westonpace commented on a change in pull request #10008:
URL: https://github.com/apache/arrow/pull/10008#discussion_r615107817
##########
File path: cpp/src/arrow/dataset/file_base.cc
##########
@@ -102,6 +102,58 @@ Result<std::shared_ptr<FileFragment>>
FileFormat::MakeFragment(
std::move(partition_expression),
std::move(physical_schema)));
}
+// TODO(ARROW-12355[CSV], ARROW-11772[IPC], ARROW-11843[Parquet]) The following
+// implementation of ScanBatchesAsync is both ugly and terribly ineffecient.
Each of the
+// formats should provide their own efficient implementation.
+Result<RecordBatchGenerator> FileFormat::ScanBatchesAsync(
+ const ScanOptions& options, const std::shared_ptr<FileFragment>& file) {
+ std::shared_ptr<ScanOptions> scan_options =
std::make_shared<ScanOptions>(options);
Review comment:
Done.
--
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
