOffsetsByTimestamp` only for `The start
point of timestamp when a query is started ...`?
--
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]
