zhengruifeng commented on code in PR #44177:
URL: https://github.com/apache/spark/pull/44177#discussion_r1414898203
##########
sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala:
##########
@@ -2922,18 +2922,29 @@ class Dataset[T] private[sql](
*/
@throws[AnalysisException]
def withColumnsRenamed(colsMap: Map[String, String]): DataFrame = withOrigin
{
+ val (colNames, newColNames) = colsMap.toSeq.unzip
+ withColumnsRenamed(colNames, newColNames)
+ }
+
+ private def withColumnsRenamed(
+ colNames: Seq[String],
+ newColNames: Seq[String]): DataFrame = withOrigin {
+ require(colNames.size == newColNames.size,
+ s"The size of existing column names: ${colNames.size} isn't equal to " +
+ s"the size of new column names: ${newColNames.size}")
+
val resolver = sparkSession.sessionState.analyzer.resolver
val output: Seq[NamedExpression] = queryExecution.analyzed.output
- val projectList = colsMap.foldLeft(output) {
+ val projectList = colNames.zip(newColNames).foldLeft(output) {
Review Comment:
this is a python issue.
to make sure the scala side is not changed, I add a scala test
--
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
