cloud-fan commented on a change in pull request #35132:
URL: https://github.com/apache/spark/pull/35132#discussion_r780458052
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/BasicWriteStatsTracker.scala
##########
@@ -142,8 +142,13 @@ class BasicWriteTaskStatsTracker(
numSubmittedFiles += 1
}
- override def closeFile(filePath: String): Unit = {
- updateFileStats(filePath)
+ override def closeFile(filePath: String, isPathCreated: Boolean): Unit = {
+ if (isPathCreated) {
+ updateFileStats(filePath)
+ } else {
+ logDebug(s"$filePath is not pre-touched by writer, skipping update file
stats")
Review comment:
```suggestion
logDebug(s"$filePath is not created due to no data, skip updating file
stats")
```
##########
File path:
sql/hive/src/main/scala/org/apache/spark/sql/hive/orc/OrcFileFormat.scala
##########
@@ -305,6 +305,12 @@ private[orc] class OrcOutputWriter(
recordWriter.close(Reporter.NULL)
}
}
+
+ /**
+ * If `recordWriterInstantiated` is false, the output file is not pretouched.
Review comment:
Alternatively, can we fix the Hive ORC data source to always write the
file? This seems wrong to me. We should at least write one file even if the
input query is empty, to record the output schema.
--
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: reviews-unsubscr...@spark.apache.org
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
