[SPARK-37518] inject a early scan push down rule

Author: beliefer

sql/core/src/main/scala/org/apache/spark/sql/SparkSessionExtensions.scala

@@ -226,6 +226,21 @@ class SparkSessionExtensions {
     preCBORules += builder
   }
 
+  private[this] val earlyScanPushDownRules = mutable.Buffer.empty[RuleBuilder]
+
+  private[sql] def buildEarlyScanPushDownRules(session: SparkSession): Seq[Rule[LogicalPlan]] = {
+    earlyScanPushDownRules.map(_.apply(session)).toSeq
+  }
+
+  /**
+   * Inject an optimizer `Rule` builder that rewrites logical plans into the [[SparkSession]].
+   * The injected rules will be executed once after the operator optimization batch and
+   * after any push down optimization rules.
+   */
+  def injectEarlyScanPushDownRules(builder: RuleBuilder): Unit = {
+    earlyScanPushDownRules += builder
+  }
+
   private[this] val plannerStrategyBuilders = mutable.Buffer.empty[StrategyBuilder]
 
   private[sql] def buildPlannerStrategies(session: SparkSession): Seq[Strategy] = {

sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala

@@ -270,7 +270,9 @@ abstract class BaseSessionStateBuilder(
    *
    * Note that this may NOT depend on the `optimizer` function.
    */
-  protected def customEarlyScanPushDownRules: Seq[Rule[LogicalPlan]] = Nil
+  protected def customEarlyScanPushDownRules: Seq[Rule[LogicalPlan]] = {
+    extensions.buildEarlyScanPushDownRules(session)
+  }
 
   /**
    * Custom rules for rewriting plans after operator optimization and before CBO.

sql/core/src/test/scala/org/apache/spark/sql/SparkSessionExtensionSuite.scala

@@ -95,6 +95,12 @@ class SparkSessionExtensionSuite extends SparkFunSuite {
     }
   }
 
+  test("SPARK-37518: inject a early scan push down rule") {
+    withSession(Seq(_.injectEarlyScanPushDownRules(MyRule))) { session =>
+      assert(session.sessionState.optimizer.earlyScanPushDownRules.contains(MyRule(session)))
+    }
+  }
+
   test("inject spark planner strategy") {
     withSession(Seq(_.injectPlannerStrategy(MySparkStrategy))) { session =>
       assert(session.sessionState.planner.strategies.contains(MySparkStrategy(session)))