Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/10944#discussion_r51193347
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/basicOperators.scala ---
@@ -172,38 +184,42 @@ case class Range(
s"$number > $partitionEnd"
}
- val rdd = sqlContext.sparkContext.parallelize(0 until numSlices,
numSlices)
- .map(i => InternalRow(i))
+ ctx.addNewFunction("initRange",
+ s"""
+ | private void initRange(int idx) {
+ | $BigInt index = $BigInt.valueOf(idx);
+ | $BigInt numSlice = $BigInt.valueOf(${numSlices}L);
+ | $BigInt numElement = $BigInt.valueOf(${numElements.toLong}L);
+ | $BigInt step = $BigInt.valueOf(${step}L);
+ | $BigInt start = $BigInt.valueOf(${start}L);
+ |
+ | $BigInt st =
index.multiply(numElement).divide(numSlice).multiply(step).add(start);
+ | if (st.compareTo($BigInt.valueOf(Long.MAX_VALUE)) > 0) {
+ | $number = Long.MAX_VALUE;
+ | } else if (st.compareTo($BigInt.valueOf(Long.MIN_VALUE)) < 0) {
+ | $number = Long.MIN_VALUE;
+ | } else {
+ | $number = st.longValue();
+ | }
+ |
+ | $BigInt end =
index.add($BigInt.ONE).multiply(numElement).divide(numSlice)
+ | .multiply(step).add(start);
+ | if (end.compareTo($BigInt.valueOf(Long.MAX_VALUE)) > 0) {
+ | $partitionEnd = Long.MAX_VALUE;
+ | } else if (end.compareTo($BigInt.valueOf(Long.MIN_VALUE)) < 0)
{
+ | $partitionEnd = Long.MIN_VALUE;
+ | } else {
+ | $partitionEnd = end.longValue();
+ | }
+ | }
+ """.stripMargin)
- val code = s"""
+ s"""
| // initialize Range
| if (!$initTerm) {
| $initTerm = true;
| if (input.hasNext()) {
- | $BigInt index = $BigInt.valueOf(((InternalRow)
input.next()).getInt(0));
- | $BigInt numSlice = $BigInt.valueOf(${numSlices}L);
- | $BigInt numElement = $BigInt.valueOf(${numElements.toLong}L);
- | $BigInt step = $BigInt.valueOf(${step}L);
- | $BigInt start = $BigInt.valueOf(${start}L);
- |
- | $BigInt st =
index.multiply(numElement).divide(numSlice).multiply(step).add(start);
- | if (st.compareTo($BigInt.valueOf(Long.MAX_VALUE)) > 0) {
- | $number = Long.MAX_VALUE;
- | } else if (st.compareTo($BigInt.valueOf(Long.MIN_VALUE)) < 0) {
- | $number = Long.MIN_VALUE;
- | } else {
- | $number = st.longValue();
- | }
- |
- | $BigInt end =
index.add($BigInt.ONE).multiply(numElement).divide(numSlice)
- | .multiply(step).add(start);
- | if (end.compareTo($BigInt.valueOf(Long.MAX_VALUE)) > 0) {
- | $partitionEnd = Long.MAX_VALUE;
- | } else if (end.compareTo($BigInt.valueOf(Long.MIN_VALUE)) < 0)
{
- | $partitionEnd = Long.MIN_VALUE;
- | } else {
- | $partitionEnd = end.longValue();
- | }
+ | initRange(((InternalRow) input.next()).getInt(0));
--- End diff --
This is the easy way to make Range work, or you have to find the partition
id.
---
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
