rtpsw commented on code in PR #34311:
URL: https://github.com/apache/arrow/pull/34311#discussion_r1124206218
##########
cpp/src/arrow/compute/exec/aggregate_node.cc:
##########
@@ -169,35 +185,117 @@ void AggregatesToString(std::stringstream* ss, const
Schema& input_schema,
*ss << ']';
}
+template <typename BatchHandler>
+Status HandleSegments(std::unique_ptr<GroupingSegmenter>& segmenter,
+ const ExecBatch& batch, const std::vector<int>& ids,
+ const BatchHandler& handle_batch) {
+ int64_t offset = 0;
+ ARROW_ASSIGN_OR_RAISE(auto segment_exec_batch, batch.SelectValues(ids));
+ ExecSpan segment_batch(segment_exec_batch);
+ while (true) {
+ ARROW_ASSIGN_OR_RAISE(auto segment,
segmenter->GetNextSegment(segment_batch, offset));
+ if (segment.offset >= segment_batch.length) break; // condition of
no-next-segment
+ ARROW_RETURN_NOT_OK(handle_batch(batch, segment));
+ offset = segment.offset + segment.length;
+ }
+ return Status::OK();
+}
+
+Status GetScalarFields(std::vector<Datum>* values_ptr, const ExecBatch&
input_batch,
+ const std::vector<int>& field_ids) {
+ DCHECK_GT(input_batch.length, 0);
+ std::vector<Datum>& values = *values_ptr;
+ int64_t row = input_batch.length - 1;
+ values.clear();
+ values.resize(field_ids.size());
+ for (size_t i = 0; i < field_ids.size(); i++) {
+ const Datum& value = input_batch.values[field_ids[i]];
+ if (value.is_scalar()) {
Review Comment:
This value is a column of the input batch that may be a scalar - the batch
is set by the previous node in the plan. When the value is a scalar, the column
is constant.
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
