rtpsw commented on code in PR #34311:
URL: https://github.com/apache/arrow/pull/34311#discussion_r1116169422
##########
cpp/src/arrow/compute/exec/aggregate_node.cc:
##########
@@ -169,17 +206,63 @@ 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_batch, batch.SelectValues(ids));
+ while (true) {
+ ARROW_ASSIGN_OR_RAISE(auto segment,
segmenter->GetNextSegment(segment_batch, offset));
+ if (segment.offset >= segment_batch.length) break;
+ ARROW_RETURN_NOT_OK(handle_batch(batch, segment));
+ offset = segment.offset + segment.length;
+ }
+ return Status::OK();
+}
+
+Status GetScalarFields(std::vector<Datum>& values, const ExecBatch&
input_batch,
+ const std::vector<int>& field_ids) {
+ DCHECK_GT(input_batch.length, 0);
+ 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()) {
+ values[i] = value;
+ } else if (value.is_array()) {
+ ARROW_ASSIGN_OR_RAISE(auto scalar, value.make_array()->GetScalar(row));
+ values[i] = scalar;
+ } else {
+ DCHECK(false);
+ }
+ }
+ return Status::OK();
+}
+
+void PlaceFields(ExecBatch& batch, size_t base, std::vector<Datum>& values) {
+ DCHECK_LE(base + values.size(), batch.values.size());
+ for (size_t i = 0; i < values.size(); i++) {
+ batch.values[base + i] = values[i];
+ }
+}
+
class ScalarAggregateNode : public ExecNode, public TracedNode {
public:
ScalarAggregateNode(ExecPlan* plan, std::vector<ExecNode*> inputs,
std::shared_ptr<Schema> output_schema,
+ std::unique_ptr<GroupingSegmenter> segmenter,
Review Comment:
In regular (non-segmented/ordered) aggregation, the segmenter implementation
takes the entire stream as one segment.
--
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
