Daniel-Davies commented on code in PR #38867:
URL: https://github.com/apache/spark/pull/38867#discussion_r1064048215
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:
##########
@@ -4601,6 +4601,231 @@ case class ArrayExcept(left: Expression, right:
Expression) extends ArrayBinaryL
newLeft: Expression, newRight: Expression): ArrayExcept = copy(left =
newLeft, right = newRight)
}
+@ExpressionDescription(
+ usage = "_FUNC_(x, pos, val) - Places val into index pos of array x (array
indices start at 1)",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(1, 2, 3, 4), 4, 5);
+ [1,2,3,4,5]
+ > SELECT _FUNC_(array(5, 3, 2, 1), -3, 4);
+ [5,4,3,2,1]
+ """,
+ group = "array_funcs",
+ since = "3.4.0")
+case class ArrayInsert(srcArrayExpr: Expression, posExpr: Expression,
itemExpr: Expression)
+ extends TernaryExpression with ImplicitCastInputTypes with
ComplexTypeMergingExpression
+ with QueryErrorsBase {
+
+ override def inputTypes: Seq[AbstractDataType] = {
+ (srcArrayExpr.dataType, posExpr.dataType, itemExpr.dataType) match {
+ case (ArrayType(e1, hasNull), e2: IntegralType, e3) if (e2 != LongType)
=>
+ TypeCoercion.findTightestCommonType(e1, e3) match {
+ case Some(dt) => Seq(ArrayType(dt, hasNull), IntegerType, dt)
+ case _ => Seq.empty
+ }
+ case (e1, e2, e3) => Seq.empty
+ }
+ Seq.empty
+ }
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ (first.dataType, second.dataType, third.dataType) match {
+ case (_: ArrayType, e2, e3) if e2 != IntegerType =>
+ DataTypeMismatch(
+ errorSubClass = "UNEXPECTED_INPUT_TYPE",
+ messageParameters = Map(
+ "paramIndex" -> "2",
+ "requiredType" -> toSQLType(IntegerType),
+ "inputSql" -> toSQLExpr(second),
+ "inputType" -> toSQLType(second.dataType))
+ )
+ case (ArrayType(e1, _), e2, e3) if e1.sameType(e3) =>
+ TypeUtils.checkForOrderingExpr(e2, prettyName)
Review Comment:
Amended, thank you for reviewing!
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:
##########
@@ -4601,6 +4601,231 @@ case class ArrayExcept(left: Expression, right:
Expression) extends ArrayBinaryL
newLeft: Expression, newRight: Expression): ArrayExcept = copy(left =
newLeft, right = newRight)
}
+@ExpressionDescription(
+ usage = "_FUNC_(x, pos, val) - Places val into index pos of array x (array
indices start at 1)",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(1, 2, 3, 4), 4, 5);
+ [1,2,3,4,5]
+ > SELECT _FUNC_(array(5, 3, 2, 1), -3, 4);
+ [5,4,3,2,1]
+ """,
+ group = "array_funcs",
+ since = "3.4.0")
+case class ArrayInsert(srcArrayExpr: Expression, posExpr: Expression,
itemExpr: Expression)
+ extends TernaryExpression with ImplicitCastInputTypes with
ComplexTypeMergingExpression
+ with QueryErrorsBase {
+
+ override def inputTypes: Seq[AbstractDataType] = {
+ (srcArrayExpr.dataType, posExpr.dataType, itemExpr.dataType) match {
+ case (ArrayType(e1, hasNull), e2: IntegralType, e3) if (e2 != LongType)
=>
+ TypeCoercion.findTightestCommonType(e1, e3) match {
+ case Some(dt) => Seq(ArrayType(dt, hasNull), IntegerType, dt)
+ case _ => Seq.empty
+ }
+ case (e1, e2, e3) => Seq.empty
+ }
+ Seq.empty
+ }
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ (first.dataType, second.dataType, third.dataType) match {
