vinodkc commented on a change in pull request #32411:
URL: https://github.com/apache/spark/pull/32411#discussion_r631622569
##########
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)
+ if(lStats != null && lStats.length != 0) {
+ throw new AnalysisException(
+ s"CREATE-TABLE-AS-SELECT cannot create table" +
Review comment:
In Hive ,
https://github.com/apache/hive/blob/master/common/src/java/org/apache/hadoop/hive/ql/ErrorMsg.java#L408
Error message is `CREATE-TABLE-AS-SELECT cannot create table with location
to a non-empty directory.`
To be consistent, shall we show this message?
"CREATE-TABLE-AS-SELECT cannot create table with location to a non-empty
directory. To disable the behavior, set
'spark.sql.legacy.allowNonEmptyLocationInCTAS to true"
--
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]
