Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/13909#discussion_r93654504
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/complexTypeCreator.scala
---
@@ -56,33 +58,100 @@ 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.$values = null;
- """, isNull = "false")
+ val array = ctx.freshName("array")
+
+ val et = dataType.elementType
+ val evals = children.map(e => e.genCode(ctx))
+ val isPrimitiveArray = ctx.isPrimitiveType(et)
+ val primitiveTypeName = if (isPrimitiveArray)
ctx.primitiveTypeName(et) else ""
+ val (preprocess, arrayData, arrayWriter) =
+ GenArrayData.getCodeArrayData(ctx, et, children.size,
isPrimitiveArray, array)
+
+ val assigns = if (isPrimitiveArray) {
+ evals.zipWithIndex.map { case (eval, i) =>
+ eval.code + s"""
+ if (${eval.isNull}) {
+ $arrayWriter.setNull$primitiveTypeName($i);
+ } else {
+ $arrayWriter.write($i, ${eval.value});
+ }
+ """
+ }
+ } else {
+ evals.zipWithIndex.map { case (eval, i) =>
+ eval.code + s"""
+ if (${eval.isNull}) {
+ $array[$i] = null;
+ } else {
+ $array[$i] = ${eval.value};
+ }
+ """
+ }
+ }
+ ev.copy(code =
+ preprocess +
+ ctx.splitExpressions(ctx.INPUT_ROW, assigns) +
+ 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 row = ctx.freshName("row")
+ val holder = ctx.freshName("holder")
+ val rowWriter = ctx.freshName("createRowWriter")
+ val arrayWriter = ctx.freshName("createArrayWriter")
+ val unsafeRowClass = classOf[UnsafeRow].getName
+ val unsafeArrayClass = classOf[UnsafeArrayData].getName
+ val holderClass = classOf[BufferHolder].getName
+ val rowWriterClass = classOf[UnsafeRowWriter].getName
+ val arrayWriterClass = classOf[UnsafeArrayWriter].getName
+ ctx.addMutableState(unsafeRowClass, row, "")
+ ctx.addMutableState(unsafeArrayClass, array, "")
+ ctx.addMutableState(holderClass, holder, "")
+ ctx.addMutableState(rowWriterClass, rowWriter, "")
+ ctx.addMutableState(arrayWriterClass, arrayWriter, "")
+ val unsafeArraySizeInBytes =
+ UnsafeArrayData.calculateHeaderPortionInBytes(size) +
+ ByteArrayMethods.roundNumberOfBytesToNearestWord(dt.defaultSize *
size)
+
+ // To write data to UnsafeArrayData, we create UnsafeRow with a
single array field
+ // and then prepare BufferHolder for the array.
+ // In summary, this does not use UnsafeRow and wastes some bits in
an byte array
+ (s"""
+ $row = new $unsafeRowClass(1);
+ $holder = new $holderClass($row, $unsafeArraySizeInBytes);
+ $rowWriter = new $rowWriterClass($holder, 1);
--- End diff --
I hit a problem while I was exploring something else, and I came up with a
new idea: how about we make `ArrayData` mutable like `InternalRow`? Then we can
just create a byte array here, point the unsafe array to this byte array. When
we evaluate expressions, we call `ArrayData.setInt` or something like it, and
call `ArrayData.setNullAt` when the expression result is null.
---
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