+ case (_: ArrayType, e2, e3) if e2 != IntegerType =>
+ DataTypeMismatch(
+ errorSubClass = "UNEXPECTED_INPUT_TYPE",
+ messageParameters = Map(
+ "paramIndex" -> "2",
+ "requiredType" -> toSQLType(IntegerType),
+ "inputSql" -> toSQLExpr(second),
+ "inputType" -> toSQLType(second.dataType))
+ )
+ case (ArrayType(e1, _), e2, e3) if e1.sameType(e3) =>
+ TypeUtils.checkForOrderingExpr(e2, prettyName)
+ case _ =>
+ DataTypeMismatch(
+ errorSubClass = "ARRAY_FUNCTION_DIFF_TYPES",
+ messageParameters = Map(
+ "functionName" -> toSQLId(prettyName),
+ "dataType" -> toSQLType(ArrayType),
+ "leftType" -> toSQLType(first.dataType),
+ "rightType" -> toSQLType(third.dataType)
+ )
+ )
+ }
+ }
+
+ override def eval(input: InternalRow): Any = {
+ val value1 = first.eval(input)
+ if (value1 != null) {
+ val value2 = second.eval(input)
+ if (value2 != null) {
+ val value3 = third.eval(input)
+ return nullSafeEval(value1, value2, value3)
+ }
+ }
+ null
+ }
+
+ override def nullSafeEval(arr: Any, pos: Any, item: Any): Any = {
+ val baseArr = arr.asInstanceOf[ArrayData]
+ val posInt = pos.asInstanceOf[Int]
+ val arrayElementType = dataType.asInstanceOf[ArrayType].elementType
+
+ val newPosExtendsArrayLeft = posInt < 0 && math.abs(posInt) >
baseArr.numElements() - 1
+
+ val itemInsertionIndex = if (newPosExtendsArrayLeft) {
+ 0
+ } else if (posInt < 0) {
+ posInt + baseArr.numElements()
+ } else {
+ posInt
+ }
+
+ val newArrayLength = if (newPosExtendsArrayLeft) {
+ math.abs(posInt) + 1
+ } else {
+ math.max(baseArr.numElements() + 1, itemInsertionIndex + 1)
+ }
+
+ val newArray = new Array[Any](newArrayLength)
+
+ baseArr.foreach(arrayElementType, (i, v) => {
+ var elementPosition = i
+ if (newPosExtendsArrayLeft) {
+ elementPosition = elementPosition + 1 + math.abs(posInt +
baseArr.numElements())
+ }
+ if (i >= itemInsertionIndex && !newPosExtendsArrayLeft) {
+ elementPosition = elementPosition + 1
+ }
+ newArray(elementPosition) = v
+ })
+
+ newArray(itemInsertionIndex) = item
+
+ return new GenericArrayData(newArray)
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ val f = (arrExpr: ExprCode, posExpr: ExprCode, itemExpr: ExprCode) => {
+ val arr = arrExpr.value
+ val pos = posExpr.value
+ val item = itemExpr.value
+
+ val itemInsertionIndex = ctx.freshName("itemInsertionIndex")
+ val newPosExtendsArrayLeft = ctx.freshName("newPosExtendsArrayLeft")
+ val adjustedAllocIdx = ctx.freshName("adjustedAllocIdx")
+ val resLength = ctx.freshName("resLength")
+ val insertedItemIsNull = ctx.freshName("insertedItemIsNull")
+ val i = ctx.freshName("i")
+ val j = ctx.freshName("j")
+ val values = ctx.freshName("values")
+
+ val allocation = CodeGenerator.createArrayData(
+ values, elementType, resLength, s"$prettyName failed.")
+ val assignment = CodeGenerator.createArrayAssignment(values,
elementType, arr,
+ adjustedAllocIdx, i, true)
+
+ val defaultIntValue = CodeGenerator.defaultValue(CodeGenerator.JAVA_INT,
false)
+ s"""
+ |${CodeGenerator.JAVA_INT} $itemInsertionIndex = 0;
Review Comment:
Amended, thank you for reviewing!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
