[SPARK-16994][SQL] Whitelist operators for predicate push down

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

@@ -1208,17 +1208,27 @@ object PushDownPredicate extends Rule[LogicalPlan] with PredicateHelper {
         filter
       }
 
-    // two filters should be combine together by other rules
-    case filter @ Filter(_, _: Filter) => filter
-    // should not push predicates through sample, or will generate different results.
-    case filter @ Filter(_, _: Sample) => filter
-
-    case filter @ Filter(condition, u: UnaryNode) if u.expressions.forall(_.deterministic) =>
+    case filter @ Filter(condition, u: UnaryNode)
+        if canPushThrough(u) && u.expressions.forall(_.deterministic) =>
       pushDownPredicate(filter, u.child) { predicate =>
         u.withNewChildren(Seq(Filter(predicate, u.child)))
       }
   }
 
+  private def canPushThrough(p: UnaryNode): Boolean = p match {
+    case _: AppendColumns => true
+    case _: BroadcastHint => true
+    case _: Distinct => true
+    case _: Generate => true
+    case _: Pivot => true
+    case _: RedistributeData => true
+    case _: Repartition => true
+    case _: ScriptTransformation => true
+    case _: Sort => true
+    case _: With => true
+    case _ => false
+  }
+
   private def pushDownPredicate(
       filter: Filter,
       grandchild: LogicalPlan)(insertFilter: Expression => LogicalPlan): LogicalPlan = {

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala

@@ -111,6 +111,12 @@ class FilterPushdownSuite extends PlanTest {
     assert(optimized == correctAnswer)
   }
 
+  test("SPARK-16994: filter should not be pushed through limit") {
+    val originalQuery = testRelation.limit(10).where('a === 1).analyze
+    val optimized = Optimize.execute(originalQuery)
+    comparePlans(optimized, originalQuery)
+  }
+
   test("can't push without rewrite") {
     val originalQuery =
       testRelation

sql/core/src/test/resources/sql-tests/inputs/limit.sql

@@ -18,3 +18,6 @@ select * from testdata limit key > 3;
 -- limit must be integer
 select * from testdata limit true;
 select * from testdata limit 'a';
+
+-- limit within a subquery
+select * from (select * from range(10) limit 5) where id > 3;

sql/core/src/test/resources/sql-tests/results/limit.sql.out

@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 9
+-- Number of queries: 10
 
 
 -- !query 0
@@ -81,3 +81,11 @@ struct<>
 -- !query 8 output
 org.apache.spark.sql.AnalysisException
 The limit expression must be integer type, but got string;
+
+
+-- !query 9
+select * from (select * from range(10) limit 5) where id > 3
+-- !query 9 schema
+struct<id:bigint>
+-- !query 9 output
+4