HyukjinKwon commented on a change in pull request #29942:
URL: https://github.com/apache/spark/pull/29942#discussion_r499497878
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala
##########
@@ -28,10 +28,43 @@ import org.apache.spark.sql.types.{ArrayType, StructType}
* The optimization includes:
* 1. JsonToStructs(StructsToJson(child)) => child.
* 2. Prune unnecessary columns from GetStructField/GetArrayStructFields +
JsonToStructs.
+ * 3. struct(from_json.col1, from_json.col2, from_json.col3...) =>
struct(from_json)
*/
object OptimizeJsonExprs extends Rule[LogicalPlan] {
override def apply(plan: LogicalPlan): LogicalPlan = plan transform {
case p => p.transformExpressions {
+
+ case c: CreateNamedStruct
+ // If we create struct from various fields of the same
`JsonToStructs`.
+ if c.valExprs.forall { v =>
+ v.isInstanceOf[GetStructField] &&
+ v.asInstanceOf[GetStructField].child.isInstanceOf[JsonToStructs]
&&
+ v.children.head.semanticEquals(c.valExprs.head.children.head)
+ } =>
+ val jsonToStructs = c.valExprs.map(_.children.head)
+ val sameFieldName = c.names.zip(c.valExprs).forall {
+ case (name, valExpr: GetStructField) =>
+ name.toString == valExpr.childSchema(valExpr.ordinal).name
+ case (_, _) => false
Review comment:
nit: `case (_, _) =>` -> `case _ =>`
----------------------------------------------------------------
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]
