Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/22042#discussion_r211786471
--- Diff:
external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaDataConsumer.scala
---
@@ -250,33 +294,42 @@ private[kafka010] case class InternalKafkaConsumer(
offset: Long,
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.
+ failOnDataLoss: Boolean): FetchedRecord = {
+ 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)
+ poll(offset, pollTimeoutMs)
+ } else if (!fetchedData.hasNext) {
+ // The last pre-fetched data has been drained.
+ if (offset < offsetAfterPoll) {
--- End diff --
this is the place preventing me from making `offsetAfterPoll` be a local
var.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
