[SPARK-16839][SQL] Simplify Struct creation code path

R/pkg/inst/tests/testthat/test_sparkSQL.R

@@ -1222,16 +1222,16 @@ test_that("column functions", {
   # Test struct()
   df <- createDataFrame(list(list(1L, 2L, 3L), list(4L, 5L, 6L)),
                         schema = c("a", "b", "c"))
-  result <- collect(select(df, struct("a", "c")))
+  result <- collect(select(df, alias(struct("a", "c"), "d")))
   expected <- data.frame(row.names = 1:2)
-  expected$"struct(a, c)" <- list(listToStruct(list(a = 1L, c = 3L)),
-                                 listToStruct(list(a = 4L, c = 6L)))
+  expected$"d" <- list(listToStruct(list(a = 1L, c = 3L)),
+                      listToStruct(list(a = 4L, c = 6L)))
   expect_equal(result, expected)
 
-  result <- collect(select(df, struct(df$a, df$b)))
+  result <- collect(select(df, alias(struct(df$a, df$b), "d")))
   expected <- data.frame(row.names = 1:2)
-  expected$"struct(a, b)" <- list(listToStruct(list(a = 1L, b = 2L)),
-                                 listToStruct(list(a = 4L, b = 5L)))
+  expected$"d" <- list(listToStruct(list(a = 1L, b = 2L)),
+                      listToStruct(list(a = 4L, b = 5L)))
   expect_equal(result, expected)
 
   # Test encode(), decode()

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

@@ -31,7 +31,7 @@ import org.apache.spark.sql.catalyst.optimizer.BooleanSimplification
 import org.apache.spark.sql.catalyst.plans._
 import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, _}
 import org.apache.spark.sql.catalyst.rules._
-import org.apache.spark.sql.catalyst.trees.{TreeNodeRef}
+import org.apache.spark.sql.catalyst.trees.TreeNodeRef
 import org.apache.spark.sql.catalyst.util.toPrettySQL
 import org.apache.spark.sql.types._
 
@@ -83,6 +83,7 @@ class Analyzer(
       ResolveTableValuedFunctions ::
       ResolveRelations ::
       ResolveReferences ::
+      ResolveCreateNamedStruct ::
       ResolveDeserializer ::
       ResolveNewInstance ::
       ResolveUpCast ::
@@ -653,11 +654,12 @@ class Analyzer(
             case s: Star => s.expand(child, resolver)
             case o => o :: Nil
           })
-        case c: CreateStruct if containsStar(c.children) =>
-          c.copy(children = c.children.flatMap {
-            case s: Star => s.expand(child, resolver)
-            case o => o :: Nil
-          })
+        case c: CreateNamedStruct if containsStar(c.valExprs) =>
+          val newChildren = c.children.grouped(2).flatMap {
+            case Seq(k, s : Star) => CreateStruct(s.expand(child, resolver)).children
+            case kv => kv
+          }
+          c.copy(children = newChildren.toList )
         case c: CreateArray if containsStar(c.children) =>
           c.copy(children = c.children.flatMap {
             case s: Star => s.expand(child, resolver)
@@ -1141,7 +1143,7 @@ class Analyzer(
         case In(e, Seq(l @ ListQuery(_, exprId))) if e.resolved =>
           // Get the left hand side expressions.
           val expressions = e match {
-            case CreateStruct(exprs) => exprs
+            case cns : CreateNamedStruct => cns.valExprs
             case expr => Seq(expr)
           }
           resolveSubQuery(l, plans, expressions.size) { (rewrite, conditions) =>
@@ -2072,18 +2074,8 @@ object EliminateUnions extends Rule[LogicalPlan] {
  */
 object CleanupAliases extends Rule[LogicalPlan] {
   private def trimAliases(e: Expression): Expression = {
-    var stop = false
     e.transformDown {
-      // CreateStruct is a special case, we need to retain its top level Aliases as they decide the
-      // name of StructField. We also need to stop transform down this expression, or the Aliases
-      // under CreateStruct will be mistakenly trimmed.
-      case c: CreateStruct if !stop =>
-        stop = true
-        c.copy(children = c.children.map(trimNonTopLevelAliases))
-      case c: CreateStructUnsafe if !stop =>
-        stop = true
-        c.copy(children = c.children.map(trimNonTopLevelAliases))
-      case Alias(child, _) if !stop => child
+      case Alias(child, _) => child
     }
   }
 
@@ -2116,15 +2108,8 @@ object CleanupAliases extends Rule[LogicalPlan] {
     case a: AppendColumns => a
 
     case other =>
-      var stop = false
       other transformExpressionsDown {
-        case c: CreateStruct if !stop =>
-          stop = true
-          c.copy(children = c.children.map(trimNonTopLevelAliases))
-        case c: CreateStructUnsafe if !stop =>
-          stop = true
-          c.copy(children = c.children.map(trimNonTopLevelAliases))
-        case Alias(child, _) if !stop => child
+        case Alias(child, _) => child
       }
   }
 }
@@ -2217,3 +2202,19 @@ object TimeWindowing extends Rule[LogicalPlan] {
       }
   }
 }
+
+/**
+ * Resolve a [[CreateNamedStruct]] if it contains [[NamePlaceholder]]s.
+ */
+object ResolveCreateNamedStruct extends Rule[LogicalPlan] {
+  override def apply(plan: LogicalPlan): LogicalPlan = plan.transformAllExpressions {
+    case e: CreateNamedStruct if !e.resolved =>
+      val children = e.children.grouped(2).flatMap {
+        case Seq(NamePlaceholder, e: NamedExpression) if e.resolved =>
+          Seq(Literal(e.name), e)
+        case kv =>
+          kv
+      }
+      CreateNamedStruct(children.toList)
+  }
+}

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

@@ -357,7 +357,7 @@ object FunctionRegistry {
     expression[MapValues]("map_values"),
     expression[Size]("size"),
     expression[SortArray]("sort_array"),
-    expression[CreateStruct]("struct"),
+    CreateStruct.registryEntry,
 
     // misc functions
     expression[AssertTrue]("assert_true"),

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

@@ -119,7 +119,6 @@ object UnsafeProjection {
    */
   def create(exprs: Seq[Expression]): UnsafeProjection = {
     val unsafeExprs = exprs.map(_ transform {
-      case CreateStruct(children) => CreateStructUnsafe(children)
       case CreateNamedStruct(children) => CreateNamedStructUnsafe(children)
     })
     GenerateUnsafeProjection.generate(unsafeExprs)
@@ -145,7 +144,6 @@ object UnsafeProjection {
       subexpressionEliminationEnabled: Boolean): UnsafeProjection = {
     val e = exprs.map(BindReferences.bindReference(_, inputSchema))
       .map(_ transform {
-        case CreateStruct(children) => CreateStructUnsafe(children)
         case CreateNamedStruct(children) => CreateNamedStructUnsafe(children)
     })
     GenerateUnsafeProjection.generate(e, subexpressionEliminationEnabled)