fix.

apache · Mar 29, 2017 · 8ec57f3 · 8ec57f3
1 parent 1775ca7
commit 8ec57f3
Show file tree

Hide file tree

Showing 2 changed files with 66 additions and 0 deletions.
diff --git a/.../scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala b/.../scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala
@@ -105,12 +105,23 @@ case class FilterEstimation(plan: Filter, catalystConf: CatalystConf) extends Lo
         val percent2 = calculateFilterSelectivity(cond2, update = false).getOrElse(1.0)
         Some(percent1 + percent2 - (percent1 * percent2))
 
+      // Not-operator pushdown
       case Not(And(cond1, cond2)) =>
         calculateFilterSelectivity(Or(Not(cond1), Not(cond2)), update = false)
 
+      // Not-operator pushdown
       case Not(Or(cond1, cond2)) =>
         calculateFilterSelectivity(And(Not(cond1), Not(cond2)), update = false)
 
+      // Collapse two consecutive Not operators which could be generated after Not-operator pushdown
+      case Not(Not(cond)) =>
+        calculateFilterSelectivity(cond, update = false)
+
+      // The foldable Not has been processed in the ConstantFolding rule
+      // This is a top-down traversal. The Not could be pushed down by the above two cases.
+      case Not(l @ Literal(null, _)) =>
+        calculateSingleCondition(l, update = false)
+
       case Not(cond) =>
         calculateFilterSelectivity(cond, update = false) match {
           case Some(percent) => Some(1.0 - percent)

diff --git a/.../src/test/scala/org/apache/spark/sql/catalyst/statsEstimation/FilterEstimationSuite.scala b/.../src/test/scala/org/apache/spark/sql/catalyst/statsEstimation/FilterEstimationSuite.scala
@@ -98,6 +98,61 @@ class FilterEstimationSuite extends StatsEstimationTestBase {
       expectedRowCount = 0)
   }
 
+  test("Not(null)") {
+    validateEstimatedStats(
+      Filter(Not(Literal(null, IntegerType)), childStatsTestPlan(Seq(attrInt), 10L)),
+      Nil,
+      expectedRowCount = 0)
+  }
+
+  test("Not(Not(null))") {
+    validateEstimatedStats(
+      Filter(Not(Not(Literal(null, IntegerType))), childStatsTestPlan(Seq(attrInt), 10L)),
+      Nil,
+      expectedRowCount = 0)
+  }
+
+  test("cint < 3 AND null") {
+    val condition = And(LessThan(attrInt, Literal(3)), Literal(null, IntegerType))
+    validateEstimatedStats(
+      Filter(condition, childStatsTestPlan(Seq(attrInt), 10L)),
+      Nil,
+      expectedRowCount = 0)
+  }
+
+  test("cint < 3 OR null") {
+    val condition = Or(LessThan(attrInt, Literal(3)), Literal(null, IntegerType))
+    val m = Filter(condition, childStatsTestPlan(Seq(attrInt), 10L)).stats(conf)
+    validateEstimatedStats(
+      Filter(condition, childStatsTestPlan(Seq(attrInt), 10L)),
+      Seq(attrInt -> colStatInt),
+      expectedRowCount = 3)
+  }
+
+  test("Not(cint < 3 AND null)") {
+    val condition = Not(And(LessThan(attrInt, Literal(3)), Literal(null, IntegerType)))
+    validateEstimatedStats(
+      Filter(condition, childStatsTestPlan(Seq(attrInt), 10L)),
+      Seq(attrInt -> colStatInt),
+      expectedRowCount = 8)
+  }
+
+  test("Not(cint < 3 OR null)") {
+    val condition = Not(Or(LessThan(attrInt, Literal(3)), Literal(null, IntegerType)))
+    validateEstimatedStats(
+      Filter(condition, childStatsTestPlan(Seq(attrInt), 10L)),
+      Nil,
+      expectedRowCount = 0)
+  }
+
+  test("Not(cint < 3 AND Not(null))") {
+    val condition = Not(And(LessThan(attrInt, Literal(3)), Not(Literal(null, IntegerType))))
+    validateEstimatedStats(
+      Filter(condition, childStatsTestPlan(Seq(attrInt), 10L)),
+      Seq(attrInt -> colStatInt),
+      expectedRowCount = 8)
+  }
+
   test("cint = 2") {
     validateEstimatedStats(
       Filter(EqualTo(attrInt, Literal(2)), childStatsTestPlan(Seq(attrInt), 10L)),