icexelloss commented on code in PR #34311:
URL: https://github.com/apache/arrow/pull/34311#discussion_r1125574829
##########
cpp/src/arrow/compute/exec/aggregate_node.cc:
##########
@@ -440,12 +613,29 @@ class GroupByNode : public ExecNode, public TracedNode {
int key_field_id = key_field_ids[i];
output_fields[base + i] = input_schema->field(key_field_id);
}
+ base += keys.size();
+ for (size_t i = 0; i < segment_keys.size(); ++i) {
+ int segment_key_field_id = segment_key_field_ids[i];
+ output_fields[base + i] = input_schema->field(segment_key_field_id);
+ }
return input->plan()->EmplaceNode<GroupByNode>(
input, schema(std::move(output_fields)), std::move(key_field_ids),
+ std::move(segment_key_field_ids), std::move(segmenter),
std::move(agg_src_types),
std::move(agg_src_fieldsets), std::move(aggs), std::move(agg_kernels));
}
+ Status ResetAggregates() {
Review Comment:
What are the difference between them? And which one do we use for ordered
aggregation?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
