Github user kiszk commented on a diff in the pull request:
https://github.com/apache/spark/pull/21069#discussion_r188704602
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -1468,3 +1468,104 @@ case class Flatten(child: Expression) extends
UnaryExpression {
override def prettyName: String = "flatten"
}
+
+/**
+ * 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 {
+
+ override def dataType: DataType = left.dataType
+
+ override def inputTypes: Seq[AbstractDataType] =
+ Seq(ArrayType, left.dataType.asInstanceOf[ArrayType].elementType)
+
+ lazy val elementType: DataType =
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 = {
+ nullSafeCodeGen(ctx, ev, (arr, value) => {
+ val numsToRemove = ctx.freshName("numsToRemove")
+ val newArraySize = ctx.freshName("newArraySize")
+ val i = ctx.freshName("i")
+ val getValue = CodeGenerator.getValue(arr, elementType, i)
+ val isEqual = ctx.genEqual(elementType, value, getValue)
+ s"""
+ |int $numsToRemove = 0;
+ |for (int $i = 0; $i < $arr.numElements(); $i ++) {
+ | if (!$arr.isNullAt($i) && $isEqual) {
+ | $numsToRemove = $numsToRemove + 1;
+ | }
+ |}
+ |int $newArraySize = $arr.numElements() - $numsToRemove;
+ |${genCodeForResult(ctx, ev, arr, value, newArraySize)}
+ """.stripMargin
+ })
+ }
+
+ def genCodeForResult(
+ ctx: CodegenContext,
+ ev: ExprCode,
+ inputArray: String,
+ value: String,
+ newArraySize: String): String = {
+ val values = ctx.freshName("values")
+ val i = ctx.freshName("i")
+ val pos = ctx.freshName("pos")
+ val getValue = CodeGenerator.getValue(inputArray, elementType, i)
+ val isEqual = ctx.genEqual(elementType, value, getValue)
+ if (!CodeGenerator.isPrimitiveType(elementType)) {
+ val arrayClass = classOf[GenericArrayData].getName
+ s"""
+ |int $pos = 0;
+ |Object[] $values = new Object[$newArraySize];
+ |for (int $i = 0; $i < $inputArray.numElements(); $i ++) {
+ | if ($isEqual) {
+ | ;
+ | }
+ | else {
+ | $values[$pos] = $getValue;
+ | $pos = $pos + 1;
+ | }
+ |}
+ |${ev.value} = new $arrayClass($values);
+ """.stripMargin
+ } else {
+ val primitiveValueTypeName =
CodeGenerator.primitiveTypeName(elementType)
+ s"""
+ |${ctx.createUnsafeArray(values, newArraySize, elementType, s"
$prettyName failed.")}
+ |int $pos = 0;
+ |for (int $i = 0; $i < $inputArray.numElements(); $i ++) {
+ | if ($inputArray.isNullAt($i)) {
+ | $values.setNullAt($pos);
+ | $pos = $pos + 1;
+ | }
+ | else {
+ | if ($isEqual) {
--- End diff --
ditto
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]