[GitHub] [spark] navinvishy commented on a diff in pull request #38947: [SPARK-41233][SQL] Add `array_prepend` function

["navinvishy (via GitHub)" <gi...@apache.org>]

navinvishy commented on code in PR #38947:
URL: https://github.com/apache/spark/pull/38947#discussion_r1121154959


##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala:
##########
@@ -1399,6 +1399,145 @@ case class ArrayContains(left: Expression, right: Expression)
     copy(left = newLeft, right = newRight)
 }
 
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+  usage =
+    "_FUNC_(array, value) - Returns an array containing value as well as all elements from array. The new element is positioned at the beginning of the array.",
+  examples = """
+    Examples:
+      > SELECT _FUNC_(array('b', 'd', 'c', 'a'), 'd');
+       ["d","b","d","c","a"]
+  """,
+  group = "array_funcs",
+  since = "3.4.0")
+case class ArrayPrepend(left: Expression, right: Expression)
+  extends BinaryExpression
+    with ImplicitCastInputTypes
+    with ComplexTypeMergingExpression
+    with QueryErrorsBase {
+
+  override def nullable: Boolean = left.nullable
+
+  @transient protected lazy val elementType: DataType =
+    inputTypes.head.asInstanceOf[ArrayType].elementType
+
+  override def eval(input: InternalRow): Any = {
+    val value1 = left.eval(input)
+    if (value1 == null) {
+      null
+    } else {
+      val value2 = right.eval(input)
+      nullSafeEval(value1, value2)
+    }
+  }
+  override def nullSafeEval(arr: Any, elementData: Any): Any = {
+    val arrayData = arr.asInstanceOf[ArrayData]
+    val numberOfElements = arrayData.numElements() + 1
+    if (numberOfElements > ByteArrayMethods.MAX_ROUNDED_ARRAY_LENGTH) {
+      throw QueryExecutionErrors.concatArraysWithElementsExceedLimitError(numberOfElements)
+    }
+    val finalData = new Array[Any](numberOfElements)
+    finalData.update(0, elementData)
+    arrayData.foreach(elementType, (i: Int, v: Any) => finalData.update(i + 1, v))
+    new GenericArrayData(finalData)
+  }
+  override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+    val leftGen = left.genCode(ctx)
+    val rightGen = right.genCode(ctx)
+    val f = (arr: String, value: String) => {
+      val newArraySize = ctx.freshName("newArraySize")
+      val newArray = ctx.freshName("newArray")
+      val i = ctx.freshName("i")
+      val pos = ctx.freshName("pos")

Review Comment:
   @zhengruifeng I assume you mean that we could use `i+1` here for the assignment instead of using a different var `pos`? I've done that here - please let me know if that works.



-- 
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