TJX2014 commented on a change in pull request #28745:
URL: https://github.com/apache/spark/pull/28745#discussion_r436361472
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/namedExpressions.scala
##########
@@ -23,14 +23,18 @@ import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute
import org.apache.spark.sql.catalyst.expressions.codegen._
import org.apache.spark.sql.catalyst.plans.logical.EventTimeWatermark
-import org.apache.spark.sql.catalyst.util.quoteIdentifier
+import org.apache.spark.sql.catalyst.util.{quoteIdentifier, toPrettySQL}
import org.apache.spark.sql.types._
object NamedExpression {
private val curId = new java.util.concurrent.atomic.AtomicLong()
private[expressions] val jvmId = UUID.randomUUID()
def newExprId: ExprId = ExprId(curId.getAndIncrement(), jvmId)
def unapply(expr: NamedExpression): Option[(String, DataType)] =
Some((expr.name, expr.dataType))
+ def fromExpression(expr: Expression): NamedExpression = expr match {
+ case ne: NamedExpression => ne
+ case _: Expression => Alias(expr, toPrettySQL(expr))()
+ }
Review comment:
I find `org.apache.spark.sql.Dataset#groupBy(cols: Column*)` is invoked
through py4j instead of `groupBy(col1: String, cols: String*)`, is it possible
to change param sent in python side only to invoke `groupBy(col1: String, cols:
String*)`, which may also be helpful to this jira :-)
----------------------------------------------------------------
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]
