vinodkc commented on a change in pull request #32411:
URL: https://github.com/apache/spark/pull/32411#discussion_r630278821
##########
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:
Yes, Hive does the same thing. [HIVE-11319]
ref:
https://github.com/apache/hive/blob/master/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java#L13615
Later Another JIRA HIVE-15367 added one more level of check for target
location, which only contains the staging-dirs
--
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
