Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/20097#discussion_r159960120
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/MicroBatchExecution.scala
---
@@ -236,14 +264,27 @@ class MicroBatchExecution(
val hasNewData = {
awaitProgressLock.lock()
try {
- val latestOffsets: Map[Source, Option[Offset]] = uniqueSources.map
{
+ // Generate a map from each unique source to the next available
offset.
+ val latestOffsets: Map[BaseStreamingSource, Option[Offset]] =
uniqueSources.map {
case s: Source =>
updateStatusMessage(s"Getting offsets from $s")
reportTimeTaken("getOffset") {
(s, s.getOffset)
}
+ case s: MicroBatchReader =>
+ updateStatusMessage(s"Getting offsets from $s")
+ reportTimeTaken("getOffset") {
+ // Once v1 streaming source execution is gone, we can
refactor this away.
+ // For now, we set the range here to get the source to infer
the available end offset,
+ // get that offset, and then set the range again when we
later execute.
+ s.setOffsetRange(
--- End diff --
incorrect indentation.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
