[SPARK-19451][SQL] rangeBetween method should accept Long value as bo…

…undary

## What changes were proposed in this pull request?

Long values can be passed to `rangeBetween` as range frame boundaries, but we silently convert it to Int values, this can cause wrong results and we should fix this.

Further more, we should accept any legal literal values as range frame boundaries. In this PR, we make it possible for Long values, and make accepting other DataTypes really easy to add.

This PR is mostly based on Herman's previous amazing work: hvanhovell@596f53c

After this been merged, we can close apache#16818 .

## How was this patch tested?

Add new tests in `DataFrameWindowFunctionsSuite` and `TypeCoercionSuite`.

Author: Xingbo Jiang <xingbo.jiang@databricks.com>

Closes apache#18540 from jiangxb1987/rangeFrame.

(cherry picked from commit 92d8563)
Signed-off-by: gatorsmile <gatorsmile@gmail.com>

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala

@@ -106,11 +106,9 @@ trait CheckAnalysis extends PredicateHelper {
           case w @ WindowExpression(AggregateExpression(_, _, true, _), _) =>
             failAnalysis(s"Distinct window functions are not supported: $w")
 
-          case w @ WindowExpression(_: OffsetWindowFunction, WindowSpecDefinition(_, order,
-               SpecifiedWindowFrame(frame,
-                 FrameBoundary(l),
-                 FrameBoundary(h))))
-             if order.isEmpty || frame != RowFrame || l != h =>
+          case w @ WindowExpression(_: OffsetWindowFunction,
+            WindowSpecDefinition(_, order, frame: SpecifiedWindowFrame))
+             if order.isEmpty || !frame.isOffset =>
             failAnalysis("An offset window function can only be evaluated in an ordered " +
               s"row-based window frame with a single offset: $w")
 
@@ -119,15 +117,10 @@ trait CheckAnalysis extends PredicateHelper {
             // function.
             e match {
               case _: AggregateExpression | _: OffsetWindowFunction | _: AggregateWindowFunction =>
+                w
               case _ =>
                 failAnalysis(s"Expression '$e' not supported within a window function.")
             }
-            // Make sure the window specification is valid.
-            s.validate match {
-              case Some(m) =>
-                failAnalysis(s"Window specification $s is not valid because $m")
-              case None => w
-            }
 
           case s @ ScalarSubquery(query, conditions, _) =>
             checkAnalysis(query)

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala

@@ -58,6 +58,7 @@ object TypeCoercion {
       PropagateTypes ::
       ImplicitTypeCasts ::
       DateTimeOperations ::
+      WindowFrameCoercion ::
       Nil
 
   // See https://cwiki.apache.org/confluence/display/Hive/LanguageManual+Types.
@@ -785,4 +786,26 @@ object TypeCoercion {
       Option(ret)
     }
   }
+
+  /**
+   * Cast WindowFrame boundaries to the type they operate upon.
+   */
+  object WindowFrameCoercion extends Rule[LogicalPlan] {
+    def apply(plan: LogicalPlan): LogicalPlan = plan resolveExpressions {
+      case s @ WindowSpecDefinition(_, Seq(order), SpecifiedWindowFrame(RangeFrame, lower, upper))
+          if order.resolved =>
+        s.copy(frameSpecification = SpecifiedWindowFrame(
+          RangeFrame,
+          createBoundaryCast(lower, order.dataType),
+          createBoundaryCast(upper, order.dataType)))
+    }
+
+    private def createBoundaryCast(boundary: Expression, dt: DataType): Expression = {
+      boundary match {
+        case e: SpecialFrameBoundary => e
+        case e: Expression if e.dataType != dt && Cast.canCast(e.dataType, dt) => Cast(e, dt)
+        case _ => boundary
+      }
+    }
+  }
 }

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

@@ -74,6 +74,13 @@ package object expressions  {
     def initialize(partitionIndex: Int): Unit = {}
   }
 
+  /**
+   * An identity projection. This returns the input row.
+   */
+  object IdentityProjection extends Projection {
+    override def apply(row: InternalRow): InternalRow = row
+  }
+
   /**
    * Converts a [[InternalRow]] to another Row given a sequence of expression that define each
    * column of the new row. If the schema of the input row is specified, then the given expression