HyukjinKwon commented on a change in pull request #29812:
URL: https://github.com/apache/spark/pull/29812#discussion_r508195964



##########
File path: 
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/UpdateFields.scala
##########
@@ -17,19 +17,68 @@
 
 package org.apache.spark.sql.catalyst.optimizer
 
-import org.apache.spark.sql.catalyst.expressions.UpdateFields
+import java.util.Locale
+
+import scala.collection.mutable
+
+import org.apache.spark.sql.catalyst.expressions.{Expression, UpdateFields, 
WithField}
 import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.internal.SQLConf
 
 
 /**
- * Combines all adjacent [[UpdateFields]] expression into a single 
[[UpdateFields]] expression.
+ * Optimizes [[UpdateFields]] expression chains.
  */
-object CombineUpdateFields extends Rule[LogicalPlan] {
-  def apply(plan: LogicalPlan): LogicalPlan = plan transformAllExpressions {
+object OptimizeUpdateFields extends Rule[LogicalPlan] {
+  private def canOptimize(names: Seq[String]): Boolean = {
+    if (SQLConf.get.caseSensitiveAnalysis) {
+      names.distinct.length != names.length
+    } else {
+      names.map(_.toLowerCase(Locale.ROOT)).distinct.length != names.length
+    }
+  }
+
+  val optimizeUpdateFields: PartialFunction[Expression, Expression] = {
+    case UpdateFields(structExpr, fieldOps)
+      if fieldOps.forall(_.isInstanceOf[WithField]) &&
+        canOptimize(fieldOps.map(_.asInstanceOf[WithField].name)) =>
+      val caseSensitive = SQLConf.get.caseSensitiveAnalysis
+
+      val withFields = fieldOps.map(_.asInstanceOf[WithField])
+      val names = withFields.map(_.name)
+      val values = withFields.map(_.valExpr)
+
+      val newNames = mutable.ArrayBuffer.empty[String]
+      val newValues = mutable.ArrayBuffer.empty[Expression]
+
+      if (caseSensitive) {
+        names.zip(values).reverse.foreach { case (name, value) =>

Review comment:
       I wonder if we could just do like: 
`collection.immutable.ListMap(names.zip(values): _*)` which will keep the last 
win here and keep the order of fields to use later. But I guess it's no big 
deal. Just saying.




----------------------------------------------------------------
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]

Reply via email to