Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/13909#discussion_r92985372
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
---
@@ -56,33 +58,93 @@ 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.$values = null;")
+ val array = ctx.freshName("array")
- ev.copy(code = s"""
- this.$values = new Object[${children.size}];""" +
+ val et = dataType.elementType
+ val evals = children.map(e => e.genCode(ctx))
+ val isPrimitiveArray = ctx.isPrimitiveType(et)
+ val primitiveTypeName = if (isPrimitiveArray)
ctx.primitiveTypeName(et) else ""
+ val (preprocess, arrayData, arrayWriter) =
+ GenArrayData.getCodeArrayData(ctx, et, children.size,
isPrimitiveArray, array)
+
+ ev.copy(code =
+ preprocess +
ctx.splitExpressions(
ctx.INPUT_ROW,
- children.zipWithIndex.map { case (e, i) =>
- val eval = e.genCode(ctx)
- eval.code + s"""
- if (${eval.isNull}) {
- $values[$i] = null;
+ evals.zipWithIndex.map { case (eval, i) =>
+ eval.code +
+ (if (isPrimitiveArray) {
+ (if (!children(i).nullable) {
+ s"\n$arrayWriter.write($i, ${eval.value});"
+ } else {
+ s"""
+ if (${eval.isNull}) {
+ $arrayWriter.setNull$primitiveTypeName($i);
+ } else {
+ $arrayWriter.write($i, ${eval.value});
+ }
+ """
+ })
} else {
- $values[$i] = ${eval.value};
- }
- """
+ s"""
+ if (${eval.isNull}) {
+ $array[$i] = null;
+ } else {
+ $array[$i] = ${eval.value};
+ }
+ """
+ })
}) +
- s"""
- final ArrayData ${ev.value} = new $arrayClass($values);
- this.$values = null;
- """, isNull = "false")
+ s"\nfinal ArrayData ${ev.value} = $arrayData;\n",
+ isNull = "false")
}
override def prettyName: String = "array"
}
+private [sql] object GenArrayData {
+ // This function returns Java code pieces based on DataType and
isPrimitive
+ // for allocation of ArrayData class
+ def getCodeArrayData(
+ ctx: CodegenContext,
+ dt: DataType,
+ size: Int,
+ isPrimitive : Boolean,
+ array: String): (String, String, String) = {
+ if (!isPrimitive) {
+ val arrayClass = classOf[GenericArrayData].getName
+ ctx.addMutableState("Object[]", array,
+ s"this.$array = new Object[${size}];")
+ ("", s"new $arrayClass($array)", null)
+ } else {
+ val holder = ctx.freshName("holder")
+ val arrayWriter = ctx.freshName("createArrayWriter")
+ val unsafeArrayClass = classOf[UnsafeArrayData].getName
+ val holderClass = classOf[BufferHolder].getName
+ val arrayWriterClass = classOf[UnsafeArrayWriter].getName
+ ctx.addMutableState(unsafeArrayClass, array, "")
+ ctx.addMutableState(holderClass, holder, "")
+ ctx.addMutableState(arrayWriterClass, arrayWriter, "")
+ val baseOffset = Platform.BYTE_ARRAY_OFFSET
+ val unsafeArraySizeInBytes =
+ UnsafeArrayData.calculateHeaderPortionInBytes(size) +
+ ByteArrayMethods.roundNumberOfBytesToNearestWord(dt.defaultSize *
size)
+
+ (s"""
+ $array = new $unsafeArrayClass();
+ $holder = new $holderClass($unsafeArraySizeInBytes);
+ $arrayWriter = new $arrayWriterClass();
--- End diff --
@kiszk oh, I see. When used with aggregate function, the byte array will be
overwritten.
---
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
