Github user mgaido91 commented on a diff in the pull request:
https://github.com/apache/spark/pull/21045#discussion_r192993235
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -128,6 +128,174 @@ case class MapKeys(child: Expression)
override def prettyName: String = "map_keys"
}
+@ExpressionDescription(
+ usage = """_FUNC_(a1, a2, ...) - Returns a merged array containing in
the N-th position the
+ N-th value of each array given.""",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(1, 2, 3), array(2, 3, 4));
+ [[1, 2], [2, 3], [3, 4]]
+ > SELECT _FUNC_(array(1, 2), array(2, 3), array(3, 4));
+ [[1, 2, 3], [2, 3, 4]]
+ """,
+ since = "2.4.0")
+case class Zip(children: Seq[Expression]) extends Expression with
ExpectsInputTypes {
+
+ override def inputTypes: Seq[AbstractDataType] =
Seq.fill(children.length)(ArrayType)
+
+ override def dataType: DataType = ArrayType(mountSchema)
+
+ override def nullable: Boolean = children.exists(_.nullable)
+
+ private lazy val arrayTypes =
children.map(_.dataType.asInstanceOf[ArrayType])
+
+ private lazy val arrayElementTypes = arrayTypes.map(_.elementType)
+
+ def mountSchema: StructType = {
+ val fields = children.zip(arrayElementTypes).zipWithIndex.map {
+ case ((expr: NamedExpression, elementType), _) =>
+ StructField(expr.name, elementType, nullable = true)
+ case ((_, elementType), idx) =>
+ StructField(s"$idx", elementType, nullable = true)
+ }
+ StructType(fields)
+ }
+
+ val numberOfArrays: Int = children.length
+
+ def emptyInputGenCode(ev: ExprCode): ExprCode = {
+ val genericArrayData = classOf[GenericArrayData].getName
+
+ ev.copy(code"""
+ |${CodeGenerator.javaType(dataType)} ${ev.value} = new
$genericArrayData(new Object[0]);
+ |boolean ${ev.isNull} = false;
+ """.stripMargin)
+ }
+
+ def nonEmptyInputGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ val genericArrayData = classOf[GenericArrayData].getName
+ val genericInternalRow = classOf[GenericInternalRow].getName
+ val arrVals = ctx.freshName("arrVals")
+ val arrCardinality = ctx.freshName("arrCardinality")
+ val biggestCardinality = ctx.freshName("biggestCardinality")
+
+ val myobject = ctx.freshName("myobject")
+ val j = ctx.freshName("j")
+ val i = ctx.freshName("i")
+ val args = ctx.freshName("args")
+
+ val evals = children.map(_.genCode(ctx))
+ val getValuesAndCardinalities = evals.zipWithIndex.map { case (eval,
index) =>
+ s"""
+ |if ($biggestCardinality != -1) {
+ | ${eval.code}
+ | if (!${eval.isNull}) {
+ | $arrVals[$index] = ${eval.value};
+ | $arrCardinality[$index] = ${eval.value}.numElements();
+ | $biggestCardinality = Math.max($biggestCardinality,
$arrCardinality[$index]);
+ | } else {
+ | $biggestCardinality = -1;
+ | }
+ |}
+ """.stripMargin
+ }
+
+ val splittedGetValuesAndCardinalities = ctx.splitExpressions(
+ expressions = getValuesAndCardinalities,
+ funcName = "getValuesAndCardinalities",
+ returnType = "int",
+ makeSplitFunction = body =>
+ s"""
+ |$body
+ |return $biggestCardinality;
+ """.stripMargin,
+ foldFunctions = _.map(funcCall => s"$biggestCardinality =
$funcCall;").mkString("\n"),
+ arguments =
+ ("ArrayData[]", arrVals) ::
+ ("int[]", arrCardinality) ::
+ ("int", biggestCardinality) :: Nil)
+
+ val getValueForType = arrayElementTypes.zipWithIndex.map { case
(eleType, idx) =>
+ val g = CodeGenerator.getValue(s"$arrVals[$idx]", eleType, i)
+ s"""
+ |if ($i < $arrCardinality[$idx] && !$arrVals[$idx].isNullAt($i)) {
--- End diff --
nit: indent
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
