Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/13909#discussion_r93815041
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
---
@@ -56,33 +58,130 @@ case class CreateArray(children: Seq[Expression])
extends Expression {
}
override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
- val arrayClass = classOf[GenericArrayData].getName
- val values = ctx.freshName("values")
- ctx.addMutableState("Object[]", values, s"this.$values = null;")
-
- ev.copy(code = s"""
- this.$values = new Object[${children.size}];""" +
- ctx.splitExpressions(
- ctx.INPUT_ROW,
- children.zipWithIndex.map { case (e, i) =>
- val eval = e.genCode(ctx)
- eval.code + s"""
- if (${eval.isNull}) {
- $values[$i] = null;
- } else {
- $values[$i] = ${eval.value};
- }
- """
- }) +
- s"""
- final ArrayData ${ev.value} = new $arrayClass($values);
- this.$values = null;
- """, isNull = "false")
+ val et = dataType.elementType
+ val evals = children.map(e => e.genCode(ctx))
+ val isPrimitiveArray = ctx.isPrimitiveType(et)
+ val (preprocess, postprocess, arrayData, array) =
+ GenArrayData.genCodeToCreateArrayData(ctx, et, children.size,
isPrimitiveArray)
+ val assigns = GenArrayData.genCodeToAssignArrayElements(
+ ctx, evals, et, isPrimitiveArray, arrayData, array, true)
+ /*
+ TODO: When we generate simpler code, we have to solve the following
exception
+ https://github.com/apache/spark/pull/13909/files#r93813725
+ ev.copy(
+ code = preprocess + ctx.splitExpressions(ctx.INPUT_ROW, assigns) +
postprocess
+ value = arrayData,
+ isNull = "false")
+ */
+ ev.copy(
+ code = preprocess + ctx.splitExpressions(ctx.INPUT_ROW, assigns) +
postprocess +
+ s"\nfinal ArrayData ${ev.value} = $arrayData;\n",
+ isNull = "false")
}
override def prettyName: String = "array"
}
+private [sql] object GenArrayData {
+ /**
+ * Return Java code pieces based on DataType and isPrimitive to allocate
ArrayData class
+ *
+ * @param ctx a [[CodegenContext]]
+ * @param elementType data type of an underlying array
+ * @param numElements the number of array elements
+ * @param isPrimitive Are all of the elements of an underlying array
primitive type
+ * @return (code pre-assignments, code post-assignments, underlying
array name, arrayData name)
+ */
+ def genCodeToCreateArrayData(
+ ctx: CodegenContext,
+ elementType: DataType,
+ numElements: Int,
+ isPrimitive : Boolean): (String, String, String, String) = {
+ val arrayName = ctx.freshName("array")
+ val arrayDataName = ctx.freshName("arrayData")
+ if (!isPrimitive) {
+ val arrayClass = classOf[GenericArrayData].getName
+ ctx.addMutableState("Object[]", arrayName,
+ s"this.$arrayName = new Object[${numElements}];")
+ ("",
+ s"$arrayClass $arrayDataName = new $arrayClass($arrayName);",
+ arrayDataName,
+ arrayName)
+ } else {
+ val unsafeArrayClass = classOf[UnsafeArrayData].getName
+ val baseObject = ctx.freshName("baseObject")
+ val unsafeArraySizeInBytes =
+ UnsafeArrayData.calculateHeaderPortionInBytes(numElements) +
+
ByteArrayMethods.roundNumberOfBytesToNearestWord(elementType.defaultSize *
numElements)
+ val baseOffset = Platform.BYTE_ARRAY_OFFSET
+
+ (s"""
+ byte[] $arrayName = new byte[$unsafeArraySizeInBytes];
+ $unsafeArrayClass $arrayDataName = new $unsafeArrayClass();
--- End diff --
Don't we need to make this mutable state for the case assignments are split?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
