Simplify conditional in predicate

Author: wangyum

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala

@@ -103,6 +103,7 @@ abstract class Optimizer(catalogManager: CatalogManager)
         RemoveDispensableExpressions,
         SimplifyBinaryComparison,
         ReplaceNullWithFalseInPredicate,
+        SimplifyConditionalInPredicate,
         PruneFilters,
         SimplifyCasts,
         SimplifyCaseConversionExpressions,

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala

@@ -30,6 +30,7 @@ import org.apache.spark.sql.catalyst.plans.logical._
 import org.apache.spark.sql.catalyst.rules._
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.types._
+import org.apache.spark.util.Utils
 
 /*
  * Optimization rules defined in this file should not affect the structure of the logical plan.
@@ -570,6 +571,33 @@ object PushFoldableIntoBranches extends Rule[LogicalPlan] with PredicateHelper {
 }
 
 
+object SimplifyConditionalInPredicate extends Rule[LogicalPlan] {
+  def apply(plan: LogicalPlan): LogicalPlan = plan transform {
+    case f @ Filter(cond, _) => f.copy(condition = simplifyConditional(cond))
+  }
+
+  private def simplifyConditional(e: Expression): Expression = e match {
+    case cw @ CaseWhen(branches, elseValue) if cw.dataType == BooleanType && branches.size == 1 &&
+        elseValue.forall(_.semanticEquals(FalseLiteral)) =>
+      val (whenVal, thenVal) = branches.head
+      And(whenVal, thenVal)
+    case i @ If(pred, trueVal, FalseLiteral) if i.dataType == BooleanType =>
+      And(pred, trueVal)
+    case e if e.dataType == BooleanType =>
+      e
+    case e =>
+      val message = "Expected a Boolean type expression in simplifyConditional, " +
+        s"but got the type `${e.dataType.catalogString}` in `${e.sql}`."
+      if (Utils.isTesting) {
+        throw new IllegalArgumentException(message)
+      } else {
+        logWarning(message)
+        e
+      }
+  }
+}
+
+
 /**
  * Simplifies LIKE expressions that do not need full regular expressions to evaluate the condition.
  * For example, when the expression is just checking to see if a string starts with a given