Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/22042#discussion_r209476548
--- Diff:
external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaDataConsumer.scala
---
@@ -251,32 +274,53 @@ private[kafka010] case class InternalKafkaConsumer(
untilOffset: Long,
pollTimeoutMs: Long,
failOnDataLoss: Boolean): ConsumerRecord[Array[Byte], Array[Byte]] =
{
- if (offset != nextOffsetInFetchedData || !fetchedData.hasNext()) {
- // This is the first fetch, or the last pre-fetched data has been
drained.
+ if (offset != nextOffsetInFetchedData) {
+ // This is the first fetch, or the fetched data has been reset.
// Seek to the offset because we may call seekToBeginning or
seekToEnd before this.
seek(offset)
poll(pollTimeoutMs)
+ } else if (!fetchedData.hasNext) {
+ // The last pre-fetched data has been drained.
+ if (offset < offsetAfterPoll) {
+ // Offsets in [offset, offsetAfterPoll) are missing. We should
skip them.
+ resetFetchedData()
+ throw new MissingOffsetException(offset, offsetAfterPoll)
+ } else {
+ seek(offset)
+ poll(pollTimeoutMs)
+ }
}
if (!fetchedData.hasNext()) {
- // We cannot fetch anything after `poll`. Two possible cases:
+ // We cannot fetch anything after `poll`. Three possible cases:
// - `offset` is out of range so that Kafka returns nothing. Just
throw
// `OffsetOutOfRangeException` to let the caller handle it.
// - Cannot fetch any data before timeout. TimeoutException will be
thrown.
+ // - Fetched something but all of them are not valid date messages.
In this case, the position
--- End diff --
date => data
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
