Github user pepinoflo commented on a diff in the pull request:
https://github.com/apache/spark/pull/21208#discussion_r185962048
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -1229,3 +1229,98 @@ case class Flatten(child: Expression) extends
UnaryExpression {
override def prettyName: String = "flatten"
}
+
+/**
+ * Returns the array containing the given input value (left) count (right)
times.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(element, count) - Returns the array containing element
count times.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_('123', 2);
+ ['123', '123']
+ """)
+case class ArrayRepeat(left: Expression, right: Expression)
+ extends BinaryExpression {
+
+ override def dataType: ArrayType = ArrayType(left.dataType,
left.nullable)
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ val expected = IntegerType
+ if (!expected.acceptsType(right.dataType)) {
+ val mismatch = s"argument 2 requires ${expected.simpleString} type,
" +
+ s"however, '${right.sql}' is of ${right.dataType.simpleString}
type."
+ TypeCheckResult.TypeCheckFailure(mismatch)
+ } else {
+ TypeCheckResult.TypeCheckSuccess
+ }
+ }
+
+ override def nullable: Boolean = false
+
+ override def eval(input: InternalRow): Any = {
+ new
GenericArrayData(List.fill(right.eval(input).asInstanceOf[Integer])(left.eval(input)))
+ }
+
+ override def prettyName: String = "array_repeat"
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+
+ val leftGen = left.genCode(ctx)
+ val rightGen = right.genCode(ctx)
+ val element = leftGen.value
+ val count = rightGen.value
+ val et = dataType.elementType
+ val isPrimitive = CodeGenerator.isPrimitiveType(et)
+
+ val arrayDataName = ctx.freshName("arrayData")
+ val arrayName = ctx.freshName("arrayObject")
+ val initialization = (numElements: String) => if (isPrimitive) {
+ val arrayName = ctx.freshName("array")
+ val baseOffset = Platform.BYTE_ARRAY_OFFSET
+ s"""
+ | int numBytes = ${et.defaultSize} * $numElements;
+ | int unsafeArraySizeInBytes =
UnsafeArrayData.calculateHeaderPortionInBytes($numElements)
+ | + org.apache.spark.unsafe.array.ByteArrayMethods
+ | .roundNumberOfBytesToNearestWord(numBytes);
+ | byte[] $arrayName = new byte[unsafeArraySizeInBytes];
+ | UnsafeArrayData $arrayDataName = new UnsafeArrayData();
+ | Platform.putLong($arrayName, $baseOffset, $numElements);
+ | $arrayDataName.pointTo($arrayName, $baseOffset,
unsafeArraySizeInBytes);
+ | ${ev.value} = $arrayDataName;
+ """.stripMargin
+ } else {
+ s"${ev.value} = new ${classOf[GenericArrayData].getName()}(new
Object[$numElements]);"
+ }
+
+ val primitiveValueTypeName = CodeGenerator.primitiveTypeName(et)
+ val assignments = {
+ val updateArray = if (isPrimitive) {
+ s"${ev.value}.set$primitiveValueTypeName(k, $element);"
+ } else {
+ s"${ev.value}.update(k, $element);"
--- End diff --
Then we put null in the array... I think the update method handle that?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
