[SPARK-23940][SQL] Add transform_values SQL function

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

@@ -446,6 +446,7 @@ object FunctionRegistry {
     expression[ArrayFilter]("filter"),
     expression[ArrayExists]("exists"),
     expression[ArrayAggregate]("aggregate"),
+    expression[TransformValues]("transform_values"),
     expression[MapZipWith]("map_zip_with"),
     CreateStruct.registryEntry,
 

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

@@ -497,6 +497,60 @@ case class ArrayAggregate(
   override def prettyName: String = "aggregate"
 }
 
+/**
+ * Returns a map that applies the function to each value of the map.
+ */
+@ExpressionDescription(
+usage = "_FUNC_(expr, func) - Transforms values in the map using the function.",
+examples = """
+    Examples:
+       > SELECT _FUNC_(map(array(1, 2, 3), array(1, 2, 3), (k, v) -> v + 1);
+        map(array(1, 2, 3), array(2, 3, 4))
+       > SELECT _FUNC_(map(array(1, 2, 3), array(1, 2, 3), (k, v) -> k + v);
+        map(array(1, 2, 3), array(2, 4, 6))
+  """,
+since = "2.4.0")
+case class TransformValues(
+    argument: Expression,
+    function: Expression)
+  extends MapBasedSimpleHigherOrderFunction with CodegenFallback {
+
+  override def nullable: Boolean = argument.nullable
+
+  override def dataType: DataType = {
+    val map = argument.dataType.asInstanceOf[MapType]
+    MapType(map.keyType, function.dataType, function.nullable)
+  }
+
+  @transient val MapType(keyType, valueType, valueContainsNull) = argument.dataType
+
+  override def bind(f: (Expression, Seq[(DataType, Boolean)]) => LambdaFunction)
+  : TransformValues = {
+    copy(function = f(function, (keyType, false) :: (valueType, valueContainsNull) :: Nil))
+  }
+
+  @transient lazy val (keyVar, valueVar) = {
+    val LambdaFunction(
+    _, (keyVar: NamedLambdaVariable) :: (valueVar: NamedLambdaVariable) :: Nil, _) = function
+    (keyVar, valueVar)
+  }
+
+  override def nullSafeEval(inputRow: InternalRow, argumentValue: Any): Any = {
+    val map = argumentValue.asInstanceOf[MapData]
+    val f = functionForEval
+    val resultValues = new GenericArrayData(new Array[Any](map.numElements))
+    var i = 0
+    while (i < map.numElements) {
+      keyVar.value.set(map.keyArray().get(i, keyVar.dataType))
+      valueVar.value.set(map.valueArray().get(i, valueVar.dataType))
+      resultValues.update(i, f.eval(inputRow))
+      i += 1
+    }
+    new ArrayBasedMapData(map.keyArray(), resultValues)
+  }
+  override def prettyName: String = "transform_values"
+}
+
 /**
  * Merges two given maps into a single map by applying function to the pair of values with
  * the same key.

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/HigherOrderFunctionsSuite.scala

@@ -95,6 +95,12 @@ class HigherOrderFunctionsSuite extends SparkFunSuite with ExpressionEvalHelper
     aggregate(expr, zero, merge, identity)
   }
 
+  def transformValues(expr: Expression, f: (Expression, Expression) => Expression): Expression = {
+    val valueType = expr.dataType.asInstanceOf[MapType].valueType
+    val keyType = expr.dataType.asInstanceOf[MapType].keyType
+    TransformValues(expr, createLambda(keyType, false, valueType, true, f))
+  }
+
   test("ArrayTransform") {
     val ai0 = Literal.create(Seq(1, 2, 3), ArrayType(IntegerType, containsNull = false))
     val ai1 = Literal.create(Seq[Integer](1, null, 3), ArrayType(IntegerType, containsNull = true))
@@ -283,6 +289,61 @@ class HigherOrderFunctionsSuite extends SparkFunSuite with ExpressionEvalHelper
       15)
   }
 
