[GitHub] [spark] LuciferYang commented on a diff in pull request #38865: [SPARK-41232][SQL][PYTHON] Adding array_append function

[GitBox <gi...@apache.org>]

LuciferYang commented on code in PR #38865:
URL: https://github.com/apache/spark/pull/38865#discussion_r1050442341


##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:
##########
@@ -4600,3 +4600,111 @@ case class ArrayExcept(left: Expression, right: Expression) extends ArrayBinaryL
   override protected def withNewChildrenInternal(
     newLeft: Expression, newRight: Expression): ArrayExcept = copy(left = newLeft, right = newRight)
 }
+
+/**
+ * Given an array, and another element append the element at the end of the array.
+ */
+@ExpressionDescription(
+  usage = """_FUNC_(array, element) - Add the element at the end of the array passed as first
+      argument. Type of element should be similar to type of the elements of the array.""",
+  examples = """
+    Examples:
+      > SELECT _FUNC_(array('b', 'd', 'c', 'a'), 'd');
+       ["b","d","c","a","d"]
+
+  """,
+  since = "3.4.0",
+  group = "array_funcs")
+case class ArrayAppend(left: Expression, right: Expression)
+  extends BinaryExpression
+    with ImplicitCastInputTypes
+    with ComplexTypeMergingExpression
+    with NullIntolerant
+    with QueryErrorsBase {
+  override def prettyName: String = "array_append"
+
+  @transient protected lazy val elementType: DataType =
+    inputTypes.head.asInstanceOf[ArrayType].elementType
+
+  override def inputTypes: Seq[AbstractDataType] = {
+    (left.dataType, right.dataType) match {
+      case (ArrayType(e1, hasNull), e2) =>
+        TypeCoercion.findTightestCommonType(e1, e2) match {
+          case Some(dt) => Seq(ArrayType(dt, hasNull), dt)
+          case _ => Seq.empty
+        }
+      case _ => Seq.empty
+    }
+  }
+
+  override def checkInputDataTypes(): TypeCheckResult = {
+    (left.dataType, right.dataType) match {
+      case (ArrayType(e1, _), e2) if e1.sameType(e2) => TypeCheckResult.TypeCheckSuccess
+      case (ArrayType(e1, _), e2) => DataTypeMismatch(
+        errorSubClass = "ARRAY_FUNCTION_DIFF_TYPES",
+        messageParameters = Map(
+          "functionName" -> toSQLId(prettyName),
+          "leftType" -> toSQLType(left.dataType),
+          "rightType" -> toSQLType(right.dataType),
+          "dataType" -> toSQLType(ArrayType)
+        ))
+      case _ =>
+        DataTypeMismatch(
+          errorSubClass = "UNEXPECTED_INPUT_TYPE",
+          messageParameters = Map(
+            "paramIndex" -> "0",
+            "requiredType" -> toSQLType(ArrayType),
+            "inputSql" -> toSQLExpr(left),
+            "inputType" -> toSQLType(left.dataType)
+          )
+        )
+    }
+  }
+
+
+  override protected def nullSafeEval(input1: Any, input2: Any): Any = {
+    val arrayData = input1.asInstanceOf[ArrayData]
+    val elementData = input2

Review Comment:
   how about change the method signature directly to `nullSafeEval(arr: Any, elementData: Any)`?
   
   ```
   val elementData = input2
   ```
   Looks like it's just to make variable name more readable?
   
   
   
   



-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org