gaborgsomogyi commented on a change in pull request #29729: URL: https://github.com/apache/spark/pull/29729#discussion_r489221735
########## File path: external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReader.scala ########## @@ -213,64 +187,68 @@ private[kafka010] class KafkaOffsetReader( assert(partitions.asScala == partitionTimestamps.keySet, "If starting/endingOffsetsByTimestamp contains specific offsets, you must specify all " + s"topics. Specified: ${partitionTimestamps.keySet} Assigned: ${partitions.asScala}") - logDebug(s"Partitions assigned to consumer: $partitions. Seeking to $partitionTimestamps") + logDebug(s"Assigned partitions: $partitions. Seeking to $partitionTimestamps") } val fnRetrievePartitionOffsets: ju.Set[TopicPartition] => Map[TopicPartition, Long] = { _ => { - val converted = partitionTimestamps.map { case (tp, timestamp) => - tp -> java.lang.Long.valueOf(timestamp) + val listOffsetsParams = partitionTimestamps.map { case (tp, timestamp) => + tp -> OffsetSpec.forTimestamp(timestamp) }.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 $tp and timestamp " + + s"${partitionTimestamps(tp)}.") + } - val offsetForTime: ju.Map[TopicPartition, OffsetAndTimestamp] = - consumer.offsetsForTimes(converted) - - offsetForTime.asScala.map { case (tp, offsetAndTimestamp) => - if (failsOnNoMatchingOffset) { - assert(offsetAndTimestamp != null, "No offset matched from request of " + - s"topic-partition $tp and timestamp ${partitionTimestamps(tp)}.") - } - - if (offsetAndTimestamp == null) { - tp -> KafkaOffsetRangeLimit.LATEST - } else { - tp -> offsetAndTimestamp.offset() - } + if (offsetSpec.offset() == OffsetFetchResponse.INVALID_OFFSET) { + tp -> KafkaOffsetRangeLimit.LATEST + } else { + tp -> offsetSpec.offset() + } }.toMap } } - val fnAssertFetchedOffsets: Map[TopicPartition, Long] => Unit = { _ => } - - fetchSpecificOffsets0(fnAssertParametersWithPartitions, fnRetrievePartitionOffsets, - fnAssertFetchedOffsets) + fetchSpecificOffsets0(fnAssertParametersWithPartitions, fnRetrievePartitionOffsets) } private def fetchSpecificOffsets0( fnAssertParametersWithPartitions: ju.Set[TopicPartition] => Unit, - fnRetrievePartitionOffsets: ju.Set[TopicPartition] => Map[TopicPartition, Long], - fnAssertFetchedOffsets: Map[TopicPartition, Long] => Unit): KafkaSourceOffset = { + fnRetrievePartitionOffsets: ju.Set[TopicPartition] => Map[TopicPartition, Long] Review comment: It mustn't be unless the code you've pinpointed can fire up somehow: https://github.com/apache/spark/pull/29729#discussion_r488831782 ---------------------------------------------------------------- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org