From f892d927d7246856dd3ea617b2942873359454bc Mon Sep 17 00:00:00 2001
From: Yash Datta <Yash.Datta@guavus.com>
Date: Thu, 10 Sep 2015 10:34:00 -0700
Subject: [PATCH] [SPARK-7142] [SQL] Minor enhancement to BooleanSimplification
 Optimizer rule

Use these in the optimizer as well:

            A and (not(A) or B) => A and B
            not(A and B) => not(A) or not(B)
            not(A or B) => not(A) and not(B)

Author: Yash Datta <Yash.Datta@guavus.com>

Closes #5700 from saucam/bool_simp.
---
 .../spark/sql/catalyst/optimizer/Optimizer.scala |  9 +++++++++
 .../optimizer/BooleanSimplificationSuite.scala   | 16 ++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
index a430000bef..d9b50f3c97 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
@@ -434,6 +434,11 @@ object BooleanSimplification extends Rule[LogicalPlan] with PredicateHelper {
         case (_, Literal(false, BooleanType)) => Literal(false)
         // a && a  =>  a
         case (l, r) if l fastEquals r => l
+        // a && (not(a) || b) => a && b
+        case (l, Or(l1, r)) if (Not(l) fastEquals l1) => And(l, r)
+        case (l, Or(r, l1)) if (Not(l) fastEquals l1) => And(l, r)
+        case (Or(l, l1), r) if (l1 fastEquals Not(r)) => And(l, r)
+        case (Or(l1, l), r) if (l1 fastEquals Not(r)) => And(l, r)
         // (a || b) && (a || c)  =>  a || (b && c)
         case _ =>
           // 1. Split left and right to get the disjunctive predicates,
@@ -512,6 +517,10 @@ object BooleanSimplification extends Rule[LogicalPlan] with PredicateHelper {
         case LessThan(l, r) => GreaterThanOrEqual(l, r)
         // not(l <= r)  =>  l > r
         case LessThanOrEqual(l, r) => GreaterThan(l, r)
+        // not(l || r) => not(l) && not(r)
+        case Or(l, r) => And(Not(l), Not(r))
+        // not(l && r) => not(l) or not(r)
+        case And(l, r) => Or(Not(l), Not(r))
         // not(not(e))  =>  e
         case Not(e) => e
         case _ => not
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/BooleanSimplificationSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/BooleanSimplificationSuite.scala
index 1877cff133..cde346e99e 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/BooleanSimplificationSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/BooleanSimplificationSuite.scala
@@ -89,6 +89,22 @@ class BooleanSimplificationSuite extends PlanTest with PredicateHelper {
       ('a === 'b || 'b > 3 && 'a > 3 && 'a < 5))
   }
 
+  test("a && (!a || b)") {
+    checkCondition(('a && (!('a) || 'b )), ('a && 'b))
+
+    checkCondition(('a && ('b || !('a) )), ('a && 'b))
+
+    checkCondition(((!('a) || 'b ) && 'a), ('b && 'a))
+
+    checkCondition((('b || !('a) ) && 'a), ('b && 'a))
+  }
+
+  test("!(a && b) , !(a || b)") {
+    checkCondition((!('a && 'b)), (!('a) || !('b)))
+
+    checkCondition(!('a || 'b), (!('a) && !('b)))
+  }
+
   private val caseInsensitiveAnalyzer =
     new Analyzer(EmptyCatalog, EmptyFunctionRegistry, new SimpleCatalystConf(false))
 
-- 
GitLab