Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/21069#discussion_r185716774
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -883,3 +883,70 @@ case class Concat(children: Seq[Expression]) extends
Expression {
override def sql: String = s"concat(${children.map(_.sql).mkString(",
")})"
}
+
+/**
+ * Remove all elements that equal to element from the given array
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(array, element) - Remove all elements that equal to
element from array.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(1, 2, 3, null, 3), 3);
+ [1,2,null]
+ """, since = "2.4.0")
+case class ArrayRemove(left: Expression, right: Expression)
+ extends BinaryExpression with ImplicitCastInputTypes with
CodegenFallback {
+
+ override def dataType: DataType = left.dataType
+
+ override def inputTypes: Seq[AbstractDataType] =
+ Seq(ArrayType, left.dataType.asInstanceOf[ArrayType].elementType)
+
+ override def nullSafeEval(arr: Any, value: Any): Any = {
+ val elementType = left.dataType.asInstanceOf[ArrayType].elementType
+ val data =
arr.asInstanceOf[ArrayData].toArray[AnyRef](elementType).filter(_ != value)
+ new GenericArrayData(data.asInstanceOf[Array[Any]])
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ val elementType = left.dataType.asInstanceOf[ArrayType].elementType
+ nullSafeCodeGen(ctx, ev, (arr, value) => {
+ val arrayClass = classOf[GenericArrayData].getName
+ val values = ctx.freshName("values")
+ val i = ctx.freshName("i")
+ val pos = ctx.freshName("arrayPosition")
+ val numsToRemove = ctx.freshName("newArrLen")
+ val getValue = CodeGenerator.getValue(arr, right.dataType, i)
+ s"""
+ |int $pos = 0;
+ |int $numsToRemove = 0;
+ |Object[] $values;
+ |
+ |for (int $i = 0; $i < $arr.numElements(); $i ++) {
+ | if (!$arr.isNullAt($i) && ${ctx.genEqual(right.dataType,
value, getValue)}) {
--- End diff --
`ctx.genEqual(elementType, value, getValue)`?
Btw, this expression is used twice, so we should extract it.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
