[SPARK-5985][SQL] DataFrame sortBy -> orderBy in Python.

Also added desc/asc function for constructing sorting expressions more conveniently. And added a small fix to lift alias out of cast expression.

Author: Reynold Xin <rxin@databricks.com>

Closes #4752 from rxin/SPARK-5985 and squashes the following commits:

aeda5ae [Reynold Xin] Added Experimental flag to ColumnName.
047ad03 [Reynold Xin] Lift alias out of cast.
c9cf17c [Reynold Xin] [SPARK-5985][SQL] DataFrame sortBy -> orderBy in Python.

4 files changed, 48 insertions, 2 deletions

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
index 980754322e..a2cc9a9b93 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/Column.scala
@@ -600,7 +600,11 @@ class Column(protected[sql] val expr: Expression) {
    *
    * @group expr_ops
    */
-  def cast(to: DataType): Column = Cast(expr, to)
+  def cast(to: DataType): Column = expr match {
+    // Lift alias out of cast so we can support col.as("name").cast(IntegerType)
+    case Alias(childExpr, name) => Alias(Cast(childExpr, to), name)()
+    case _ => Cast(expr, to)
+  }
 
   /**
    * Casts the column to a different data type, using the canonical string representation
@@ -613,7 +617,7 @@ class Column(protected[sql] val expr: Expression) {
    *
    * @group expr_ops
    */
-  def cast(to: String): Column = Cast(expr, to.toLowerCase match {
+  def cast(to: String): Column = cast(to.toLowerCase match {
     case "string" | "str" => StringType
     case "boolean" => BooleanType
     case "byte" => ByteType
@@ -671,6 +675,11 @@ class Column(protected[sql] val expr: Expression) {
 }
 
 
+/**
+ * :: Experimental ::
+ * A convenient class used for constructing schema.
+ */
+@Experimental
 class ColumnName(name: String) extends Column(name) {
 
   /** Creates a new AttributeReference of type boolean */
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index 2a1e086891..4fdbfc6d22 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -33,6 +33,7 @@ import org.apache.spark.sql.types._
  *
  * @groupname udf_funcs UDF functions
  * @groupname agg_funcs Aggregate functions
+ * @groupname sort_funcs Sorting functions
  * @groupname normal_funcs Non-aggregate functions
  * @groupname Ungrouped Support functions for DataFrames.
  */
@@ -96,6 +97,33 @@ object functions {
   }
 
   //////////////////////////////////////////////////////////////////////////////////////////////
+  // Sort functions
+  //////////////////////////////////////////////////////////////////////////////////////////////
+
+  /**
+   * Returns a sort expression based on ascending order of the column.
+   * {{
+   *   // Sort by dept in ascending order, and then age in descending order.
+   *   df.sort(asc("dept"), desc("age"))
+   * }}
+   *
+   * @group sort_funcs
+   */
+  def asc(columnName: String): Column = Column(columnName).asc
+
+  /**
+   * Returns a sort expression based on the descending order of the column.
+   * {{
+   *   // Sort by dept in ascending order, and then age in descending order.
+   *   df.sort(asc("dept"), desc("age"))
+   * }}
+   *
+   * @group sort_funcs
+   */
+  def desc(columnName: String): Column = Column(columnName).desc
+
+  //////////////////////////////////////////////////////////////////////////////////////////////
+  // Aggregate functions
   //////////////////////////////////////////////////////////////////////////////////////////////
 
   /**
@@ -263,6 +291,7 @@ object functions {
   def max(columnName: String): Column = max(Column(columnName))
 
   //////////////////////////////////////////////////////////////////////////////////////////////
+  // Non-aggregate functions
   //////////////////////////////////////////////////////////////////////////////////////////////
 
   /**
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/ColumnExpressionSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/ColumnExpressionSuite.scala
index 928b0deb61..37c02aaa54 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/ColumnExpressionSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/ColumnExpressionSuite.scala
@@ -309,4 +309,8 @@ class ColumnExpressionSuite extends QueryTest {
       (1 to 100).map(n => Row(null))
     )
   }
+
+  test("lift alias out of cast") {
+    assert(col("1234").as("name").cast("int").expr === col("1234").cast("int").as("name").expr)
+  }
 }
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
index 30e77e4ef3..c392a553c0 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameSuite.scala
@@ -240,6 +240,10 @@ class DataFrameSuite extends QueryTest {
       Seq(Row(1,1), Row(1,2), Row(2,1), Row(2,2), Row(3,1), Row(3,2)))
 
     checkAnswer(
+      testData2.orderBy(asc("a"), desc("b")),
+      Seq(Row(1,2), Row(1,1), Row(2,2), Row(2,1), Row(3,2), Row(3,1)))
+
+    checkAnswer(
       testData2.orderBy('a.asc, 'b.desc),
       Seq(Row(1,2), Row(1,1), Row(2,2), Row(2,1), Row(3,2), Row(3,1)))