+  test("TransformValues") {
+    val ai0 = Literal.create(
+      Map(1 -> 1, 2 -> 2, 3 -> 3),
+      MapType(IntegerType, IntegerType))
+    val ai1 = Literal.create(
+      Map(1 -> 1, 2 -> null, 3 -> 3),
+      MapType(IntegerType, IntegerType))
+    val ain = Literal.create(
+      Map.empty[Int, Int],
+      MapType(IntegerType, IntegerType))
+
+    val plusOne: (Expression, Expression) => Expression = (k, v) => v + 1
+    val valueUpdate: (Expression, Expression) => Expression = (k, v) => k * k
+
+    checkEvaluation(transformValues(ai0, plusOne), Map(1 -> 2, 2 -> 3, 3 -> 4))
+    checkEvaluation(transformValues(ai0, valueUpdate), Map(1 -> 1, 2 -> 4, 3 -> 9))
+    checkEvaluation(
+      transformValues(transformValues(ai0, plusOne), valueUpdate), Map(1 -> 1, 2 -> 4, 3 -> 9))
+    checkEvaluation(transformValues(ai1, plusOne), Map(1 -> 2, 2 -> null, 3 -> 4))
+    checkEvaluation(transformValues(ai1, valueUpdate), Map(1 -> 1, 2 -> 4, 3 -> 9))
+    checkEvaluation(
+      transformValues(transformValues(ai1, plusOne), valueUpdate), Map(1 -> 1, 2 -> 4, 3 -> 9))
+    checkEvaluation(transformValues(ain, plusOne), Map.empty[Int, Int])
+
+    val as0 = Literal.create(
+      Map("a" -> "xy", "bb" -> "yz", "ccc" -> "zx"), MapType(StringType, StringType))
+    val as1 = Literal.create(
+      Map("a" -> "xy", "bb" -> null, "ccc" -> "zx"), MapType(StringType, StringType))
+    val asn = Literal.create(Map.empty[StringType, StringType], MapType(StringType, StringType))
+
+    val concatValue: (Expression, Expression) => Expression = (k, v) => Concat(Seq(k, v))
+    val valueTypeUpdate: (Expression, Expression) => Expression =
+      (k, v) => Length(v) + 1
+
+    checkEvaluation(
+      transformValues(as0, concatValue), Map("a" -> "axy", "bb" -> "bbyz", "ccc" -> "ccczx"))
+    checkEvaluation(transformValues(as0, valueTypeUpdate),
+      Map("a" -> 3, "bb" -> 3, "ccc" -> 3))
+    checkEvaluation(
+      transformValues(transformValues(as0, concatValue), concatValue),
+      Map("a" -> "aaxy", "bb" -> "bbbbyz", "ccc" -> "cccccczx"))
+    checkEvaluation(transformValues(as1, concatValue),
+      Map("a" -> "axy", "bb" -> null, "ccc" -> "ccczx"))
+    checkEvaluation(transformValues(as1, valueTypeUpdate),
+      Map("a" -> 3, "bb" -> null, "ccc" -> 3))
+    checkEvaluation(
+      transformValues(transformValues(as1, concatValue), concatValue),
+      Map("a" -> "aaxy", "bb" -> null, "ccc" -> "cccccczx"))
+    checkEvaluation(transformValues(asn, concatValue), Map.empty[String, String])
+    checkEvaluation(transformValues(asn, valueTypeUpdate), Map.empty[String, Int])
+    checkEvaluation(
+      transformValues(transformValues(asn, concatValue), valueTypeUpdate),
+      Map.empty[String, Int])
+    }
+
   test("MapZipWith") {
     def map_zip_with(
         left: Expression,

sql/core/src/test/resources/sql-tests/inputs/higher-order-functions.sql

@@ -51,3 +51,17 @@ select exists(ys, y -> y > 30) as v from nested;
 
 -- Check for element existence in a null array
 select exists(cast(null as array<int>), y -> y > 30) as v;
+
+create or replace temporary view nested as values
+  (1, map(1,1,2,2,3,3)),
+  (2, map(4,4,5,5,6,6))
+  as t(x, ys);
+
+-- Identity Transform Keys in a map
+select transform_values(ys, (k, v) -> v) as v from nested;
+
+-- Transform Keys in a map by adding constant
+select transform_values(ys, (k, v) -> v + 1) as v from nested;
+
+-- Transform Keys in a map using values
+select transform_values(ys, (k, v) -> k + v) as v from nested;

sql/core/src/test/resources/sql-tests/results/higher-order-functions.sql.out

@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 15
+-- Number of queries: 20
 
 
 -- !query 0
@@ -163,3 +163,40 @@ select exists(cast(null as array<int>), y -> y > 30) as v
 struct<v:boolean>
 -- !query 16 output
 NULL
+
+
+-- !query 17
+create or replace temporary view nested as values
+  (1, map(1,1,2,2,3,3)),
+  (2, map(4,4,5,5,6,6))
+  as t(x, ys)
+-- !query 17 schema
+struct<>
+-- !query 17 output
+
+
+-- !query 18
+select transform_values(ys, (k, v) -> v) as v from nested
+-- !query 18 schema
+struct<v:map<int,int>>
+-- !query 18 output
+{1:1,2:2,3:3}
+{4:4,5:5,6:6}
+
+
+-- !query 19
+select transform_values(ys, (k, v) -> v + 1) as v from nested
+-- !query 19 schema
+struct<v:map<int,int>>
+-- !query 19 output
+{1:2,2:3,3:4}
+{4:5,5:6,6:7}
+
+
+-- !query 20
+select transform_values(ys, (k, v) -> k + v) as v from nested
+-- !query 20 schema
+struct<v:map<int,int>>
+-- !query 20 output
+{1:2,2:4,3:6}
+{4:8,5:10,6:12}