dongjoon-hyun commented on code in PR #44636:
URL: https://github.com/apache/spark/pull/44636#discussion_r1473284940
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSource.scala:
##########
@@ -113,16 +118,42 @@ class FileStreamSource(
// Visible for testing and debugging in production.
val seenFiles = new SeenFilesMap(maxFileAgeMs, fileNameOnly)
- private var allFilesForTriggerAvailableNow: Seq[(SparkPath, Long)] = _
+ private var allFilesForTriggerAvailableNow: Seq[NewFileEntry] = _
metadataLog.restore().foreach { entry =>
seenFiles.add(entry.sparkPath, entry.timestamp)
}
seenFiles.purge()
- logInfo(s"maxFilesPerBatch = $maxFilesPerBatch, maxFileAgeMs =
$maxFileAgeMs")
+ logInfo(s"maxFilesPerBatch = $maxFilesPerBatch, " +
+ s"maxBytesPerBatch = $maxBytesPerBatch, maxFileAgeMs = $maxFileAgeMs")
+
+ private var unreadFiles: Seq[NewFileEntry] = _
- private var unreadFiles: Seq[(SparkPath, Long)] = _
+ /**
+ * Split files into a selected/unselected pair according to a total size
threshold.
+ * Always puts the 1st element in a left split and keep adding it to a left
split
+ * until reaches a specified threshold or [[Long.MaxValue]].
+ */
+ private def takeFilesUntilMax(files: Seq[NewFileEntry], maxSize: Long):
+ (FilesSplit, FilesSplit) = {
Review Comment:
Yes, Rollback on the unnecessary change is the recommended way. Only new
code should follow the coding style.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
