lidavidm commented on a change in pull request #9589:
URL: https://github.com/apache/arrow/pull/9589#discussion_r612730713
##########
File path: cpp/src/arrow/dataset/scanner.cc
##########
@@ -182,7 +273,30 @@ Result<FragmentIterator> SyncScanner::GetFragments() {
return GetFragmentsFromDatasets({dataset_}, scan_options_->filter);
}
-Result<ScanTaskIterator> SyncScanner::Scan() {
+Result<ScanTaskIterator> SyncScanner::Scan() { return ScanInternal(); }
+
+Status SyncScanner::Scan(std::function<Status(TaggedRecordBatch)> visitor) {
+ ARROW_ASSIGN_OR_RAISE(auto scan_task_it, ScanInternal());
+
+ auto task_group = scan_options_->TaskGroup();
+
+ for (auto maybe_scan_task : scan_task_it) {
+ ARROW_ASSIGN_OR_RAISE(auto scan_task, maybe_scan_task);
+ task_group->Append([scan_task, visitor] {
+ ARROW_ASSIGN_OR_RAISE(auto batch_it, scan_task->Execute());
Review comment:
See #10018
--
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
