jackylk commented on a change in pull request #3388: [CARBONDATA-3520] CTAS should fail if select query contains duplicate columns
URL:
https://github.com/apache/carbondata/pull/3388#discussion_r326906657
##########
File path: integration/spark2/src/main/scala/org/apache/spark/sql/parser/CarbonSparkSqlParserUtil.scala
##########
@@ -355,16 +357,27 @@ object CarbonSparkSqlParserUtil {
// Ensuring whether no duplicate name is used in table definition
val colNames: Seq[String] = cols.map(_.name)
+ checkIfDuplicateColumnExists(columns, tableIdentifier, colNames)
+ colNames
+ }
+
+ private def checkIfDuplicateColumnExists(columns: ColTypeListContext,
+ tableIdentifier: TableIdentifier,
+ colNames: Seq[String]): Unit = {
if (colNames.length != colNames.distinct.length) {
val duplicateColumns = colNames.groupBy(identity).collect {
case (x, ys) if ys.length > 1 => "\"" + x + "\""
}
- operationNotAllowed(s"Duplicated column names found in table definition of " +
- s"$tableIdentifier: ${ duplicateColumns.mkString("[", ",", "]") }",
- columns)
+ val errorMessage = s"Duplicated column names found in table definition of " +
+ s"$tableIdentifier: ${ duplicateColumns.mkString("[", ",", "]") }"
+ if (null != columns) {
+ operationNotAllowed(errorMessage, columns)
+ } else {
+ throw new UnsupportedOperationException(errorMessage)
Review comment:
in what case `columns` is null?
----------------------------------------------------------------
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:
[hidden email]
With regards,
Apache Git Services