HeartSaVioR commented on a change in pull request #28904:
URL: https://github.com/apache/spark/pull/28904#discussion_r471910255
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSinkLog.scala
##########
@@ -97,18 +97,15 @@ class FileStreamSinkLog(
s"Please set ${SQLConf.FILE_SINK_LOG_COMPACT_INTERVAL.key} (was
$defaultCompactInterval) " +
"to a positive value.")
- override def compactLogs(logs: Seq[SinkFileStatus]): Seq[SinkFileStatus] = {
- val deletedFiles = logs.filter(_.action ==
FileStreamSinkLog.DELETE_ACTION).map(_.path).toSet
- if (deletedFiles.isEmpty) {
- logs
- } else {
- logs.filter(f => !deletedFiles.contains(f.path))
- }
+ override def shouldRetain(log: SinkFileStatus): Boolean = {
+ log.action != FileStreamSinkLog.DELETE_ACTION
}
}
object FileStreamSinkLog {
val VERSION = 1
+ // TODO: This action hasn't been used from the introduction. We should just
remove this.
+ // TODO: We can remove the field "action" as well, ignoring "action" in
existing metadata log.
Review comment:
Let's consider only when we are open to introduce another version. Don't
want to deal with compatibility even without bumping version.
----------------------------------------------------------------
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
