HyukjinKwon commented on a change in pull request #32411:
URL: https://github.com/apache/spark/pull/32411#discussion_r630102713
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/command/DataWritingCommand.scala
##########
@@ -96,4 +98,23 @@ object DataWritingCommand {
sparkContext.getLocalProperty(SQLExecution.EXECUTION_ID_KEY),
metrics.values.toSeq)
}
+
+ def assertEmptyRootPath(tablePath: URI, saveMode: SaveMode, sparkSession:
SparkSession) {
+ if (saveMode != SaveMode.Overwrite &&
+ !sparkSession.sqlContext.conf.allowCreateTableAsSelectNonEmptyLocation) {
+ val filePath = new org.apache.hadoop.fs.Path(tablePath)
+ val fs =
filePath.getFileSystem(sparkSession.sparkContext.hadoopConfiguration)
+ if(fs != null && fs.exists(filePath)) {
+ val locStats = fs.getFileStatus(filePath)
+ if(locStats != null && locStats.isDirectory) {
+ val lStats = fs.listStatus(filePath)
Review comment:
The problem here is that it does one more extra listing which can make
the query slow (e.g., S3). Does Hive do the same thing?
--
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
